To use clinical, radiographic, and CT radiomics features to develop and validate a preoperative prediction model for the early recurrence of pancreatic cancer. We retrospectively analyzed 190 patients (150 and 40 in the development and test cohort from different centers) with pancreatic cancer who underwent pancreatectomy between January 2018 and June 2021. Radiomics, clinical-radiologic (CR), and clinical-radiologic-radiomics (CRR) models were developed for the prediction of recurrence within 12 months after surgery. Performance was evaluated using the area under the curve (AUC), Brier score, sensitivity, and specificity. Early recurrence occurred in 36.7% and 42.5% of the development and test cohorts, respectively (P = 0.62). The features for the CR model included carbohydrate antigen 19-9 > 500 U/mL (odds ratio [OR], 3.60; P = 0.01), abutment to the portal and/or superior mesenteric vein (OR, 2.54; P = 0.054), and adjacent organ invasion (OR, 2.91; P = 0.03). The CRR model demonstrated significantly higher AUCs than the radiomics model in the internal (0.77 vs. 0.73; P = 0.048) and external (0.83 vs. 0.69; P = 0.038) validations. Although we found no significant difference between AUCs of the CR and CRR models (0.83 vs. 0.76; P = 0.17), CRR models showed more balanced sensitivity and specificity (0.65 and 0.87) than CR model (0.41 and 0.91) in the test cohort. The CRR model outperformed the radiomics and CR models in predicting the early recurrence of pancreatic cancer, providing valuable information for risk stratification and treatment guidance.

中文翻译：

---

结合临床、放射学和 CT 放射组学特征对可切除胰腺癌早期复发进行术前预测

利用临床、放射学和 CT 放射组学特征来开发和验证胰腺癌早期复发的术前预测模型。我们回顾性分析了 2018 年 1 月至 2021 年 6 月期间接受胰腺切除术的 190 名胰腺癌患者（来自不同中心的开发和测试队列中的 150 名和 40 名）。放射组学、临床放射学 (CR) 和临床放射学放射组学 (CRR)开发模型用于预测术后 12 个月内的复发。使用曲线下面积 (AUC)、Brier 评分、敏感性和特异性来评估性能。开发组和测试组的早期复发率分别为 36.7% 和 42.5%（P = 0.62）。CR 模型的特征包括碳水化合物抗原 19-9 > 500 U/mL（比值比 [OR]，3.60；P = 0.01）、邻接门静脉和/或肠系膜上静脉（OR，2.54；P = 0.054）和邻近器官侵犯（OR，2.91；P = 0.03）。在内部（0.77 vs. 0.73；P = 0.048）和外部（0.83 vs. 0.69；P = 0.038）验证中，CRR 模型的 AUC 显着高于放射组学模型。尽管我们发现 CR 和 CRR 模型的 AUC 之间没有显着差异（0.83 与 0.76；P = 0.17），但在测试队列中，CRR 模型比 CR 模型（0.41 和 0.91）表现出更平衡的敏感性和特异性（0.65 和 0.87）。 。CRR模型在预测胰腺癌早期复发方面优于放射组学和CR模型，为风险分层和治疗指导提供了有价值的信息。