Towards a personalized health care using a divisive hierarchical clustering approach for comorbidity and the prediction of conditioned group risks


Por: Navarro-Cerdán J, Sánchez-Gomis M, Pons P, Gálvez-Settier S, Valverde F, Ferrer-Albero A, Saurí I, Fernández A, Redon J

Publicada: 1 oct 2023
Resumen:
The objective was to assess risk of hospitalization and mortality of comorbidities using divisive hierarchical risk clustering to advice clinical interventions. Subjects and Methods: Data from the EHR of a general population, 3799885 adults, followed by 5 years. Model were performed using Spark and Scikit-learn and accuracy for the models was analyzed. Results: The number of models generated depends in part on the number of chronic diseases included (ex testing a sample of six diseases, a total number of 397 models for all-cause mortality and 431 models for hospitalization). The estimated models offered an ordered selection for the relevant clinical variables and their estimated risk as a group and for the individual patient in the group. Accuracy was assessed according to age, sex and the cardinality of the comorbid groups. A mobile version and dashboard were developed. Conclusion: The software developed stratified hospital admission and mortality risk in clusters of chronic diseases, and for a given patient, it could advise intensifying treatment or reallocating the patient risk.

Filiaciones:
Navarro-Cerdán J:
 Univ Politecnia Valencia, InstitutoTecnol Informat, Valencia, Spain

 Univ Politecnia Valencia, Inst Tecnol Informat, Valencia 46022, Spain

Sánchez-Gomis M:
 Univ Politecnia Valencia, InstitutoTecnol Informat, Valencia, Spain

Pons P:
 Univ Politecnia Valencia, InstitutoTecnol Informat, Valencia, Spain

Gálvez-Settier S:
 Univ Politecnia Valencia, InstitutoTecnol Informat, Valencia, Spain

Valverde F:
 Univ Valencia, Valencia, Spain

Ferrer-Albero A:
 INCLIVA, Valencia, Spain

Saurí I:
 INCLIVA, Valencia, Spain

Fernández A:
 INCLIVA, Valencia, Spain

Redon J:
 INCLIVA, Valencia, Spain

 CIBEROBN, Inst Salud Carlos III, Madrid, Spain
ISSN: 14604582





Health Informatics Journal
Editorial
SAGE Publications, 2455 TELLER RD, THOUSAND OAKS, CA 91320 USA, Reino Unido
Tipo de documento: Article
Volumen: 29 Número: 4
Páginas:
WOS Id: 001122214900001
ID de PubMed: 38072502
imagen gold

FULL TEXT

imagen Published Version
No Accesible

MÉTRICAS