Prediction of iodine-125 seed implantation efficacy in lung cancer using an enhanced CT-based nomogram model

by Deng Guibin, Shen Xiaolan, Zhang Wei, Lan Xiaoli, Dehui Liu

Background

Lung cancer, a leading cause of death, sees variable outcomes with iodine-125 seed implantation. Predictive tools are lacking, complicating clinical decisions. This study integrates radiomics and clinical features to develop a predictive model, advancing personalized treatment.

Objective

To construct a nomogram model combining enhanced CT image features and general clinical characteristics to evaluate the efficacy of radioactive iodine-125 seed implantation in lung cancer treatment.

Methods

Patients who underwent lung iodine-125 seed implantation at the Nuclear Medicine Department of Xiling Campus, Yichang Central People’s Hospital from January 1, 2018, to January 31, 2024, were randomly divided into a training set (73 cases) and a test set (31 cases). Radiomic features were extracted from the enhanced CT images, and optimal clinical factors were analyzed to construct clinical, radiomics, and combined models. The best model was selected and validated for its role in assessing the efficacy of iodine-125 seed implantation in lung cancer patients.

Results

Three clinical features and five significant radiomic features were successfully selected, and a combined nomogram model was constructed to evaluate the efficacy of iodine-125 seed implantation in lung cancer patients. The AUC values of the model in the training and test sets were 0.95 (95% CI: 0.91–0.99) and 0.83 (95% CI: 0.69–0.98), respectively. The calibration curve demonstrated good agreement between predicted and observed values, and the decision curve indicated that the combined model outperformed the clinical or radiomics model across the majority of threshold ranges.

Conclusion

A combined nomogram model was successfully developed to assess the efficacy of iodine-125 seed implantation in lung cancer patients, demonstrating good clinical predictive performance and high clinical value.