首页|Second Affiliated Hospital of Soochow University Reports Findings in Rectal Cancer (Development and validation of machine learning models and nomograms for predicting the surgical difficulty of laparoscopic resection in rectal cancer)
Second Affiliated Hospital of Soochow University Reports Findings in Rectal Cancer (Development and validation of machine learning models and nomograms for predicting the surgical difficulty of laparoscopic resection in rectal cancer)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Oncology - Rectal Canc er is the subject of a report. According tonews reporting originating from Suzh ou, People’s Republic of China, by NewsRx correspondents, researchstated, “The objective of this study is to develop and validate a machine learning (ML) predi ction model forthe assessment of laparoscopic total mesorectal excision (LaTME) surgery difficulty, as well as to identifyindependent risk factors that influe nce surgical difficulty. Establishing a nomogram aims to assist clinicalpractit ioners in formulating more effective surgical plans before the procedure.”Our news editors obtained a quote from the research from the Second Affiliated H ospital of SoochowUniversity, “This study included 186 patients with rectal can cer who underwent LaTME from January2018 to December 2020. They were divided in to a training cohort (n = 131) versus a validation cohort (n= 55). The difficul ty of LaTME was defined based on Escal’s et al. scoring criteria with modificati ons.We utilized Lasso regression to screen the preoperative clinical characteri stic variables and intraoperativeinformation most relevant to surgical difficul ty for the development and validation of four ML models:logistic regression (LR ), support vector machine (SVM), random forest (RF), and decision tree (DT).The performance of the model was assessed based on the area under the receiver oper ating characteristiccurve(AUC), sensitivity, specificity, and accuracy. Logisti c regression-based column-line plots were createdto visualize the predictive mo del. Consistency statistics (C-statistic) and calibration curves were usedto di scriminate and calibrate the nomogram, respectively. In the validation cohort, a ll four ML modelsdemonstrate good performance: SVM AUC = 0.987, RF AUC = 0.953, LR AUC = 0.950, and DT AUC= 0.904. To enhance visual evaluation, a logistic re gression-based nomogram has been established.Predictive factors included in the nomogram are body mass index (BMI), distance between the tumor tothe dentate l ine 10 cm, radiodensity of visceral adipose tissue (VAT), area of subcutaneous a dipose tissue(SAT), tumor diameter >3 cm, and comorbid hypertension.”
SuzhouPeople’s Republic of ChinaAsiaCancerCyborgsEmerging TechnologiesGastroenterologyHealth and MedicineMachine LearningOncologyRectal CancerRisk and PreventionSurgery
NETL
NSTL
