7235University of Saskatchewan, Saskatoon, Canada.
12371College of Medicine, 7235University of Saskatchewan, Saskatoon, Canada.
Technol Cancer Res Treat. 2021 Jan-Dec;20:15330338211050767. doi: 10.1177/15330338211050767.
The purpose of this project is to identify prognostic features in resectable pancreatic head adenocarcinoma and use these features to develop a machine learning algorithm that prognosticates survival for patients pursuing pancreaticoduodenectomy. A retrospective cohort study of 93 patients who underwent a pancreaticoduodenectomy was performed. The patients were analyzed in 2 groups: Group 1 (n = 38) comprised of patients who survived < 2 years, and Group 2 (n = 55) comprised of patients who survived > 2 years. After comparing the two groups, 9 categorical features and 2 continuous features (11 total) were selected to be statistically significant (p < .05) in predicting outcome after surgery. These 11 features were used to train a machine learning algorithm that prognosticates survival. The algorithm obtained 75% accuracy, 41.9% sensitivity, and 97.5% specificity in predicting whether survival is less than 2 years after surgery. A supervised machine learning algorithm that prognosticates survival can be a useful tool to personalize treatment plans for patients with pancreatic cancer.
本项目旨在识别可切除胰腺头部腺癌的预后特征，并利用这些特征开发一种机器学习算法，对接受胰十二指肠切除术的患者的生存情况进行预测。对 93 名接受胰十二指肠切除术的患者进行了回顾性队列研究。将患者分为两组：第 1 组（n=38）由生存时间<2 年的患者组成，第 2 组（n=55）由生存时间>2 年的患者组成。比较两组后，选择了 9 个分类特征和 2 个连续特征（共 11 个），这些特征在预测手术后的结果方面具有统计学意义（p<.05）。这些 11 个特征用于训练预测生存的机器学习算法。该算法在预测手术后生存时间是否少于 2 年方面的准确率为 75%，灵敏度为 41.9%，特异性为 97.5%。预测生存的有监督机器学习算法可以成为为胰腺癌患者制定个性化治疗计划的有用工具。
