Dataset Information

Home care aides' observations and machine learning algorithms for the prediction of visits to emergency departments by older community-dwelling individuals receiving home care assistance: A proof of concept study.

ABSTRACT:

Background

Older individuals receiving home assistance are at high risk for emergency visits and unplanned hospitalization. Anticipating their health difficulties could prevent these events. This study investigated the effectiveness of an at-home monitoring method using social workers' observations to predict risk for 7- and 14-day emergency department (ED) visits.

Methods

This was a prospective cohort study of persons ?75 years, living at home and receiving assistance from home care aides (HCA) at 6 French facilities. After each home visit, HCAs reported on participants' functional status using a smartphone application that recorded 27 functional items about each participant (e.g., ability to stand, move, eat, mood, loneliness). We recorded ED visits. Finally, we used machine learning techniques (i.e., leveraging random forest predictors) to develop a 7- and 14-day predictive algorithm for the risk of ED visit.

Results

The study included 301 participants, and the HCA made 9,987 observations. Over the mean 10-month follow-up, 97 participants (32%) had at least one ED visit. Modeling techniques identified 9 contributory factors from the longitudinal records of the HCA and developed a predictive algorithm for the risk of ED visit. The predictive performance (i.e., the area under the ROC curve) was 0.70 at 7 days and 0.67 at 14 days.

Interpretation

For frail elders receiving in-home care, information on functional status collected by HCA helps predict the risk of ED visits 7 to 14 days in advance. A survey system for real-time identification of risks could be developed using this exploratory work.

SUBMITTER: Veyron JH

PROVIDER: S-EPMC6692042 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Home care aides' observations and machine learning algorithms for the prediction of visits to emergency departments by older community-dwelling individuals receiving home care assistance: A proof of concept study.

Veyron Jacques-Henri JH Friocourt Patrick P Jeanjean Olivier O Luquel Laurence L Bonifas Nicolas N Denis Fabrice F Belmin Joël J

PloS one 20190813 8

<h4>Background</h4>Older individuals receiving home assistance are at high risk for emergency visits and unplanned hospitalization. Anticipating their health difficulties could prevent these events. This study investigated the effectiveness of an at-home monitoring method using social workers' observations to predict risk for 7- and 14-day emergency department (ED) visits.<h4>Methods</h4>This was a prospective cohort study of persons ≥75 years, living at home and receiving assistance from home c ...[more]

PMID: 31408458

Similar Datasets

Project description:BackgroundHome care (HC) services are crucial to the health and social wellbeing of older adults, people with disabilities, and the chronically ill. Although the HC sector is growing rapidly in the USA, there is high job turnover among the HC aide workforce. HC provides an important alternative to facility-based care, yet it has often been overlooked within the larger health care system: most recently, in COVID-19 pandemic planning. The objective of the study was to characterize qualitatively the impact of the COVID-19 pandemic on three key HC stakeholders: clients, aides, and agency managers.MethodsThe study included 37 phone interviews conducted during April - November 2020: HC clients (n = 9), aides (n = 16), and agency managers (n = 12). All interviews were audio recorded and transcribed verbatim. Qualitative analysis of the transcripts followed the grounded theory approach. The interview transcriptions were coded line-by-line into hierarchical themes with NVivo 12 software which allowed weighting of themes based on the number of interviews where they were coded.ResultsFear of infection and transmission among HC clients and aides were strong themes. Infection prevention and control became the top priority guiding day-to-day business operations at agencies; sourcing adequate personal protective equipment for staff was the most urgent task. HC aides expressed concerns for their clients who showed signs of depression, due to increased isolation during the pandemic. The disappearance of comforting touch - resulting from physical distancing practices - altered the expression of compassion in the HC aide-client care relationship.ConclusionsThe findings suggest that the pandemic has further increased psychosocial job demands of HC aides. Increased isolation of clients may be contributing to a wider public health problem of elder loneliness and depression. To support the HC stakeholders during the on-going COVID-19 pandemic, for future pandemic planning or other health emergencies, it is important to improve HC aide job retention. This action could also ease the serious care services shortage among the growing population of older adults.

Dataset Information

Home care aides' observations and machine learning algorithms for the prediction of visits to emergency departments by older community-dwelling individuals receiving home care assistance: A proof of concept study.

Background

Methods

Results

Interpretation

Publications

Home care aides' observations and machine learning algorithms for the prediction of visits to emergency departments by older community-dwelling individuals receiving home care assistance: A proof of concept study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure