Eugenia Piragine, Sabrina Trippoli, Sara Veneziano, Andrea Messori, Vincenzo Calderone
{"title":"基于Kaplan-Meier (IPDfromKM)方法的非劣效性分析:一种新的潜在应用。","authors":"Eugenia Piragine, Sabrina Trippoli, Sara Veneziano, Andrea Messori, Vincenzo Calderone","doi":"10.3390/mps8010013","DOIUrl":null,"url":null,"abstract":"<p><p>The IPDfromKM method, or Shiny method, is an artificial intelligence tool that enables indirect comparisons between studies by reconstructing individual patient data (IPD) from Kaplan-Meier (KM) curves. The IPDfromKM method is generally used for superiority analyses, but a further application could be represented by non-inferiority analyses. However, there are no studies supporting this methodological hypothesis. The aim of this work was to validate the IPDfromKM method for non-inferiority analyses by \"exploiting\" the well-described non-inferiority of implantable devices occluding the left atrial appendage compared to oral anticoagulants in patients with atrial fibrillation. We performed a systematic review searching for randomized controlled trials (RCTs) in the PubMed database and found five studies. The R software (version 4.3.3) was used to perform a standard survival analysis comparing Watchman and Amlet devices with warfarin. The hazard ratio (HR), with 95% confidence interval (CI), was the main parameter of our analysis. The results confirmed the non-inferiority of Amlet and Watchman compared to warfarin (HR of Watchman vs. warfarin: 1.23, 95% CI 0.80 to 1.9; HR of Amlet vs. warfarin: 1.05, 95% CI 0.61 to 1.80). Therefore, we proposed a new application of the IPDfromKM method that could be potentially relevant in decision-making for the management of this common cardiac arrhythmia and a wide range of other pathological conditions.</p>","PeriodicalId":18715,"journal":{"name":"Methods and Protocols","volume":"8 1","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11857869/pdf/","citationCount":"0","resultStr":"{\"title\":\"The Reconstructed Individual Patient Data from Kaplan-Meier (IPDfromKM) Method for Non-Inferiority Analyses: A New Potential Application.\",\"authors\":\"Eugenia Piragine, Sabrina Trippoli, Sara Veneziano, Andrea Messori, Vincenzo Calderone\",\"doi\":\"10.3390/mps8010013\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The IPDfromKM method, or Shiny method, is an artificial intelligence tool that enables indirect comparisons between studies by reconstructing individual patient data (IPD) from Kaplan-Meier (KM) curves. The IPDfromKM method is generally used for superiority analyses, but a further application could be represented by non-inferiority analyses. However, there are no studies supporting this methodological hypothesis. The aim of this work was to validate the IPDfromKM method for non-inferiority analyses by \\\"exploiting\\\" the well-described non-inferiority of implantable devices occluding the left atrial appendage compared to oral anticoagulants in patients with atrial fibrillation. We performed a systematic review searching for randomized controlled trials (RCTs) in the PubMed database and found five studies. The R software (version 4.3.3) was used to perform a standard survival analysis comparing Watchman and Amlet devices with warfarin. The hazard ratio (HR), with 95% confidence interval (CI), was the main parameter of our analysis. The results confirmed the non-inferiority of Amlet and Watchman compared to warfarin (HR of Watchman vs. warfarin: 1.23, 95% CI 0.80 to 1.9; HR of Amlet vs. warfarin: 1.05, 95% CI 0.61 to 1.80). Therefore, we proposed a new application of the IPDfromKM method that could be potentially relevant in decision-making for the management of this common cardiac arrhythmia and a wide range of other pathological conditions.</p>\",\"PeriodicalId\":18715,\"journal\":{\"name\":\"Methods and Protocols\",\"volume\":\"8 1\",\"pages\":\"\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-02-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11857869/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Methods and Protocols\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/mps8010013\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BIOCHEMICAL RESEARCH METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Methods and Protocols","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/mps8010013","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0
摘要
IPDfromKM方法,或Shiny方法,是一种人工智能工具,通过从Kaplan-Meier (KM)曲线重建个体患者数据(IPD),实现研究之间的间接比较。IPDfromKM方法通常用于优势分析,但进一步的应用可以通过非劣效分析来表示。然而,没有研究支持这种方法论假设。这项工作的目的是验证IPDfromKM方法的非劣效性分析,通过“利用”在房颤患者中,与口服抗凝剂相比,阻塞左心房附件的植入式装置具有良好的非劣效性。我们对PubMed数据库中的随机对照试验(rct)进行了系统回顾,发现了5项研究。使用R软件(版本4.3.3)对Watchman和Amlet装置与华法林进行标准生存分析。风险比(HR), 95%置信区间(CI)是我们分析的主要参数。结果证实Amlet和Watchman与华法林相比无劣效性(Watchman vs.华法林HR: 1.23, 95% CI 0.80 ~ 1.9;Amlet与华法林的HR: 1.05, 95% CI 0.61 ~ 1.80)。因此,我们提出了一种新的IPDfromKM方法的应用,这可能与这种常见心律失常和广泛的其他病理状况的管理决策有关。
The Reconstructed Individual Patient Data from Kaplan-Meier (IPDfromKM) Method for Non-Inferiority Analyses: A New Potential Application.
The IPDfromKM method, or Shiny method, is an artificial intelligence tool that enables indirect comparisons between studies by reconstructing individual patient data (IPD) from Kaplan-Meier (KM) curves. The IPDfromKM method is generally used for superiority analyses, but a further application could be represented by non-inferiority analyses. However, there are no studies supporting this methodological hypothesis. The aim of this work was to validate the IPDfromKM method for non-inferiority analyses by "exploiting" the well-described non-inferiority of implantable devices occluding the left atrial appendage compared to oral anticoagulants in patients with atrial fibrillation. We performed a systematic review searching for randomized controlled trials (RCTs) in the PubMed database and found five studies. The R software (version 4.3.3) was used to perform a standard survival analysis comparing Watchman and Amlet devices with warfarin. The hazard ratio (HR), with 95% confidence interval (CI), was the main parameter of our analysis. The results confirmed the non-inferiority of Amlet and Watchman compared to warfarin (HR of Watchman vs. warfarin: 1.23, 95% CI 0.80 to 1.9; HR of Amlet vs. warfarin: 1.05, 95% CI 0.61 to 1.80). Therefore, we proposed a new application of the IPDfromKM method that could be potentially relevant in decision-making for the management of this common cardiac arrhythmia and a wide range of other pathological conditions.