Developing and validating models for predicting nursing home admission using only RAI-HC instrument data

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.

COVID-19 related visiting ban in nursing homes as a source of concern for residents’ family members: a cross sectional study

Background

Visiting a close relative who resides in a nursing home is an opportunity for family members to extend their caring roles and find reassurance that the older person’s life is continuing as well as possible. At the same time, visits allow family members to observe the quality of formal care in the facility. In Finland, the COVID-19 pandemic led to the imposition of visiting bans in nursing homes in March 2020, thereby preventing customary interaction between residents and their family members. The aim of this study is to investigate family members’ experiences of the visiting ban and its effects on their concern over the wellbeing of close relatives living in nursing homes.

Methods

A cross-sectional study was conducted to explore family members’ self-reported concerns and the factors associated with those concerns. In the context of this unpredictable pandemic, this was considered an appropriate approach, as information at the very beginning of the visiting ban was sought, and causal relations were not investigated. The data consist of a quantitative survey (n = 366) conducted among family members in May–June 2020. Binary logistic regression analyses were performed to explore the association between the independent variables and reported concern.

Results

The results showed that increased concern was extremely common (79%). The factors associated with this notable increase were adequacy of contact and information, observations of changes in the wellbeing of the relative in question, and doubts over the appropriateness of the visiting restriction.

Conclusions

In light of the findings, care providers should improve their information provision to residents’ family members and find new ways of allowing visits to nursing homes in the future in all circumstances.

The impact of Covid-19-related distancing on the well-being of nursing home residents and their family members: a qualitative study

OBJECTIVES

The aim of this study is to examine the consequences of Covid-19-related isolation and social restrictions on the well-being of nursing home residents and their family members, and to analyze how distancing has affected the relationships of family members with residents and the nursing home staff.

DESIGN

The data consist of 41 thematic one-on-one interviews conducted during May-December 2020 with family members of nursing home residents. Convenience sampling was utilized by asking several nursing homes in different parts of Finland to relay a contact request from the researchers to the residents' family members. The main themes of the interviews were lockdown and visiting restrictions. Subthemes included the frequency of visits, other means of interaction, changes in the relationships of family members with their loved ones and with nursing home staff, and the feelings aroused by the situation. The interviews were audio recorded and transcribed verbatim, resulting in 794 pages of data.

METHOD

The qualitative study uses inductive content analysis. NVivo12 software facilitated the systematic coding of the data.

RESULTS

According to the family members, distancing aggravated the residents' pre-existing conditions: they reported a sudden progression in memory disorders and significant deterioration in physical abilities, for example. Both residents and family members experienced anxiety, grief, and severe stress, and family members expressed concern that residents might die due to a lack of social contact and activity. Family members were also frustrated about not being able to touch their relatives or participate in their care, and therefore sometimes thought that their visits were useless. New forms of interaction with family members, introduced by the nursing homes, were appreciated. However, some family members perceived the interactional protocols as unfair and complained about insufficient information.

CONCLUSIONS

The findings underline the need for nursing homes to implement a good interactional protocol. Overall, the results show that the measures taken to protect residents' health during the Covid-19 outbreak were short-sighted in terms of the social dimension of well-being. It is therefore important to continue developing safe and humane solutions for interaction when social restrictions are in place. Tweetable abstract: Covid-19-related distancing has caused anxiety, grief, and severe stress for nursing home residents and their family members.