Sequential autoencoders for feature engineering and pretraining in major depressive disorder risk prediction.

Objectives: We evaluated autoencoders as a feature engineering and pretraining technique to improve major depressive disorder (MDD) prognostic risk prediction. Autoencoders can represent temporal feature relationships not identified by aggregate features. The predictive performance of autoencoders of multiple sequential structures was evaluated as feature engineering and pretraining strategies on an array of prediction tasks and compared to a restricted Boltzmann machine (RBM) and random forests as a benchmark. Materials and Methods: We study MDD patients from Vanderbilt University Medical Center. Autoencoder models with Attention and long-short-term memory (LSTM) layers were trained to create latent representations of the input data. Predictive performance was evaluated temporally by fitting random forest models to predict future outcomes with engineered features as input and using autoencoder weights to initialize neural network layers. We evaluated area under the precision-recall curve (AUPRC) trends and variation over the study population's treatment course. Results: The pretrained LSTM model improved predictive performance over pretrained Attention models and benchmarks in 3 of 4 outcomes including self-harm/suicide attempt (AUPRCs, LSTM pretrained = 0.012, Attention pretrained = 0.010, RBM = 0.009, random forest = 0.005). The use of autoencoders for feature engineering had varied results, with benchmarks outperforming LSTM and Attention encodings on the self-harm/suicide attempt outcome (AUPRCs, LSTM encodings = 0.003, Attention encodings = 0.004, RBM = 0.009, random forest = 0.005). Discussion: Improvement in prediction resulting from pretraining has the potential for increased clinical impact of MDD risk models. We did not find evidence that the use of temporal feature encodings was additive to predictive performance in the study population. This suggests that predictive information retained by model weights may be lost during encoding. LSTM pretrained model predictive performance is shown to be clinically useful and improves over state-of-the-art predictors in the MDD phenotype. LSTM model performance warrants consideration of use in future related studies. Conclusion: LSTM models with pretrained weights from autoencoders were able to outperform the benchmark and a pretrained Attention model. Future researchers developing risk models in MDD may benefit from the use of LSTM autoencoder pretrained weights.

Unsupervised characterization of Major Depressive Disorder medication treatment pathways.

Learning health systems have the ability to systematically evaluate treatments and treatment pathways. Characterization of treatment pathways can enhance a health system's ability to perform systematic evaluation to improve care quality. In this study we use a Long-Short Term Memory (LSTM) autoencoder model to systematically characterize treatment pathways in a prevalent phenotype-Major Depressive Disorder (MDD). LSTM autoencoder models generate representations of medication treatment pathways that account for temporality and complex interactions. Patients with similar pathways are grouped with K-means clustering. Clusters are characterized by analysis of medication utilization sequences and trends, as well as clinical features, such as demographics, outcomes and comorbidities. Cluster characterization identifies endotypes of MDD including acute MDD, moderate-chronic MDD and severe-chronic, but managed MDD.

Mining tasks and task characteristics from electronic health record audit logs with unsupervised machine learning.

OBJECTIVE: The characteristics of clinician activities while interacting with electronic health record (EHR) systems can influence the time spent in EHRs and workload. This study aims to characterize EHR activities as tasks and define novel, data-driven metrics. MATERIALS AND METHODS: We leveraged unsupervised learning approaches to learn tasks from sequences of events in EHR audit logs. We developed metrics characterizing the prevalence of unique events and event repetition and applied them to categorize tasks into 4 complexity profiles. Between these profiles, Mann-Whitney U tests were applied to measure the differences in performance time, event type, and clinician prevalence, or the number of unique clinicians who were observed performing these tasks. In addition, we apply process mining frameworks paired with clinical annotations to support the validity of a sample of our identified tasks. We apply our approaches to learn tasks performed by nurses in the Vanderbilt University Medical Center neonatal intensive care unit. RESULTS: We examined EHR audit logs generated by 33 neonatal intensive care unit nurses resulting in 57 234 sessions and 81 tasks. Our results indicated significant differences in performance time for each observed task complexity profile. There were no significant differences in clinician prevalence or in the frequency of viewing and modifying event types between tasks of different complexities. We presented a sample of expert-reviewed, annotated task workflows supporting the interpretation of their clinical meaningfulness. CONCLUSIONS: The use of the audit log provides an opportunity to assist hospitals in further investigating clinician activities to optimize EHR workflows.

Learning Tasks of Pediatric Providers from Electronic Health Record Audit Logs.

The amount of time spent working in the Electronic Health Record (EHR) has become a burden for many providers. We propose computational methods to learn EHR tasks of Pediatrics residents and attending physicians in the treatment of healthy newborns by analyzing EHR audit log data. We perform statistical analyses of the association between EHR events and provider role, leverage word embedding, k-means, and ProM process mining software on audit log data to learn EHR tasks and visualize them. Residents more commonly perform note preparation and result viewing relative to attendings. Attendings perform more communication and chart review. Task workflows analysis resulted in 2 tasks for attendings and 3 tasks for residents. The attending tasks focus on chart review patient report and history, and inbox service. Primary themes for residents are admit/discharge with order creation, note review, and result review.

Measuring Mortality Information in Clinical Data Warehouses.

The ability to track and report long-term outcomes, especially mortality, is essential for advancing clinical research. The purpose of this study was to present a framework for assessing the quality of mortality information in clinical research databases. Using the clinical data warehouse (CDW) at Columbia University Medical Center as a case study, we measured: 1) agreement in vital status between our institution's patient registration system and the U.S. Social Security Administration's Death Master File (DMF), 2) the proportion of patients marked as deceased according to the DMF records who had subsequent visits to our institution, and 3) the proportion of patients still living according to Columbia's CDW who were over 100 and 120 years of age. Of 33,295 deaths recorded in our institution's patient registration system, 13,167 (39.5%) did not exist in the DMF. Of 315,037 patients in our CDW who marked as deceased according to the DMF, 2.1% had a subsequent clinical encounter at our institution. The proportion of patients still living according to Columbia's CDW who were over 100 and 120 years of age was 43.6% and 43.1%, respectively. These measures may be useful to other clinical research investigators seeking to assess the quality of mortality data (1-4).