XGBoost-based lung cancer risk prediction model shows greater accuracy than logistic regression in a large screening cohort.
Key Details
- 1Study analyzed data from 11,708 participants in the Guangzhou Lung-Care Project.
- 2Data split into 70% training and 30% validation cohorts.
- 3XGBoost machine learning algorithm achieved an AUC of 0.658, compared to 0.647 for logistic regression.
- 4Childhood exposure to cooking fuels was found to significantly affect lung cancer risk.
- 5Study addresses a gap in machine learning-based lung cancer risk prediction research in China.
Why It Matters
Machine learning models like XGBoost can provide more accurate and robust risk predictions for lung cancer screening, potentially improving early identification and targeting of high-risk individuals. This enhances the effectiveness of radiology-led screening programs and supports broader adoption of AI-driven risk assessments.
Source
AuntMinnie
Related News
•Radiology Business
Imaging AI Systems Could Play Key Role in Future Pandemic Response
A study finds that repurposed AI detection tools in radiology could help address future pandemics more effectively.
•AuntMinnie
GPT-4o Outperforms Radiologists in CT Protocoling With Prompt Engineering
GPT-4o, with prompt engineering, selected optimal abdominal/pelvic CT protocols more accurately than radiologists without increasing inappropriate selections.
•Radiology Business
GPT-4o Surpasses Radiologists in CT Protocol Selection Using AI
GPT-4o, a large language model, demonstrates superior performance to radiologists in protocoling CT scans when provided with appropriate context.