Get started
Work

AI and Machine Learning for Early Detection of Infectious Diseases in the US: Opportunities and Challenges

Year: 2025
Type: article
Abstract: Artificial intelligence and machine learning are reshaping U.S. infectious-disease surveillance by rapidly integrating clinical, environmental, and open-source data to flag anomalies sooner than conventional methods. This article aims to assess how artificial intelligence (AI) and machine learning (ML) can accelerate early detection of emerging infectious diseases in the United States In case studies, real-time ML tools cut hospital-acquired infections by 40 %, and systems like BlueDot predicted major outbreaks days before official alerts, underscoring strong gains in speed and accuracy. However, biased training data, opaque “black-box” models, privacy risks, and high implementation costs still threaten equitable, trustworthy deployment. Overcoming these barriers will require rigorous data-quality standards, explainable algorithms, interdisciplinary governance, and scalable validation frameworks—advances that could extend early-warning capacity from local hospitals to global health security networks.
DOI: 10.69739/jmsbc.v2i1.465
Authors: Adekunle Adeoye, Chibuzo Okechukwu Onah, Enibokun Theresa Orobator, Elizabeth Anuoluwa Akintayo, Jacob Ukpabio Inuaeyen, Daniel Ojonugwa Umoru, Isaiah Olumeko, Gladys Jacob Dick, Kelechi Wisdom Elechi, Ubalaeze Solomon Elechi, Muhammad Bello Demola
Institutions: Georgia State University, University of Edinburgh, Wayne State University, University of Nigeria, National Hospital Abuja, University of Houston, Elmleigh Hospital, The University of Texas at San Antonio Health Science Center, University of Ulster
Language: English
Subfield: Epidemiology
Field: Medicine
Open Access status: hybrid
OpenAlex ID: W4410021955
FWCI: 5.607
Cites:
Cited by: 9
Related to: 10