ijerph-logo

Journal Browser

Journal Browser

Artificial Intelligence and the Future of Public and Global Health: Promises, Expectations and Reality

A special issue of International Journal of Environmental Research and Public Health (ISSN 1660-4601). This special issue belongs to the section "Digital Health".

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 8903

Special Issue Editors

Brandeis International Business School, Waltham, MA 02453, USA
Interests: health information technology; big data analytics; information technology; decision support; online consumer behavior; healthcare information; social science and data science; internet health
Department of Science and Industry Systems, Faculty of Technology, Natural Sciences, and Maritime Sciences, University of South Eastern Norway, 3603 Kongsberg, Norway
Interests: predictive and learning technologies; semantic computing; pervasive computational spaces across problem domains; biomedical semantic and translational informatics; e-Health/M-health personalized healthcare; precision medicine; intelligent engineering
Computer Science Department, Texas A&M University-Commerce, Commerce, TX, USA
Interests: data mining; machine learning; artificial intelligence; bid data; data analytics; IoT

Special Issue Information

Dear Colleagues,

AI-driven health interventions and delivery have already started affecting the management of health services—from clinical decision making and predictions of mortality risk and healthcare planning to identifying disease outbreaks—thus addressing challenges in Public and Global Health. In this Special Issue, we would like to welcome papers which discuss the problems of suitability, reliability, and expectations of AI, learning, and predictive technologies in the Public/Global Health domains. This includes debates on the initiative for creating explainable and accountable AI to the public and to public health organizations. We would also like to receive papers which focus on the accuracy of the prediction apparatus used for forecasting in the time of pandemics, which may reveal their various perceptions, including public healthcare management and behavioral issues of individuals as well as societies. The three main themes of the Special Issue are itemized below. However, we also welcome any other research in progress and experiences of using learning and predictive technologies when the management of Public Health depends on our own manipulation of data and information generated during the COVID-19 pandemic.

We welcome papers in three areas of Artificial Intelligence intersecting with Public/Global Health.

1. Learning and predictive technologies facilitating Public Health sectors’ decision making: trends, feasibility studies, practicality, trustworthiness, and expectations:

  • Predictive and learning technologies in the context of managing PHO domain knowledge including the impact of individual behavior and group dynamics to organizational impacts and government policies;
  • Text and data mining, text sentiment analysis, and public opinions for the Public Health sector and their impact on decision making;
  • Collaboration between PHO professionals and computer scientists: from creating joint, sustainable, reliable, and accountable AI algorithms to dealing with uncertainty, validation of models, interaction effects, and combinations (ensembles) of modeling principles;
  • PHO practices based on case-based, history-based, rule-based, or regression-based reasoning versus predictive and logic based computational inference typical of ML and AI algorithms;
  • Transparency of AI and predictive models/algorithms to PHO professionals and policymakers: searching for technically rigorous and accurate models and opaque black-boxes, or looking at the levels of their explainabilities, interpretability, and intuitiveness for PHO;
  • Detecting paradigm shift in PHO regarding the deployment of AI: searching for new models and expectations from AI promises. Public Health practitioners’/policymakers’ approaches to dealing with black-box model values in layman’s terms;
  • AI accountability to public, PHO practitioners, policy makers and governments: awareness of bringing new software technologies, computational methods, and data processing to address issues and problems of PHO and their decision making;

 2. The accuracy of traditional statistic forecasting in time of pandemics and impact of data/software tools on their results:

  • Statistical and epidemiological models for predicting the outcome of epidemic/pandemic: characteristics, features, and parametrization (the role of R and its impact on modeling);
  • Impact of human behavior, healthcare organization functions, and efficient governance on statistical models in times of epidemics/pandemics;
  • Addressing the potentially biased nature of statistical models: provisions for uncertainty, validation, testing, and quality;
  • Improving the accuracy of the statistical models: from deploying software tools and collection/manipulation of abundance of data to creating new computational models and using predictive and learning technologies with AI algorithmic computing;

 3. Statistical models versus computational models versus data models: do they affect each other and do we understand the impact of their potential inter-relationship on modeling and predictions in the times of pandemics? Perceptions of pandemics, from governance, political decisions, and healthcare management to cultural and behavioral issues of individuals and societies:

  • Human perception in modeling, predicting, and communicating the results of a pandemic; the impact of human behavior on the modeling and interpretation/communication of modeling results;
  • Converting the results of modeling and predictions into clear messages, best practices, and adaptable procedures when managing and living during the pandemic, applicable to various types of audience;
  • Assessing risks in the pandemic: how citizens, healthcare professionals, business leaders, government leaders, opinion leaders, and celebrities assess the risks, costs, and benefits of different responses to the management of the pandemic;
  • Scientific evidence versus persuasion when managing pandemics and making decisions: understanding the difference between abstract modeling/predictions and real life situations;
  • Going a step further beyond a list of DOs and DON’Ts when managing a pandemic by creating accurate, precise, and actionable perceptions; making modeling intrinsically sensitive to different cultures, debating a tradeoff between “saving lives” and downturns in economies, sharing information and data across borders, and developing trust among different parties and political establishments;
  • Debating pandemics as an (un)avoidable, treatable, preventable, natural phenomenon and the source for learning from the experiences of others.

Dr. Arnold Kamis
Dr. Radmila Juric
Prof. Dr. Sang C. Suh
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. International Journal of Environmental Research and Public Health 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 2500 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

  • explainable artificial intelligence in healthcare
  • perceptions of artificial intelligence in healthcare
  • public healthcare management
  • strategic decision making
  • individual and societal behavior in pandemics
  • statistical models of pandemics
  • public health crisis
  • pandemics

Published Papers (2 papers)

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

Research

20 pages, 414 KiB  
Article
Do People Trust in Robot-Assisted Surgery? Evidence from Europe
by Joan Torrent-Sellens, Ana Isabel Jiménez-Zarco and Francesc Saigí-Rubió
Int. J. Environ. Res. Public Health 2021, 18(23), 12519; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph182312519 - 28 Nov 2021
Cited by 11 | Viewed by 5020
Abstract
(1) Background: The goal of the paper was to establish the factors that influence how people feel about having a medical operation performed on them by a robot. (2) Methods: Data were obtained from a 2017 Flash Eurobarometer (number 460) of the European [...] Read more.
(1) Background: The goal of the paper was to establish the factors that influence how people feel about having a medical operation performed on them by a robot. (2) Methods: Data were obtained from a 2017 Flash Eurobarometer (number 460) of the European Commission with 27,901 citizens aged 15 years and over in the 28 countries of the European Union. Logistic regression (odds ratios, OR) to model the predictors of trust in robot-assisted surgery was calculated through motivational factors, using experience and sociodemographic independent variables. (3) Results: The results obtained indicate that, as the experience of using robots increases, the predictive coefficients related to information, attitude, and perception of robots become more negative. Furthermore, sociodemographic variables played an important predictive role. The effect of experience on trust in robots for surgical interventions was greater among men, people between 40 and 54 years old, and those with higher educational levels. (4) Conclusions: The results show that trust in robots goes beyond rational decision-making, since the final decision about whether it should be a robot that performs a complex procedure like a surgical intervention depends almost exclusively on the patient’s wishes. Full article
27 pages, 2817 KiB  
Article
Predicting Lung Cancer in the United States: A Multiple Model Examination of Public Health Factors
by Arnold Kamis, Rui Cao, Yifan He, Yuan Tian and Chuyue Wu
Int. J. Environ. Res. Public Health 2021, 18(11), 6127; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18116127 - 06 Jun 2021
Cited by 3 | Viewed by 2798
Abstract
In this research, we take a multivariate, multi-method approach to predicting the incidence of lung cancer in the United States. We obtain public health and ambient emission data from multiple sources in 2000–2013 to model lung cancer in the period 2013–2017. We compare [...] Read more.
In this research, we take a multivariate, multi-method approach to predicting the incidence of lung cancer in the United States. We obtain public health and ambient emission data from multiple sources in 2000–2013 to model lung cancer in the period 2013–2017. We compare several models using four sources of predictor variables: adult smoking, state, environmental quality index, and ambient emissions. The environmental quality index variables pertain to macro-level domains: air, land, water, socio-demographic, and built environment. The ambient emissions consist of Cyanide compounds, Carbon Monoxide, Carbon Disulfide, Diesel Exhaust, Nitrogen Dioxide, Tropospheric Ozone, Coarse Particulate Matter, Fine Particulate Matter, and Sulfur Dioxide. We compare various models and find that the best regression model has variance explained of 62 percent whereas the best machine learning model has 64 percent variance explained with 10% less error. The most hazardous ambient emissions are Coarse Particulate Matter, Fine Particulate Matter, Sulfur Dioxide, Carbon Monoxide, and Tropospheric Ozone. These ambient emissions could be curtailed to improve air quality, thus reducing the incidence of lung cancer. We interpret and discuss the implications of the model results, including the tradeoff between transparency and accuracy. We also review limitations of and directions for the current models in order to extend and refine them. Full article
Show Figures

Figure 1

Back to TopTop