Dataset Information

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.

ABSTRACT: BACKGROUND:Home hospitalization is widely accepted as a cost-effective alternative to conventional hospitalization for selected patients. A recent analysis of the home hospitalization and early discharge (HH/ED) program at Hospital Clínic de Barcelona over a 10-year period demonstrated high levels of acceptance by patients and professionals, as well as health value-based generation at the provider and health-system levels. However, health risk assessment was identified as an unmet need with the potential to enhance clinical decision making. OBJECTIVE:The objective of this study is to generate and assess predictive models of mortality and in-hospital admission at entry and at HH/ED discharge. METHODS:Predictive modeling of mortality and in-hospital admission was done in 2 different scenarios: at entry into the HH/ED program and at discharge, from January 2009 to December 2015. Multisource predictive variables, including standard clinical data, patients' functional features, and population health risk assessment, were considered. RESULTS:We studied 1925 HH/ED patients by applying a random forest classifier, as it showed the best performance. Average results of the area under the receiver operating characteristic curve (AUROC; sensitivity/specificity) for the prediction of mortality were 0.88 (0.81/0.76) and 0.89 (0.81/0.81) at entry and at home hospitalization discharge, respectively; the AUROC (sensitivity/specificity) values for in-hospital admission were 0.71 (0.67/0.64) and 0.70 (0.71/0.61) at entry and at home hospitalization discharge, respectively. CONCLUSIONS:The results showed potential for feeding clinical decision support systems aimed at supporting health professionals for inclusion of candidates into the HH/ED program, and have the capacity to guide transitions toward community-based care at HH discharge.

SUBMITTER: Calvo M

PROVIDER: S-EPMC7578817 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.

Calvo Mireia M González Rubèn R Seijas Núria N Vela Emili E Hernández Carme C Batiste Guillem G Miralles Felip F Roca Josep J Cano Isaac I Jané Raimon R

Journal of medical Internet research 20201007 10

<h4>Background</h4>Home hospitalization is widely accepted as a cost-effective alternative to conventional hospitalization for selected patients. A recent analysis of the home hospitalization and early discharge (HH/ED) program at Hospital Clínic de Barcelona over a 10-year period demonstrated high levels of acceptance by patients and professionals, as well as health value-based generation at the provider and health-system levels. However, health risk assessment was identified as an unmet need w ...[more]

PMID: 33026357

Similar Datasets

Project description:Background/objectivesCare-partner support affects outcomes among assisted living (AL) residents. Yet, little is known about care-partner support and its effects on hospitalization during post-acute care transitions. This study examined the variation in care-partner support and its impact on hospitalizations among AL residents receiving Medicare home health (HH) services.DesignAnalysis of national data from the Outcome and Assessment Information Set, Medicare claims, Area Health Resources File, and the Social Deprivation Index File.SettingAL facilities and Medicare HH agencies in the United States.Participants741,926 Medicare HH admissions of AL residents in 2017.MeasurementsCare-partner support during the HH admission was measured based on the type and frequency of assistance from AL staff in seven domains (i.e., activities of daily living (ADL), instrumental ADLs, medication administration, treatment, medical equipment, home safety, and transportation). Care-partner support in each domain was measured as "assistance not needed" (reference group), "Care-partner currently provides assistance," "care-partner need additional training/support to provide assistance" (i.e., inadequate care-partner support), and "care-partner unavailable/unlikely to provide assistance" (i.e., unavailable care-partner support). Outcome was time-to-hospitalization during the HH admission.ResultsAmong the 741,926 Medicare HH admissions of AL residents, inadequate care-partner support was identified for all seven domains that ranged from 13.1% (for transportation) to 49.8% (for treatment), and care-partner support was unavailable from 0.9% (for transportation) to 11.0% (for treatment). In Cox proportional hazard models adjusted for patient covariates and geography, compared with "assistance not needed", having inadequate and unavailable care-partner support was related to increased risk of hospitalization by 8.9% (treatment (hazard ratio (HR) =1.089, P < .001)) to 41.3% (medication administration (HR =1.413, P < .001)).ConclusionFor AL residents receiving HH services, having less care-partner support was related to increased risk of hospitalization, particularly regarding medication administration, medical equipment, and transportation/advocacy.

Dataset Information

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.

Publications

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets