Development of AI to screen high-risk groups for developing serious complications after chronic hepatitis C treatment: Health and Welfare News

【Health and Welfare News】AI has been developed to preemptively identify high-risk patients who are likely to develop serious complications such as hepatocellular carcinoma after curing chronic hepatitis C.

The research team of Professors Kim Seung-up and Lee Hye-won from the Department of Gastroenterology at Scarry Hospital announced on the 5th that they had developed an AI that could select high-risk patients who may develop liver-related problems after curing chronic hepatitis C. .

The results of this study were published in the Journal of Hepatology (IF 26.8), an academic journal of the European Society for the Study of the Liver.

Chronic hepatitis C is not transmitted through casual contact, but through contaminated blood such as needle sticks, acupuncture, tattoos, etc. It can be treated with ‘Direct-acting Antiviral Agents (DAA)’ which are usually taken orally.

If there is no cirrhosis of the liver after hepatitis C treatment, the risk of developing hepatocellular carcinoma is likely to be ignored. However, even without cirrhosis of the liver, some patients with treatment can develop serious complications such as hepatocellular carcinoma, so caution is required. In cases where cirrhosis is not diagnosed through abdominal ultrasound, it is difficult to identify the risk, so it is very important to predict.

The research team developed an AI that can select high-risk groups with a poor prognosis, such as those who have cured hepatitis C and developed hepatocellular carcinoma even without cirrhosis, and verified their performance.

First, an AI was created using data from 913 hepatitis C patients without cirrhosis who were treated with antiviral therapy at Scarry Hospital. AI predicts whether there will be serious problems using the results of six blood tests that can check liver elasticity, age, gender, platelet count, and bilirubin level.

Next, the accuracy of predicting liver-related complications such as hepatocellular carcinoma, decompensated cirrhosis, liver transplantation, and death was tested using data from 1,264 patients in Hong Kong and France. The ‘C-index’ value, which means a higher prediction performance the closer it is to 1, is recorded at 0.86, boasting an AI prediction accuracy of 86%. When only hepatocellular carcinoma was separately diagnosed, the figure rose to 0.87.

In fact, the incidence of liver-related complications within 5 years in high-risk patients with calculated AI values ​​of 0.7 or higher was 3.2-6.2%, up to 30 times higher than the incidence rate (0.2-0.5%) in low-risk patients with calculated AI values ​​less than 0.7.

Professor Kim Seung-up said, “Chronic hepatitis C can be easily treated with antiviral drugs, but even after treatment, serious complications such as hepatocellular carcinoma can be experienced.” He said, “Using the AI ​​developed in this study, high-risk groups that need regular follow-up even after choosing a treatment “You can do it,” he said.