Special Issue "The Future of Artificial Intelligence in Clinical Medicine"

A special issue of Journal of Clinical Medicine (ISSN 2077-0383). This special issue belongs to the section "Epidemiology & Public Health".

Deadline for manuscript submissions: closed (31 August 2019).

Special Issue Editor

Dr. Jorge Luis Espinoza
E-Mail Website
Guest Editor
Department of Hematology and RheumatoDepartment of Hematology and Rheumatology, Kindai University Faculty of Medicine, 377-2, Ohno-Higashi, Osaka-Sayama, Osaka 577-8502, Japan
Interests: hematology and Oncology; microbe-induced carcinogenesis; cancer drug discovery; parasitic infections; opportunistic microorganisms; immunology; microbiota; infectious diseases; artificial intelligence and medical Sciences
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) is the ability of computers to accomplish tasks that are normally completed by intelligent beings such as humans and animals. Among current AI applications, machine learning (ML) is a tool that combines computer science with statistics for generating advanced algorithms capable of identifying the complex relationships within large datasets. At present, ML is being applied in numerous fields of modern society, including web searching, social media networking, and facial recognition. In medicine, ML has shown impressive diagnostic skills through imaging analysis with potential applicability in radiology, pathology, and dermatology. For example, in a recent study, ML algorithms performed better than experienced dermatologists at detecting skin cancer. Similarly, the C-Path tool, an automated pathologist algorithm that used unsupervised ML and automated image processing to identify thousands of novel imaging features successfully identified high-risk breast cancers. In addition, based on chest X-ray images, deep learning algorithms showed remarkable precision and accuracy in the diagnosis of tuberculosis. These examples provide proof of concept for ML use in medicine. However, the feasibility of this approach in everyday clinical practice is unknown and requires further validation. Nevertheless, with the new advancements in computer processing power and the exponential growth of digital health data, there is growing enthusiasm for the potential utilization of ML in clinical medicine. This Special Issue will highlight recent advances in the diverse utilization of AI tools in clinical medicine. We welcome the submission of original research articles encompassing both preclinical and clinical studies, as well as review and opinion articles that include, but are not limited to, the following aspects: (1) artificial intelligence in medical practice; (2) artificial intelligence in medicine ethical considerations; (3) diagnostic applications of artificial intelligence; (4) predicting infection complications with artificial intelligence; (5) cancer and artificial intelligence; (6) predicting patients’ survival with artificial intelligence; and (7) artificial intelligence for interpreting radiographic images: friend or foe?

Dr. Luis Espinoza
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Clinical Medicine is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Artificial intelligence
  • Machine learning
  • Deep learning
  • Future medicine
  • Medical ethics

Published Papers (32 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

Open AccessCommunication
Computed and Subjective Blue Scleral Color Analysis as a Diagnostic Tool for Iron Deficiency: A Pilot Study
J. Clin. Med. 2019, 8(11), 1876; https://doi.org/10.3390/jcm8111876 - 05 Nov 2019
Abstract
Iron deficiency (ID) is the most common nutritional deficiency. ID diagnosis requires ferritin measurement because clinical findings are poor and nonspecific. We studied the diagnostic value of blue sclera, which was scarcely reported as a specific and sensitive sign of ID. We enrolled [...] Read more.
Iron deficiency (ID) is the most common nutritional deficiency. ID diagnosis requires ferritin measurement because clinical findings are poor and nonspecific. We studied the diagnostic value of blue sclera, which was scarcely reported as a specific and sensitive sign of ID. We enrolled 74 patients suspected of having ID. Pictures of their eyes were taken using a smartphone under similar daylight conditions. Three independent physicians graded the scleral color, and a computer analysis yielded the blue percentile of the sclera image. Final analysis included 67 patients (mean age 59.9 ± 20.1 years). Fifty-one had ID. Subjective blue scleral color was associated with ID for physician 1 (64.5% vs. 86.1%, p = 0.03). Sensitivity was 60.8% (CI95: 46.1%; 74.2%), specificity 68.8% (CI95: 41.3%; 89%), and positive predictive value 86.1% (CI95: 70.5%; 95.3%). A marginal difference was observed for other physicians (p = 0.05). Computer analysis showed higher blue in the ID group (p = 0.04). The area under the receiver operating characteristic (ROC) curve was 0.7 (0.54; 0.85). Sensitivity was 78.4% (CI95: 63.7%; 88.7%), specificity was 50% (CI95: 24.7%; 75.3%). Assessment of blue sclera was not influenced by iris color, sex, or anemia. We showed that blue sclera has good positive predictive value for ID diagnosis, and computer analysis was correlated to clinical assessment. Improvement of this innovative, non-invasive method could provide an easy handling and inexpensive diagnosis tool for ID. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Artificial Intelligence for Automatic Measurement of Sagittal Vertical Axis Using ResUNet Framework
J. Clin. Med. 2019, 8(11), 1826; https://doi.org/10.3390/jcm8111826 - 01 Nov 2019
Abstract
We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative [...] Read more.
We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative changes or deformities. The ResUNet was trained and evaluated on 990 standing lateral radiographs taken at Chang Gung Memorial Hospital, Linkou and performs SVA measurement with median absolute error of 1.183 ± 0.166 mm. The 5-mm detection rate of the C7 body and the sacrum are 91% and 87%, respectively. The SVA calculation takes approximately 0.2 s per image. The intra-class correlation coefficient of the SVA estimates between the algorithm and physicians of different years of experience ranges from 0.946 to 0.993, indicating an excellent consistency. The superior performance of the proposed method and its high consistency with physicians proved its usefulness for automatic measurement of SVA in clinical settings. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Artificial Intelligence Algorithms and Natural Language Processing for the Recognition of Syncope Patients on Emergency Department Medical Records
J. Clin. Med. 2019, 8(10), 1677; https://doi.org/10.3390/jcm8101677 - 14 Oct 2019
Abstract
Background: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. Aim: To develop a Natural Language Processing (NLP) algorithm to [...] Read more.
Background: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. Aim: To develop a Natural Language Processing (NLP) algorithm to automatically identify syncope from Emergency Department (ED) electronic medical records (EMRs). Methods: De-identified EMRs of all consecutive patients evaluated at Humanitas Research Hospital ED from 1 December 2013 to 31 March 2014 and from 1 December 2015 to 31 March 2016 were manually annotated to identify syncope. Records were combined in a single dataset and classified. The performance of combined multiple NLP feature selectors and classifiers was tested. Primary Outcomes: NLP algorithms’ accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F3 score. Results: 15,098 and 15,222 records from 2013 and 2015 datasets were analyzed. Syncope was present in 571 records. Normalized Gini Index feature selector combined with Support Vector Machines classifier obtained the best F3 value (84.0%), with 92.2% sensitivity and 47.4% positive predictive value. A 96% analysis time reduction was computed, compared with EMRs manual review. Conclusions: This artificial intelligence algorithm enabled the automatic identification of a large population of syncope patients using EMRs. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Early Detection of Bacteraemia Using Ten Clinical Variables with an Artificial Neural Network Approach
J. Clin. Med. 2019, 8(10), 1592; https://doi.org/10.3390/jcm8101592 - 02 Oct 2019
Abstract
An adequate model for predicting bacteraemia has not yet been developed. This study aimed to evaluate the performance of an artificial neural network (ANN)-based prediction model in comparison with previous statistical models. The performance of multi-layer perceptron (MLP), a representative ANN model, was [...] Read more.
An adequate model for predicting bacteraemia has not yet been developed. This study aimed to evaluate the performance of an artificial neural network (ANN)-based prediction model in comparison with previous statistical models. The performance of multi-layer perceptron (MLP), a representative ANN model, was verified via comparison with a non-neural network model. A total of 1260 bacteraemia episodes were identified in 13,402 patients. In MLP with 128 hidden layer nodes, the area under the receiver operating characteristic curve (AUC) of the prediction performance was 0.729 (95% confidence interval [CI]; 0.712–0.728), while in MLP with 256 hidden layer nodes, it was 0.727 (95% CI; 0.713–0.727). In a conventional Bayesian statistical method, the AUC was 0.7. The aforementioned two MLP models exhibited the highest sensitivity (0.810). The ranking of clinical variables was used to describe the influential power of the prediction. Serum alkaline phosphatase was one of the most influential clinical variables, and one-out search was the best ranking method for measuring the influence of the clinical variables. Furthermore, adding variables beyond the 10 top-ranking ones did not significantly affect the prediction of bacteraemia. The ANN model is not inferior to conventional statistical approaches. Bacteraemia can be predicted using only the top 10 clinical variables determined by a ranking method, and the model can be used in clinical practice by applying real-time monitoring. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Insights into Amyotrophic Lateral Sclerosis from a Machine Learning Perspective
J. Clin. Med. 2019, 8(10), 1578; https://doi.org/10.3390/jcm8101578 - 01 Oct 2019
Abstract
Objective: Amyotrophic lateral sclerosis (ALS) disease state prediction usually assumes linear progression and uses a classifier evaluated by its accuracy. Since disease progression is not linear, and the accuracy measurement cannot tell large from small prediction errors, we dispense with the linearity assumption [...] Read more.
Objective: Amyotrophic lateral sclerosis (ALS) disease state prediction usually assumes linear progression and uses a classifier evaluated by its accuracy. Since disease progression is not linear, and the accuracy measurement cannot tell large from small prediction errors, we dispense with the linearity assumption and apply ordinal classification that accounts for error severity. In addition, we identify the most influential variables in predicting and explaining the disease. Furthermore, in contrast to conventional modeling of the patient’s total functionality, we also model separate patient functionalities (e.g., in walking or speaking). Methods: Using data from 3772 patients from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database, we introduce and train ordinal classifiers to predict patients’ disease state in their last clinic visit, while accounting differently for different error severities. We use feature-selection methods and the classifiers themselves to determine the most influential variables in predicting the disease from demographic, clinical, and laboratory data collected in either the first, last, or both clinic visits, and the Bayesian network classifier to identify interrelations among these variables and their relations with the disease state. We apply these methods to model each of the patient functionalities. Results: We show the error distribution in ALS state prediction and demonstrate that ordinal classifiers outperform classifiers that do not account for error severity. We identify clinical and lab test variables influential to prediction of different ALS functionalities and their interrelations, and specific value combinations of these variables that occur more frequently in patients with severe deterioration than in patients with mild deterioration and vice versa. Conclusions: Ordinal classification of ALS state is superior to conventional classification. Identification of influential ALS variables and their interrelations help explain disease mechanism. Modeling of patient functionalities separately allows relation of variables and their connections to different aspects of the disease as may be expressed in different body segments. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
J. Clin. Med. 2019, 8(10), 1535; https://doi.org/10.3390/jcm8101535 - 25 Sep 2019
Abstract
Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained histopathology images remains largely uncharacterized. Here we investigate [...] Read more.
Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained histopathology images remains largely uncharacterized. Here we investigate such associations through the application of machine learning, including deep neural networks, to proteomics and histology imaging datasets generated by the Clinical Proteomic Tumor Analysis Consortium (CPTAC) from clear cell renal cell carcinoma patients. We report robust correlations between a set of diagnostic proteins and predictions generated by an imaging-based classification model. Proteins significantly correlated with the histology-based predictions are significantly implicated in immune responses, extracellular matrix reorganization, and metabolism. Moreover, we showed that the genes encoding these proteins also reliably recapitulate the biological associations with imaging-derived predictions based on strong gene–protein expression correlations. Our findings offer novel insights into the integrative modeling of histology and omics data through machine learning, as well as the methodological basis for new research opportunities in this and other cancer types. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Closing the Gap in Surveillance and Audit of Invasive Mold Diseases for Antifungal Stewardship Using Machine Learning
J. Clin. Med. 2019, 8(9), 1390; https://doi.org/10.3390/jcm8091390 - 05 Sep 2019
Abstract
Clinical audit of invasive mold disease (IMD) in hematology patients is inefficient due to the difficulties of case finding. This results in antifungal stewardship (AFS) programs preferentially reporting drug cost and consumption rather than measures that actually reflect quality of care. We used [...] Read more.
Clinical audit of invasive mold disease (IMD) in hematology patients is inefficient due to the difficulties of case finding. This results in antifungal stewardship (AFS) programs preferentially reporting drug cost and consumption rather than measures that actually reflect quality of care. We used machine learning-based natural language processing (NLP) to non-selectively screen chest tomography (CT) reports for pulmonary IMD, verified by clinical review against international definitions and benchmarked against key AFS measures. NLP screened 3014 reports from 1 September 2008 to 31 December 2017, generating 784 positives that after review, identified 205 IMD episodes (44% probable-proven) in 185 patients from 50,303 admissions. Breakthrough-probable/proven-IMD on antifungal prophylaxis accounted for 60% of episodes with serum monitoring of voriconazole or posaconazole in the 2 weeks prior performed in only 53% and 69% of episodes, respectively. Fiberoptic bronchoscopy within 2 days of CT scan occurred in only 54% of episodes. The average turnaround of send-away bronchoalveolar galactomannan of 12 days (range 7–22) was associated with high empiric liposomal amphotericin consumption. A random audit of 10% negative reports revealed two clinically significant misses (0.9%, 2/223). This is the first successful use of applied machine learning for institutional IMD surveillance across an entire hematology population describing process and outcome measures relevant to AFS. Compared to current methods of clinical audit, semi-automated surveillance using NLP is more efficient and inclusive by avoiding restrictions based on any underlying hematologic condition, and has the added advantage of being potentially scalable. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Predicting Cardiac Arrest and Respiratory Failure Using Feasible Artificial Intelligence with Simple Trajectories of Patient Data
J. Clin. Med. 2019, 8(9), 1336; https://doi.org/10.3390/jcm8091336 - 29 Aug 2019
Abstract
We introduce a Feasible Artificial Intelligence with Simple Trajectories for Predicting Adverse Catastrophic Events (FAST-PACE) solution for preparing immediate intervention in emergency situations. FAST-PACE utilizes a concise set of collected features to construct an artificial intelligence model that predicts the onset of cardiac [...] Read more.
We introduce a Feasible Artificial Intelligence with Simple Trajectories for Predicting Adverse Catastrophic Events (FAST-PACE) solution for preparing immediate intervention in emergency situations. FAST-PACE utilizes a concise set of collected features to construct an artificial intelligence model that predicts the onset of cardiac arrest or acute respiratory failure from 1 h to 6 h prior to its occurrence. Data from the trajectory of 29,181 patients in intensive care units of two hospitals includes periodic vital signs, a history of treatment, current health status, and recent surgery. It excludes the results of laboratory data to construct a feasible application in wards, out-hospital emergency care, emergency transport, or other clinical situations where instant medical decisions are required with restricted patient data. These results are superior to previous warning scores including the Modified Early Warning Score (MEWS) and the National Early Warning Score (NEWS). The primary outcome was the feasibility of an artificial intelligence (AI) model predicting adverse events 1 h to 6 h prior to occurrence without lab data; the area under the receiver operating characteristic curve of this model was 0.886 for cardiac arrest and 0.869 for respiratory failure 6 h before occurrence. The secondary outcome was the superior prediction performance to MEWS (net reclassification improvement of 0.507 for predicting cardiac arrest and 0.341 for predicting respiratory failure) and NEWS (net reclassification improvement of 0.412 for predicting cardiac arrest and 0.215 for predicting respiratory failure) 6 h before occurrence. This study suggests that AI consisting of simple vital signs and a brief interview could predict a cardiac arrest or acute respiratory failure 6 h earlier. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients
J. Clin. Med. 2019, 8(9), 1298; https://doi.org/10.3390/jcm8091298 - 24 Aug 2019
Abstract
The present study aims to compare the performance of eight Machine Learning Techniques (MLTs) in the prediction of hospitalization among patients with heart failure, using data from the Gestione Integrata dello Scompenso Cardiaco (GISC) study. The GISC project is an ongoing study that [...] Read more.
The present study aims to compare the performance of eight Machine Learning Techniques (MLTs) in the prediction of hospitalization among patients with heart failure, using data from the Gestione Integrata dello Scompenso Cardiaco (GISC) study. The GISC project is an ongoing study that takes place in the region of Puglia, Southern Italy. Patients with a diagnosis of heart failure are enrolled in a long-term assistance program that includes the adoption of an online platform for data sharing between general practitioners and cardiologists working in hospitals and community health districts. Logistic regression, generalized linear model net (GLMN), classification and regression tree, random forest, adaboost, logitboost, support vector machine, and neural networks were applied to evaluate the feasibility of such techniques in predicting hospitalization of 380 patients enrolled in the GISC study, using data about demographic characteristics, medical history, and clinical characteristics of each patient. The MLTs were compared both without and with missing data imputation. Overall, models trained without missing data imputation showed higher predictive performances. The GLMN showed better performance in predicting hospitalization than the other MLTs, with an average accuracy, positive predictive value and negative predictive value of 81.2%, 87.5%, and 75%, respectively. Present findings suggest that MLTs may represent a promising opportunity to predict hospital admission of heart failure patients by exploiting health care information generated by the contact of such patients with the health care system. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Open AccessArticle
Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis
J. Clin. Med. 2019, 8(8), 1241; https://doi.org/10.3390/jcm8081241 - 17 Aug 2019
Abstract
Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case [...] Read more.
Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case to physicians otherwise. In this paper, we investigate how Bayesian deep learning can improve the performance of the machine–physician team in the skin lesion classification task. We used the publicly available HAM10000 dataset, which includes samples from seven common skin lesion categories: Melanoma (MEL), Melanocytic Nevi (NV), Basal Cell Carcinoma (BCC), Actinic Keratoses and Intraepithelial Carcinoma (AKIEC), Benign Keratosis (BKL), Dermatofibroma (DF), and Vascular (VASC) lesions. Our experimental results show that Bayesian deep networks can boost the diagnostic performance of the standard DenseNet-169 model from 81.35% to 83.59% without incurring additional parameters or heavy computation. More importantly, a hybrid physician–machine workflow reaches a classification accuracy of 90 % while only referring 35 % of the cases to physicians. The findings are expected to generalize to other medical diagnosis applications. We believe that the availability of risk-aware machine learning methods will enable a wider adoption of machine learning technology in clinical settings. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Phasetime: Deep Learning Approach to Detect Nuclei in Time Lapse Phase Images
J. Clin. Med. 2019, 8(8), 1159; https://doi.org/10.3390/jcm8081159 - 02 Aug 2019
Abstract
Time lapse microscopy is essential for quantifying the dynamics of cells, subcellular organelles and biomolecules. Biologists use different fluorescent tags to label and track the subcellular structures and biomolecules within cells. However, not all of them are compatible with time lapse imaging, and [...] Read more.
Time lapse microscopy is essential for quantifying the dynamics of cells, subcellular organelles and biomolecules. Biologists use different fluorescent tags to label and track the subcellular structures and biomolecules within cells. However, not all of them are compatible with time lapse imaging, and the labeling itself can perturb the cells in undesirable ways. We hypothesized that phase image has the requisite information to identify and track nuclei within cells. By utilizing both traditional blob detection to generate binary mask labels from the stained channel images and the deep learning Mask RCNN model to train a detection and segmentation model, we managed to segment nuclei based only on phase images. The detection average precision is 0.82 when the IoU threshold is to be set 0.5. And the mean IoU for masks generated from phase images and ground truth masks from experts is 0.735. Without any ground truth mask labels during the training time, this is good enough to prove our hypothesis. This result enables the ability to detect nuclei without the need for exogenous labeling. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Outpatient Readmission in Rheumatology: A Machine Learning Predictive Model of Patient’s Return to the Clinic
J. Clin. Med. 2019, 8(8), 1156; https://doi.org/10.3390/jcm8081156 - 02 Aug 2019
Abstract
Our objective is to develop and validate a predictive model based on the random forest algorithm to estimate the readmission risk to an outpatient rheumatology clinic after discharge. We included patients from the Hospital Clínico San Carlos rheumatology outpatient clinic, from 1 April [...] Read more.
Our objective is to develop and validate a predictive model based on the random forest algorithm to estimate the readmission risk to an outpatient rheumatology clinic after discharge. We included patients from the Hospital Clínico San Carlos rheumatology outpatient clinic, from 1 April 2007 to 30 November 2016, and followed-up until 30 November 2017. Only readmissions between 2 and 12 months after the discharge were analyzed. Discharge episodes were chronologically split into training, validation, and test datasets. Clinical and demographic variables (diagnoses, treatments, quality of life (QoL), and comorbidities) were used as predictors. Models were developed in the training dataset, using a grid search approach, and performance was compared using the area under the receiver operating characteristic curve (AUC-ROC). A total of 18,662 discharge episodes were analyzed, out of which 2528 (13.5%) were followed by outpatient readmissions. Overall, 38,059 models were developed. AUC-ROC, sensitivity, and specificity of the reduced final model were 0.653, 0.385, and 0.794, respectively. The most important variables were related to follow-up duration, being prescribed with disease-modifying anti-rheumatic drugs and corticosteroids, being diagnosed with chronic polyarthritis, occupation, and QoL. We have developed a predictive model for outpatient readmission in a rheumatology setting. Identification of patients with higher risk can optimize the allocation of healthcare resources. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction
J. Clin. Med. 2019, 8(7), 1050; https://doi.org/10.3390/jcm8071050 - 18 Jul 2019
Cited by 1
Abstract
Machine learning is often perceived as a sophisticated technology accessible only by highly trained experts. This prevents many physicians and biologists from using this tool in their research. The goal of this paper is to eliminate this out-dated perception. We argue that the [...] Read more.
Machine learning is often perceived as a sophisticated technology accessible only by highly trained experts. This prevents many physicians and biologists from using this tool in their research. The goal of this paper is to eliminate this out-dated perception. We argue that the recent development of auto machine learning techniques enables biomedical researchers to quickly build competitive machine learning classifiers without requiring in-depth knowledge about the underlying algorithms. We study the case of predicting the risk of cardiovascular diseases. To support our claim, we compare auto machine learning techniques against a graduate student using several important metrics, including the total amounts of time required for building machine learning models and the final classification accuracies on unseen test datasets. In particular, the graduate student manually builds multiple machine learning classifiers and tunes their parameters for one month using scikit-learn library, which is a popular machine learning library to obtain ones that perform best on two given, publicly available datasets. We run an auto machine learning library called auto-sklearn on the same datasets. Our experiments find that automatic machine learning takes 1 h to produce classifiers that perform better than the ones built by the graduate student in one month. More importantly, building this classifier only requires a few lines of standard code. Our findings are expected to change the way physicians see machine learning and encourage wide adoption of Artificial Intelligence (AI) techniques in clinical domains. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Exploration of Artificial Intelligence Use with ARIES in Multiple Myeloma Research
J. Clin. Med. 2019, 8(7), 999; https://doi.org/10.3390/jcm8070999 - 09 Jul 2019
Abstract
Background: Natural language processing (NLP) is a powerful tool supporting the generation of Real-World Evidence (RWE). There is no NLP system that enables the extensive querying of parameters specific to multiple myeloma (MM) out of unstructured medical reports. We therefore created a MM-specific [...] Read more.
Background: Natural language processing (NLP) is a powerful tool supporting the generation of Real-World Evidence (RWE). There is no NLP system that enables the extensive querying of parameters specific to multiple myeloma (MM) out of unstructured medical reports. We therefore created a MM-specific ontology to accelerate the information extraction (IE) out of unstructured text. Methods: Our MM ontology consists of extensive MM-specific and hierarchically structured attributes and values. We implemented “A Rule-based Information Extraction System” (ARIES) that uses this ontology. We evaluated ARIES on 200 randomly selected medical reports of patients diagnosed with MM. Results: Our system achieved a high F1-Score of 0.92 on the evaluation dataset with a precision of 0.87 and recall of 0.98. Conclusions: Our rule-based IE system enables the comprehensive querying of medical reports. The IE accelerates the extraction of data and enables clinicians to faster generate RWE on hematological issues. RWE helps clinicians to make decisions in an evidence-based manner. Our tool easily accelerates the integration of research evidence into everyday clinical practice. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Artificial Intelligence Prediction Model for the Cost and Mortality of Renal Replacement Therapy in Aged and Super-Aged Populations in Taiwan
J. Clin. Med. 2019, 8(7), 995; https://doi.org/10.3390/jcm8070995 - 09 Jul 2019
Cited by 1
Abstract
Background: Prognosis of the aged population requiring maintenance dialysis has been reportedly poor. We aimed to develop prediction models for one-year cost and one-year mortality in aged individuals requiring dialysis to assist decision-making for deciding whether aged people should receive dialysis or not. [...] Read more.
Background: Prognosis of the aged population requiring maintenance dialysis has been reportedly poor. We aimed to develop prediction models for one-year cost and one-year mortality in aged individuals requiring dialysis to assist decision-making for deciding whether aged people should receive dialysis or not. Methods: We used data from the National Health Insurance Research Database (NHIRD). We identified patients first enrolled in the NHIRD from 2000–2011 for end-stage renal disease (ESRD) who underwent regular dialysis. A total of 48,153 Patients with ESRD aged ≥65 years with complete age and sex information were included in the ESRD cohort. The total medical cost per patient (measured in US dollars) within one year after ESRD diagnosis was our study’s main outcome variable. We were also concerned with mortality as another outcome. In this study, we compared the performance of the random forest prediction model and of the artificial neural network prediction model for predicting patient cost and mortality. Results: In the cost regression model, the random forest model outperforms the artificial neural network according to the mean squared error and mean absolute error. In the mortality classification model, the receiver operating characteristic (ROC) curves of both models were significantly better than the null hypothesis area of 0.5, and random forest model outperformed the artificial neural network. Random forest model outperforms the artificial neural network models achieved similar performance in the test set across all data. Conclusions: Applying artificial intelligence modeling could help to provide reliable information about one-year outcomes following dialysis in the aged and super-aged populations; those with cancer, alcohol-related disease, stroke, chronic obstructive pulmonary disease (COPD), previous hip fracture, osteoporosis, dementia, and previous respiratory failure had higher medical costs and a high mortality rate. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Artificial Intelligence-Based Classification of Multiple Gastrointestinal Diseases Using Endoscopy Videos for Clinical Diagnosis
J. Clin. Med. 2019, 8(7), 986; https://doi.org/10.3390/jcm8070986 - 07 Jul 2019
Cited by 1
Abstract
Various techniques using artificial intelligence (AI) have resulted in a significant contribution to field of medical image and video-based diagnoses, such as radiology, pathology, and endoscopy, including the classification of gastrointestinal (GI) diseases. Most previous studies on the classification of GI diseases use [...] Read more.
Various techniques using artificial intelligence (AI) have resulted in a significant contribution to field of medical image and video-based diagnoses, such as radiology, pathology, and endoscopy, including the classification of gastrointestinal (GI) diseases. Most previous studies on the classification of GI diseases use only spatial features, which demonstrate low performance in the classification of multiple GI diseases. Although there are a few previous studies using temporal features based on a three-dimensional convolutional neural network, only a specific part of the GI tract was involved with the limited number of classes. To overcome these problems, we propose a comprehensive AI-based framework for the classification of multiple GI diseases by using endoscopic videos, which can simultaneously extract both spatial and temporal features to achieve better classification performance. Two different residual networks and a long short-term memory model are integrated in a cascaded mode to extract spatial and temporal features, respectively. Experiments were conducted on a combined dataset consisting of one of the largest endoscopic videos with 52,471 frames. The results demonstrate the effectiveness of the proposed classification framework for multi-GI diseases. The experimental results of the proposed model (97.057% area under the curve) demonstrate superior performance over the state-of-the-art methods and indicate its potential for clinical applications. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Shared Decision-Making in Chronic Patients with Polypharmacy: An Interventional Study for Assessing Medication Appropriateness
J. Clin. Med. 2019, 8(6), 904; https://doi.org/10.3390/jcm8060904 - 24 Jun 2019
Abstract
Potentially inappropriate medications are associated with polypharmacy and polypathology. Some interventions such as pharmacotherapy reviews have been designed to reduce the prescribing of inappropriate medications. The objective of this study is to evaluate how effective a decision-making support tool is for determining medication [...] Read more.
Potentially inappropriate medications are associated with polypharmacy and polypathology. Some interventions such as pharmacotherapy reviews have been designed to reduce the prescribing of inappropriate medications. The objective of this study is to evaluate how effective a decision-making support tool is for determining medication appropriateness in patients with one or more chronic diseases (hypertension, dyslipidaemia, and/or diabetes) and polypharmacy in the primary care setting. For this, a quasi-experimental study (randomised, controlled and multicentre) has been developed. The study compares an intervention group, which assesses medication appropriateness by applying a decision support tool, with a control group that follows the usual clinical practice. The intervention included a decision support tool in paper format, where participants were informed about polypharmacy, inappropriate medications, associated problems and available alternatives, as well as shared decision-making. This is an informative guide aimed at helping patients with decision-making by providing them with information about the secondary risks associated with inappropriate medications in their treatment, according to the Beers and START/STOPP criteria. The outcome measure was the proportion of medication appropriateness. The proportion of patients who confirmed medication appropriateness after six months of follow-up is greater in the intervention group (32.5%) than in the control group (27.9%) p = 0.008. The probability of medication appropriateness, which was calculated by the proportion of drugs withdrawn or replaced according to the STOPP/Beers criteria and those initiated according to the START criteria, was 2.8 times higher in the intervention group than in the control group (OR = 2.8; 95% CI 1.3–6.1) p = 0.008. In patients with good adherence to the treatment, the percentage of appropriateness was 62.1% in the shared decision-making group versus 37.9% in the control group (p = 0.005). The use of a decision-making support tool in patients with potentially inappropriate medications increases the percentage of medication appropriateness when compared to the usual clinical practice. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Supervised Machine Learning Based Multi-Task Artificial Intelligence Classification of Retinopathies
J. Clin. Med. 2019, 8(6), 872; https://doi.org/10.3390/jcm8060872 - 18 Jun 2019
Cited by 3
Abstract
Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography [...] Read more.
Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography (OCTA) imaging provides excellent capability to identify subtle vascular distortions, which are useful for classifying retinovascular diseases. However, application of AI for differentiation and classification of multiple eye diseases is not yet established. In this study, we demonstrate supervised machine learning based multi-task OCTA classification. We sought (1) to differentiate normal from diseased ocular conditions, (2) to differentiate different ocular disease conditions from each other, and (3) to stage the severity of each ocular condition. Quantitative OCTA features, including blood vessel tortuosity (BVT), blood vascular caliber (BVC), vessel perimeter index (VPI), blood vessel density (BVD), foveal avascular zone (FAZ) area (FAZ-A), and FAZ contour irregularity (FAZ-CI) were fully automatically extracted from the OCTA images. A stepwise backward elimination approach was employed to identify sensitive OCTA features and optimal-feature-combinations for the multi-task classification. For proof-of-concept demonstration, diabetic retinopathy (DR) and sickle cell retinopathy (SCR) were used to validate the supervised machine leaning classifier. The presented AI classification methodology is applicable and can be readily extended to other ocular diseases, holding promise to enable a mass-screening platform for clinical deployment and telemedicine. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Machine Learning Models of Survival Prediction in Trauma Patients
J. Clin. Med. 2019, 8(6), 799; https://doi.org/10.3390/jcm8060799 - 05 Jun 2019
Cited by 1
Abstract
Background: We aimed to build a model using machine learning for the prediction of survival in trauma patients and compared these model predictions to those predicted by the most commonly used algorithm, the Trauma and Injury Severity Score (TRISS). Methods: Enrolled hospitalized trauma [...] Read more.
Background: We aimed to build a model using machine learning for the prediction of survival in trauma patients and compared these model predictions to those predicted by the most commonly used algorithm, the Trauma and Injury Severity Score (TRISS). Methods: Enrolled hospitalized trauma patients from 2009 to 2016 were divided into a training dataset (70% of the original data set) for generation of a plausible model under supervised classification, and a test dataset (30% of the original data set) to test the performance of the model. The training and test datasets comprised 13,208 (12,871 survival and 337 mortality) and 5603 (5473 survival and 130 mortality) patients, respectively. With the provision of additional information such as pre-existing comorbidity status or laboratory data, logistic regression (LR), support vector machine (SVM), and neural network (NN) (with the Stuttgart Neural Network Simulator (RSNNS)) were used to build models of survival prediction and compared to the predictive performance of TRISS. Predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operating characteristic curves. Results: In the validation dataset, NN and the TRISS presented the highest score (82.0%) for balanced accuracy, followed by SVM (75.2%) and LR (71.8%) models. In the test dataset, NN had the highest balanced accuracy (75.1%), followed by the TRISS (70.2%), SVM (70.6%), and LR (68.9%) models. All four models (LR, SVM, NN, and TRISS) exhibited a high accuracy of more than 97.5% and a sensitivity of more than 98.6%. However, NN exhibited the highest specificity (51.5%), followed by the TRISS (41.5%), SVM (40.8%), and LR (38.5%) models. Conclusions: These four models (LR, SVM, NN, and TRISS) exhibited a similar high accuracy and sensitivity in predicting the survival of the trauma patients. In the test dataset, the NN model had the highest balanced accuracy and predictive specificity. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Machine Learning Application for Rupture Risk Assessment in Small-Sized Intracranial Aneurysm
J. Clin. Med. 2019, 8(5), 683; https://doi.org/10.3390/jcm8050683 - 15 May 2019
Abstract
The assessment of rupture probability is crucial to identifying at risk intracranial aneurysms (IA) in patients harboring multiple aneurysms. We aimed to develop a computer-assisted detection system for small-sized aneurysm ruptures using a convolutional neural network (CNN) based on images of three-dimensional digital [...] Read more.
The assessment of rupture probability is crucial to identifying at risk intracranial aneurysms (IA) in patients harboring multiple aneurysms. We aimed to develop a computer-assisted detection system for small-sized aneurysm ruptures using a convolutional neural network (CNN) based on images of three-dimensional digital subtraction angiography. A retrospective data set, including 368 patients, was used as a training cohort for the CNN using the TensorFlow platform. Aneurysm images in six directions were obtained from each patient and the region-of-interest in each image was extracted. The resulting CNN was prospectively tested in 272 patients and the sensitivity, specificity, overall accuracy, and receiver operating characteristics (ROC) were compared to a human evaluator. Our system showed a sensitivity of 78.76% (95% CI: 72.30%–84.30%), a specificity of 72.15% (95% CI: 60.93%–81.65%), and an overall diagnostic accuracy of 76.84% (95% CI: 71.36%–81.72%) in aneurysm rupture predictions. The area under the ROC (AUROC) in the CNN was 0.755 (95% CI: 0.699%–0.805%), better than that obtained from a human evaluator (AUROC: 0.537; p < 0.001). The CNN-based prediction system was feasible to assess rupture risk in small-sized aneurysms with diagnostic accuracy superior to human evaluators. Additional studies based on a large data set are necessary to enhance diagnostic accuracy and to facilitate clinical application. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
A Comparative Study of Machine Learning Algorithms in Predicting Severe Complications after Bariatric Surgery
J. Clin. Med. 2019, 8(5), 668; https://doi.org/10.3390/jcm8050668 - 12 May 2019
Cited by 1
Abstract
Background: Severe obesity is a global public health threat of growing proportions. Accurate models to predict severe postoperative complications could be of value in the preoperative assessment of potential candidates for bariatric surgery. So far, traditional statistical methods have failed to produce high [...] Read more.
Background: Severe obesity is a global public health threat of growing proportions. Accurate models to predict severe postoperative complications could be of value in the preoperative assessment of potential candidates for bariatric surgery. So far, traditional statistical methods have failed to produce high accuracy. We aimed to find a useful machine learning (ML) algorithm to predict the risk for severe complication after bariatric surgery. Methods: We trained and compared 29 supervised ML algorithms using information from 37,811 patients that operated with a bariatric surgical procedure between 2010 and 2014 in Sweden. The algorithms were then tested on 6250 patients operated in 2015. We performed the synthetic minority oversampling technique tackling the issue that only 3% of patients experienced severe complications. Results: Most of the ML algorithms showed high accuracy (>90%) and specificity (>90%) in both the training and test data. However, none of the algorithms achieved an acceptable sensitivity in the test data. We also tried to tune the hyperparameters of the algorithms to maximize sensitivity, but did not yet identify one with a high enough sensitivity that can be used in clinical praxis in bariatric surgery. However, a minor, but perceptible, improvement in deep neural network (NN) ML was found. Conclusion: In predicting the severe postoperative complication among the bariatric surgery patients, ensemble algorithms outperform base algorithms. When compared to other ML algorithms, deep NN has the potential to improve the accuracy and it deserves further investigation. The oversampling technique should be considered in the context of imbalanced data where the number of the interested outcome is relatively small. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Developing a Diagnostic Decision Support System for Benign Paroxysmal Positional Vertigo Using a Deep-Learning Model
J. Clin. Med. 2019, 8(5), 633; https://doi.org/10.3390/jcm8050633 - 08 May 2019
Abstract
Background: Diagnosis of benign paroxysmal positional vertigo (BPPV) depends on the accurate interpretation of nystagmus induced by positional tests. However, difficulties in interpreting eye-movement often can arise in primary care practice or emergency room. We hypothesized that the use of machine learning [...] Read more.
Background: Diagnosis of benign paroxysmal positional vertigo (BPPV) depends on the accurate interpretation of nystagmus induced by positional tests. However, difficulties in interpreting eye-movement often can arise in primary care practice or emergency room. We hypothesized that the use of machine learning would be helpful for the interpretation. Methods: From our clinical data warehouse, 91,778 nystagmus videos from 3467 patients with dizziness were obtained, in which the three-dimensional movement of nystagmus was annotated by four otologic experts. From each labeled video, 30 features changed into 255 grid images fed into the input layer of the neural network for the training dataset. For the model validation, video dataset of 3566 horizontal, 2068 vertical, and 720 torsional movements from 1005 patients with BPPV were collected. Results: The model had a sensitivity and specificity of 0.910 ± 0.036 and 0.919 ± 0.032 for horizontal nystagmus; of 0.879 ± 0.029 and 0.894 ± 0.025 for vertical nystagmus; and of 0.783 ± 0.040 and 0.799 ± 0.038 for torsional nystagmus, respectively. The affected canal was predicted with a sensitivity of 0.806 ± 0.010 and a specificity of 0.971 ± 0.003. Conclusions: As our deep-learning model had high sensitivity and specificity for the classification of nystagmus and localization of affected canal in patients with BPPV, it may have wide clinical applicability. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Effective Diagnosis and Treatment through Content-Based Medical Image Retrieval (CBMIR) by Using Artificial Intelligence
J. Clin. Med. 2019, 8(4), 462; https://doi.org/10.3390/jcm8040462 - 05 Apr 2019
Cited by 6
Abstract
Medical-image-based diagnosis is a tedious task‚ and small lesions in various medical images can be overlooked by medical experts due to the limited attention span of the human visual system, which can adversely affect medical treatment. However, this problem can be resolved by [...] Read more.
Medical-image-based diagnosis is a tedious task‚ and small lesions in various medical images can be overlooked by medical experts due to the limited attention span of the human visual system, which can adversely affect medical treatment. However, this problem can be resolved by exploring similar cases in the previous medical database through an efficient content-based medical image retrieval (CBMIR) system. In the past few years, heterogeneous medical imaging databases have been growing rapidly with the advent of different types of medical imaging modalities. Recently, a medical doctor usually refers to various types of imaging modalities all together such as computed tomography (CT), magnetic resonance imaging (MRI), X-ray, and ultrasound, etc of various organs in order for the diagnosis and treatment of specific disease. Accurate classification and retrieval of multimodal medical imaging data is the key challenge for the CBMIR system. Most previous attempts use handcrafted features for medical image classification and retrieval, which show low performance for a massive collection of multimodal databases. Although there are a few previous studies on the use of deep features for classification, the number of classes is very small. To solve this problem, we propose the classification-based retrieval system of the multimodal medical images from various types of imaging modalities by using the technique of artificial intelligence, named as an enhanced residual network (ResNet). Experimental results with 12 databases including 50 classes demonstrate that the accuracy and F1.score by our method are respectively 81.51% and 82.42% which are higher than those by the previous method of CBMIR (the accuracy of 69.71% and F1.score of 69.63%). Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Global Evolution of Research in Artificial Intelligence in Health and Medicine: A Bibliometric Study
J. Clin. Med. 2019, 8(3), 360; https://doi.org/10.3390/jcm8030360 - 14 Mar 2019
Cited by 12
Abstract
The increasing application of Artificial Intelligence (AI) in health and medicine has attracted a great deal of research interest in recent decades. This study aims to provide a global and historical picture of research concerning AI in health and medicine. A total of [...] Read more.
The increasing application of Artificial Intelligence (AI) in health and medicine has attracted a great deal of research interest in recent decades. This study aims to provide a global and historical picture of research concerning AI in health and medicine. A total of 27,451 papers that were published between 1977 and 2018 (84.6% were dated 2008–2018) were retrieved from the Web of Science platform. The descriptive analysis examined the publication volume, and authors and countries collaboration. A global network of authors’ keywords and content analysis of related scientific literature highlighted major techniques, including Robotic, Machine learning, Artificial neural network, Artificial intelligence, Natural language process, and their most frequent applications in Clinical Prediction and Treatment. The number of cancer-related publications was the highest, followed by Heart Diseases and Stroke, Vision impairment, Alzheimer’s, and Depression. Moreover, the shortage in the research of AI application to some high burden diseases suggests future directions in AI research. This study offers a first and comprehensive picture of the global efforts directed towards this increasingly important and prolific field of research and suggests the development of global and national protocols and regulations on the justification and adaptation of medical AI products. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Exploration of Machine Learning for Hyperuricemia Prediction Models Based on Basic Health Checkup Tests
J. Clin. Med. 2019, 8(2), 172; https://doi.org/10.3390/jcm8020172 - 02 Feb 2019
Abstract
Background: Machine learning (ML) is a promising methodology for classification and prediction applications in healthcare. However, this method has not been practically established for clinical data. Hyperuricemia is a biomarker of various chronic diseases. We aimed to predict uric acid status from basic [...] Read more.
Background: Machine learning (ML) is a promising methodology for classification and prediction applications in healthcare. However, this method has not been practically established for clinical data. Hyperuricemia is a biomarker of various chronic diseases. We aimed to predict uric acid status from basic healthcare checkup test results using several ML algorithms and to evaluate the performance. Methods: We designed a prediction model for hyperuricemia using a comprehensive health checkup database designed by the classification of ML algorithms, such as discrimination analysis, K-nearest neighbor, naïve Bayes (NBC), support vector machine, decision tree, and random forest classification (RFC). The performance of each algorithm was evaluated and compared with the performance of a conventional logistic regression (CLR) algorithm by receiver operating characteristic curve analysis. Results: Of the 38,001 participants, 7705 were hyperuricemic. For the maximum sensitivity criterion, NBC showed the highest sensitivity (0.73), and RFC showed the second highest (0.66); for the maximum balanced classification rate (BCR) criterion, RFC showed the highest BCR (0.68), and NBC showed the second highest (0.66) among the various ML algorithms for predicting uric acid status. In a comparison to the performance of NBC (area under the curve (AUC) = 0.669, 95% confidence intervals (CI) = 0.669–0.675) and RFC (AUC = 0.775, 95% CI 0.770–0.780) with a CLR algorithm (AUC = 0.568, 95% CI = 0.563–0.571), NBC and RFC showed significantly better performance (p < 0.001). Conclusions: The ML model was superior to the CLR model for the prediction of hyperuricemia. Future studies are needed to determine the best-performing ML algorithms based on data set characteristics. We believe that this study will be informative for studies using ML tools in clinical research. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Open AccessArticle
Driving Type 2 Diabetes Risk Scores into Clinical Practice: Performance Analysis in Hospital Settings
J. Clin. Med. 2019, 8(1), 107; https://doi.org/10.3390/jcm8010107 - 17 Jan 2019
Cited by 2
Abstract
Electronic health records and computational modelling have paved the way for the development of Type 2 Diabetes risk scores to identify subjects at high risk. Unfortunately, few risk scores have been externally validated, and their performance can be compromised when routine clinical data [...] Read more.
Electronic health records and computational modelling have paved the way for the development of Type 2 Diabetes risk scores to identify subjects at high risk. Unfortunately, few risk scores have been externally validated, and their performance can be compromised when routine clinical data is used. The aim of this study was to assess the performance of well-established risk scores for Type 2 Diabetes using routinely collected clinical data and to quantify their impact on the decision making process of endocrinologists. We tested six risk models that have been validated in external cohorts, as opposed to model development, on electronic health records collected from 2008-2015 from a population of 10,730 subjects. Unavailable or missing data in electronic health records was imputed using an existing validated Bayesian Network. Risk scores were assessed on the basis of statistical performance to differentiate between subjects who developed diabetes and those who did not. Eight endocrinologists provided clinical recommendations based on the risk score output. Due to inaccuracies and discrepancies regarding the exact date of Type 2 Diabetes onset, 76 subjects from the initial population were eligible for the study. Risk scores were useful for identifying subjects who developed diabetes (Framingham risk score yielded a c-statistic of 85%), however, our findings suggest that electronic health records are not prepared to massively use this type of risk scores. Use of a Bayesian Network was key for completion of the risk estimation and did not affect the risk score calculation (p > 0.05). Risk score estimation did not have a significant effect on the clinical recommendation except for starting pharmacological treatment (p = 0.004) and dietary counselling (p = 0.039). Despite their potential use, electronic health records should be carefully analyzed before the massive use of Type 2 Diabetes risk scores for the identification of high-risk subjects, and subsequent targeting of preventive actions. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Efficacy of Integrating a Novel 16-Gene Biomarker Panel and Intelligence Classifiers for Differential Diagnosis of Rheumatoid Arthritis and Osteoarthritis
J. Clin. Med. 2019, 8(1), 50; https://doi.org/10.3390/jcm8010050 - 06 Jan 2019
Cited by 3
Abstract
Introducing novel biomarkers for accurately detecting and differentiating rheumatoid arthritis (RA) and osteoarthritis (OA) using clinical samples is essential. In the current study, we searched for a novel data-driven gene signature of synovial tissues to differentiate RA from OA patients. Fifty-three RA, 41 [...] Read more.
Introducing novel biomarkers for accurately detecting and differentiating rheumatoid arthritis (RA) and osteoarthritis (OA) using clinical samples is essential. In the current study, we searched for a novel data-driven gene signature of synovial tissues to differentiate RA from OA patients. Fifty-three RA, 41 OA, and 25 normal microarray-based transcriptome samples were utilized. The area under the curve random forests (RF) variable importance measurement was applied to seek the most influential differential genes between RA and OA. Five algorithms including RF, k-nearest neighbors (kNN), support vector machines (SVM), naïve-Bayes, and a tree-based method were employed for the classification. We found a 16-gene signature that could effectively differentiate RA from OA, including TMOD1, POP7, SGCA, KLRD1, ALOX5, RAB22A, ANK3, PTPN3, GZMK, CLU, GZMB, FBXL7, TNFRSF4, IL32, MXRA7, and CD8A. The externally validated accuracy of the RF model was 0.96 (sensitivity = 1.00, specificity = 0.90). Likewise, the accuracy of kNN, SVM, naïve-Bayes, and decision tree was 0.96, 0.96, 0.96, and 0.91, respectively. Functional meta-analysis exhibited the differential pathological processes of RA and OA; suggested promising targets for further mechanistic and therapeutic studies. In conclusion, the proposed genetic signature combined with sophisticated classification methods may improve the diagnosis and management of RA patients. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Graphical abstract

Open AccessArticle
A Novel Machine Learning Algorithm to Automatically Predict Visual Outcomes in Intravitreal Ranibizumab-Treated Patients with Diabetic Macular Edema
J. Clin. Med. 2018, 7(12), 475; https://doi.org/10.3390/jcm7120475 - 24 Nov 2018
Cited by 1
Abstract
Purpose: Artificial neural networks (ANNs) are one type of artificial intelligence. Here, we use an ANN-based machine learning algorithm to automatically predict visual outcomes after ranibizumab treatment in diabetic macular edema. Methods: Patient data were used to optimize ANNs for regression calculation. The [...] Read more.
Purpose: Artificial neural networks (ANNs) are one type of artificial intelligence. Here, we use an ANN-based machine learning algorithm to automatically predict visual outcomes after ranibizumab treatment in diabetic macular edema. Methods: Patient data were used to optimize ANNs for regression calculation. The target was established as the final visual acuity at 52, 78, or 104 weeks. The input baseline variables were sex, age, diabetes type or condition, systemic diseases, eye status and treatment time tables. Three groups were randomly devised to build, test and demonstrate the accuracy of the algorithms. Results: At 52, 78 and 104 weeks, 512, 483 and 464 eyes were included, respectively. For the training group, testing group and validation group, the respective correlation coefficients were 0.75, 0.77 and 0.70 (52 weeks); 0.79, 0.80 and 0.55 (78 weeks); and 0.83, 0.47 and 0.81 (104 weeks), while the mean standard errors of final visual acuity were 6.50, 6.11 and 6.40 (52 weeks); 5.91, 5.83 and 7.59; (78 weeks); and 5.39, 8.70 and 6.81 (104 weeks). Conclusions: Machine learning had good correlation coefficients for predicating prognosis with ranibizumab with just baseline characteristics. These models could be the useful clinical tools for prediction of success of the treatments. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessArticle
Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
J. Clin. Med. 2018, 7(11), 428; https://doi.org/10.3390/jcm7110428 - 08 Nov 2018
Cited by 9
Abstract
Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of [...] Read more.
Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86–0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56–0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Review

Jump to: Research

Open AccessReview
Artificial Intelligence vs. Natural Stupidity: Evaluating AI Readiness for the Vietnamese Medical Information System
J. Clin. Med. 2019, 8(2), 168; https://doi.org/10.3390/jcm8020168 - 01 Feb 2019
Cited by 6
Abstract
This review paper presents a framework to evaluate the artificial intelligence (AI) readiness for the healthcare sector in developing countries: a combination of adequate technical or technological expertise, financial sustainability, and socio-political commitment embedded in a healthy psycho-cultural context could bring about the [...] Read more.
This review paper presents a framework to evaluate the artificial intelligence (AI) readiness for the healthcare sector in developing countries: a combination of adequate technical or technological expertise, financial sustainability, and socio-political commitment embedded in a healthy psycho-cultural context could bring about the smooth transitioning toward an AI-powered healthcare sector. Taking the Vietnamese healthcare sector as a case study, this paper attempts to clarify the negative and positive influencers. With only about 1500 publications about AI from 1998 to 2017 according to the latest Elsevier AI report, Vietnamese physicians are still capable of applying the state-of-the-art AI techniques in their research. However, a deeper look at the funding sources suggests a lack of socio-political commitment, hence the financial sustainability, to advance the field. The AI readiness in Vietnam’s healthcare also suffers from the unprepared information infrastructure—using text mining for the official annual reports from 2012 to 2016 of the Ministry of Health, the paper found that the frequency of the word “database” actually decreases from 2012 to 2016, and the word has a high probability to accompany words such as “lacking”, “standardizing”, “inefficient”, and “inaccurate.” Finally, manifestations of psycho-cultural elements such as the public’s mistaken views on AI or the non-transparent, inflexible and redundant of Vietnamese organizational structures can impede the transition to an AI-powered healthcare sector. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessReview
Methods Used to Assess the 3D Accuracy of Dental Implant Positions in Computer-Guided Implant Placement: A Review
J. Clin. Med. 2019, 8(1), 54; https://doi.org/10.3390/jcm8010054 - 07 Jan 2019
Cited by 1
Abstract
The purpose of this review is to examine various assessment methods in order to compare the accuracy between the virtually planned and clinically achieved implant positions. In this review, comparison methods using pre- and post-operative computed topography (CT) data and digital impressions for [...] Read more.
The purpose of this review is to examine various assessment methods in order to compare the accuracy between the virtually planned and clinically achieved implant positions. In this review, comparison methods using pre- and post-operative computed topography (CT) data and digital impressions for definitive prosthesis will be described. The method for the displacement and strain for quantification of the error will also be explored. The difference between the planned and the actual implant placement position in guided implant surgery is expressed as an error. Assessing the accuracy of implant-guided surgery can play an important role as positive feedback in order to reduce errors. All of the assessment methods have their own inevitable errors and require careful interpretation in evaluation. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Open AccessReview
Current Research and New Perspectives of Telemedicine in Chronic Heart Failure: Narrative Review and Points of Interest for the Clinician
J. Clin. Med. 2018, 7(12), 544; https://doi.org/10.3390/jcm7120544 - 13 Dec 2018
Cited by 4
Abstract
Background: This is a narrative review of both the literature and Internet pertaining to telemedicine projects within the field of heart failure, with special attention placed on remote monitoring of second-generation projects and trials, particularly in France. Results: Since the beginning of the [...] Read more.
Background: This is a narrative review of both the literature and Internet pertaining to telemedicine projects within the field of heart failure, with special attention placed on remote monitoring of second-generation projects and trials, particularly in France. Results: Since the beginning of the 2000’s, several telemedicine projects and trials focused on chronic heart failure have been developed. The first telemedicine projects (e.g., TEN-HMS, BEAT-HF, Tele-HF, and TIM-HF) primarily investigated telemonitoring or for the older ones, telephone follow-up. Numerous second-generation telemedicine projects have emerged in Europe over the last ten years or are still under development for computer science heart failure, especially in Europe, such as SCAD, OSICAT, E-care, PRADO-INCADO, and TIM-HF2. The E-care telemonitoring project fits within the telemedicine 2.0 framework, based on connected objects, new information and communication technologies (ICT) and Web 2.0 technologies. E-care is the first telemedicine project including artificial intelligence (AI). TIM-HF2 is the first positive prospective randomized study with regards to EBM with positive significant clinical benefit, in terms of unplanned cardiovascular hospital admissions and all-cause deaths. The potential contribution of second-generation telemedicine projects in terms of mortality, morbidity, and number of hospitalizations avoided is currently under study. Their impact in terms of health economics is likewise being investigated, taking into account that the economic and social benefits brought up by telemedicine solutions were previously validated by the original telemedicine projects. Full article
(This article belongs to the Special Issue The Future of Artificial Intelligence in Clinical Medicine)
Show Figures

Figure 1

Back to TopTop