Date December 20, 2021
Media Contact

Grants totaling $4.6 million support the use of machine learning to improve outcomes of people with HIV

In partnership with Moi University in Kenya, Brown University will develop, test and launch data-driven tools to maximize the effectiveness of HIV care programs.

PROVIDENCE, R.I. [Brown University] — Over the past four decades of treating HIV/AIDS, two important facts have been established: HIV-positive patients need to be put on treatment as soon as they’re diagnosed and then kept on an effective treatment plan. This response can help turn HIV into a chronic but manageable disease and can essentially help people live normal, healthy lives, said Joseph Hogan a professor of public health and of biostatistics at Brown University, who has been researching HIV/AIDS for 25 years.

Hogan is one of the primary investigators on two recently awarded grants from the National Institutes of Health, totaling nearly $4.6 million over five years, to support the creation and utilization of data-driven tools that will allow care programs in Kenya to meet these key treatment goals.

“If the system works as designed, then we have confidence that we’ll improve the health outcomes of people with HIV,” Hogan said.

The first part of the project involves using data science to understand what’s called the HIV care cascade, said Hogan, who is the co-director of the biostatistics program for Academic Model Providing Access to Healthcare (AMPATH), a consortium of 14 North American universities who collaborate with Moi University in Eldoret, Kenya, on HIV research, care and training.

Hogan will collaborate with longtime scientific partner Ann Mwangi, associate professor of biostatistics at Moi University, who received a Ph.D. in biostatistics from Brown in 2011. Using AMPATH-developed electronic health record database, a team co-led by Hogan and Mwangi will develop algorithm-based statistical machine learning tools to predict when and why patients might drop out of care and when their viral load levels indicate they are at risk of treatment failure.

These algorithms, Hogan said, will then be integrated into the electronic health record system to deliver the information at the point of care, through handheld tablets that the physicians can use when sitting in the exam room with the patient. In consultation with experts in user interface design, the team will assess and test the most effective ways to communicate the results of the algorithm to the care providers so that they can use them to make decisions about patient care, Hogan said.

The predictive modeling system the team is developing, Hogan said, will alert a physician to red flags in the patient’s treatment plan at the point of care. This way, interventions can be developed to help a patient get to their treatment appointments, for example, before the patient needs to miss or cancel them. Or if a patient is predicted to have high viral load, Hogan said, a clinician can refer them for additional monitoring to identify and treat the increase before it becomes a problem.

“ With this project, we hope to bring the promise of A.I. and machine learning to the patient and clinic level and evaluate the developed tools that are going to have a measurable impact on patient outcomes. ”

Joseph Hogan Professor of Biostatistics at Brown University and co-director of the AMPATH biostatistics program

“The idea is that the physician will be able to use the results of the algorithm to see at the point of care which patients are at risk, and then, be able to take preventive actions to avoid the negative outcomes, rather than respond to negative outcomes after they happen,” Hogan said.

The goal involves not only developing sophisticated algorithms but also putting them into practice and assessing their clinical value. It’s a true collaboration between scholars in statistics and machine learning and developers of medical informatics – as well as clinicians, Hogan said. Hamish Frasier, associate professor in the Brown Center for Biomedical Informatics and an expert in open-source medical records systems, will lead development of the user-interface system to be used at the point of care.

“With this project, we hope to bring the promise of A.I. and machine learning to the patient and clinic level and evaluate the developed tools that are going to have a measurable impact on patient outcomes,” Hogan said.

Brown University has a long-standing, multi-dimensional relationship with AMPATH that involves collaborative research on specific epidemiological and clinical research questions that are funded by the NIH. The Brown School of Public Health and the Warren Alpert Medical School also collaborate with AMPATH through exchange programs involving medical students and residents, and partnerships related to clinical care programs in HIV, oncology, tuberculosis and others.    

Hogan and Mwangi co-lead a research training program, known as NAMBARI, supported by a federal grant from the NIH Fogarty International Center, to advance biostatistics training and research capacity at Moi University. The program is a partnership between Moi University and Brown University, and provides both long- and short-term training for students, faculty and technical staff in Kenya.

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 who trained at Brown through the NAMBARI program. The Kenyan team members will be led by Mwangi.

In addition to Hogan, Mwangi and Fraser, the team includes Tao Liu, Allison DeLong, Rami Kantor, Arman Oganisian of Brown; Jonathan Dick of Indiana University School of Medicine; Jonathan Teich of Brigham and Women’s Hospital; and Lameck Diero and Juddy Wachira of Moi University.

This research is supported by National Institutes of Health research grant 1R01AI167694-01 and training grant 2D43TW010050-06.