Developing and Validating Machine Learning-Driven Risk Indices to Predict Patient Dropout During Referral, Evaluation, and Waitlisting for Kidney Transplant

Organization: John Wiley & Sons Ltd
Journey Stage: (C) Referral, (D) Evaluation, (E) Listing
Organization Type: Society or Professional Organization
Use Case(s): Allocation, Patient Access
Country: USA

Pulled from PubMed:

Solaf Al Awadhi 1, Enshuo Hsu 2, Thomas B H Potter 2, Ioannis A Kakadiaris 3, David A Axelrod 4, Faith Parsons 1, Andrea M Meinders 1, Victoria Cassell 1, Catherine Pulicken 1, Zulqarnain Javed 5, Paula K Shireman 6, Stefano Casarin 1 7 8, A L Jonathan Gelfond 9, Amy D Waterman 1

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.

Key Contact:

Solaf
Al Awadhi
Affilate Researcher at Paris Institute for Transplantation & Organ Regeneration Scientist (PITOR)

The Alliance is committed to fostering collaboration and knowledge-sharing across the donation and transplantation community. Research and materials shared on this page are contributed by individual authors and organizations. While we aim to provide a valuable forum for exchange, submissions are not formally reviewed or endorsed by The Alliance. The perspectives expressed belong solely to the authors, and users are encouraged to review content thoughtfully and in the context of their own professional judgment.