Outpatient readmission in rheumatology: A machine learning predictive model of patient's return to the clinic

Madrid García, Alfredo and Font Urgelles, Judit and Vega Barbas, Mario and León Mateos, Leticia and Freites Núñez, Dalifer Dayanira and Jesús Lajas, Cristina and Pato Cour, Esperanza and Jover Jover, Juan Ángel and Fernández Gutiérrez, Benjamín and Abásolo Alcázar, Lydia and Rodríguez Rodríguez, Luis (2019). Outpatient readmission in rheumatology: A machine learning predictive model of patient's return to the clinic. "Arthritis & Rheumatology", v. 8 (n. 8); pp. 1-20. ISSN 2077-0383. https://doi.org/10.3390/jcm8081156.

Description

Title: Outpatient readmission in rheumatology: A machine learning predictive model of patient's return to the clinic
Author/s:
  • Madrid García, Alfredo
  • Font Urgelles, Judit
  • Vega Barbas, Mario
  • León Mateos, Leticia
  • Freites Núñez, Dalifer Dayanira
  • Jesús Lajas, Cristina
  • Pato Cour, Esperanza
  • Jover Jover, Juan Ángel
  • Fernández Gutiérrez, Benjamín
  • Abásolo Alcázar, Lydia
  • Rodríguez Rodríguez, Luis
Item Type: Article
Título de Revista/Publicación: Arthritis & Rheumatology
Date: August 2019
ISSN: 2077-0383
Volume: 8
Subjects:
Freetext Keywords: musculoskeletal diseases; outpatient readmission; predictive model; random forest; quality of life
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería de Sistemas Telemáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Our objective is to develop and validate a predictive model based on the random forest algorithm to estimate the readmission risk to an outpatient rheumatology clinic after discharge. We included patients from the Hospital Clínico San Carlos rheumatology outpatient clinic, from 1 April 2007 to 30 November 2016, and followed-up until 30 November 2017. Only readmissions between 2 and 12 months after the discharge were analyzed. Discharge episodes were chronologically split into training, validation, and test datasets. Clinical and demographic variables (diagnoses, treatments, quality of life (QoL), and comorbidities) were used as predictors. Models were developed in the training dataset, using a grid search approach, and performance was compared using the area under the receiver operating characteristic curve (AUC-ROC). A total of 18,662 discharge episodes were analyzed, out of which 2528 (13.5%) were followed by outpatient readmissions. Overall, 38,059 models were developed. AUC-ROC, sensitivity, and specificity of the reduced final model were 0.653, 0.385, and 0.794, respectively. The most important variables were related to follow-up duration, being prescribed with disease-modifying anti-rheumatic drugs and corticosteroids, being diagnosed with chronic polyarthritis, occupation, and QoL. We have developed a predictive model for outpatient readmission in a rheumatology setting. Identification of patients with higher risk can optimize the allocation of healthcare resources.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainCPII17/00014UnspecifiedUnspecifiedUnspecified
Government of SpainRED16/0012/0004UnspecifiedUnspecifiedUnspecified

More information

Item ID: 63692
DC Identifier: http://oa.upm.es/63692/
OAI Identifier: oai:oa.upm.es:63692
DOI: 10.3390/jcm8081156
Official URL: https://www.mdpi.com/2077-0383/8/8/1156
Deposited by: Memoria Investigacion
Deposited on: 29 Sep 2020 13:37
Last Modified: 29 Sep 2020 13:37
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM