Machine learning using PROFUND components for 30-day readmission prediction in multimorbid patients: a prospective multicentre study

Vista sencilla de ítem
dc.contributor.authorPikatza Huerga, Amaia
dc.contributor.authorAlmeida, Aitor
dc.contributor.authorQuirós, Raúl
dc.contributor.authorLegarreta Olabarrieta, María José
dc.contributor.authorZulaika Zurimendi, Unai
dc.contributor.authorMestre, Daniela
dc.contributor.authorGarcía Gutiérrez, Susana
dc.date.accessioned2026-08-06T08:30:08Z
dc.date.available2026-08-06T08:30:08Z
dc.date.issued2026
dc.date.updated2026-08-06T08:30:08Z
dc.description.abstractEarly hospital readmission in multimorbid patients remains a major clinical challenge. Although risk stratification tools are widely used, predictive performance is often limited. The PROFUND index captures frailty, functional dependence, and social vulnerability, but its role in predicting 30-day readmission is unclear. In this prospective multicentre cohort study, multimorbid patients admitted to Internal Medicine and Geriatrics departments were followed after discharge. The primary outcome was unplanned 30-day readmission among patients surviving to 30 days. Models based on PROFUND components were developed using logistic regression and gradient boosting, including a calibrated ensemble model, and compared with LACE and HOSPITAL scores. Performance was assessed in an external validation cohort. Among 435 patients included in the readmission analysis, 14% were readmitted within 30 days. In external validation, discrimination remained modest (AUC 0.52–0.59). The ensemble XGBoost model achieved the highest AUC (0.59), followed by XGBoost (0.58), HOSPITAL (0.54), and LACE (0.52). Differences were incremental. SHAP analysis identified cognitive impairment, anaemia, advanced age, heart failure severity, functional dependence, and limited caregiver support as key contributors. Incorporating frailty, functional, and social vulnerability domains through PROFUND components resulted in only modest improvements in 30-day readmission prediction. Even with machine learning, discrimination remained limited. The observed performance likely reflects both the intrinsic complexity of short-term readmission and the constraints imposed by sample size and available predictors.en
dc.description.sponsorshipFunding for this research was provided by the Carlos III Health Institute (Instituto de Salud Carlos III, ISCIII), project reference PI18/01438 “Identification of multimorbid patients with a higher probability of readmission and mortality: Role of the patient-related variables,” co-funded by the European Union through the European Regional Development Fund (ERDF) “A way to make Europe.”en
dc.identifier.citationPikatza-Huerga, A., Almeida, A., Quirós, R., Legarreta, M. J., Zulaika, U., Mestre, D., & García-Gutiérrez, S. (2026). Machine learning using PROFUND components for 30-day readmission prediction in multimorbid patients: a prospective multicentre study. Scientific Reports, 16(1). https://doi.org/10.1038/S41598-026-51343-Y
dc.identifier.doi10.1038/S41598-026-51343-Y
dc.identifier.eissn2045-2322
dc.identifier.urihttps://hdl.handle.net/20.500.14454/6477
dc.language.isoeng
dc.publisherNature Research
dc.rights© The Author(s) 2026
dc.titleMachine learning using PROFUND components for 30-day readmission prediction in multimorbid patients: a prospective multicentre studyen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.issue1
oaire.citation.titleScientific Reports
oaire.citation.volume16
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
pikatza_machine_2026.pdf
Tamaño:
2.16 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos