Bathel

Product Information

In the presented work, two cases are considered: when previous functional status of a patient is unknown and only diagnoses and demographics can be used as predictors, and when a patient was previously evaluated and results of that evaluation (nine previous ADL attributes) can be added to the list of predictors. Thus, two sets of models were constructed: Evaluation models, M E d τ, in which previous functional status assessment is unknown, and Re-Evaluation models, M RE d τ, in which previous functional status is known. Here d is an ADL (bathing, grooming, etc.), and \(\tau \in \left\{ {0,90,180,365} \right\}\) is the prediction horizon (given as the number of days), i.e., how far ahead in time the value is predicted. As names suggest, M E d models are used in situations in which a new patient is being evaluated in terms of ADLs, and M RE d models are used when an evaluation of the previously assessed patient needs to be refreshed as new information becomes available. 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 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 Many studies attempted to predict ADLs in a specific population, i.e., related to a disease or injury [ 13, 14, 15], while others are more general. In one study, machine learning (ML) methods were linked to biomedical ontologies to predict functional status [ 16], achieving predictive accuracy of 0.6. In another work, researchers described a logistic regression-based method to predict mortality and disability post-injury for the elderly [ 17] with reported R 2 of 0.86. Tarekegn et al. developed a set of models to predict disability as a metric for frailty conditions resulting in models with F-1 scores ranging between 0.74 to 0.76 [ 18]. Similarly, Gobbens and van Assen examined six standard frailty indicators (gait speed, physical activity, hand grip, body mass index, and fatigue and balance) for assessing ADLs, of which only gait speed was predictive of ADL disabilities [ 19]; however, no actual predictive accuracy was reported. More recently, Jonkman et al., constructed logistic regression-based models from four datasets to predict decline in five ADLs [ 20], with the average AUC of 0.72. It is clear that the above studies reported model performances below ones reported here. However, it should be mentioned that these works were performed in different settings thus no direct comparison is meaningful. A systematic review of published works related to assessing ADLs identified several commonly used predictors, including age, cognitive functioning, depression, and hospital length of stay [ 21]. In the data-driven approach presented here, some of the predictors are the same as those previously reported in the literature.

Prediction of functional status and disability is challenging. Researchers in many studies have attempted to automatically assess and predict functional status, including ADLs. Overall, there are three main approaches to assess and predict ADLs by (1) using specific clinical data, (2) using sensor data collected by wearable devices or smarthome environments, and (3) using patient records extracted from EHR or claims data in making assessment and predictions. Despite wide selection of published works, the research presented here is unique in the latter category as its attempts to assess and predict ADLs purely based on diagnoses and demographics present in the patient records. It should be noted that there are a number of published papers that discuss ADLs as predictors of other outcomes such as disease progression and mortality [ 11, 12], while the focus of this study is on predicting ADLs. Not surprisingly, several research groups focused on assessing ADLs from sensor data. Assessing ADLs selected by wearable sensors is a reasonable approach as it allows for continuous monitoring rather than a snapshot of activities evaluated by a healthcare provider [ 21, 22, 23, 24, 25, 26]. In some studies, ambient intelligence and smarthome sensors were used to assess the ability to perform ADLs. These works rely on the use of specific sensors installed in smarthome environment that monitor movement [ 27, 28], as well as use of specific home devices [ 29, 30, 31]. Further, beyond the direct application to the elderly population, activity recognition is a well-established field with several review papers available to summarize the works [ 32, 33, 34]. 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.

Unique memorial services

In the original data, diagnoses have associated dates thus days are used as unit of time. This allows counting the difference in time as the number of days. In other words \(ccs_{i} Previously, a set of models capable of predicting trajectories of ADL improvement or decline post-hospitalization [ 8], as well as sequences of functional decline were constructed [ 9]. The former focused on predicting if patients are likely to follow one of seven pre-defined trajectories of improvement/decline. Predictions were anchored to the time of hospital discharge and diagnoses were extracted only from inpatient records of the corresponding hospitalization. The method and tool discussed in this paper, called the Computational Barthel Index Tool (CBIT), significantly extends the previous work and is designed to allow for assessment of functional status at any arbitrary moment. The tool that allows for prediction of each ADL up to one year ahead, is based on a larger cohort of patients, and uses both inpatient and outpatient diagnoses. The name is inspired by the original Barthel Index (Score), which is a standardized tool used to evaluate activities of daily living [ 10]. Computational machine learning methods are used to construct the index. The presented research also extends previous work [ 8] by incorporating temporal information about when events happened in the patient’s medical history, which was not applicable to hospitalization-only data. Many diagnoses present in medical records correlate with the patient’s functional ability, with some of these correlations being temporary and others being permanent. For example, some surgical patients have urinary incontinence for a short period after the surgery, while amputation affects the ability to walk permanently. Thus, it is assumed that the codes present in data are time-dependent. It was shown that adding temporal information can improve the accuracy of the constructed CBIT models, as discussed later in the paper. 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