Objective:

To develop and validate a CT-based habitat radiomics model for predicting response to immunochemotherapy in EGFR-mutant lung adenocarcinoma patients after TKI resistance, addressing a significant gap in current treatment strategies.

Key Findings:

• The combined model achieved an AUC of 0.904 (95% CI: 0.871–0.937) in the training cohort and 0.890 (95% CI: 0.838–0.942) in the validation cohort, outperforming other models (P < 0.001).

Interpretation:

The study demonstrates that a CT-based habitat radiomics model can predict immunochemotherapy response in EGFR-mutant lung adenocarcinoma post-TKI resistance, with improved performance over single-modality approaches, potentially leading to better patient stratification.

Limitations:

• Retrospective design may introduce bias, particularly in patient selection and outcome assessment.
• External validation is necessary to confirm findings and ensure generalizability.

Conclusion:

The CT-based habitat radiomics model shows promise in predicting treatment response and overall survival, highlighting the potential of habitat-based features in characterizing intratumoral heterogeneity. Further prospective and multi-center validation is warranted to confirm these findings.