Applying machine learning to identify pediatric patients with newly diagnosed acute lymphoblastic leukemia using administrative data.
Pediatr Blood Cancer
; 71(3): e30858, 2024 Mar.
Article
en En
| MEDLINE
| ID: mdl-38189744
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.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Algoritmos
/
Leucemia-Linfoma Linfoblástico de Células Precursoras
Tipo de estudio:
Diagnostic_studies
/
Prognostic_studies
Límite:
Child
/
Humans
Idioma:
En
Revista:
Pediatr Blood Cancer
Asunto de la revista:
HEMATOLOGIA
/
NEOPLASIAS
/
PEDIATRIA
Año:
2024
Tipo del documento:
Article
País de afiliación:
Estados Unidos