MIT Sloan Health Systems Initiative

HSI Research by Therapeutic Area

One way to characterize our projects is by therapeutic area. Within the analytics, operations, and incentives focus areas, HSI’s researchers are leading groundbreaking projects, many of which also address a specific condition or disease. Our researchers apply their expertise to studying issues in the context of topics highlighted below.

Two HSI-funded studies are enabling Georgia Perakis (with BI Lahey Health) and Jónas Jónasson and Nikos Trichakis (with the Staten Island Performing Provider System) to develop predictive models using both medical data, as well as non-medical data such as from housing and law enforcement agencies, to personalize interventions for those with substance use disorders.

Paul Osterman is working with the Staten Island Performing Provider System to study how it supports teaching new skills to frontline care workers and integrating them into the Emergency Department through training, certification, and development of innovative work practices, and the impact of these changes on health outcomes.

Dimitris Bertsimas develops machine-learning tools using massive datasets to optimize clinical trials to discover new cancer treatments, including for gastric cancer. Learn more

Andrew Lo uses data-driven methods informed by financial-portfolio construction in clinical trial design and trial success forecasting. Both the design and the forecasting methods are aimed at improving prediction of the probability of success and understanding the risks underlying the therapies under trial. Ultimately, a better understanding of risk may bring more investors to the table and bring more money into the drug development space.

Vivek Farias received funding through HSI to expand his efforts in using machine learning to develop more cost-efficient liquid biopsies to detect early stage cancer. Specifically, he is using machine learning methods to account for locality in gene mutations. This makes it possible to get higher accuracy for the same cost or similar accuracy for lower cost than status quo sequencing.

Joseph Doyle is working with the Camden Coalition of Healthcare Providers to test the effectiveness of care-management programs for complex patients. The first study, a randomized controlled trial of the practice of hotspotting, has recently been published. Learn more

Joseph Doyle is conducting a randomized controlled trial with Geisinger Health on evaluating the impact of their Fresh Food Farmacy effort, a food-as-medicine approach to improve health among food-insecure patients with diabetes.

David Rand and Erez Yoeli use behavioral insights, including reputational concerns and desires to support the public good, along with analytics, to develop and test robust digital health tools. Currently, in Kenya, they are testing a platform combining patient reminders and human interventions to improve adherence to TB and HIV medication. They plan to expand this study to other regions. Learn more

Jónas Jónasson and Erez Yoeli are investigating optimization of treatment pathways by studying when to use human intervention, rather than relying on only a digital platform, to promote TB treatment adherence.

Through a landmark operations research study in Mozambique, Jónas Jónasson and his colleagues investigated ways to speed up not only lab procedures, but also the supply chain itself. They were able decrease turnaround times by an estimated 22% for early infant diagnosis of HIV. This would increase the number of infected babies initiating treatment by seven percent, potentially saving the lives of up to 60 additional children per year. Learn more

Multiple MIT Sloan projects on kidney exchanges have led to national policies that improve fairness and increase life-years gained. These include changing the paired donation process by enabling longer “chains” of kidney donations and better matching, improving patient decision-making based on personalized data, and mitigating negative effects of knowing a kidney was refused by others by including information about the reason for refusal, which may not apply to the current patient.

New analytics work in liver transplants, by Nikos Trichakis and Dimitris Bertsimas with the United Network for Organ Sharing, is reshaping and improving their policies to mitigate well-known weaknesses, increasing potential lives saved through liver transplants by 400 patients per year (20%).

Related work on liver transplantation by Nikos Trichakis focuses on ways to support patient decision-making as well, such as ways to help them know the likelihood of better organs being offered in the future, along with the likely trajectory of their health post-transplantation.