JMIR Publications

ABSTRACT

Background:

Liver cancer continues to pose a significant burden in China. To enhance the efficiency of screening, it is crucial to implement population stratification for liver cancer screening.

Objective:

This study aimed to develop a simple prediction model and risk score for liver cancer surveillance and screening in the general population, with the goal of improving early detection.

Methods:

This population-based cohort study focused on residents aged 40 to 74 years old. 153,082 participants enrolled between 2014 and 2019 and were prospectively followed up until June 30, 2021. Data were collected through interview at enrollment. Cox proportional hazards regression was applied to identify predictors and construct the prediction model. A risk score system was constructed by using weighted factors included in the prediction model.

Results:

During the 781,125 person-years of follow-up, a total of 290 participants were diagnosed with liver cancer. Age, sex, education level, cirrhosis, diabetes, and HBsAg status were selected as factors for the prediction model and risk score system. The model exhibited excellent discrimination in both the development and validation sets, with area under the curves of 0.802, 0.812, and 0.791 for predicting liver cancer at 1-, 3-, and 5-years in the development set, and 0.751, 0.763, and 0.712 in the validation set. Participants in the high- and moderate-risk score groups showed 11.88-fold and 3.51-fold higher risk of liver cancer, respectively, compared to the low-risk score group.

Conclusions:

A straightforward liver cancer prediction model was created by incorporating readily available variables along with HBsAg status. This model enables the identification of asymptomatic individuals who should be prioritized for liver cancer screening.