Tiehua Rong

Background: This research focused on evaluating the utility of multimodal radiomics integrated with machine learning to predict pathological complete response (pCR) in a prospective cohort of esophageal squamous cell carcinoma (ESCC) patients undergoing neoadjuvant immunochemotherapy (nICT). Methods: We retrospectively analyzed prospectively collected trial data from 66 ESCC patients. Radiomic features were extracted from computed tomography (CT) and magnetic resonance imaging (MRI) images. Four machine learning algorithms—Random Forest (RF), logistic regression, Support Vector Machine, and Extreme Gradient Boosting (XGBoost)—were applied with leave-one-out cross-validation to predict pCR after nICT. The predictive performance of the models was evaluated using receiver operating characteristic curve analysis. Results: In total, 851 features were identified. Among the four machine learning algorithms, the XGBoost machine learning method demonstrated the best model performance across CT, MRI, and clinical feature-based models. Furthermore, the integrated model demonstrated superior performance compared to individual models based solely on CT, MRI, or clinical features across all machine learning algorithms. Among these, the XGboost-based integrated model achieved the highest performance on the test set, with an AUC of 0.961, a TPR of 84.2%, a TNR of 95.7%, a PPV 88.9% of and a NPV of 93.8%. Decision curve analysis validated the model’s robust clinical utility, with calibration curves demonstrating strong concordance between predicted and observed therapeutic responses. Conclusions: The study demonstrates the potential for predicting pCR in patients with ESCC treated with standardized neoadjuvant chemotherapy and PD-1 inhibitors using machine learning methods that integrate multimodal CT and MRI images with clinical features.

Body mass index (BMI) has a U-shaped association with lung cancer risk. However, the effect of BMI on prognosis is controversial. This retrospective study aimed to investigate the effect of BMI on the survival of patients with stage I non-small cell lung cancer (NSCLC) after surgical resection. In total, 624 consecutive stage I NSCLC patients who underwent radical resection were classified into four groups according to their BMI: underweight (BMI < 18.5 kg/m2), normal weight (BMI = 18.5–22.4 kg/m2), overweight (BMI = 22.5–28.0 kg/m2), and obese (BMI > 28.0 kg/m2). The effect of BMI on progression-free survival (PFS) and overall survival (OS) was estimated using the Kaplan–Meier method and Cox proportional hazards model. Postoperative complications in each group were analyzed using the Chi square test or Fisher’s exact test. A univariate analysis showed that PFS and OS were longer in the overweight group than in other groups (both P < 0.05). A multivariate analysis showed that OS was longer in the overweight group than in other groups (compared with the other three groups in combination: hazard ratio [HR] = 1.87, 95% confidence interval [CI] 1.30–2.68, P = 0.003; compared with the underweight group: HR = 2.24, 95% CI 1.18–4.25, P = 0.013; compared with the normal weight group: HR = 1.58, 95% CI 1.07–2.33, P = 0.022; compared with the obese group: HR = 2.87, 95% CI 1.48–5.59, P = 0.002), but PFS was similar among the groups (HR = 1.28, 95% CI 0.97–1.68, P = 0.080). A subgroup analysis showed an association between being overweight and prolonged OS in patients at stage T1a (P = 0.024), T1b (P = 0.051), and T2a (P = 0.02), as well as in patients with a non-smoking history (P = 0.001). Overweight patients had lower rates of postoperative complications, such as respiratory failure (compared with the underweight and obese groups: P = 0.014), myocardial infarction (compared with the obese group: P = 0.033), and perioperative death (compared with the other three groups: P = 0.016). Preoperative BMI is an independent prognostic factor for stage I NSCLC patients after resection, with overweight patients having a favorable prognosis.

To compare the right and left transthoracic approach on the post-operative survival of patients with lymph node-negative esophageal squamous cell carcinoma. Six hundred and ninety-five ESCC patients who underwent esophagectomy between 1990 and 2005 were retrospectively enrolled in the present study and were confirmed by histology to be of no lymph node metastasis. Those who had received neoadjuvant chemotherapy or radiotherapy were excluded from the study. Patients were divided into two groups, the left (n = 545) and right (n = 150) transthoracic groups. The follow-up duration ranged from 1 to 20 years with a mean of 7 years. Kaplan–Meier and univariate and multivariate Cox proportional hazards were used for analysis. 3- and 5-year CSS rates were 62.0 % and 44.0 % in the left group, while the corresponding figures in the right group were 56.0 % and 40.0 %(P < 0.05). The overall survival for the two groups was significantly different (P = 0.045). Survival analyses were stratified by stages, which found that the favorable survival advantage was not present. When the survival curves were stratified by tumor locations, a significant difference was not revealed. Surgical approaches were regarded as one of the prognostic factors in the univariate analysis (P = 0.019). However, this significance could not be confirmed in multivariate Cox regression analysis (P = 0.193). The left transthoracic approach is superior in some aspects to the right transthoracic approach regarding surgical and oncological outcomes in the treatment of lymph node negative ESCC.

Background: To assess the therapeutic outcome and failure pattern of three-dimensional conformal radiotherapy (3D-CRT)-based concurrent chemoradiotherapy (CCRT) for recurrence of esophageal squamous cell carcinoma (SCC) after radical surgery. Methods: Treatment outcome and failure pattern were retrospectively evaluated in 83 patients with localized cervical and thoracic recurrences after radical surgery for thoracic esophageal SCC. All patients were treated with 3DCRT-based CCRT (median radiation dose 60 Gy), in which 39 received concurrent cisplatin plus 5-fluorouracil (PF), and 44 received concurrent docetaxel plus cisplatin (TP). Treatment response was evaluated at 1–3 months after CCRT. Results: With a median follow-up of 34 months (range, 2–116 months), the 3-year overall survival (OS) of all the patients was 51.8% and the median OS time was 43.0 months. The overall tumor response rate was 75.9% (63/83), with a complete remission (CR) rate of 44.6% (37/83). In univariate analysis, tumor response after CCRT (p = 0.000), recurrence site (p = 0.028) and concurrent chemotherapy (p = 0.090) showed a trend favoring better OS. Multivariate analysis revealed that tumor response after CCRT (p = 0.000) and concurrent chemotherapy (p = 0.010) were independent predictors of OS. Forty-seven patients had progressive diseases after CCRT, 27 had local failure (27/47, 57.4%), 18 had distant metastasis (18/47, 38.3%) and 2 had both local and distant failures (2/47, 4.3%). Conclusions: 3DCRT-based CCRT is effective in postoperatively recurrent esophageal SCC. Patients that obtained complete remission after CCRT appeared to achieve long-term OS and might benefit from concurrent TP regimen. Local and distant failures remained high and prospective studies are needed to validate these factors.