Home / Current Issue / Paper 1706413
Biostatistics for Predicting Health Disparities in Infectious Disease Outcomes, Using Real-world Evidence and Public Health Intervention Data
Subject area: Biological & Medical Sciences · Area of research: Fisheries and Aquaculture
Abstract
This review explores emerging biostatistical methods, the integration of machine learning (ML) and advanced analytics, and the role of big data and artificial intelligence (AI) in addressing health disparities in public health. It highlights the growing importance of Bayesian models and ML algorithms for predicting infectious disease outcomes and stratifying populations by social determinants of health. The review accentuates the potential of AI in precision public health, with applications ranging from real-time disease surveillance to the development of personalized interventions. However, it also emphasizes the ethical challenges and biases associated with AI and ML, particularly in marginalized populations. Future research recommendations focus on developing ethical frameworks, improving the representativeness of training data, and optimizing the use of real-world evidence (RWE) in public health. By combining traditional biostatistical approaches with modern AI-driven tools, this review outlines a path toward more accurate and equitable health outcome predictions, ultimately contributing to the reduction of health disparities on a global scale.
Keywords
Biostatistical methods, Machine learning, Health disparities, Artificial intelligence, Real-world evidence
How to cite this paper
@article{1706413,
author = {David Oche Idoko, Okoroji Emmanuel Mbachu, Idayat Ninilola Ololade Babalola, Erondu Okechukwu Felix, Oluwayemisi Dada-Abidakun; Yewande Adeyeye},
title = {Biostatistics for Predicting Health Disparities in Infectious Disease Outcomes, Using Real-world Evidence and Public Health Intervention Data},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {8},
number = {4},
pages = {319-344},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1706413.pdf},
abstract = {This review explores emerging biostatistical methods, the integration of machine learning (ML) and advanced analytics, and the role of big data and artificial intelligence (AI) in addressing health disparities in public health. It highlights the growing importance of Bayesian models and ML algorithms for predicting infectious disease outcomes and stratifying populations by social determinants of health. The review accentuates the potential of AI in precision public health, with applications ranging from real-time disease surveillance to the development of personalized interventions. However, it also emphasizes the ethical challenges and biases associated with AI and ML, particularly in marginalized populations. Future research recommendations focus on developing ethical frameworks, improving the representativeness of training data, and optimizing the use of real-world evidence (RWE) in public health. By combining traditional biostatistical approaches with modern AI-driven tools, this review outlines a path toward more accurate and equitable health outcome predictions, ultimately contributing to the reduction of health disparities on a global scale.},
keywords = {Biostatistical methods, Machine learning, Health disparities, Artificial intelligence, Real-world evidence},
month = {October},
}