Researchers use artificial intelligence, clinical data to create prediction tool for primary sclerosing cholangitis

Featured News

Researchers use artificial intelligence, clinical data to create prediction tool for primary sclerosing cholangitis

By
Joe Dangor

October 9, 2018

Primary sclerosing cholangitis : are you at risk? yes or no

ROCHESTER, Minn. — An international team of researchers led by Konstantinos Lazaridis, M.D., a Mayo Clinic gastroenterologist, has developed a new tool to help predict outcomes of primary sclerosing cholangitis. The team’s work is published in Hepatology.

Primary sclerosing cholangitis is a disease of the bile ducts, in which persistent inflammation causes scarring, hardening and narrowing of the ducts that eventually may lead to serious liver damage. The disease is commonly associated with inflammatory bowel disease and, usually, ulcerative colitis.

“Primary sclerosing cholangitis is a progressive liver condition, and researchers as well as clinicians need better prognostic tools to assess patients’ outcomes,” says John Eaton, M.D., a Mayo Clinic gastroenterologist and first author of the study.

For the study, researchers used a large set of clinical data from patients with primary sclerosing cholangitis, along with machine learning, a form of artificial intelligence, to discover and validate a tool that predicts disease outcomes at five years. Dr. Eaton says such a tool is urgently needed to better define potential outcomes for patients with primary sclerosing cholangitis and select patients to participate in future clinical trials. Researchers named the tool "PREsTo," which is short for Primary Sclerosing Cholangitis Risk Estimate Tool.

Researchers followed a cohort of 509 patients from across North American and validated their results in an international cohort of 278 patients. The end point for the study was hepatic decompensation, a condition that occurs when there is a deterioration in liver function.

They applied machine learning to analyze the available clinical data. PREsTo has nine variables:

Bilirubin
Albumin
Serum alkaline phosphatase times the upper limit of normal
Platelets
Aspartate aminotransferase
Hemoglobin
Sodium
Patient age
Number of years since primary sclerosing cholangitis was diagnosed

“We found that PREsTo accurately predicts hepatic decompensation in primary sclerosing cholangitis patients and exceeds the performance of other widely available, noninvasive prognostic scoring systems for this disease,” says Dr. Eaton. “We are proud to have developed an objective tool that can be utilized in clinical research and to provide more accurate estimates of liver decompensation in five years for patients with primary sclerosing cholangitis.”

“This work is the product of a strong international collaboration between Mayo Clinic and the Norwegian Primary Sclerosing Cholangitis Research Center led by Dr. Tom H. Karlsen,” says Dr. Lazaridis. “We are very grateful for the important contributions of the Norwegian group in this novel study.”

The PREsTo calculator is available online at https://rtools.mayo.edu/PRESTO_calculator/.

Funding for this study was provided by the National Institutes of Health grant RO1 DK 084960 (KNL), RC2 DK 118619 (KNL), and the Chris M. Carlos and Catharine Nicole Jockisch Carlos Endowment in Primary Sclerosing Cholangitis.

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to clinical practice, education and research, providing expert, comprehensive care to everyone who needs healing. Learn more about Mayo Clinic. Visit the Mayo Clinic News Network.

Media contact: