Isha Thapa , Raymond Ye Lee , Marcelo Fernandez Vina , Bing Melody Zhang , Humera Ahmed , Andrew Y Shin , Nicholas Bambos , David N Rosenthal , David Scheinker
{"title":"检验数据驱动决策支持实体器官移植虚拟交叉匹配的可行性:一项单中心研究","authors":"Isha Thapa , Raymond Ye Lee , Marcelo Fernandez Vina , Bing Melody Zhang , Humera Ahmed , Andrew Y Shin , Nicholas Bambos , David N Rosenthal , David Scheinker","doi":"10.1016/j.tpr.2023.100144","DOIUrl":null,"url":null,"abstract":"<div><p>The virtual crossmatch is used in transplant medicine to assess the compatibility of organ donors and recipients. Virtual crossmatch methods vary considerably across institutions; require highly trained HLA laboratory experts and clinicians for interpretation; and do not generate data in a standardized format suitable for comparison across institutions. It is not known if standardized multi-center data collection and reporting could potentially facilitate the development of data-driven immunologic decision-making. We sought to examine the feasibility of an algorithmic approach to interpreting virtual crossmatch data.</p><p>We examined Histocompatibility and Immunogenetics laboratory data from 1,152 transplant patients and 1,180 donors from an academic medical transplant center over a ten-year time interval. Principal component analysis was used to simplify the complex high-dimensional data with rare outcomes into a format better suited for analysis. Machine learning models were used to predict negative flow crossmatch results. A training subset of the oldest 80% of the data was used to identify the top-performing model. The model's performance was assessed on the newest 20% of the data with the area under receiver operating characteristic curve (AUC).</p><p>The final dataset included 2205 crossmatch results from 1446 patient-donor pairs of which 2019 (91.6%) were negative and 186 (8.4%) positive. The top-performing model test set AUC was 0.80.</p><p>This study offers the first proof-of-concept of the feasibility of an algorithmic approach to estimate physical crossmatch results. Standardized, multi-institution data collection is necessary to further explore the possibility of a standardized, data-driven virtual crossmatch process.</p></div>","PeriodicalId":37786,"journal":{"name":"Transplantation Reports","volume":"8 3","pages":"Article 100144"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Examining the feasibility of data-driven decision support for the virtual crossmatch for solid organ transplantation: A single center study\",\"authors\":\"Isha Thapa , Raymond Ye Lee , Marcelo Fernandez Vina , Bing Melody Zhang , Humera Ahmed , Andrew Y Shin , Nicholas Bambos , David N Rosenthal , David Scheinker\",\"doi\":\"10.1016/j.tpr.2023.100144\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The virtual crossmatch is used in transplant medicine to assess the compatibility of organ donors and recipients. Virtual crossmatch methods vary considerably across institutions; require highly trained HLA laboratory experts and clinicians for interpretation; and do not generate data in a standardized format suitable for comparison across institutions. It is not known if standardized multi-center data collection and reporting could potentially facilitate the development of data-driven immunologic decision-making. We sought to examine the feasibility of an algorithmic approach to interpreting virtual crossmatch data.</p><p>We examined Histocompatibility and Immunogenetics laboratory data from 1,152 transplant patients and 1,180 donors from an academic medical transplant center over a ten-year time interval. Principal component analysis was used to simplify the complex high-dimensional data with rare outcomes into a format better suited for analysis. Machine learning models were used to predict negative flow crossmatch results. A training subset of the oldest 80% of the data was used to identify the top-performing model. The model's performance was assessed on the newest 20% of the data with the area under receiver operating characteristic curve (AUC).</p><p>The final dataset included 2205 crossmatch results from 1446 patient-donor pairs of which 2019 (91.6%) were negative and 186 (8.4%) positive. The top-performing model test set AUC was 0.80.</p><p>This study offers the first proof-of-concept of the feasibility of an algorithmic approach to estimate physical crossmatch results. Standardized, multi-institution data collection is necessary to further explore the possibility of a standardized, data-driven virtual crossmatch process.</p></div>\",\"PeriodicalId\":37786,\"journal\":{\"name\":\"Transplantation Reports\",\"volume\":\"8 3\",\"pages\":\"Article 100144\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transplantation Reports\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2451959623000197\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transplantation Reports","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2451959623000197","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
Examining the feasibility of data-driven decision support for the virtual crossmatch for solid organ transplantation: A single center study
The virtual crossmatch is used in transplant medicine to assess the compatibility of organ donors and recipients. Virtual crossmatch methods vary considerably across institutions; require highly trained HLA laboratory experts and clinicians for interpretation; and do not generate data in a standardized format suitable for comparison across institutions. It is not known if standardized multi-center data collection and reporting could potentially facilitate the development of data-driven immunologic decision-making. We sought to examine the feasibility of an algorithmic approach to interpreting virtual crossmatch data.
We examined Histocompatibility and Immunogenetics laboratory data from 1,152 transplant patients and 1,180 donors from an academic medical transplant center over a ten-year time interval. Principal component analysis was used to simplify the complex high-dimensional data with rare outcomes into a format better suited for analysis. Machine learning models were used to predict negative flow crossmatch results. A training subset of the oldest 80% of the data was used to identify the top-performing model. The model's performance was assessed on the newest 20% of the data with the area under receiver operating characteristic curve (AUC).
The final dataset included 2205 crossmatch results from 1446 patient-donor pairs of which 2019 (91.6%) were negative and 186 (8.4%) positive. The top-performing model test set AUC was 0.80.
This study offers the first proof-of-concept of the feasibility of an algorithmic approach to estimate physical crossmatch results. Standardized, multi-institution data collection is necessary to further explore the possibility of a standardized, data-driven virtual crossmatch process.
期刊介绍:
To provide to national and regional audiences experiences unique to them or confirming of broader concepts originating in large controlled trials. All aspects of organ, tissue and cell transplantation clinically and experimentally. Transplantation Reports will provide in-depth representation of emerging preclinical, impactful and clinical experiences. -Original basic or clinical science articles that represent initial limited experiences as preliminary reports. -Clinical trials of therapies previously well documented in large trials but now tested in limited, special, ethnic or clinically unique patient populations. -Case studies that confirm prior reports but have occurred in patients displaying unique clinical characteristics such as ethnicities or rarely associated co-morbidities. Transplantation Reports offers these benefits: -Fast and fair peer review -Rapid, article-based publication -Unrivalled visibility and exposure for your research -Immediate, free and permanent access to your paper on Science Direct -Immediately citable using the article DOI