Special Issue "Big Data in Biology, Life Sciences and Healthcare"

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Biological Systems".

Deadline for manuscript submissions: 10 November 2019.

Special Issue Editors

Guest Editor
Prof. Peter He Website E-Mail
Chemical Engineering, Auburn University, Auburn, AL 36849, USA
Interests: Smart manufacturing; Big data; Data analytics; Cancer informatics; Modeling and control
Guest Editor
Prof. Jin Wang Website E-Mail
Department of Chemical Engineering, Auburn University, Auburn, Alabama 36849, USA
Interests: apply systems engineering approaches, control engineering principles and techniques in particular, to understand, predict, and control complex dynamic processes

Special Issue Information

Dear Colleagues,

Massive quantities of data are being generated in biology, the life sciences and healthcare industries and institutions, which hold the promise of advancing our understandings of various biological systems and diseases, developing new biocatalysts and drugs, as well as delivering more effective patient care and reducing costs, etc. In this Special Issue, we seek research and case studies that demonstrate the application of big data modeling and analysis to support scientific research, drug development, clinical decision making, personalized medicine, and other critical tasks. Example topics include (but are not limited to) the following topics relating big data to biology, the life sciences or healthcare:

  • Novel systems engineering approaches, including modeling and numerical analysis algorithms
  • New statistical tools and algorithms
  • Machine learning and artificial intelligence
  • Integration of systems engineering approaches with machine learning
  • Novel visualization approaches
  • Computer or model-aided diagnostics
  • Model-based drug development
  • Evidence-based medicine
  • Modeling and analysis of data from a multitude of sources
  • Application of wearable devices
  • Public health surveillance

Prof. Peter He
Prof. Jin Wang
Guest Editors

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. Processes 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 1200 CHF (Swiss Francs). Please note that for papers submitted after 31 December 2019 an APC of 1400 CHF applies. 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

  • big data
  • omics data
  • electronic health record
  • modeling
  • monitoring
  • optimization
  • visualization
  • statistical analysis
  • machine learning
  • artificial intelligence
  • systems biology
  • biocatalyst
  • healthcare
  • drug development

Published Papers (7 papers)

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

Research

Open AccessArticle
Proposal of a Learning Health System to Transform the National Health System of Spain
Processes 2019, 7(9), 613; https://doi.org/10.3390/pr7090613 - 10 Sep 2019
Abstract
This article identifies the main challenges of the National Health Service of Spain and proposes its transformation into a Learning Health System. For this purpose, the main indicators and reports published by the Spanish Ministries of Health and Finance, Organization for Economic Co-operation [...] Read more.
This article identifies the main challenges of the National Health Service of Spain and proposes its transformation into a Learning Health System. For this purpose, the main indicators and reports published by the Spanish Ministries of Health and Finance, Organization for Economic Co-operation and Development (OECD) and World Health Organization (WHO) were reviewed. The Learning Health System proposal is based on some sections of an unpublished report, written by two of the authors under request of the Ministry of Health of Spain on Big Data for the National Health System. The main challenges identified are the rising old age dependency ratio; health expenditure pressures and the likely increase of out-of-pocket expenditure; drug expenditures, both retail and consumed in hospitals; waiting lists for surgery; potentially preventable hospital admissions; and the use of electronic health record (EHR) data to fulfil national health information and research objectives. To improve its efficacy, efficiency, and quality, the National Health Service of Spain should be transformed into a Learning Health System. Information and communication technologies (IT) enablers are a fundamental tool to address the complexity and vastness of health data as well as the urgency that clinical and management decisions require. Big Data solutions are a perfect match for that problem in health systems. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Show Figures

Figure 1

Open AccessArticle
Key Points for an Ethical Evaluation of Healthcare Big Data
Processes 2019, 7(8), 493; https://doi.org/10.3390/pr7080493 - 01 Aug 2019
Cited by 1
Abstract
Background: The article studies specific ethical issues arising from the use of big data in Life Sciences and Healthcare. Methods: Main consensus documents, other studies, and particular cases are analyzed. Results: New concepts that emerged in five key areas for the bioethical debate [...] Read more.
Background: The article studies specific ethical issues arising from the use of big data in Life Sciences and Healthcare. Methods: Main consensus documents, other studies, and particular cases are analyzed. Results: New concepts that emerged in five key areas for the bioethical debate on big data and health are identified—the accuracy and validity of data and algorithms, questions related to transparency and confidentiality in the use of data; aspects that raise the coding or pseudonymization and the anonymization of data, and also problems derived from the possible individual or group identification; the new ways of obtaining consent for the transfer of personal data; the relationship between big data and the responsibility of professional decision; and the commitment of the Institutions and Public Administrations. Conclusions: Good practices in the management of big data related to Life Sciences and Healthcare depend on respect for the rights of individuals, the improvement that these practices can introduce in assistance to individual patients, the promotion of society’s health in general and the advancement of scientific knowledge. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Open AccessArticle
CDL4CDRP: A Collaborative Deep Learning Approach for Clinical Decision and Risk Prediction
Processes 2019, 7(5), 265; https://doi.org/10.3390/pr7050265 - 07 May 2019
Abstract
(1) Background: Recommendation algorithms have played a vital role in the prediction of personalized recommendation for clinical decision support systems (CDSSs). Machine learning methods are powerful tools for disease diagnosis. Unfortunately, they must deal with missing data, as this will result in data [...] Read more.
(1) Background: Recommendation algorithms have played a vital role in the prediction of personalized recommendation for clinical decision support systems (CDSSs). Machine learning methods are powerful tools for disease diagnosis. Unfortunately, they must deal with missing data, as this will result in data error and limit the potential patterns and features associated with obtaining a clinical decision; (2) Methods: Recent years, collaborative filtering (CF) have proven to be a valuable means of coping with missing data prediction. In order to address the challenge of missing data prediction and latent feature extraction, neighbor-based and latent features-based CF methods are presented for clinical disease diagnosis. The novel discriminative restricted Boltzmann machine (DRBM) model is proposed to extract the latent features, where the deep learning technique is adopted to analyze the clinical data; (3) Results: Proposed methods were compared to machine learning models, using two different publicly available clinical datasets, which has various types of inputs and different quantity of missing. We also evaluated the performance of our algorithm, using clinical datasets that were missing at random (MAR), which were missing at various degrees; and (4) Conclusions: The experimental results demonstrate that DRBM can effectively capture the latent features of real clinical data and exhibits excellent performance for predicting missing values and result classification. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Show Figures

Figure 1

Open AccessArticle
Filter Variable Selection Algorithm Using Risk Ratios for Dimensionality Reduction of Healthcare Data for Classification
Processes 2019, 7(4), 222; https://doi.org/10.3390/pr7040222 - 18 Apr 2019
Abstract
This research developed and tested a filter algorithm that serves to reduce the feature space in healthcare datasets. The algorithm binarizes the dataset, and then separately evaluates the risk ratio of each predictor with the response, and outputs ratios that represent the association [...] Read more.
This research developed and tested a filter algorithm that serves to reduce the feature space in healthcare datasets. The algorithm binarizes the dataset, and then separately evaluates the risk ratio of each predictor with the response, and outputs ratios that represent the association between a predictor and the class attribute. The value of the association translates to the importance rank of the corresponding predictor in determining the outcome. Using Random Forest and Logistic regression classification, the performance of the developed algorithm was compared against the regsubsets and varImp functions, which are unsupervised methods of variable selection. Equally, the proposed algorithm was compared with the supervised Fisher score and Pearson’s correlation feature selection methods. Different datasets were used for the experiment, and, in the majority of the cases, the predictors selected by the new algorithm outperformed those selected by the existing algorithms. The proposed filter algorithm is therefore a reliable alternative for variable ranking in data mining classification tasks with a dichotomous response. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Show Figures

Figure 1

Open AccessArticle
Employment of Emergency Advanced Nurses of Turkey: A Discrete-Event Simulation Application
Processes 2019, 7(1), 48; https://doi.org/10.3390/pr7010048 - 18 Jan 2019
Abstract
In the present study, problems in emergency services (ESs) were dealt with by analyzing the working system of ESs in Turkey. The purpose of this study was to reduce the waiting times spent in hospitals by employing advanced nurses (ANs) to treat patients [...] Read more.
In the present study, problems in emergency services (ESs) were dealt with by analyzing the working system of ESs in Turkey. The purpose of this study was to reduce the waiting times spent in hospitals by employing advanced nurses (ANs) to treat patients who are not urgent, or who may be treated as outpatients in ESs. By applying discrete-event simulation on a 1/24 (daily) and 7/24 (weekly) basis, and by employing ANs, it was determined that the number of patients that were treated increased by 26.71% on a 1/24 basis, and by 15.13% on a 7/24 basis. The waiting time that was spent from the admission to the ES until the treatment time decreased by 38.67% on a 1/24 basis and 53.66% on a 24/7 basis. Similarly, the length of stay was reduced from 82.46 min to 53.97 min in the ES. Among the findings, it was observed that the efficiency rate of the resources was balanced by the employment of ANs, although it was not possible to obtain sufficient efficiency from the resources used in the ESs prior to the present study. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Show Figures

Figure 1

Open AccessArticle
Catastrophic Health Expenditures and Its Inequality in Households with Cancer Patients: A Panel Study
Processes 2019, 7(1), 39; https://doi.org/10.3390/pr7010039 - 14 Jan 2019
Abstract
This study aims to examine the determinants of catastrophic health expenditure in households with cancer patients by conducting a panel analysis of three-year data. Data are adopted from surveys administered by Korea Health Panel for 2012–2014. We conducted correspondence and conditional transition probability [...] Read more.
This study aims to examine the determinants of catastrophic health expenditure in households with cancer patients by conducting a panel analysis of three-year data. Data are adopted from surveys administered by Korea Health Panel for 2012–2014. We conducted correspondence and conditional transition probability analyses to examine households that incurred catastrophic health expenditure, followed by a panel logit analysis. The analyses reveal three notable results. First, the occurrence of catastrophic health expenditure differs by age group, that is, the probability of incurring catastrophic health expenditure increases with age. Second, this probability is higher in households with National Health Insurance than those receiving medical care benefits. Finally, households without private health insurance report a higher occurrence rate. The findings suggest that elderly people with cancer have greater medical coverage and healthcare needs. Private health insurance contributes toward protecting households from catastrophic health expenditure. Therefore, future research is needed on catastrophic health expenditure with focus on varying age groups, healthcare coverage type, and private health insurance. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Open AccessArticle
An Efficient Solitary Senior Citizens Care Algorithm and Application: Considering Emotional Care for Big Data Collection
Processes 2018, 6(12), 244; https://doi.org/10.3390/pr6120244 - 27 Nov 2018
Cited by 3
Abstract
The issue of solitary senior citizens dying alone has become serious in advanced countries where the average lifespan of their citizens is continuously extending due to improved health care and diet. Such unattended deaths are considered to be one of the major issues [...] Read more.
The issue of solitary senior citizens dying alone has become serious in advanced countries where the average lifespan of their citizens is continuously extending due to improved health care and diet. Such unattended deaths are considered to be one of the major issues pertaining to the ever-growing number of senior citizens so that many research studies have been conducted to find a solution to mitigate the situation. The framework proposed in this study allows monitoring of electric power consumption patterns of solitary senior citizens. At the same time, a test bed was constructed to estimate the performance of the framework. The results from the test bed experiment revealed that the framework was effective, flexible, and expandable for actual implementation. This framework is the product of these research studies describing individual designs and the method of implementing them for actual application. This research has confirmed that the framework for an extendable solitary senior citizens care system can be designed and implemented at low cost and the operations between system components worked smoothly while interacting flexibly. In particular, the rate of these old people dying alone in poor areas was above normal so that the proposed system would be quite meaningful to society as it helps in monitoring their safety by locating the whereabouts of those people with dementia or checking their daily routines, for example. Full article
(This article belongs to the Special Issue Big Data in Biology, Life Sciences and Healthcare)
Show Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Construction process and application of Chinese medical Health knowledge Map based on deep learning
Author:Dalin Zhang
Abstract: Hospital electronic medical records as the core clinical data, it records the patient's disease, diagnosis and treatment information. Mining such data can assist doctors in clinical research and clinical diagnosis and treatment. In this paper, we first proposed one construction process of clinical specialty database based on Chinese knowledge map, and put forward the solution to each task in this process. Secondly, we carry out two aspects clinical medical applications, include clinical curative effect analysis and disease prediction based on knowledge map, and gave the experimental results.

Title: Detection of drivers’ anxiety invoked by driving situations using multimodal bio-signals
Author: Dr. Sung-Phil
Abstract: It is important to monitor drivers’ negative emotions during driving to prevent accidents. Despite drivers’ anxiety being critical for safe driving, there lack systematic approaches to detect anxiety in driving situations. This study employed multimodal bio-signals, including photoplethysmography (PPG), electrodermal activity (EDA), pupil and electroencephalography (EEG), to infer anxiety at various driving situations. Thirty-one drivers with at least one year of driving experience watched a set of thirty black box videos including anxiety-invoking events and another set of thirty videos without them, while their bio-signals were measured. Then, they self-reported anxiety-invoked point in each video, from which features of each bio-signal were extracted. Support vector machine (SVM) classified single bio-signals to detect anxiety. Furthermore, in the order of PPG, EDA, pupil, and EEG (easiest to hardest accessibility), SVM classified accumulated multimodal signals. Classification using EEG showed the highest accuracy of 83.97%, followed by 62% and 63% using EDA and pupil size respectively. PPG yielded classification accuracy similar to the chance level (56%). Classifications using multiple bio-signals all reached less than 60% due to the impact of PPG. This study exhibited the feasibility of utilizing multi-modal bio-signals to detect anxiety invoked by driving situations, demonstrating benefits of EEG over other signals.

Back to TopTop