Applying machine learning to identify pediatric patients with newly diagnosed acute lymphoblastic leukemia using administrative data
- 8 January 2024
- journal article
- research article
- Published by Wiley in Pediatric Blood & Cancer
- Vol. 71 (3) , e30858
Abstract
Case identification in administrative databases is challenging as diagnosis codes alone are not adequate for case ascertainment. We utilized machine learning (ML) to efficiently identify pediatric patients with newly diagnosed acute lymphoblastic leukemia. We tested nine ML models and validated the best model internally and externally. The optimal model had 97% positive predictive value (PPV) and 99% sensitivity in internal validation; 94% PPV and 82% sensitivity in external validation. Our ML model identified a large cohort of 21,044 patients, demonstrating an efficient approach for cohort assembly and enhancing the usability of administrative data.Keywords
This publication has 12 references indexed in Scilit:
- A report from the Leukemia Electronic Abstraction of Records Network on risk of hepatotoxicity during pediatric acute lymphoblastic leukemia treatmentHaematologica, 2022
- Identifying relapses and stem cell transplants in pediatric acute lymphoblastic leukemia using administrative data: Capturing national outcomes irrespective of trial enrollmentPediatric Blood & Cancer, 2020
- Dissecting racial bias in an algorithm used to manage the health of populationsScience, 2019
- Development and evaluation of a computable phenotype to identify pediatric patients with leukemia and lymphoma treated with chemotherapy using electronic health record dataPediatric Blood & Cancer, 2019
- Machine Learning in MedicineNew England Journal of Medicine, 2019
- Volume–Outcome Relationships in Pediatric Acute Lymphoblastic Leukemia: Association Between Hospital Pediatric and Pediatric Oncology Volume With Mortality and Intensive Care Resources During Initial TherapyClinical Lymphoma Myeloma and Leukemia, 2016
- Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic reviewJournal of the American Medical Informatics Association, 2016
- Merging Children’s Oncology Group Data with an External Administrative Database Using Indirect Patient Identifiers: A Report from the Children’s Oncology GroupPLOS ONE, 2015
- Establishment of an 11-Year Cohort of 8733 Pediatric Patients Hospitalized at United States Free-standing Children’s Hospitals With De Novo Acute Lymphoblastic Leukemia From Health Care Administrative DataMedical Care, 2014
- Differential Case Ascertainment in Clinical Registry Versus Administrative Data and Impact on Outcomes Assessment for Pediatric Cardiac OperationsThe Annals of Thoracic Surgery, 2013