Higher adjuvant radioactive iodine therapy dosage helps intermediate-risk papillary thyroid carcinoma patients achieve better therapeutic effect

Abstract

ObjectiveThis retrospective study aims to evaluate the therapeutic effect of varying dosages of adjuvant radioactive iodine (RAI) therapy on intermediate-risk papillary thyroid carcinoma (PTC) patients.MethodsThis retrospective study involved a total of 427 intermediate-risk PTC patients, out of which 202 received a 3.7GBq dosage of RAI, and 225 received a 5.55GBq dosage. The evaluation involved assessing the therapeutic outcomes, number of treatment cycles, and successful remnant ablation rates in both dose groups, six months post-adjuvant RAI therapy. Univariate and multivariate logistic regression analyses were employed to identify factors linked with excellent response (ER). Following this, prognostic nomograms were constructed to provide a visual representation of the prediction models. Calibration curves, the concordance index (C-index), and the receiver operating characteristic (ROC) curve were employed to evaluate the predictive performance of these nomograms. The Hosmer-Lemeshow test was applied to assess the models’ goodness-of-fit. Additionally, the clinical utility of the prognostic nomograms was appraised through decision curve analysis (DCA)ResultsThe high-dose (HD) group exhibited significantly higher proportions of ER, single treatment cycles, and successful remnant ablation rates (p<0.05). Being male, receiving a 3.7GBq dose, having an N1b stage, an sTg level ≥10ng/ml, or an sTg/TSH ratio ≥0.11 were independent risk factors for Non-ER. Two prognostic nomograms, “sTg Nomogram” and “sTg/TSH Nomogram”, were established. The ranking of factors contributing to ER, in descending order, included the sTg or sTg/TSH ratio, N stage, therapy dosage, sex, and soft tissue invasion. The “sTg/TSH Nomogram” demonstrated a higher C-index compared to the “sTg Nomogram”. The calibration curves indicated excellent calibration for both nomograms. DCA demonstrated that the net benefit of the “sTg/TSH Nomogram” was higher than that of the “sTg Nomogram”.ConclusionHigher initial RAI therapy doses can improve therapeutic efficacy for intermediate-risk PTC patients. The developed nomograms, particularly the “sTg/TSH Nomogram”, could assist clinicians in optimal therapeutic decision-making.

Construction of a predictive model for postoperative hospitalization time in colorectal cancer patients based on interpretable machine learning algorithm: a prospective preliminary study

“…It involves random sampling with replacement from the training dataset to create multiple subsets for model validation, reducing the variance of validation results and ensuring more reliable evaluations compared to proportional splits, especially with small sample sizes ( 9 , 10 ). SHAP (SHapley Additive exPlanations), based on cooperative game theory, offers clear explanations for feature contribution values, bridging the gap between complex algorithms and clinical application, ensuring transparency and traceability in model-based decision-making, which is crucial for the scientific validity and credibility of medical decisions ( 11 , 12 ).…”

DataSheet_1.docx

“…It involves random sampling with replacement from the training dataset to create multiple subsets for model validation, reducing the variance of validation results and ensuring more reliable evaluations compared to proportional splits, especially with small sample sizes (9,10). SHAP (SHapley Additive exPlanations), based on cooperative game theory, offers clear explanations for feature contribution values, bridging the gap between complex algorithms and clinical application, ensuring transparency and traceability in model-based decision-making, which is crucial for the scientific validity and credibility of medical decisions (11,12).…”