AI to predict which HIV patients will stop taking ARVs: How it will work

Lecturers from Moi University have won a Sh523 million grant to develop a system that can predict when an HIV patient is likely to default on ARVs.
The system will alert physicians in advance, predicting possible reasons for stopping treatment and risking the development of Aids.
This would allow the physicians to engage patients in advance to prevent stoppage and allow treatment to continue.
The work, in collaboration with the US’s Brown University, will be supported by two grants from the National Institutes of Health (NIH) totalling Sh523 ($4.6 million) over five years.
The project is led by Prof Ann Mwangi, a biostatistician from Moi’s department of behavioural science, and her longtime research partner, Joseph Hogan, a professor of public health and biostatistics at Brown.
“The idea is that the physician will be able to use the results of the algorithm to see the point of care at which patients are at risk,”Hogan said.
“Then he or she will be able to take preventive actions to avoid the negative outcomes, rather than respond to negative outcomes after they happen.”
The team will use a health records database to develop the algorithm-based statistical machine learning tools to make the predictions.
The results will be delivered through handheld tablets that the physicians can use when in the office or exam room with the patient.
Hogan said an important feature of the new research grant is that much of the technical work related to developing and implementing the algorithms will be carried out on-site in Eldoret by Kenyan statisticians.
Other members of the team are Lameck Diero and Judy Wachira of Moi University; Tao Liu, Allison DeLong, Rami Kantor and Arman Oganisation of Brown; Jonathan Dick of Indiana University School of Medicine; and Jonathan Teich of Boston-based Brigham and Women’s Hospital.
“With this project, we hope to bring the promise of artificial intelligence and machine learning to the patient and clinic level,” Hogan said in a news release.
“We will evaluate the development tools that are going to have a measurable impact on patient outcomes.”
Kenya has about 1.5 million people living with HIV and about one million of them are on antiretroviral treatment.
The ARVs must be taken daily for life, but many patients often default and some are completely drop out.
This could lead to drug resistance, spread of disease and even death because HIV progresses quickly to Aids without treatment.
“If the system works as designed, then we have confidence we’ll improve the health outcomes of people with HIV,” Hogan said. He is co director of the biostatistics programme for Academic Model Providing Access to Healthcare (Ampath).
It is a consortium of 14 North American universities that collaborate with Moi University on HIV research, care and training.
BY MPASHO NEWS