摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-肿瘤学的新研究-黑色素瘤是一篇报道的主题。据NewsRx记者从重庆发回的消息报道，研究表明：“免疫疗法的出现改变了黑色素瘤的治疗方式，延长了许多患者的生存期。然而，少数患者对免疫疗法仍无反应，目前仍缺乏有效的早期识别工具。”我们的新闻记者引用重庆医科大学第三附属D医院的一篇研究，“研究人员已经开发了机器学习算法来预测黑色素瘤免疫治疗反应，但它们的预测精度不一致，因此，本文对机器学习算法在黑色素瘤免疫治疗反应预测中的准确性进行了系统的重新审视和Meta分析，并在PubMed上检索相关研究。科学网、科克伦图书馆和Embase从成立到2003年7月30日2022.采用偏倚评估预测模型Risk of Bias Assessment TOL(PROBAST)对Included研究的偏倚风险和适用性进行了评估。对R4.2.0.进行了Meta分析，共纳入36项研究，包括30项队列研究和6项病例对照研究。这些研究主要发表于2019年至2022年，包含75个模型。本研究的Outcome度量为无进展的。生存率(PFS),总生存率(OS)和治疗反应。训练组PFS合并C指数为0.728(95%CI:0.629-0.828),训练组和验证组治疗反应合并C指数分别为0.760(95%CI:0.728-0.792)和0.819(95%CI:0.757-0.880),ALOS合并C指数分别为0.746(95%CI:0.721-0.771)和0.700(95%CI"机器学习在黑色素瘤免疫治疗反应和预后方面具有相当大的预测能力,尤其是前者."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Melanoma is the subject of a report. According to news originating from Chongqing, People's Republic of China, by NewsRx correspondents, research stated, "The emergence of immunotherapy has changed the treatment modality for melanoma and prolonged the survival of many patients. However, a handful of patients remain unresponsive t o immunotherapy and effective tools for early identification of this patient pop ulation are still lacking." Our news journalists obtained a quote from the research from the Third Affiliate d Hospital of Chongqing Medical University, "Researchers have developed machine learning algorithms for predicting immunotherapy response in melanoma, but their predictive accuracy has been inconsistent. Therefore, the present systematic re view and meta-analysis was performed to comprehensively evaluate the predictive accuracy of machine learning in melanoma response to immunotherapy. Relevant stu dies were searched in PubMed, Web of Sciences, Cochrane Library, and Embase from their inception to July 30, 2022. The risk of bias and applicability of the inc luded studies were assessed using the Prediction Model Risk of Bias Assessment T ool (PROBAST). Meta-analysis was performed on R4.2.0. A total of 36 studies cons isting of 30 cohort studies and 6 case-control studies were included. These stud ies were mainly published between 2019 and 2022 and encompassed 75 models. The o utcome measures of this study were progression-free survival (PFS), overall surv ival (OS), and treatment response. The pooled c-index was 0.728 (95% CI: 0.629-0.828) for PFS in the training set, 0.760 (95%CI: 0.728-0 .792) and 0.819 (95%CI: 0.757-0.880) for treatment response in the training and validation sets, respectively, and 0.746 (95%CI: 0.721 -0.771) and 0.700 (95%CI: 0.677-0.724) for OS in the training and v alidation sets, respectively. Machine learning has considerable predictive accur acy in melanoma immunotherapy response and prognosis, especially in the former."
NETL
NSTL