Search

Background and Purpose: Patients' adherence to medication is a complex, multidimensional phenomenon. Dispensation data and electronic health records are used to approximate medication-taking through refill adherence. In-depth discussions on the adverse effects of data quality and computational differences are rare. The purpose of this article is to evaluate the impact of common pitfalls when computing medication adherence using electronic health records., Procedures: We point out common pitfalls associated with the data and operationalization of adherence measures. We provide operational definitions of refill adherence and conduct experiments to determine the effect of the pitfalls on adherence estimations. We performed statistical significance testing on the impact of common pitfalls using a baseline scenario as reference., Findings: Slight changes in definition can significantly skew refill adherence estimates. Pickup patterns cause significant disagreement between measures and the commonly used proportion of days covered. Common data related issues had a small but statistically significant (p < 0.05) impact on population-level and significant effect on individual cases., Conclusion: Data-related issues encountered in real-world administrative databases, which affect various operational definitions of refill adherence differently, can significantly skew refill adherence values, leading to false conclusions about adherence, particularly when estimating adherence for individuals., (Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.)

Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Objectives: The aim of this work was to train machine learning models to identify patients at end of life with clinically meaningful diagnostic accuracy, using 30-day mortality in patients discharged from the emergency department (ED) as a proxy., Design: Retrospective, population-based registry study., Setting: Swedish health services., Primary and Secondary Outcome Measures: All cause 30-day mortality., Methods: Electronic health records (EHRs) and administrative data were used to train six supervised machine learning models to predict all-cause mortality within 30 days in patients discharged from EDs in southern Sweden, Europe., Participants: The models were trained using 65 776 ED visits and validated on 55 164 visits from a separate ED to which the models were not exposed during training., Results: The outcome occurred in 136 visits (0.21%) in the development set and in 83 visits (0.15%) in the validation set. The model with highest discrimination attained ROC-AUC 0.95 (95% CI 0.93 to 0.96), with sensitivity 0.87 (95% CI 0.80 to 0.93) and specificity 0.86 (0.86 to 0.86) on the validation set., Conclusions: Multiple models displayed excellent discrimination on the validation set and outperformed available indexes for short-term mortality prediction interms of ROC-AUC (by indirect comparison). The practical utility of the models increases as the data they were trained on did not require costly de novo collection but were real-world data generated as a by-product of routine care delivery., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2019. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Data-driven medical care delivery must always respect patient privacy—a requirement that is not easily met. This issue has impeded improvements to healthcare software and has delayed the long-predicted prevalence of artificial intelligence in healthcare. Until now, it has been very difficult to share data between healthcare organizations, resulting in poor statistical models due to unrepresentative patient cohorts. Synthetic data, i.e., artificial but realistic electronic health records, could overcome the drought that is troubling the healthcare sector. Deep neural network architectures, in particular, have shown an incredible ability to learn from complex data sets and generate large amounts of unseen data points with the same statistical properties as the training data. Here, we present a generative neural network model that can create synthetic health records with realistic timelines. These clinical trajectories are generated on a per-patient basis and are represented as linear-sequence graphs of clinical events over time. We use a variational graph autoencoder (VGAE) to generate synthetic samples from real-world electronic health records. Our approach generates health records not seen in the training data. We show that these artificial patient trajectories are realistic and preserve patient privacy and can therefore support the safe sharing of data across organizations. [ABSTRACT FROM AUTHOR]

As Deep Neural Networks (DNN) make their way into safety-critical decision processes, it becomes imperative to have robust and reliable uncertainty estimates for their predictions for both in-distribution and out-of-distribution (OOD) examples. This is particularly important in real-life high-risk settings such as healthcare, where OOD examples (e.g., patients with previously unseen or rare labels, i.e., diagnoses) are frequent, and an incorrect clinical decision might put human life in danger, in addition to having severe ethical and financial costs. While evidential uncertainty estimates for deep learning have been studied for multi-class problems, research in multi-label settings remains untapped. In this paper, we propose a DEep Evidential Doctor (DEED), which is a novel deterministic approach to estimate multi-label targets along with uncertainty. We achieve this by placing evidential priors over the original likelihood functions and directly estimating the parameters of the evidential distribution using a novel loss function. Additionally, we build a redundancy layer (particularly for high uncertainty and OOD examples) to minimize the risk associated with erroneous decisions based on dubious predictions. We achieve this by learning the mapping between the evidential space and a continuous semantic label embedding space via a recurrent decoder. Thereby inferring, even in the case of OOD examples, reasonably close predictions to avoid catastrophic consequences. We demonstrate the effectiveness of DEED on a digit classification task based on a modified multi-label MNIST dataset, and further evaluate it on a diagnosis prediction task from a real-life electronic health record dataset. We highlight that in terms of prediction scores, our approach is on par with the existing state-of-the-art having a clear advantage of generating reliable, memory and time-efficient uncertainty estimates with minimal changes to any multi-label DNN classifier. [ABSTRACT FROM AUTHOR]