The role of ai in strengthening public health system through digital health
1
Science and Technology, Kailali Multiple Campus, Dhangadhi, Nepal
Popul. Med. 2026;8(Supplement Supplement 1):A729
ABSTRACT
INTRODUCTION:
Public health systems are typically hindered by late detection of disease outbreaks, diagnosis, and misdiagnosis, and wastage of resources—most notably in rural and low- and middle-income settings. The integration of Artificial Intelligence (AI) into digital health has the potential to counteract these setbacks by enabling earlier, more accurate, and equitable disease control and treatment.
METHODS:
We conducted a systematic review of 2019-2025 research on AI-based interventions in disease surveillance, diagnostics, and health systems support. We included studies with performance measures and real-world implementation. Subject matter explored: outbreak detection accuracy, diagnostic error minimization, decision support, and equity for rural/underserved populations. In Kenya, the "AI Consult" tool applied in primary care clinics reduced diagnostic mistakes by 16% and treatment mistakes by 13% among clinicians who employed the tool versus those who did not. Machine-learning algorithms (Random Forest, XGBoost) were applied in detection of COVID-19 outbreak in a study and forecasted start dates of outbreaks with 80–100% accuracy versus official reported data. In developing rural settings, artificial intelligence-based diagnostic software for diabetic retinopathy and glaucoma had high-quality diagnostic performance: sensitivity ~ 98.57%, specificity ~ 92.97% for retinopathy; for glaucoma, sensitivity ~ 92.74%, specificity ~ 96.49%. The facilities enhanced access among hard-to-reach populations. For rural malaria and peripheral neuropathy, AI-based diagnostic systems had ~ 93.3% and ~ 91% accuracy respectively against reference standards of expert level.
CONCLUSIONS:
Real-world experience demonstrates that AI embedded in digital health systems has the potential to positively impact public health: improving outbreak detection, reducing diagnostic and treatment errors, and enhancing access to quality care in underserved populations. Policies and investment must ensure optimal infrastructure, responsible governance, and equitable deployment, especially in remote and resource-poor environments, to have their maximum impact.
Public health systems are typically hindered by late detection of disease outbreaks, diagnosis, and misdiagnosis, and wastage of resources—most notably in rural and low- and middle-income settings. The integration of Artificial Intelligence (AI) into digital health has the potential to counteract these setbacks by enabling earlier, more accurate, and equitable disease control and treatment.
METHODS:
We conducted a systematic review of 2019-2025 research on AI-based interventions in disease surveillance, diagnostics, and health systems support. We included studies with performance measures and real-world implementation. Subject matter explored: outbreak detection accuracy, diagnostic error minimization, decision support, and equity for rural/underserved populations. In Kenya, the "AI Consult" tool applied in primary care clinics reduced diagnostic mistakes by 16% and treatment mistakes by 13% among clinicians who employed the tool versus those who did not. Machine-learning algorithms (Random Forest, XGBoost) were applied in detection of COVID-19 outbreak in a study and forecasted start dates of outbreaks with 80–100% accuracy versus official reported data. In developing rural settings, artificial intelligence-based diagnostic software for diabetic retinopathy and glaucoma had high-quality diagnostic performance: sensitivity ~ 98.57%, specificity ~ 92.97% for retinopathy; for glaucoma, sensitivity ~ 92.74%, specificity ~ 96.49%. The facilities enhanced access among hard-to-reach populations. For rural malaria and peripheral neuropathy, AI-based diagnostic systems had ~ 93.3% and ~ 91% accuracy respectively against reference standards of expert level.
CONCLUSIONS:
Real-world experience demonstrates that AI embedded in digital health systems has the potential to positively impact public health: improving outbreak detection, reducing diagnostic and treatment errors, and enhancing access to quality care in underserved populations. Policies and investment must ensure optimal infrastructure, responsible governance, and equitable deployment, especially in remote and resource-poor environments, to have their maximum impact.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
