Topic Menu

Topic Editors

E-Mail Website

Associate Professor, Department of Health Science and Biostatistics, School of Health Sciences, Swinburne University of Technology, Melbourne, Hawthorn, VIC 3122, Australia

Dr. Raaj Kishore Biswas

E-Mail Website

Assistant Editor
Clinical Research Centre Sydney Local Health District, Royal Prince Hospital, Camperdown, NSW 2050, Australia

Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods

Abstract submission deadline

closed (31 August 2023)

Manuscript submission deadline

closed (31 October 2023)

Viewed by

31209

Topic Information

Dear Colleagues,

We are inviting submissions to the Topic entitled “Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods” in JCM, IJERPH, Cancers, Viruses, COVID and Biomedicines, devoted to the application of advanced biostatistical methods in the broad area of clinical research, including mental health. Rapid advancements in clinical research through the use of modern digital technologies have created new challenges and opportunities for statisticians. For example, clinical big data, the detection and treatment of rare diseases, statistical inference in interventions and observational studies and many other emerging clinical research areas have motivated researchers worldwide to develop and apply cutting-edge statistical methods and analytical approaches. The aim of this Topic is to stimulate the dissemination of information in the wider area of clinical research in order to improve the effectiveness and competence of public health interventions to improve the overall health outcomes of populations worldwide using cutting-edge modelling approaches. Statistical methods have a long history of being applied in multifaceted health research to investigate critical health-related issues, including assessment of innovative intervention as well as disease control and global health awareness. In this process, many revolutions in statistical procedures have risen and aptly applied in across disciplines. Therefore, this Topic seeks the submission of scientific articles relevant to clinical research, from different areas of the field of health, and will assemble them into issues that improve our awareness and understanding of public health problems, including mental health, and will provide solutions through the evaluation of real-life data using latest statistical methods. One of the focuses of this Topic is to capture the current scenario of COVID-19 and its impact on global health going forward. The contribution of any clinical research into COVID-19 and its impact on mental health will be highly appreciated.

This Special Issue welcomes submissions of original research in the following areas:

Mental health;
Behavioural analysis;
Clinical nursing;
Health data modelling;
COVID-19;
Epidemiology and public health;
Clinical psychology;
Women’s health and policy;
Sustainable development goals;
Health economics;
Health education;
eHealth;
Heath technology;
Infectious diseases;
Non-communicable diseases;
Oncology;
Big data;
Biostatistics;
Biomedical research.

We are happy to announce this Topic, entitled “Modelling Clinical Data using Advanced Biostatistical Methods” in JCM, IJERPH, Cancers, Viruses, COVID and Biomedicines, and look forward to receiving your submissions.

Dr. Jahar Bhowmik
Dr. Raaj Kishore Biswas
Topic Editors

Keywords

mental health
addictive behaviour
epidemiology
cancer
smoking
public health
clinical nursing
biostatistics
epidemiology
sustainable development goals
COVID-19
infectious diseases
non-communicable diseases
women’s health
interpersonal violence
older adults

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Biomedicines biomedicines	3.9	6.8	2013	17 Days	CHF 2600
Cancers cancers	4.4	8.8	2009	20.3 Days	CHF 2900
COVID covid	1.0	2.3	2021	20.6 Days	CHF 1200
International Journal of Environmental Research and Public Health ijerph	-	8.5	2004	27.8 Days	CHF 2500
Journal of Clinical Medicine jcm	2.9	5.2	2012	17.7 Days	CHF 2600
Viruses viruses	3.5	7.7	2009	18.6 Days	CHF 2600

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (11 papers)

Download All Papers

Order results

Result details

Journals

Show export options Show export options

Select all

Export citation of selected articles as:

13 pages, 409 KB

Open AccessArticle

A Flexible Regression Modeling Approach Applied to Observational Laboratory Virological Data Suggests That SARS-CoV-2 Load in Upper Respiratory Tract Samples Changes with COVID-19 Epidemiology

by Laura Pellegrinelli, Ester Luconi, Giuseppe Marano, Cristina Galli, Serena Delbue, Laura Bubba, Sandro Binda, Silvana Castaldi, Elia Biganzoli, Elena Pariani and Patrizia Boracchi

Viruses 2023, 15(10), 1988; https://doi.org/10.3390/v15101988 - 23 Sep 2023

Viewed by 1742

Abstract

(1) Background. Exploring the evolution of SARS-CoV-2 load and clearance from the upper respiratory tract samples is important to improving COVID-19 control. Data were collected retrospectively from a laboratory dataset on SARS-CoV-2 load quantified in leftover nasal pharyngeal swabs (NPSs) collected from symptomatic/asymptomatic individuals who tested positive to SARS-CoV-2 RNA detection in the framework of testing activities for diagnostic/screening purpose during the 2020 and 2021 winter epidemic waves. (2) Methods. A Statistical approach (quantile regression and survival models for interval-censored data), novel for this kind of data, was applied. We included in the analysis SARS-CoV-2-positive adults >18 years old for whom at least two serial NPSs were collected. A total of 262 SARS-CoV-2-positive individuals and 784 NPSs were included: 193 (593 NPSs) during the 2020 winter wave (before COVID-19 vaccine introduction) and 69 (191 NPSs) during the 2021 winter wave (all COVID-19 vaccinated). We estimated the trend of the median value, as well as the 25th and 75th centiles of the viral load, from the index episode (i.e., first SARS-CoV-2-positive test) until the sixth week (2020 wave) and the third week (2021 wave). Interval censoring methods were used to evaluate the time to SARS-CoV-2 clearance (defined as Ct < 35). (3) Results. At the index episode, the median value of viral load in the 2021 winter wave was 6.25 log copies/mL (95% CI: 5.50–6.70), and the median value in the 2020 winter wave was 5.42 log copies/mL (95% CI: 4.95–5.90). In contrast, 14 days after the index episode, the median value of viral load was 3.40 log copies/mL (95% CI: 3.26–3.54) for individuals during the 2020 winter wave and 2.93 Log copies/mL (95% CI: 2.80–3.19) for those of the 2021 winter wave. A significant difference in viral load shapes was observed among age classes (p = 0.0302) and between symptomatic and asymptomatic participants (p = 0.0187) for the first wave only; the median viral load value is higher at the day of episode index for the youngest (18–39 years) as compared to the older (40–64 years and >64 years) individuals. In the 2021 epidemic, the estimated proportion of individuals who can be considered infectious (Ct < 35) was approximately half that of the 2020 wave. (4) Conclusions. In case of the emergence of new SARS-CoV-2 variants, the application of these statistical methods to the analysis of virological laboratory data may provide evidence with which to inform and promptly support public health decision-makers in the modification of COVID-19 control measures. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

10 pages, 956 KB

Open AccessArticle

Self-Efficacy and Self-Care as Risk Factors for Ischemic Stroke: Development and Validation of a Nomogram

by Al Rasyid, Uke Pemila, Siti Aisah, Salim Harris, Elvan Wiyarta and Marc Fisher

J. Clin. Med. 2023, 12(17), 5665; https://doi.org/10.3390/jcm12175665 - 31 Aug 2023

Cited by 4 | Viewed by 2306

Abstract

Background: This study addresses the knowledge gap on how self-efficacy and self-care affect stroke risk as factors and develops a valuable tool for clinicians to assess stroke risk. Methods: From January 2022 to January 2023, this nested-case control study was conducted. Medical data including gender, age, ethnicity, locality, education, marital status, employment, caregiver, social environment, blood viscosity, Barthel Index, modified Rankin Scale (mRS), stroke risk score, self-care score, and self-efficacy score were collected. Logistic regression was used to predict stroke risk, and a nomogram was developed and validated. Results: 240 patients were included in the analysis. Stroke risk score (OR: 3.513; p = 0.005), self-efficacy score (OR: 0.753; p = 0.048), and self-care score (OR: 0.817; p = 0.018) were predictors of ischemic stroke. Internal validation was carried out, with a C-index of 0.774, and the Hosmer–Lemeshow test indicated a good fit (p = 0.92). The calibration plot also shows that this nomogram model has good calibration abilities. The decision curve analysis (DCA) results show a threshold probability range of 10–95%. Conclusion: A nomogram has been developed with good validity, calibration, and clinical utility, including self-care and self-efficacy as risk factors for predicting ischemic stroke. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

13 pages, 1190 KB

Open AccessArticle

Development and External Validation of Partial Proportional Odds Risk Prediction Models for Cancer Stage at Diagnosis among Males and Females in Canada

by Timofei Biziaev, Michelle L. Aktary, Qinggang Wang, Thierry Chekouo, Parveen Bhatti, Lorraine Shack, Paula J. Robson and Karen A. Kopciuk

Cancers 2023, 15(14), 3545; https://doi.org/10.3390/cancers15143545 - 8 Jul 2023

Viewed by 1812

Abstract

Risk prediction models for cancer stage at diagnosis may identify individuals at higher risk of late-stage cancer diagnoses. Partial proportional odds risk prediction models for cancer stage at diagnosis for males and females were developed using data from Alberta’s Tomorrow Project (ATP). Prediction models were validated on the British Columbia Generations Project (BCGP) cohort using discrimination and calibration measures. Among ATP males, older age at diagnosis was associated with an earlier stage at diagnosis, while full- or part-time employment, prostate-specific antigen testing, and former/current smoking were associated with a later stage at diagnosis. Among ATP females, mammogram and sigmoidoscopy or colonoscopy were associated with an earlier stage at diagnosis, while older age at diagnosis, number of pregnancies, and hysterectomy were associated with a later stage at diagnosis. On external validation, discrimination results were poor for both males and females while calibration results indicated that the models did not over- or under-fit to derivation data or over- or under-predict risk. Multiple factors associated with cancer stage at diagnosis were identified among ATP participants. While the prediction model calibration was acceptable, discrimination was poor when applied to BCGP data. Updating our models with additional predictors may help improve predictive performance. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

15 pages, 1893 KB

Open AccessArticle

Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers

by Yoon Kyoung So, Zero Kim, Taek Yoon Cheong, Myung Jin Chung, Chung-Hwan Baek, Young-Ik Son, Jungirl Seok, Yuh-Seog Jung, Myung-Ju Ahn, Yong Chan Ahn, Dongryul Oh, Baek Hwan Cho and Man Ki Chung

Cancers 2023, 15(14), 3540; https://doi.org/10.3390/cancers15143540 - 8 Jul 2023

Cited by 4 | Viewed by 2317

Abstract

Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model’s performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (N = 778), data were augmented to split the training dataset (N = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

13 pages, 1379 KB

Open AccessArticle

Same but Different? Comparing the Epidemiology, Treatments and Outcomes of COVID-19 and Non-COVID-19 ARDS Cases in Germany Using a Sample of Claims Data from 2021 and 2019

by Eva Bernauer, Felix Alebrand and Manuel Heurich

Viruses 2023, 15(6), 1324; https://doi.org/10.3390/v15061324 - 5 Jun 2023

Cited by 3 | Viewed by 2886

Abstract

Background: Acute respiratory distress syndrome (ARDS) is a severe lung condition that can be caused by a variety of underlying illnesses. Due to SARS-CoV-2, the number of cases with ARDS has increased worldwide, making it essential to compare this form of acute respiratory failure with classical causes of ARDS. While there have been several studies investigating the differences between COVID-19 and non-COVID-19 ARDS in early stages of the pandemic, little is known about the differences in later phases, especially in Germany. Aim: The aim of this study is to characterize and compare the comorbidities, treatments, adverse events, and outcomes of COVID-19-associated ARDS and non-COVID-19 ARDS using a representative sample of German health claims data from the years 2019 and 2021. Methods: We compare percentages and median values of the quantities of interest from the COVID-19 and non-COVID-19 ARDS group, with p-values calculated after conducting Pearson’s chi-squared test or the Wilcoxon rank sum test. We also run logistic regressions to access the effect of comorbidities on mortality for COVID-19 ARDS and non-COVID-19 ARDS. Results: Despite many similarities, we find that that there are some remarkable differences between COVID-19 and non-COVID-19 ARDS cases in Germany. Most importantly, COVID-19 ARDS cases display fewer comorbidities and adverse events, and are more often treated with non-invasive ventilation and nasal high-flow therapy. Conclusions: This study highlights the importance of comprehending the contrasting epidemiological features and clinical outcomes of COVID-19 and non-COVID-19 ARDS. This understanding can aid in clinical decision making and guide future research initiatives aimed at enhancing the management of patients afflicted with this severe condition. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

16 pages, 2793 KB

Open AccessArticle

Population-Based Model of the Fraction of Incidental COVID-19 Hospitalizations during the Omicron BA.1 Wave in the United States

by Jeffrey E. Harris

COVID 2023, 3(5), 728-743; https://doi.org/10.3390/covid3050054 - 8 May 2023

Cited by 2 | Viewed by 2800

Abstract

1. Background: Some reports have suggested that as many as one-half of all hospital inpatients identified as COVID-19-positive during the Omicron BA.1 variant-driven wave were incidental cases admitted primarily for reasons other than their viral infections. To date, however, there are no prospective longitudinal studies of a representative panel of hospitals based on pre-established criteria for determining whether a patient was, in fact, admitted as a result of the disease. 2. Materials and Methods: To fill this gap, we developed a formula to estimate the fraction of incidental COVID-19 hospitalizations that relies on measurable, population-based parameters. We applied our approach to a longitudinal panel of 164 counties throughout the United States, covering a 4-week interval ending in the first week of January 2022. 3. Results: Within this panel, we estimated that COVID-19 incidence was rising exponentially at a rate of 9.34% per day (95% CI, 8.93–9.87). Assuming that only one-quarter of all Omicron BA.1 infections had been reported by public authorities, we further estimated the aggregate prevalence of active SARS-CoV-2 infection during the first week of January to be 3.45%. During the same week, among 250 high-COVID-volume hospitals within our 164-county panel, an estimated one in four inpatients was COVID-positive. Based upon these estimates, we computed that 10.6% of such COVID-19-positive hospitalized patients were incidental infections. Across individual counties, the median fraction of incidental COVID-19 hospitalizations was 9.5%, with an interquartile range of 6.7 to 12.7%. 4. Conclusion: Incidental COVID-19 infections appear to have been a nontrivial fraction of all COVID-19-positive hospitalized patients during the Omicron BA.1 wave. In the aggregate, however, the burden of patients admitted for complications of their viral infections was far greater. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

16 pages, 1840 KB

Open AccessArticle

Sensitivity and Specificity of Different Prognostic Systems in Guiding Surveillance for Metastases in Uveal Melanoma

by Helena Robinson, Antonio Eleuteri, Joseph J. Sacco, Rumana Hussain, Heinrich Heimann, Azzam F. G. Taktak, Bertil Damato, Alexander J. Thompson, Thomas Allen, Helen Kalirai and Sarah E. Coupland

Cancers 2023, 15(9), 2610; https://doi.org/10.3390/cancers15092610 - 4 May 2023

Cited by 7 | Viewed by 2278

Abstract

Uveal melanoma (UM) metastasises in ~50% of patients, most frequently to the liver. Surveillance imaging can provide early detection of hepatic metastases; however, guidance regarding UM patient risk stratification for surveillance is unclear. This study compared sensitivity and specificity of four current prognostic systems, when used for risk stratification for surveillance, on patients treated at the Liverpool Ocular Oncology Centre (LOOC) between 2007–2016 (n = 1047). It found that the Liverpool Uveal Melanoma Prognosticator Online III (LUMPOIII) or Liverpool Parsimonious Model (LPM) offered greater specificity at equal levels of sensitivity than the American Joint Committee on Cancer (AJCC) system or monosomy 3 alone, and suggests guidance to achieve 95% sensitivity and 51% specificity (i.e., how to detect the same number of patients with metastases, while reducing the number of negative scans). For example, 180 scans could be safely avoided over 5 years in 200 patients using the most specific approach. LUMPOIII also offered high sensitivity and improved specificity over the AJCC in the absence of genetic information, making the result relevant to centres that do not perform genetic testing, or where such testing is inappropriate or fails. This study provides valuable information for clinical guidelines for risk stratification for surveillance in UM. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

14 pages, 4289 KB

Open AccessArticle

Rapid and Accurate Discrimination of Mycobacterium abscessus Subspecies Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Spectrum and Machine Learning Algorithms

by Hsin-Yao Wang, Chi-Heng Kuo, Chia-Ru Chung, Wan-Ying Lin, Yu-Chiang Wang, Ting-Wei Lin, Jia-Ruei Yu, Jang-Jih Lu and Ting-Shu Wu

Biomedicines 2023, 11(1), 45; https://doi.org/10.3390/biomedicines11010045 - 25 Dec 2022

Cited by 12 | Viewed by 3087

Abstract

Mycobacterium abscessus complex (MABC) has been reported to cause complicated infections. Subspecies identification of MABC is crucial for adequate treatment due to different antimicrobial resistance properties amid subspecies. However, long incubation days are needed for the traditional antibiotic susceptibility testing (AST). Delayed effective antibiotics administration often causes unfavorable outcomes. Thus, we proposed a novel approach to identify subspecies and potential antibiotic resistance, guiding early and accurate treatment. Subspecies of MABC isolates were determined by secA1, rpoB, and hsp65. Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI–TOF MS) spectra were analyzed, and informative peaks were detected by random forest (RF) importance. Machine learning (ML) algorithms were used to build models for classifying MABC subspecies based on spectrum. The models were validated by repeated five-fold cross-validation to avoid over-fitting. In total, 102 MABC isolates (52 subspecies abscessus and 50 subspecies massiliense) were analyzed. Top informative peaks including m/z 6715, 4739, etc. were identified. RF model attained AUROC of 0.9166 (95% CI: 0.9072–0.9196) and outperformed other algorithms in discriminating abscessus from massiliense. We developed a MALDI–TOF based ML model for rapid and accurate MABC subspecies identification. Due to the significant correlation between subspecies and corresponding antibiotics resistance, this diagnostic tool guides a more precise and timelier MABC subspecies-specific treatment. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

14 pages, 13964 KB

Open AccessArticle

Blood Pressure Signal Entropy as a Novel Marker of Physical Frailty: Results from the FRAILMatics Clinical Cohort

by Silvin P. Knight, Eoin Duggan and Roman Romero-Ortuno

J. Clin. Med. 2023, 12(1), 53; https://doi.org/10.3390/jcm12010053 - 21 Dec 2022

Cited by 1 | Viewed by 2046

Abstract

In this study we investigated the association between information entropy in short length blood pressure signals and physical frailty status, in a group of patients aged 50+ recruited from the Falls and Syncope Unit at the Mercer’s Institute for Successful Ageing in St James’s Hospital, Dublin, Ireland. This work is an external clinical validation of findings previously derived in a population-based cohort from The Irish Longitudinal Study on Ageing (TILDA). The hypothesis under investigation was that dysregulation (as quantified by entropy) in continuous non-invasive blood pressure signals could provide a clinically useful marker of physical frailty status. We found that in the 100 patients investigated, higher entropy in continuously measured resting state diastolic blood pressure was associated with worse physical frailty score, as measured by the Frailty Instrument for primary care of the Survey of Health, Ageing and Retirement in Europe (SHARE-FI). Since physical frailty is defined as a pre-disability state and hence it can be difficult for clinicians to identify at an early stage, the quantification of entropy in short length cardiovascular signals could provide a clinically useful marker of the physiological dysregulations that underlie physical frailty, potentially aiding in identifying individuals at higher risk of adverse health outcomes. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

11 pages, 575 KB

Open AccessArticle

Goals of Care, Critical Care Utilization and Clinical Outcomes in Obese Patients Admitted under General Medicine

by Andy K. H. Lim, Greasha K. Rathnasekara, Priyanka Kanumuri, Janith K. Malawaraarachchi, Zheng Song and Claire A. Curtis

J. Clin. Med. 2022, 11(24), 7267; https://doi.org/10.3390/jcm11247267 - 7 Dec 2022

Cited by 1 | Viewed by 1721

Abstract

Obesity is associated with long-term morbidity and mortality, but it is unclear if obesity affects goals of care determination and intensive care unit (ICU) resource utilization during hospitalization under a general medicine service. In a cohort of 5113 adult patients admitted under general medicine, 15.3% were obese. Patients with obesity were younger and had a different comorbidity profile than patients who were not obese. In age-adjusted regression analysis, the distribution of goals of care categories for patients with obesity was not different to patients who were not obese (odds ratio for a lower category with more limitations, 0.94; 95% confidence interval [CI]: 0.79–1.12). Patients with obesity were more likely to be directly admitted to ICU from the Emergency Department, require more ICU admissions, and stayed longer in ICU once admitted. Hypercapnic respiratory failure and heart failure were more common in patients with obesity, but they were less likely to receive mechanical ventilation in favor of non-invasive ventilation. The COVID-19 pandemic was associated with 16% higher odds of receiving a lower goals of care category, which was independent of obesity. Overall hospital length of stay was not affected by obesity. Patients with obesity had a crude mortality of 3.8 per 1000 bed-days, and age-adjusted mortality rate ratio of 0.75 (95% CI: 0.49–1.14) compared to patients who were not obese. In conclusion, there was no evidence to suggest biased goals of care determination in patients with obesity despite greater ICU resource utilization. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

15 pages, 10892 KB

Open AccessArticle

Selective Electrochemical Detection of SARS-CoV-2 Using Deep Learning

by Ozhan Gecgel, Ashwin Ramanujam and Gerardine G. Botte

Viruses 2022, 14(9), 1930; https://doi.org/10.3390/v14091930 - 30 Aug 2022

Cited by 9 | Viewed by 2890

Abstract

COVID-19 has been in the headlines for the past two years. Diagnosing this infection with minimal false rates is still an issue even with the advent of multiple rapid antigen tests. Enormous data are being collected every day that could provide insight into reducing the false diagnosis. Machine learning (ML) and deep learning (DL) could be the way forward to process these data and reduce the false diagnosis rates. In this study, ML and DL approaches have been applied to the data set collected using an ultra-fast COVID-19 diagnostic sensor (UFC-19). The ability of ML and DL to specifically detect SARS-CoV-2 signals against SARS-CoV, MERS-CoV, Human CoV, and Influenza was investigated. UFC-19 is an electrochemical sensor that was used to test these virus samples and the obtained current response dataset was used to diagnose SARS-CoV-2 using different algorithms. Our results indicate that the convolution neural networks algorithm could diagnose SARS-CoV-2 samples with a sensitivity of 96.15%, specificity of 98.17%, and accuracy of 97.20%. Combining this DL model with the existing UFC-19 could selectively identify SARS-CoV-2 presence within two minutes. Full article

(This article belongs to the Topic Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods)

► Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Displaying articles 1-11

Submit your Abstract

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Biomedicines biomedicines	3.9	6.8	2013	17 Days	CHF 2600
Cancers cancers	4.4	8.8	2009	20.3 Days	CHF 2900
COVID covid	1.0	2.3	2021	20.6 Days	CHF 1200
International Journal of Environmental Research and Public Health ijerph	-	8.5	2004	27.8 Days	CHF 2500
Journal of Clinical Medicine jcm	2.9	5.2	2012	17.7 Days	CHF 2600
Viruses viruses	3.5	7.7	2009	18.6 Days	CHF 2600

Topic Menu

Topic Editors

Analytics and Modelling Clinical Data Using Advanced Biostatistical Methods

Topic Information

Keywords

Participating Journals

Published Papers (11 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI