Liver Cancer Screening Prediction Model
Author Information
Author(s): Li Xue, Wang Youqing, Li Huizhang, Wang Le, Zhu Juan, Yang Chen, Du Lingbin
Primary Institution: Zhejiang Cancer Hospital, Hangzhou Institute of Medicine, Chinese Academy of Sciences
Hypothesis
This study aimed to develop a simple prediction model and risk score for liver cancer screening in the general population.
Conclusion
A straightforward liver cancer prediction model was created by incorporating easily accessible variables, enabling the identification of asymptomatic individuals who should be prioritized for liver cancer screening.
Supporting Evidence
- 290 individuals were diagnosed with liver cancer during the study.
- The model exhibited excellent discrimination with AUCs of 0.802, 0.812, and 0.791 for predicting liver cancer at 1-, 3-, and 5-year periods.
- Participants in the high-risk group had 11.88-fold higher risks of liver cancer compared to the low-risk group.
- The risk score provided a higher net benefit compared to the current strategy.
- Key factors for the prediction model included age, sex, education level, cirrhosis, diabetes, and HBsAg status.
Takeaway
The study created a tool to help people figure out if they might be at risk for liver cancer, so they can get checked early.
Methodology
This population-based cohort study focused on residents aged 40 to 74 years, with data collected through interviews and follow-up until June 30, 2021.
Potential Biases
The study may have selection bias as it focused on a specific age group and excluded individuals with a history of cancer.
Limitations
The study population may not fully represent the general population of China, and the follow-up duration may not be sufficient to capture all liver cancer cases.
Participant Demographics
Participants included 67,586 males and 85,496 females with a mean age of 55.86 years.
Statistical Information
P-Value
<0.001
Confidence Interval
95% CI 1.04-1.08
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website