Machine learning models for predicting hepatocellular carcinoma development in patients with chronic viral hepatitis B infection.

Abstract

Background: Chronic hepatitis B (CHB) infection is the major risk factor for hepatocellular carcinoma (HCC).

Objective: To develop machine-learning models for predicting an individual risk of HCC development in CHB-infected patients.

Methods: Machine learning models were constructed using features from follow-up visits of CHB patients to predict the diagnosis of HCC development within 6 months after each index follow-up. We developed 4 model variants using all features, with alpha fetoprotein (AFP) (AF ^A ) and without AFP (AF^N ); and selected features, with AFP (SF ^A ) and without AFP (SF^N ). Performance was evaluated using 10-fold cross-validation on a derivation cohort and further validated on an independent cohort.

Results: In the derivation cohort of 2,382 patients, of whom 117 developed HCC, AF^A achieved higher sensitivity (0.634, 95% confidence interval [CI]: 0.559-0.708) and specificity (0.836; 0.830-0.842) than AF ^N (sensitivity 0.553; 0.476-0.630 and specificity 0.786; 0.779-0.792). SF^A also achieved higher sensitivity (0.683; 0.611-0.755 vs. 0.658; 0.585-0.732) and specificity (0.756; 0.749-0.763 vs. 0.744; 0.737-0.751) than SF^N . Performance of SF^A and SF^N were tested in another cohort of 162 patients in which 57 patients developed HCC. SF^A achieved sensitivity and specificity of 0.634 (0.522-0.746) and 0.657 (0.615-0.699), while sensitivity and specificity of SF^N were 0.690 (0.583-0.798) and 0.651 (0.609-0.693), respectively.

Conclusion: The machine learning models demonstrate good performance for predicting short-term risk for HCC development and may potentially be used for tailoring surveillance interval for CHB patients.