Artificial Intelligence Applications in Public Health
A special issue of Computation (ISSN 2079-3197).
Deadline for manuscript submissions: 30 November 2024 | Viewed by 5621
Special Issue Editors
2. Ubiquitous Health Technologies Lab, University of Waterloo, Waterloo, ON, Canada
Interests: artificial intelligence; machine learning; epidemic model; infectious diseases simulation
Special Issues, Collections and Topics in MDPI journals
Interests: mathematical modeling; optimization of complex systems; combinatorial optimization; packing and covering problems; computational intelligence
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
We're pleased to announce a forthcoming Special Issue titled “Artificial Intelligence Applications in Public Health”. This Special Issue aims to gather research studies across various disciplines to shed light on the cutting-edge uses of computational techniques and artificial intelligence (AI) in the field of public health.
This Special Issue emphasizes AI's transformative potential in managing and addressing critical challenges in public health, from disease surveillance, outbreak prediction, and health systems’ optimization, to personalized health interventions. The rapidly expanding capabilities of AI and computation make them increasingly indispensable in public health decision making, enhancing both efficiency and effectiveness.
The articles collected in this Special Issue will cover a broad spectrum of topics, including, but not limited to, AI-enhanced predictive modeling for disease spread; big data analytics for health trend forecasting; machine learning for patient stratification; and deep learning for image-based diagnostics in public health settings. With this Special Issue, we aim to provide a comprehensive overview of the current state of the art of this field and to inspire innovative future research.
This Special Issue is a call to all researchers, data scientists, public health experts, and policymakers to submit their original research, reviews, case studies, and thought-provoking perspectives that demonstrate the novel uses and potentials of AI and computation in public health.
Dr. Dmytro Chumachenko
Dr. Sergiy Yakovlev
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 submissions that pass pre-check are 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. Computation 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
- public health
- computation
- disease surveillance
- predictive modeling
- health systems optimization
- public health informatics
- data-driven medicine
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: Resilient-aware MLOps for AI-based Medical Diagnostic Systems
Authors: Viacheslav Moskalenko; Vyacheslav Kharchenko
Affiliation: Computer Science Department, Sumy State University, Sumy, Ukraine; Head of Department of Computer Systems, Networks and Cybersecurity National Aerospace University "KhAI", Kharkiv, Ukraine
Abstract: The healthcare sector demands a higher degree of responsibility, trustworthiness, and accountability when implementing AI systems. Machine learning operations (MLOps) for AI-based medical diagnostic systems are primarily focused on aspects such as data quality and confidentiality, bias reduction, model deployment, performance monitoring, and continuous improvement. However, MLOps techniques do not take into account the need to provide resilience to disturbances such as adversarial attacks, including fault injections, and drift, including out-of-distribution. Resilience is defined as the ability to absorb disturbances, detect disturbances (or estimate uncertainty), degrade gracefully, and adapt models quickly without losing (forgetting) the experience accumulated in the models.
The subject of study is the methods of ensuring the resilience of AI systems as a component of MLOps for AI-based Medical Diagnostic Systems. The goal is to improve the MLOPs methodology for AI-based Medical Diagnostic Systems by identifying characteristic disturbances in healthcare and developing appropriate methods to ensure resilience as part of MLOPs. The paper analyzes and systematizes the disturbing influences on Medical Diagnostic Systems, DevOPS methods, and methods for ensuring the resilience of AI systems. In addition, the positive effect of the implementation of Resilient-aware MLOps in Medical Diagnostic Systems was experimentally confirmed on the the task of classifying medical images into malignant and benign classes. The study used large, publicly available clinical datasets such as BreakHis, BraTS, NIH-Xray and COVID-19 X-ray in different scenarios of disturbance exposure.
Title: Personified Approach to the Bone Density Measuring
Authors: Viktor Reshetnik1; Alina Nechyporenko1,2; Ievgen Meniailov3; Marcus Frohme2; Victoriia Alekseeva2,4,5; Andrii Lupyr4; Vitaliy Gargin4,5
Affiliation: 1Systems Engineering Department, Kharkiv National University of Radioelectronics, Kharkiv, Ukraine
2Department of Molecular Biotechnology and Functional Genomics, Technical University of Applied Sciences, Wildau, Germany
3 V.N. Karazin Kharkiv National University, Kharkiv, Ukraine
4Department of Otorhinolaryngology, Kharkiv National Medical University, Kharkiv, Ukraine
5Department of Professionally Oriented Disciplines, Kharkiv International Medical University, Kharkiv, Ukraine
Abstract: Abstract: Density serves as a crucial diagnostic indicator for the structure of bone tissue, with alterations in this structure being a pivotal factor in complications risk. The aim of our study is to develop a personified approach to determining the density of paranasal sinus bone tissue for potential integration into medical practice.
Material and Methods: A study involving 100 young males and females included dual CT scans for each group, unrelated to ENT pathology. Based on the scan timing, patients were categorized into two groups, and the research unfolded in four stages:
a. Initial CT Scan Uncertainty Computation. In the first stage, we computed uncertainty for patients by analyzing their initial CT scans
b. Specific Time Interval Uncertainty Computation: the second stage involved repeating uncertainty calculations at specific intervals (1-2 years and 4-5 years in our case)
c. Identification of High-Priority Patients
d. Implementation of a Chat-bot for Identifying Factors Impacting Density:
Results: The range of U value spread is within the +-Uc range concerning the measured y value. The certainty degree for Y values in this interval is determined by the probability (confidence level) p = 0.95.
Conclusions: In assessing the condition of bone tissue, we employed the method of uncertainty calculation. Detected changes in bone tissue structure, such as a decrease in density over time, can serve as precursors to complications, emphasizing not only the diagnostic but also the preventive role of studying this parameter.
The application of uncertainty calculation methods in various time intervals allows for a more precise determination of the dynamics of changes and identification of patients who require special attention.
The effective integration of a Chabot into medical practice enables a personalized approach to each patient and the identification of a group of individuals whose inflammatory processes may be associated with the potential development of complications.