Contrast-Enhanced Computed Tomography-Based Machine Learning Radiomics Predicts IDH1 Expression and Clinical Prognosis in Head and Neck Squamous Cell Carcinoma

Rationale and Objectives

Isocitrate dehydrogenase 1 (IDH1) is a potential therapeutic target across various tumor types. Here, we aimed to devise a radiomic model capable of predicting the IDH1 expression levels in patients with head and neck squamous cell carcinoma (HNSCC) and examined its prognostic significance.

Materials and Methods

We utilized genomic data, clinicopathological features, and contrast-enhanced computed tomography (CECT) images from The Cancer Genome Atlas and the Cancer Imaging Archive for prognosis analysis and radiomic model construction. The selection of optimal features was conducted using the intraclass correlation coefficient, minimum redundancy maximum relevance, and recursive feature elimination algorithms. A radiomic model for IDH1 prediction and radiomic score (RS) were established using a gradient-boosting machine. Associations between IDH1 expression, RS, clinicopathological variables, and overall survival (OS) were determined using univariate and multivariate Cox proportional hazards regression analyses and Kaplan–Meier curves.

Results

IDH1 emerged as a distinct predictive factor in patients with HNSCC (hazard ratio [HR] 1.535, 95% confidence interval [CI]: 1.117–2.11, P = 0.008). The radiomic model, built on eight optimal features, demonstrated area under the curve values of 0.848 and 0.779 in the training and validation sets, respectively, for predicting IDH1 expression levels. Calibration and decision curve analyses validated the model’s suitability and clinical utility. RS was significantly associated with OS (HR = 2.22, 95% CI: 1.026–4.805, P = 0.043).

Conclusion

IDH1 expression is a significant prognostic marker. The developed radiomic model, derived from CECT features, offers a promising approach for diagnosing and prognosticating HNSCC.