scholarly journals Computational Barthel Index: An Automated Tool for Assessing and Predicting Activities of Daily Living Among Nursing Home Patients

2020 ◽  
Author(s):  
Janusz Wojtusiak ◽  
Negin Asadzadehzanjani ◽  
Cari Levy ◽  
Farrokh Alemi ◽  
Allison E. Williams
Keyword(s):  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Supervised Machine Learning ◽  
Department Of Veterans Affairs ◽  
Model Quality ◽  
Support Tool ◽  
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.

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

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Janusz Wojtusiak ◽  
Negin Asadzadehzanjani ◽  
Cari Levy ◽  
Farrokh Alemi ◽  
Allison E. Williams
Keyword(s):  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Supervised Machine Learning ◽  
Department Of Veterans Affairs ◽  
Model Quality ◽  
Support Tool ◽  
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.

scholarly journals Computational Barthel Index: An Automated Tool for Assessing and Predicting Activities of Daily Living Among Nursing Home Patients

2020 ◽  
Author(s):  
Janusz Wojtusiak ◽  
Negin Asadzadehzanjani ◽  
Cari Levy ◽  
Farrokh Alemi ◽  
Allison E. Williams
Keyword(s):  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Supervised Machine Learning ◽  
Department Of Veterans Affairs ◽  
Model Quality ◽  
Support Tool ◽  
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.

scholarly journals Computational Barthel Index: An Automated Tool for Assessing and Predicting Activities of Daily Living Among Nursing Home Patients

2020 ◽  
Author(s):  
Janusz Wojtusiak ◽  
Negin Asadzadehzanjani ◽  
Cari Levy ◽  
Farrokh Alemi ◽  
Allison E. Williams
Keyword(s):  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Supervised Machine Learning ◽  
Department Of Veterans Affairs ◽  
Model Quality ◽  
Support Tool ◽  
Nursing Home Patients

Abstract Background: Assessment of functional ability, including Activities of Daily Living (ADLs), is a manual process completed by skilled health professionals. We investigated the possibility of constructing an automated decision support tool, the Computational Barthel Index Tool (CBIT), that automatically assesses and predicts probabilities of current and future ADLs based on patients’ medical history. Methods: The data used to construct the tool include the demographic information, 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 isonomic 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, clinicians evaluating comparative effectiveness of treatments can use CBIT to assess and predict information on functional status of patients.

scholarly journals Use of the Barthel Index to Assess Activities of Daily Living before and after SARS-COVID 19 Infection of Institutionalized Nursing Home Patients

2021 ◽  
Vol 18 (14) ◽  
pp. 7258
Author(s):  
Bibiana Trevissón-Redondo ◽  
Daniel López-López ◽  
Eduardo Pérez-Boal ◽  
Pilar Marqués-Sánchez ◽  
Cristina Liébana-Presa ◽  
...  
Keyword(s):  
Nursing Homes ◽  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Elderly Population ◽  
The Elderly ◽  
Elderly Subjects ◽  
Nursing Home Patients ◽  
Before And After

The objective of the present study was to evaluate the activities of daily living (ADLs) using the Barthel Index before and after infection with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and also to determine whether or not the results varied according to gender. The ADLs of 68 cohabiting geriatric patients, 34 men and 34 women, in two nursing homes were measured before and after SARS-CoV-2 (Coronavirus 2019 (COVID-19)) infection. COVID-19 infection was found to affect the performance of ADLs in institutionalized elderly in nursing homes, especially in the more elderly subjects, regardless of sex. The COVID-19 pandemic, in addition to having claimed many victims, especially in the elderly population, has led to a reduction in the abilities of these people to perform their ADLs and caused considerable worsening of their quality of life even after recovering from the disease.

scholarly journals Use of the Barthel Index to Assess Activities of Daily Living before and after SARS-COVID 19 Infection of Institutionalized Nursing Home Patients

2021 ◽  
Author(s):  
Bibiana Trevissón-Redondo ◽  
Daniel Lopez Lopez ◽  
Eduardo Perez-Boal ◽  
Pilar Marques-Sanchez ◽  
Cristina Liébana-Presa ◽  
...  
Keyword(s):  
Nursing Homes ◽  
Activities Of Daily Living ◽  
Barthel Index ◽  
Daily Living ◽  
Daily Life ◽  
The Elderly ◽  
Daily Life Activities ◽  
Nursing Home Patients ◽  
Before And After

Objective: The objective of the present study was to evaluate the activities of daily living using the Barthel Index, before and after the infection by SARS-COV-2 and to see if the results vary according to sex. Methods: The activities of daily living of 68 cohabiting geriatric patients, 34 men and 34 women, in 2 nursing homes were measured before and after SARS-COV-2 infection using the Barthel index. Results: The Covid 19 infection affects the performance of daily life activities in institutionalized elderly in nursing homes, and it does so especially the older the subject, regardless of sex. Conclusions: The Covid 19 pandemic, in addition to having claimed some victims, especially in the elderly population, has reduced the ability of these people to carry out their activities of daily life, considerably worsening their quality of life despite have been able to overcome the disease.

scholarly journals Clinical prediction of thrombectomy eligibility: A systematic review and 4-item decision tree

2018 ◽  
Vol 14 (5) ◽  
pp. 530-539 ◽  
Author(s):  
Gaia T Koster ◽  
T Truc My Nguyen ◽  
Erik W van Zwet ◽  
Bjarty L Garcia ◽  
Hannah R Rowling ◽  
...  
Keyword(s):  
Decision Tree ◽  
Prediction Model ◽  
External Validation ◽  
Facial Asymmetry ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Group Lasso ◽  
Lasso Regression ◽  
Vessel Occlusion ◽  
Support Tool

Background A clinical large anterior vessel occlusion (LAVO)-prediction scale could reduce treatment delays by allocating intra-arterial thrombectomy (IAT)-eligible patients directly to a comprehensive stroke center. Aim To subtract, validate and compare existing LAVO-prediction scales, and develop a straightforward decision support tool to assess IAT-eligibility. Methods We performed a systematic literature search to identify LAVO-prediction scales. Performance was compared in a prospective, multicenter validation cohort of the Dutch acute Stroke study (DUST) by calculating area under the receiver operating curves (AUROC). With group lasso regression analysis, we constructed a prediction model, incorporating patient characteristics next to National Institutes of Health Stroke Scale (NIHSS) items. Finally, we developed a decision tree algorithm based on dichotomized NIHSS items. Results We identified seven LAVO-prediction scales. From DUST, 1316 patients (35.8% LAVO-rate) from 14 centers were available for validation. FAST-ED and RACE had the highest AUROC (both >0.81, p < 0.01 for comparison with other scales). Group lasso analysis revealed a LAVO-prediction model containing seven NIHSS items (AUROC 0.84). With the GACE (Gaze, facial Asymmetry, level of Consciousness, Extinction/inattention) decision tree, LAVO is predicted (AUROC 0.76) for 61% of patients with assessment of only two dichotomized NIHSS items, and for all patients with four items. Conclusion External validation of seven LAVO-prediction scales showed AUROCs between 0.75 and 0.83. Most scales, however, appear too complex for Emergency Medical Services use with prehospital validation generally lacking. GACE is the first LAVO-prediction scale using a simple decision tree as such increasing feasibility, while maintaining high accuracy. Prehospital prospective validation is planned.

scholarly journals Associations among occupational roles, independence, assistive technology, and purchasing power of individuals with physical disabilities

2013 ◽  
Vol 21 (2) ◽  
pp. 484-491 ◽  
Author(s):  
Daniel Marinho Cezar da Cruz ◽  
Maria Luisa Guillaumon Emmel
Keyword(s):  
Activities Of Daily Living ◽  
Assistive Technology ◽  
Functional Status ◽  
Barthel Index ◽  
Daily Living ◽  
Physical Disabilities ◽  
Lower Number ◽  
Purchasing Power ◽  
Classification Criterion ◽  
Occupational Roles

OBJECTIVE: to verify whether there are associations among occupational roles, independence to perform Activities of Daily Living, purchasing power, and assistive technology for individuals with physical disabilities. METHOD: 91 individuals with physical disabilities participated in the study. The instruments used were: Role Checklist, Brazilian Economic Classification Criterion, Barthel Index, and a Questionnaire to characterize the subjects. RESULTS: an association with a greater number of roles was found among more independent individuals using a lower number of technological devices. Higher purchasing power was associated with a lower functional status of dependence. CONCLUSION: even though technology was not directly associated with independence, the latter was associated with a greater number of occupational roles, which requires reflection upon independence issues when considering the participation in occupational roles. These findings support interdisciplinary actions designed to promote occupational roles in individuals with physical disabilities.

Activities of daily living at hospital admission and estimated survival time of older patients

2020 ◽  
Author(s):  
Jesper Ryg ◽  
Henriette Engberg ◽  
Pavithra Laxsen Anru ◽  
Solvejg Gram Henneberg Pedersen ◽  
Martin Gronbech Jorgensen ◽  
...  
Keyword(s):  
Hospital Admission ◽  
Activities Of Daily Living ◽  
Survival Time ◽  
Barthel Index ◽  
Daily Living ◽  
Older Patients ◽  
Cox Regression ◽  
Multivariable Analysis ◽  
Population Based ◽  
Kaplan Meier

Abstract Background Predicting expected survival time in acutely hospitalised older patients is a clinical challenge. Objective To examine if activities of daily living (ADL) assessed by Barthel-Index-100 (Barthel-Index) at hospital admission adds useful information to clinicians on expected survival time in older patients. Methods A nationwide population-based cohort study was used. All patients aged ≥65 years in the National Danish Geriatric Database from 2005 to 2014 were followed up until death, emigration or study termination (31 December 2015). Individual data were linked to national health registers. Barthel-Index was categorised into five-point subcategories with a separate category of Barthel-Index = 0. Kaplan–Meier analysis was used to assess crude survival proportions (95% CI) and Cox regression to examine association of Barthel-Index and mortality adjusting for age, Charlson comorbidity index, medication use, BMI, marital status, prior hospitalisations and admission year. Results In total, 74,589 patients (63% women) aged (mean (SD)) 82.5(7.5) years with Barthel-Index (median (IQR)) 54(29-77) were included. In patients with Barthel-Index = 100-96 crude survival was 0.96(0.95-0.97) after 90-days, 0.88(0.87-0.89) after 1-year, and 0.79(0.78-0.80) after 2-years. Corresponding survival in patients with Barthel-Index = 0 was 0.49(0.47-0.51), 0.35(0.34-0.37) and 0.26(0.24-0.27). Decreasing Barthel-Index was associated with increasing mortality in the multivariable analysis. In women with Barthel-Index = 0, the mortality risk (HR (95% CI)) was 14.74(11.33-19.18) after 90-days, 8.40(7.13-9.90) after 1-year and 6.22(5.47-7.07) after 2-years using Barthel-Index = 100-96 as reference. In men, the corresponding risks were 11.36(8.81-14.66), 6.22(5.29-7.31) and 5.22(4.56-5.98). Conclusions ADL measured by Barthel-Index provides useful, easily accessible and independent information to clinicians on expected survival time in patients admitted to a geriatric department.

Sign in / Sign up

Export Citation Format

Share Document