Researchers: Eran Segal¹, Ziv Neeman², Rawi Hazzan³

Background: Despite increased prevalence of liver disease in the general population, diagnostic tests are performed mainly in high-risk populations, rendering most patients undiagnosed for periods of several years. Available non-invasive tests (FIB-4 and NSF)3 suffer from low accuracies making them suboptimal for screening in the general population.

Objectives: 1) Develop a model for predicting the risk for liver cirrhosis. Specifically, a predicting model that computes likelihood of developing liver cirrhosis in the next five years given available medical history.
(2) Test and validate the accuracy of the developed model in real-life settings and perform a clinical study.

Method: A liver cirrhosis diagnostic framework was constructed by analyzing EHR data from 2,255,580 observations. This framework is centered on Fibro-Predict, a machine-learning model capable of predicting five-year disease diagnosis trajectories based on routine blood tests. We conducted a retrospective temporal validation of the model and an external prospective validation in clinical settings, employing transient elastography.

Findings: The temporal validation of Fibro-Predict demonstrated a promising five-year AUC of 0.81 (95% CI 0.80-0.82) in the training set and 0.79 (95% CI 0.78-0.80) in the validation set. In a clinical context, our framework exhibited an impressive True Positive Rate (TPR) of 36.8% (28/76) when comparing predicted risk to observed outcomes, surpassing the widely used FIB-4, which had a TPR of only 3.7% (1/27).
Fibro-Predict, relying solely on routine blood tests and standard demographics, emerges as a valuable tool for cost-effective patient prioritization in advanced fibrosis screening within the general population.

Conclusions: By leveraging nationwide EHR data, we can efficiently identify individuals needing clinical follow-ups and expedite advanced fibrosis diagnosis.

Recommendations: This approach holds the potential to significantly improve the early detection of advanced liver fibrosis and subsequently reduce its associated morbidity and mortality.

Research end date: 12/2024