Jiping Wang, Shunqin Zhang, Huangdi Yi, Shuangge Ma
{"title":"Comparative Effectiveness Analysis of Lumpectomy and Mastectomy for Elderly Female Breast Cancer Patients: A Deep Learning-based Big Data Analysis.","authors":"Jiping Wang, Shunqin Zhang, Huangdi Yi, Shuangge Ma","doi":"10.59249/IAJU7580","DOIUrl":null,"url":null,"abstract":"<p><p><b>Objectives</b>: To evaluate the comparative effectiveness of treatments, a randomized clinical trial remains the gold standard but can be challenged by a high cost, a limited sample size, an inability to fully reflect the real world, and feasibility concerns. The objective is to showcase a big data approach that takes advantage of large electronic medical record (EMR) data to emulate clinical trials. To overcome the limitations of regression analysis, a deep learning-based analysis pipeline was developed. <b>Study Design and Setting</b>: Lumpectomy (breast-conserving surgery) and mastectomy are the two most commonly used surgical procedures for early-stage female breast cancer patients. An emulation trial was designed using the Surveillance, Epidemiology, and End Results (SEER)-Medicare data to evaluate their relative effectiveness in overall survival. The analysis pipeline consisted of a propensity score step, a weighted survival analysis step, and a bootstrap inference step. <b>Results</b>: A total of 65,997 subjects were enrolled in the emulated trial, with 50,704 and 15,293 in the lumpectomy and mastectomy arms, respectively. The two surgery procedures had comparable effects in terms of overall survival (survival year change = 0.08, 95% confidence interval (CI): -0.08, 0.25) for the elderly SEER-Medicare early-stage female breast cancer patients. <b>Conclusion</b>: This study demonstrated the power of \"mining large EMR data + deep learning-based analysis,\" and the proposed analysis strategy and technique can be potentially broadly applicable. It provided convincing evidence of the comparative effectiveness of lumpectomy and mastectomy.</p>","PeriodicalId":48617,"journal":{"name":"Yale Journal of Biology and Medicine","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/0a/be/yjbm_96_3_327.PMC10524818.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Yale Journal of Biology and Medicine","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.59249/IAJU7580","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/9/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: To evaluate the comparative effectiveness of treatments, a randomized clinical trial remains the gold standard but can be challenged by a high cost, a limited sample size, an inability to fully reflect the real world, and feasibility concerns. The objective is to showcase a big data approach that takes advantage of large electronic medical record (EMR) data to emulate clinical trials. To overcome the limitations of regression analysis, a deep learning-based analysis pipeline was developed. Study Design and Setting: Lumpectomy (breast-conserving surgery) and mastectomy are the two most commonly used surgical procedures for early-stage female breast cancer patients. An emulation trial was designed using the Surveillance, Epidemiology, and End Results (SEER)-Medicare data to evaluate their relative effectiveness in overall survival. The analysis pipeline consisted of a propensity score step, a weighted survival analysis step, and a bootstrap inference step. Results: A total of 65,997 subjects were enrolled in the emulated trial, with 50,704 and 15,293 in the lumpectomy and mastectomy arms, respectively. The two surgery procedures had comparable effects in terms of overall survival (survival year change = 0.08, 95% confidence interval (CI): -0.08, 0.25) for the elderly SEER-Medicare early-stage female breast cancer patients. Conclusion: This study demonstrated the power of "mining large EMR data + deep learning-based analysis," and the proposed analysis strategy and technique can be potentially broadly applicable. It provided convincing evidence of the comparative effectiveness of lumpectomy and mastectomy.
期刊介绍:
The Yale Journal of Biology and Medicine (YJBM) is a graduate and medical student-run, peer-reviewed, open-access journal dedicated to the publication of original research articles, scientific reviews, articles on medical history, personal perspectives on medicine, policy analyses, case reports, and symposia related to biomedical matters. YJBM is published quarterly and aims to publish articles of interest to both physicians and scientists. YJBM is and has been an internationally distributed journal with a long history of landmark articles. Our contributors feature a notable list of philosophers, statesmen, scientists, and physicians, including Ernst Cassirer, Harvey Cushing, Rene Dubos, Edward Kennedy, Donald Seldin, and Jack Strominger. Our Editorial Board consists of students and faculty members from Yale School of Medicine and Yale University Graduate School of Arts & Sciences. All manuscripts submitted to YJBM are first evaluated on the basis of scientific quality, originality, appropriateness, contribution to the field, and style. Suitable manuscripts are then subject to rigorous, fair, and rapid peer review.