Solaf Al Awadhi, Enshuo Hsu, Thomas B. H. Potter, Ioannis A. Kakadiaris, David A. Axelrod, Faith Parsons, Andrea M. Meinders, Victoria Cassell, Catherine Pulicken, Zulqarnain Javed, Paula K. Shireman, Stefano Casarin, A. L. Jonathan Gelfond, Amy D. Waterman
{"title":"开发和验证机器学习驱动的风险指数,以预测患者在转诊,评估和等待肾脏移植的过程中退出。","authors":"Solaf Al Awadhi, Enshuo Hsu, Thomas B. H. Potter, Ioannis A. Kakadiaris, David A. Axelrod, Faith Parsons, Andrea M. Meinders, Victoria Cassell, Catherine Pulicken, Zulqarnain Javed, Paula K. Shireman, Stefano Casarin, A. L. Jonathan Gelfond, Amy D. Waterman","doi":"10.1111/ctr.70325","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Transplant is the optimal treatment for kidney failure; however, disparities in access persist. We developed and validated risk indices to predict early dropout at key stages of the transplant-seeking process not captured in national registries.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>We included patients referred for kidney transplant at Houston Methodist Hospital between June 2016, and November 2023. We collected demographic, clinical, patient- and contextual-level socioeconomic variables from electronic health records and publicly available census data. We used machine learning (ML) models to predict the characteristics of patients at higher risk of dropping out: (1) at referral (before starting evaluation), (2) in the process of evaluation (before waitlisting), and (3) during waitlisting (before receiving a transplant). Model performance was evaluated using AUROC.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Of 4133 referred patients, 46% did not attend their first transplant evaluation visit. Of 2414 patients who were medically eligible for transplant and started evaluation, 54% did not become waitlisted. Of 2457 waitlisted patients, 31% became inactive on the waitlist. Higher risk patients were consistently older, obese, and socioeconomically disadvantaged, with stage-specific differences: social factors—such as being single, unemployed, less educated, and living in high-deprivation areas—and African American race dominated at referral (AUROC 0.79); clinical comorbidities and both African American and Hispanic ethnicity were prominent at evaluation (AUROC 0.71); and Hispanic ethnicity, smoking, and digital exclusion were key drivers at waitlisting (AUROC 0.76).</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>ML models effectively identified dropout risk at referral, evaluation, and waitlisting, enabling early identification of at-risk patients. Targeted interventions could reduce disparities, improve evaluation completion, and increase transplant access.</p>\n </section>\n </div>","PeriodicalId":10467,"journal":{"name":"Clinical Transplantation","volume":"39 9","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Developing and Validating Machine Learning-Driven Risk Indices to Predict Patient Dropout During Referral, Evaluation, and Waitlisting for Kidney Transplant\",\"authors\":\"Solaf Al Awadhi, Enshuo Hsu, Thomas B. H. Potter, Ioannis A. Kakadiaris, David A. Axelrod, Faith Parsons, Andrea M. Meinders, Victoria Cassell, Catherine Pulicken, Zulqarnain Javed, Paula K. Shireman, Stefano Casarin, A. L. Jonathan Gelfond, Amy D. Waterman\",\"doi\":\"10.1111/ctr.70325\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>Transplant is the optimal treatment for kidney failure; however, disparities in access persist. We developed and validated risk indices to predict early dropout at key stages of the transplant-seeking process not captured in national registries.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>We included patients referred for kidney transplant at Houston Methodist Hospital between June 2016, and November 2023. We collected demographic, clinical, patient- and contextual-level socioeconomic variables from electronic health records and publicly available census data. We used machine learning (ML) models to predict the characteristics of patients at higher risk of dropping out: (1) at referral (before starting evaluation), (2) in the process of evaluation (before waitlisting), and (3) during waitlisting (before receiving a transplant). Model performance was evaluated using AUROC.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>Of 4133 referred patients, 46% did not attend their first transplant evaluation visit. Of 2414 patients who were medically eligible for transplant and started evaluation, 54% did not become waitlisted. Of 2457 waitlisted patients, 31% became inactive on the waitlist. Higher risk patients were consistently older, obese, and socioeconomically disadvantaged, with stage-specific differences: social factors—such as being single, unemployed, less educated, and living in high-deprivation areas—and African American race dominated at referral (AUROC 0.79); clinical comorbidities and both African American and Hispanic ethnicity were prominent at evaluation (AUROC 0.71); and Hispanic ethnicity, smoking, and digital exclusion were key drivers at waitlisting (AUROC 0.76).</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusion</h3>\\n \\n <p>ML models effectively identified dropout risk at referral, evaluation, and waitlisting, enabling early identification of at-risk patients. Targeted interventions could reduce disparities, improve evaluation completion, and increase transplant access.</p>\\n </section>\\n </div>\",\"PeriodicalId\":10467,\"journal\":{\"name\":\"Clinical Transplantation\",\"volume\":\"39 9\",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-09-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical Transplantation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/ctr.70325\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"SURGERY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Transplantation","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/ctr.70325","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SURGERY","Score":null,"Total":0}
Developing and Validating Machine Learning-Driven Risk Indices to Predict Patient Dropout During Referral, Evaluation, and Waitlisting for Kidney Transplant
Background
Transplant is the optimal treatment for kidney failure; however, disparities in access persist. We developed and validated risk indices to predict early dropout at key stages of the transplant-seeking process not captured in national registries.
Methods
We included patients referred for kidney transplant at Houston Methodist Hospital between June 2016, and November 2023. We collected demographic, clinical, patient- and contextual-level socioeconomic variables from electronic health records and publicly available census data. We used machine learning (ML) models to predict the characteristics of patients at higher risk of dropping out: (1) at referral (before starting evaluation), (2) in the process of evaluation (before waitlisting), and (3) during waitlisting (before receiving a transplant). Model performance was evaluated using AUROC.
Results
Of 4133 referred patients, 46% did not attend their first transplant evaluation visit. Of 2414 patients who were medically eligible for transplant and started evaluation, 54% did not become waitlisted. Of 2457 waitlisted patients, 31% became inactive on the waitlist. Higher risk patients were consistently older, obese, and socioeconomically disadvantaged, with stage-specific differences: social factors—such as being single, unemployed, less educated, and living in high-deprivation areas—and African American race dominated at referral (AUROC 0.79); clinical comorbidities and both African American and Hispanic ethnicity were prominent at evaluation (AUROC 0.71); and Hispanic ethnicity, smoking, and digital exclusion were key drivers at waitlisting (AUROC 0.76).
Conclusion
ML models effectively identified dropout risk at referral, evaluation, and waitlisting, enabling early identification of at-risk patients. Targeted interventions could reduce disparities, improve evaluation completion, and increase transplant access.
期刊介绍:
Clinical Transplantation: The Journal of Clinical and Translational Research aims to serve as a channel of rapid communication for all those involved in the care of patients who require, or have had, organ or tissue transplants, including: kidney, intestine, liver, pancreas, islets, heart, heart valves, lung, bone marrow, cornea, skin, bone, and cartilage, viable or stored.
Published monthly, Clinical Transplantation’s scope is focused on the complete spectrum of present transplant therapies, as well as also those that are experimental or may become possible in future. Topics include:
Immunology and immunosuppression;
Patient preparation;
Social, ethical, and psychological issues;
Complications, short- and long-term results;
Artificial organs;
Donation and preservation of organ and tissue;
Translational studies;
Advances in tissue typing;
Updates on transplant pathology;.
Clinical and translational studies are particularly welcome, as well as focused reviews. Full-length papers and short communications are invited. Clinical reviews are encouraged, as well as seminal papers in basic science which might lead to immediate clinical application. Prominence is regularly given to the results of cooperative surveys conducted by the organ and tissue transplant registries.
Clinical Transplantation: The Journal of Clinical and Translational Research is essential reading for clinicians and researchers in the diverse field of transplantation: surgeons; clinical immunologists; cryobiologists; hematologists; gastroenterologists; hepatologists; pulmonologists; nephrologists; cardiologists; and endocrinologists. It will also be of interest to sociologists, psychologists, research workers, and to all health professionals whose combined efforts will improve the prognosis of transplant recipients.