Online Decision Support Tool that Explains Temporal Prediction of Activities of Daily Living (ADL)

This paper presents an online decision support tool that can be used to assess and predict functional abilities in terms of nine Activities of Daily Living (ADLs) up to one year ahead. The tool is based on previously developed Computational Barthel Index (CBIT) and has been rebuilt using Gradient Boost (GB) models with average Area under ROC (AUC) of 0.79 (0.77-0.80), accuracy of 0.74 (0.70-0.79), recall of 0.78 (0.58-0.93), and precision of 0.75 (0.67-0.82) when evaluating ADLs for new patients. When re-evaluating patients, the models achieved AUC 0.95 (0.94-0.96), accuracy of 0.91 (0.90-0.92), recall of 0.91 (0.86-0.95), and precision of 0.92 (0.88-0.94). The decision support tool has been equipped with a prediction explanation module that calculates and visualizes influence of patient characteristics on the predicted values. The explanation approach focuses on patient characteristics present in the data, rather than all attributes used to construct models. The tool has been implemented in Python programming language using Flask Web framework and is accessible through a website or an Application Programming Interface (API).

[1]  D. Bates,et al.  Clinical Decision Support Systems , 1999, Health Informatics.

[2]  Ciarán M Lee,et al.  Improving the accuracy of medical diagnosis with causal machine learning , 2020, Nature Communications.

[3]  E. McCarthy,et al.  Dying with Cancer: Patients' Function, Symptoms, and Care Preferences as Death Approaches , 2000, Journal of the American Geriatrics Society.

[4]  Christopher J. Dente,et al.  Precision diagnosis: a view of the clinical decision support systems (CDSS) landscape through the lens of critical care , 2017, Journal of Clinical Monitoring and Computing.

[5]  A. Holmes,et al.  Machine learning for clinical decision support in infectious diseases: A narrative review of current applications. , 2020, Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases.

[6]  F. Mahoney,et al.  Functional evaluation ; the Barthel index. A simple index of the independence useful in scoring improvement in the rehabilitation of the chronically ill. , 1965 .

[7]  R. Gobbens,et al.  The Prediction of ADL and IADL Disability Using Six Physical Indicators of Frailty: A Longitudinal Study in the Netherlands , 2014, Current gerontology and geriatrics research.

[8]  Elizabeth H Bradley,et al.  Understanding the treatment preferences of seriously ill patients. , 2002, The New England journal of medicine.

[9]  Farrokh Alemi,et al.  Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients , 2021, BMC Medical Informatics and Decision Making.

[10]  Ryszard S. Michalski,et al.  A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  Farrokh Alemi,et al.  Predicting Functional Decline and Recovery for Residents in Veterans Affairs Nursing Homes. , 2016, The Gerontologist.

[13]  James Zou,et al.  DeepTag: inferring diagnoses from veterinary clinical notes , 2018, npj Digital Medicine.

[14]  C. Terwee,et al.  Measurement Properties of the Barthel Index in Geriatric Rehabilitation. , 2019, Journal of the American Medical Directors Association.

[15]  Bernt Schiele,et al.  ADL recognition based on the combination of RFID and accelerometer sensing , 2008, 2008 Second International Conference on Pervasive Computing Technologies for Healthcare.

[16]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[17]  Xia Hu,et al.  Techniques for interpretable machine learning , 2018, Commun. ACM.

[18]  Judea Pearl,et al.  The seven tools of causal inference, with reflections on machine learning , 2019, Commun. ACM.

[19]  Hua Min,et al.  Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology , 2017, Journal of Biomedical Semantics.

[20]  David T. Marc,et al.  Reasons For Physicians Not Adopting Clinical Decision Support Systems: Critical Analysis , 2018, JMIR medical informatics.

[21]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[22]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[23]  M. Brookhart,et al.  Using claims data to predict dependency in activities of daily living as a proxy for frailty , 2015, Pharmacoepidemiology and drug safety.