For those who need it, an organ transplant is a matter of life and death.
Every year, a medical procedure gives thousands of people with advanced or terminal illnesses a longer life. This “second chance” is largely dependent on the availability, compatibility, and proximity of a valuable resource that simply cannot be bought, grown, or manufactured—at least not yet.
Instead, organs must be donated—cut from one body and implanted into another. And because living organ donation is only feasible in some cases, many organs are only available for donation after the donor dies.
Not surprisingly, the logistical and ethical complexities of distributing a circumscribed number of organs for transplant to a growing waiting list of patients have attracted much attention. But there is an essential part of the process that has attracted less attention and that may have significant untapped potential: organ procurement itself.
“If you have an organ to donate, who should you donate it to? This question has been widely studied in operations research, economics, and even applied computer science,” he says. Hammaada AdamPhD student in Social and Engineering Systems (SES) at MIT Institute of Data, Systems and Society (IDSS). “But there has been much less research on where this organ comes from.”
In the United States, nonprofit organizations called organ procurement organizations, or OPOs, are responsible for finding and evaluating potential donors, interacting with grieving families and hospital administrators, and procuring and delivering organs—all while adhering to federal regulations that are both their mandate and safeguards. Recent studies estimate that these obstacles and inefficiencies lead to thousands of organs not being procured each year, even as demand for transplants continues to grow.
“There was little transparent data on organ harvesting,” Adam says. Collaboration with MIT computer science professors Marzyeh Ghassemi AND Ashia Wilsonand in collaboration with stakeholders involved in organ procurement, Adam led a project to create a dataset called ORCHID: Organ collection and health information gathering for donation purposes. ORCHID contains clinical, financial, and administrative data from six OPOs spanning the last ten years.
“Our goal is for the ORCHID database to impact the way organ procurement is viewed, both internally and externally,” Ghassemi says.
Efficiency and equality
It was this desire to make an impact that drew Adam to SES and MIT. With a background in applied mathematics and a background in strategy consulting, solving problems with technical components is in his nature.
“I really missed the hard technical problems from a statistics and machine learning perspective,” he says of his time at the consulting firm. “So I went back and got a master’s in data science, and during my master’s I got involved in a lot of research projects in a few different areas, including biology, management science, and public policy. Some of the projects I enjoyed the most were more focused on the social sciences, which had an immediate impact.”
As a postgraduate student at SES, Adam focuses on using statistical tools to uncover inequalities in healthcare and developing machine learning approaches to address them. “Part of my PhD research focuses on building tools that can improve equity in clinical trials and other randomized experiments,” he explains.
One of the last an example of Adam’s work: developing a up-to-date method for stopping clinical trials early if a treatment has an unintended harmful effect on a minority group of participants. “I’ve also been thinking about ways to increase minority representation in clinical trials through improved patient recruitment,” he adds.
Racial inequities in health care extend to organ transplantation, where the majority of patients waiting for a transplant are not white—far outweighing their demographic share of the general population. Many of these communities are experiencing lower organ donations because of a variety of barriers that need to be better understood if they are to be overcome.
“My work in organ transplantation began on the allocation side,” Adam explains. “In this study, we examined the role of race in physicians’ acceptance of heart, liver, and lung transplants on behalf of their patients. We found that black race was associated with significantly lower odds of accepting an offer of transplant—in other words, transplant physicians seemed more likely to reject organs offered to black patients. This trend could have many explanations, but it is still concerning.”
Adam’s research also found that matching the race of the donor to the candidate was associated with significantly higher odds of an offer being accepted, which Adam says “underscores the importance of organ donation from racial minorities and motivates our work to promote equitable organ procurement.”
Collaboration with Ghassemi through IDSS Initiative to Combat Systemic RacismAdam was introduced to OPO stakeholders who were eager to collaborate. “It was this opportunity to impact not only healthcare efficiency but also healthcare equity that really interested me in this study,” Adam says.
Making an impression
Building a database like ORCHID means solving problems in multiple domains, from technical to political. Some efforts never get past the first step: getting the data in the first place. Fortunately, several OPOs were already looking for collaborations and trying to improve their results.
“We have been fortunate to have a strong partnership with OPOs and hope that together we can find important information that will help us improve efficiency and equity,” Ghassemi says.
The value of a database like ORCHID lies in its potential to generate up-to-date insights, especially through quantitative analysis with statistics and computational tools such as machine learning. ORCHID’s potential value was recognized by the MIT Prize for Open Data, an award from MIT Libraries that recognizes the importance and impact of research data that is made openly available.
“It’s nice to have the work recognized,” Adam says of the award. “And it was cool to see all the other great open data work happening at MIT. I think there’s a real impact in making data publicly available in an important and under-researched area.”
Regardless, Adam knows that creating the database is only the first step.
“I’m very interested in understanding the bottlenecks in the organ procurement process,” he explains. “As part of my master’s thesis research, I’m investigating this by modeling OPO decision-making using causal inference and structural econometrics.”
Using the findings from this study, Adam also plans to evaluate policy changes that could improve both equity and efficiency in organ procurement. “And we hope to recruit more OPOs and increase the amount of data we share,” he says. “The dream is for every OPO to join our collaboration and provide updated data every year.”
Adam is excited about how other researchers can exploit the data to address inefficiencies in organ procurement. “Every organ donor saves three to four lives,” he says. “So any research project that comes out of this data set could have a real impact.”