1
|
Jaotombo F, Pauly V, Fond G, Orleans V, Auquier P, Ghattas B, Boyer L. Machine-learning prediction for hospital length of stay using a French medico-administrative database. JOURNAL OF MARKET ACCESS & HEALTH POLICY 2022; 11:2149318. [PMID: 36457821 PMCID: PMC9707380 DOI: 10.1080/20016689.2022.2149318] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/18/2022] [Revised: 10/17/2022] [Accepted: 11/16/2022] [Indexed: 06/17/2023]
Abstract
INTRODUCTION Prolonged Hospital Length of Stay (PLOS) is an indicator of deteriorated efficiency in Quality of Care. One goal of public health management is to reduce PLOS by identifying its most relevant predictors. The objective of this study is to explore Machine Learning (ML) models that best predict PLOS. METHODS Our dataset was collected from the French Medico-Administrative database (PMSI) as a retrospective cohort study of all discharges in the year 2015 from a large university hospital in France (APHM). The study outcomes were LOS transformed into a binary variable (long vs. short LOS) according to the 90th percentile (14 days). Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB) and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the area under the ROC curve (AUC). RESULTS Our analysis included 73,182 hospitalizations, of which 7,341 (10.0%) led to PLOS. The GB classifier was the most performant model with the highest AUC (0.810), superior to all the other models (all p-values <0.0001). The performance of the RF, GB and NN models (AUC ranged from 0.808 to 0.810) was superior to that of the LR model (AUC = 0.795); all p-values <0.0001. In contrast, LR was superior to CART (AUC = 0.786), p < 0.0001. The variable most predictive of the PLOS was the destination of the patient after hospitalization to other institutions. The typical clinical profile of these patients (17.5% of the sample) was the elderly patient, admitted in emergency, for a trauma, a neurological or a cardiovascular pathology, more often institutionalized, with more comorbidities notably mental health problems, dementia and hemiplegia. DISCUSSION The integration of ML, particularly the GB algorithm, may be useful for health-care professionals and bed managers to better identify patients at risk of PLOS. These findings underscore the need to strengthen hospitals through targeted allocation to meet the needs of an aging population.
Collapse
Affiliation(s)
- Franck Jaotombo
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, La Timone Medical University, Marseille, France
- I2M, CNRS, UMR, Aix-Marseille University, Marseille, France
- Operations Data and Artificial Intelligence, EM Lyon Business School, Ecully, France
| | - Vanessa Pauly
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, La Timone Medical University, Marseille, France
- Service d’Information Médicale, Public Health Department, La Conception Hospital, Assistance Publique - Hôpitaux de Marseille, Marseille, France
| | - Guillaume Fond
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, La Timone Medical University, Marseille, France
| | - Veronica Orleans
- Service d’Information Médicale, Public Health Department, La Conception Hospital, Assistance Publique - Hôpitaux de Marseille, Marseille, France
| | - Pascal Auquier
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, La Timone Medical University, Marseille, France
| | - Badih Ghattas
- I2M, CNRS, UMR, Aix-Marseille University, Marseille, France
| | - Laurent Boyer
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, La Timone Medical University, Marseille, France
- Service d’Information Médicale, Public Health Department, La Conception Hospital, Assistance Publique - Hôpitaux de Marseille, Marseille, France
| |
Collapse
|
2
|
Bachmann N, Zumbrunn A, Bayer-Oglesby L. Social and Regional Factors Predict the Likelihood of Admission to a Nursing Home After Acute Hospital Stay in Older People With Chronic Health Conditions: A Multilevel Analysis Using Routinely Collected Hospital and Census Data in Switzerland. Front Public Health 2022; 10:871778. [PMID: 35615032 PMCID: PMC9126315 DOI: 10.3389/fpubh.2022.871778] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 04/13/2022] [Indexed: 12/15/2022] Open
Abstract
If hospitalization becomes inevitable in the course of a chronic disease, discharge from acute hospital care in older persons is often associated with temporary or persistent frailty, functional limitations and the need for help with daily activities. Thus, acute hospitalization represents a particularly vulnerable phase of transient dependency on social support and health care. This study examines how social and regional inequality affect the decision for an institutionalization after acute hospital discharge in Switzerland. The current analysis uses routinely collected inpatient data from all Swiss acute hospitals that was linked on the individual level with Swiss census data. The study sample included 60,209 patients 75 years old and older living still at a private home and being hospitalized due to a chronic health condition in 199 hospitals between 2010 and 2016. Random intercept multilevel logistic regression was used to assess the impact of social and regional factors on the odds of a nursing home admission after hospital discharge. Results show that 7.8% of all patients were admitted directly to a nursing home after hospital discharge. We found significant effects of education level (compulsory vs. tertiary education OR = 1.16 (95% CI: 1.03-1.30), insurance class (compulsory vs. private insurance OR = 1.24 (95% CI: 1.09-1.41), living alone vs. living with others (OR = 1.64; 95% CI: 1.53-1.76) and language regions (French vs. German speaking part: OR = 0.54; 95% CI: 0.37-0.80) on the odds of nursing home admission in a model adjusted for age, gender, nationality, health status, year of hospitalization and hospital-level variance. The language regions moderated the effect of education and insurance class but not of living alone. This study shows that acute hospital discharge in older age is a critical moment of transient dependency especially for socially disadvantaged patients. Social and health care should work coordinated together to avoid unnecessary institutionalizations.
Collapse
Affiliation(s)
- Nicole Bachmann
- Institute for Social Work and Health, School of Social Work, University of Applied Sciences and Arts Northwestern Switzerland, Olten, Switzerland
| | | | | |
Collapse
|