AI could help transplant candidates too sick to survive sobriety ‘road test’

A screening tool developed with artificial intelligence and trained on hundreds of hours of patient interviews could flag relapse risks in liver transplant patients with liver disorders, according to a new USC study. alcohol consumption – and provoke precise interventions.

“We know that alcohol use disorder is a chronic disease. A liver transplant will cure their liver disease, but not necessarily cure their alcohol use disorder,” said Brian Leelead study author and hepatologist specializing in the care of patients before and after liver transplantation in USC Keck School of Medicine. “A better understanding of their risk of relapse after the transplant helps us to adapt the treatments. There is an urgent need for more tools.

The research was recently published in the American Journal of Transplantation.

Severe alcohol-associated hepatitis is the fastest growing reason for liver transplantation in the United States and Europe. Liver transplant programs typically require six months of abstinence in patients with alcohol-associated liver disease prior to transplantation, as a return to harmful alcohol use can be fatal.

Liver transplant patients may not be six months old

However, some patients don’t have much longer to live. Severe alcohol-associated hepatitis is a disease in which a person develops alcohol-induced liver failure suddenly, within days or weeks. Moreover, studies and data show that six months of abstinence before the transplant is not a guarantee against relapses.

“The six-month rule doesn’t do a good job of predicting alcohol relapse and excludes many patients who would die without an urgent transplant and who might actually do just fine after the transplant,” Lee said.

That’s why USC is at the forefront of early transplantation for these patients without an abstinence “road test” — even as questions about relapse prevention remain.

Lee and his colleagues decided to see if they could fill the knowledge gap. To disentangle the red flags for relapse, they studied the anonymized psychosocial assessments of 116 early liver transplant patients from 10 transplant centers, 34 of whom returned to harmful alcohol use.

Prior to transplantation, patients undergo rigorous assessments by social workers, psychiatrists, and addiction specialists who ask questions about the patient’s medical needs, social supports, employment history, living situation, and family life. .

A content analysis tool designed to interpret Twitter chatter combed through patient ratings and selected 219 questions as potentially important for predicting post-transplant outcomes. Using artificial intelligence, the computer program narrowed the list down to 13 questions.

Liver transplants: surprising risks of relapse

The top three relapse risks were somewhat surprising. AI identified them as:

  • The patient does not have a primary support person lined up for post-transplant care at the time of the assessment.
  • The presence of children or grandchildren at home.
  • If the patient was recently a home caregiver for relatives.

Data shows that people who have young children in the household are more likely to have relapsed after the transplant. We have to think about what that means.

Brian LeeUSC hepatologist

“We rarely think of this as a risk factor, but it’s true. If you look, the data shows that people who have young children in the household are more likely to have relapsed after the transplant,” Lee said. “We have to think about what that means. Is it a more stressful environment? Is it because they take care of it normally, and after the transplant, they don’t take care of it anymore? »

Lee said someone at average risk of relapse could be encouraged to attend group therapy on a regular basis, such as that offered by Alcoholics Anonymous. A person at higher risk might need to go to inpatient rehabilitation. Patients may need more frequent monitoring of their alcohol consumption. There are medications to curb cravings and prevent relapses; AI could inform prescribing practices.

“These are just ideas. The research should prompt more research into why these questions are predictive. It’s a very promising tool in our decision making,” Lee said. “I treated so many patients that we knew they would do well, but because of a six-month stay [sobriety] as a rule, we were unable to transplant them in time. I’m so glad we’ve come such a long way.


In addition to Lee, other USC authors of the study include Prathik Rao, Jordan Davis, Hyosun Han, Bistra Dilkina and Norah Terrault.

More stories on: Artificial Intelligence, Liver, Research

Comments are closed.