International institutions, including the World Health Organization (WHO), the Organisation for Economic Co-operation and Development (OECD), and the World Bank, have consistently emphasized that investing in prevention can yield returns of two to five times per dollar spent, in both reduced healthcare costs and economic losses from people getting sick.
But the scalability and cost-efficiency of preventive healthcare programs are heavily tied to digital infrastructure. It is easier said than done when not every community has equal access to technology or the digital literacy needed to effectively use digital health tools. This “digital divide” can exacerbate health inequities, particularly for older adults, low-income populations, and those in rural areas.
Enter predictive analytics and artificial intelligence (AI) diagnostics.
Globally, predictive health platforms are being used by insurers and healthcare providers to flag high-risk individuals before symptoms arise, allowing for targeted outreach and personalized interventions.
In the United Kingdom, for example, the National Health Service is in the process of integrating AI-driven breast cancer screening tools that reduce radiologist workload while increasing early detection rates into their healthcare system. Over the next few years, AI will be deployed to analyze two-thirds of at least 700,000 mammograms done in England as a preliminary test of accuracy and reliability.
If it proves successful, AI can significantly improve the ‘second reader’ system adopted by hospitals, where two radiologists are required to study every mammogram for signs of breast cancer to ensure nothing is missed.
“This landmark trial could lead to a significant step forward in the early detection of breast cancer, offering women faster, more accurate diagnoses when it matters most,” said Prof. Lucy Chappell, the chief scientific adviser of UK’s Department of Health and Social Care, and chief executive of the National Institute for Health and Care Research.
The trial follows increasing scientific evidence of the transformative effects AI is creating in medical diagnosis.
For instance, a study published in the journal Nature Medicine in January examined the impact of AI on cancer detection and recall rates.
The study was conducted within a breast cancer screening program in Germany targeting asymptomatic individuals aged 50-69, with data collected from multiple screening sites implementing the AI system between July 2021 and February 2023.
“In conclusion, our findings substantially add to the growing body of evidence suggesting that AI-supported mammography screening is feasible and safe, and can reduce workload. Our study also demonstrates that integrating AI into the screening workflow can improve the breast cancer detection rate with a similar or even lower recall rate,” the study reported.
“Nevertheless, based on the now available evidence on breast cancer detection, recall rates, PPV (positive predictive value) of biopsy and time savings, urgent efforts should be made to integrate AI-supported mammography into screening guidelines and to promote the widespread adoption of AI in mammography screening programs,” the researchers added.
This shift is not limited to high-income countries. In Kenya, where nearly 350,000 children under five suffer from acute malnutrition, AI is being used to predict malnutrition up to six months in advance.
A team from University of Southern California (USC), Microsoft AI for Good Lab, Amref Health Africa, and Kenya’s Ministry of Health has developed an AI model that combines clinical records from 17,000 health facilities with satellite data on crop health, with the aim of identifying where malnutrition is likely to spike next.
Kenya’s District Health Information System 2 (DHIS2) uses the data gathered from clinics nationwide. And while data gaps exist — primarily due to rural children having no access to clinics, leaving them out of the DHIS2 dataset — the research team hopes their findings can be used to address malnutrition worldwide.
The study, titled “Forecasting acute childhood malnutrition in Kenya using machine learning and diverse sets of indicators,” was published in PLOS One earlier in May.
“By using data-driven AI models, you can capture more complex relationships between multiple variables that work together to help us predict malnutrition prevalence more accurately,” Bistra Dilkina, co-director of USC’s Center for Artificial Intelligence in Society and one of the co-authors of the study, said.
“If we can do this for Kenya, we can do it for other countries. The sky’s the limit when there is a genuine commitment to work in partnerships.”
In Southeast Asia, similar advancements are being made. The Singapore Eye Research Institute (SERI) and National University of Singapore (NUS) developed SELENA+, a deep-learning AI software system that can detect potential critical eye conditions such as diabetic eye disease, glaucoma, and age-related macular degeneration.
Singapore’s national health technology agency Synapxe estimated that the system has the potential of reducing the workload of medical professionals by up to 50%, in addition to coming out with patient results in minutes instead of hours or days.
“In studies conducted to date, the AI-powered image reader has proven to be faster and as accurate compared to human graders. For patients, this means earlier, more targeted treatment, cheaper medical bills and better quality of life,” the agency said on its website.
“The use of the AI system also allows clinicians to reach out to patients earlier, make better decisions supported by AI and manage patient conditions more efficiently.”
Similarly, researchers at the Oxford University Clinical Research Unit (OUCRU) in Ho Chi Minh City, Vietnam are developing AI tools to enhance pneumonia diagnosis and care.
“Building on over eight years of innovative research, OUCRU, in partnership with The Institute of Biomedical Engineering and the Computational Health Informatics (CHI) Lab, University of Oxford and the Hospital for Tropical Diseases (Ho Chi Minh City) aims to develop novel artificial intelligence tools for the treatment of severe pneumonia,” OUCRU announced.
“This project will combine cutting-edge AI, advanced pathogen identification techniques, and immune profiling to improve care for critically ill patients while advancing the scientific understanding of pneumonia in [low- and middle-income countries].”
The project follows the success of the Vietnam ICU Translational Applications Laboratory (VITAL) project, which was supported by a Wellcome Innovations Flagship grant from 2019 to 2023. VITAL has been instrumental in using innovative, low-cost tools to improve the care of critically ill patients in Vietnam.
“By leveraging the software, technologies, and expertise developed during VITAL, this new project is well-positioned to make significant advancements in pneumonia care,” OUCRU added.
It is clear that AI is revolutionizing healthcare globally, helping doctors detect diseases earlier, enabling governments act faster, and allowing communities to live healthier lives. The world is in the midst of a profound shift where prevention becomes the foundation of healthcare, rather than a secondary to cure. — Bjorn Biel M. Beltran