- AI models, particularly those using imaging data, may outperform traditional regression models in predicting lung cancer risk.
- LDCT scans were found to improve accuracy in predicting lung cancer risk.
- AI models achieved the highest accuracy for 1-year lung cancer incidence predictions.
- Both AI and traditional models were associated with a high risk of bias.
- Further validation across diverse populations and standardization of development practices are crucial before widespread implementation.
- Prospective validations in underrepresented populations are needed to determine real-world utility.
Source: JACR
