Dataset Information

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients.

ABSTRACT:

Background

Assessment of functional ability, including activities of daily living (ADLs), is a manual process completed by skilled health professionals. In the presented research, an automated decision support tool, the Computational Barthel Index Tool (CBIT), was constructed that can automatically assess and predict probabilities of current and future ADLs based on patients' medical history.

Methods

The data used to construct the tool include the demographic information, inpatient and outpatient diagnosis codes, and reported disabilities of 181,213 residents of the Department of Veterans Affairs' (VA) Community Living Centers. Supervised machine learning methods were applied to construct the CBIT. Temporal information about times from the first and the most recent occurrence of diagnoses was encoded. Ten-fold cross-validation was used to tune hyperparameters, and independent test sets were used to evaluate models using AUC, accuracy, recall and precision. Random forest achieved the best model quality. Models were calibrated using isotonic regression.

Results

The unabridged version of CBIT uses 578 patient characteristics and achieved average AUC of 0.94 (0.93-0.95), accuracy of 0.90 (0.89-0.91), precision of 0.91 (0.89-0.92), and recall of 0.90 (0.84-0.95) when re-evaluating patients. CBIT is also capable of predicting ADLs up to one year ahead, with accuracy decreasing over time, giving average AUC of 0.77 (0.73-0.79), accuracy of 0.73 (0.69-0.80), precision of 0.74 (0.66-0.81), and recall of 0.69 (0.34-0.96). A simplified version of CBIT with 50 top patient characteristics reached performance that does not significantly differ from full CBIT.

Conclusion

Discharge planners, disability application reviewers and clinicians evaluating comparative effectiveness of treatments can use CBIT to assess and predict information on functional status of patients.

SUBMITTER: Wojtusiak J

PROVIDER: S-EPMC7796534 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients.

Wojtusiak Janusz J Asadzadehzanjani Negin N Levy Cari C Alemi Farrokh F Williams Allison E AE

BMC medical informatics and decision making 20210109 1

<h4>Background</h4>Assessment of functional ability, including activities of daily living (ADLs), is a manual process completed by skilled health professionals. In the presented research, an automated decision support tool, the Computational Barthel Index Tool (CBIT), was constructed that can automatically assess and predict probabilities of current and future ADLs based on patients' medical history.<h4>Methods</h4>The data used to construct the tool include the demographic information, inpatien ...[more]

PMID: 33422059

Similar Datasets

Project description:Objectives:To evaluate application of the Barthel Index (BI) in assessing basic activities of daily living (ADL) of patients with dementia using Rasch analysis. Design:A multi-country cross-sectional study. Setting and Participants:Nineteen long-term care facilities located in China, Japan, South Korea, and Thailand. A total of 644 patients with dementia were included. Methods:Unidimensionality, global and item fit, local dependence, person-item targeting, threshold disordering, and differential item functioning (DIF) were examined. Negative correlations between scores for DIF items and Neuropsychiatric Inventory Nursing Home version (NPI-NH) were evaluated. Results:Item reliability (1.0) and person reliability (.88) were acceptable. The Rasch dimension explained 72.9% of the variance (Eigenvalue = 27), while the first contrast explained 6.6% (Eigenvalue = 2.4). The "mobility" was misfitting to the Rasch model (infit mean square = 1.86). The overall difficulty of the BI exceeded patients' ability (person location = -2.27 logits). The "stairs climbing" and "mobility" showed narrow category thresholds (< 1.4 logits). The location of "controlling bladder" and "toilet use" overlapped. Removing "stairs climbing", collapsing categories with narrow threshold widths in "mobility", and combining "controlling bowel" and "controlling bladder" into one item, improved unidimensionality, and item fit of the scale. Only three items ("grooming", "dressing", and "toilet use") were free from DIF across countries. The scores for "feeding" were negatively related to scores for "disinhibition" (r = -0.46, P < 0.01), and scores for "controlling bowel" were negatively related to scores for "disinhibition" (r = -0.44, P < 0.01), "agitation" (r = -0.32, P < 0.05), and "aggression" (r = -0.27, P < 0.01) in Japanese samples. Conclusions and Implications:The performance of the BI for assessing patients with dementia might be compromised by misfit items, person-item mistargeting, measurement gaps, redundant items, narrow threshold width, and item bias. Mobility ability might not be helpful for determining capability of basic ADL in the patients. Comparisons of BI scores between countries should be undertaken with caution due to item bias. Neuropsychiatric symptoms might interact with basic ADL abilities of the patients. We will not suggest using the instrument in patients with dementia, without future refining to improve its performance.

Project description:BackgroundDrug Burden Index (DBI), a measure of exposure to medications with anticholinergic and sedative activity, has been associated with poorer physical function in older adults in the general population. While extensive study has been conducted on associations between DBI and physical function in older adults in the general population, little is known about associations in older adults with intellectual disabilities (ID). This is the first study which aims to examine the association between DBI score and its two sub-scores, anticholinergic and sedative burden, with two objective measures of physical performance, grip strength and timed up and go, and a measure of dependency, Barthel Index activities of daily living, in older adults with ID.MethodsData from Wave 2 (2013/2014) of the Intellectual Disability Supplement to the Irish Longitudinal Study on Ageing (IDS-TILDA) was analysed. Analysis of Covariance (ANCOVA) was used to detect associations and produce adjusted means for the physical function and dependency measures with respect to categorical DBI scores and the anticholinergic and sedative sub-scores (DBA and DBS).ResultsAfter adjusting for confounders (age, level of ID, history of falls, comorbidities and number of non-DBI medications, Down syndrome (grip strength only) and gender (timed up and go and Barthel Index)), neither grip strength nor timed up and go were significantly associated with DBI, DBA or DBS score > 0 (p > 0.05). Higher dependency in Barthel Index was associated with DBS exposure (p < 0.001).ConclusionsDBI, DBA or DBS scores were not significantly associated with grip strength or timed up and go. This could be as a result of established limitations in physical function in this cohort, long-term exposure to these types of medications or lifelong sedentary lifestyles. Higher dependency in Barthel Index activities of daily living was associated with sedative drug burden, which is an area which can be examined further for review.

Project description:BACKGROUND:There has been an increasing interest in understanding the usefulness of wrist-based accelerometer data for physical activity (PA) assessment due to the ease of use and higher user compliance than other body placements. PA assessment studies have relied on machine learning methods which take accelerometer data in forms of variables, or feature vectors. METHODS:In this work, we introduce automated shape feature derivation methods to transform epochs of accelerometer data into feature vectors. As the first step, recurring patterns in the collected data are identified and placed in a codebook. Similarities between epochs of accelerometer data and codebook's patterns are the basis of feature calculations. In this paper, we demonstrate supervised and unsupervised approaches to learn codebooks. We evaluated these methods and compared them with the standard statistical measures for PA assessment. The experiments were performed on 146 participants who wore an ActiGraph GT3X+ accelerometer on the right wrist and performed 33 activities of daily living. RESULTS:Our evaluations show that the shape feature derivation methods were able to perform comparably with the standard wrist model (F1-score: 0.89) for identifying sedentary PAs (F1-scores of 0.86 and 0.85 for supervised and unsupervised methods, respectively). This was also observed for identifying locomotion activities (F1-scores: 0.87, 0.83, and 0.81 for the standard wrist, supervised, unsupervised models, respectively). All the wrist models were able to estimate energy expenditure required for PAs with low error (rMSE: 0.90, 0.93, and 0.90 for the standard wrist, supervised, and unsupervised models, respectively). CONCLUSION:The automated shape feature derivation methods offer insights into the performed activities by providing a summary of repeating patterns in the accelerometer data. Furthermore, they could be used as efficient alternatives (or additions) for manually engineered features, especially important for cases where the latter fail to provide sufficient information to machine learning methods for PA assessment.

Project description:BackgroundInterdependencies of health, fitness, cognition, and emotion can promote or inhibit mobility. This study aimed to analyse pathways and interactions between individual subjective and objective physical performance, cognition, and emotions with activities of daily living (ADLs) as mobility indicators in multimorbid nursing home residents.MethodsThe study included n = 448 (77.1% females, age = 84.1 ± 7.8 years) nursing home residents. To describe the participant's demographics, frailty, number of falls, and participating institutions' socioeconomic status (SES) were assessed. ADLs were measured with the Barthel Index (BI; dependent variable). Independent variables included objective physical performance, subjective physical performance, cognition, and emotions. A structural equation model (SEM) with maximum likelihood estimation was conducted with AMOS. Direct and indirect effects were estimated using standardized coefficients (significance level of 0.05).ResultsIndices showed (Chi2(148) = 217, PCMIN/DF = 1.47; p < .001; Comparative Fit Index = .940; Tucker Lewes Index = .902, RMSEA = .033) that the model fitted the data adequately. While there was no direct association between emotions, subjective physical performance, and ADLs, objective physical performance and cognition predicted higher ADLs (p < .01). Emotions had a strong relationship with subjective physical performance, and cognition had a moderate relationship with objective physical performance.Discussion and conclusionObjective performance and cognition predicted higher functional status, as expressed by higher BI scores. ADLs, such as mobility, dressing, or handling tasks, require motor and cognitive performance. Subjective performance is an important predictor of ADLs and is only partly explained by objective performance, but to a large extent also by emotions. Therefore, future interventions for nursing home residents should take a holistic approach that focuses not only on promoting objective physical and cognitive performance but also on emotions and perceived physical performance.Trial registrationTrial registration number: DRKS00014957.

Dataset Information

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients.

Background

Methods

Results

Conclusion

Publications

Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets