Objective:

To develop a multimodal deep learning model for predicting new-onset coronary heart disease (CHD) in cancer patients.

Approach:

Key Findings:

• Out of 1262 patients, 722 (57.2%) developed new-onset CHD, with 696 (55.2%) classified as early-stage (Stage II).
• The CNN-LSTM model achieved an AUC of 0.975, outperforming seven conventional machine learning models.
• In subgroup analysis, the model yielded an AUC of 0.924 in early-stage patients and 0.888 in late-stage patients.
• SHAP analysis identified PAB, CRP, age, cTnI, PT, and ECG markers (HR, QT, QTc intervals) as the strongest predictive features.

Interpretation:

Remove this section.

Limitations:

• Retrospective design may introduce bias.
• Single-center study limits generalizability.
• Potential for incomplete data affecting model accuracy.

Conclusion:

Revise to avoid implications about clinical practice.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.