Artificial Intelligence in ALK-Rearranged NSCLC: Forecasting Response and Resistance

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Management and prognosis of ALK-rearranged non-small-cell lung cancer have improved.
• Challenges persist in molecular identification, treatment response prediction, and resistance mechanisms.

Purpose of the Study:

• To systematically review and synthesize evidence on AI approaches for ALK-rearranged lung cancer.
• To evaluate AI's use of imaging, pathology, molecular, and clinical data.

Main Methods:

• Systematic literature search (2020-2025) adhering to PRISMA 2020 guidelines.
• Included studies applied AI/ML/DL to predict ALK status or treatment outcomes.
• Bibliometric co-occurrence analysis for thematic and temporal trends.

Main Results:

• Thirteen retrospective studies analyzed radiologic, pathologic, molecular, or multimodal data.
• AI models showed high performance in predicting ALK status (AUC 0.73-0.99) and outcomes.
• Research trends show a shift towards treatment-specific and integrative analyses, with limited external validation.

Conclusions:

• AI demonstrates potential in diagnosis, prognostication, and treatment assessment for ALK-rearranged lung cancer.
• Methodological heterogeneity and limited validation hinder current clinical translation.