Search

Background: Patients with peripheral artery disease (PAD) are at risk of major adverse cardiac and cerebrovascular events. There are no readily available risk scores that can accurately identify which patients are most likely to sustain an event, making it difficult to identify those who might benefit from more aggressive intervention. Thus, we aimed to develop a novel predictive model-using machine learning methods on electronic health record data-to identify which PAD patients are most likely to develop major adverse cardiac and cerebrovascular events., Methods and Results: Data were derived from patients diagnosed with PAD at 2 tertiary care institutions. Predictive models were built using a common data model that allowed for utilization of both structured (coded) and unstructured (text) data. Only data from time of entry into the health system up to PAD diagnosis were used for modeling. Models were developed and tested using nested cross-validation. A total of 7686 patients were included in learning our predictive models. Utilizing almost 1000 variables, our best predictive model accurately determined which PAD patients would go on to develop major adverse cardiac and cerebrovascular events with an area under the curve of 0.81 (95% CI, 0.80-0.83)., Conclusions: Machine learning algorithms applied to data in the electronic health record can learn models that accurately identify PAD patients at risk of future major adverse cardiac and cerebrovascular events, highlighting the great potential of electronic health records to provide automated risk stratification for cardiovascular diseases. Common data models that can enable cross-institution research and technology development could potentially be an important aspect of widespread adoption of newer risk-stratification models.

Objective: Evaluate the quality of clinical order practice patterns machine-learned from clinician cohorts stratified by patient mortality outcomes., Materials and Methods: Inpatient electronic health records from 2010 to 2013 were extracted from a tertiary academic hospital. Clinicians (n = 1822) were stratified into low-mortality (21.8%, n = 397) and high-mortality (6.0%, n = 110) extremes using a two-sided P-value score quantifying deviation of observed vs. expected 30-day patient mortality rates. Three patient cohorts were assembled: patients seen by low-mortality clinicians, high-mortality clinicians, and an unfiltered crowd of all clinicians (n = 1046, 1046, and 5230 post-propensity score matching, respectively). Predicted order lists were automatically generated from recommender system algorithms trained on each patient cohort and evaluated against (i) real-world practice patterns reflected in patient cases with better-than-expected mortality outcomes and (ii) reference standards derived from clinical practice guidelines., Results: Across six common admission diagnoses, order lists learned from the crowd demonstrated the greatest alignment with guideline references (AUROC range = 0.86-0.91), performing on par or better than those learned from low-mortality clinicians (0.79-0.84, P < 10 -5 ) or manually-authored hospital order sets (0.65-0.77, P < 10 -3 ). The same trend was observed in evaluating model predictions against better-than-expected patient cases, with the crowd model (AUROC mean = 0.91) outperforming the low-mortality model (0.87, P < 10 -16 ) and order set benchmarks (0.78, P < 10 -35 )., Discussion: Whether machine-learning models are trained on all clinicians or a subset of experts illustrates a bias-variance tradeoff in data usage. Defining robust metrics to assess quality based on internal (e.g. practice patterns from better-than-expected patient cases) or external reference standards (e.g. clinical practice guidelines) is critical to assess decision support content., Conclusion: Learning relevant decision support content from all clinicians is as, if not more, robust than learning from a select subgroup of clinicians favored by patient outcomes., (Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.)

Objective: Adverse drug events (ADEs) are undesired harmful effects resulting from use of a medication, and occur in 30% of hospitalized patients. The authors have developed a data-mining method for systematic, automated detection of ADEs from electronic medical records., Materials and Methods: This method uses the text from 9.5 million clinical notes, along with prior knowledge of drug usages and known ADEs, as inputs. These inputs are further processed into statistics used by a discriminative classifier which outputs the probability that a given drug-disorder pair represents a valid ADE association. Putative ADEs identified by the classifier are further filtered for positive support in 2 independent, complementary data sources. The authors evaluate this method by assessing support for the predictions in other curated data sources, including a manually curated, time-indexed reference standard of label change events., Results: This method uses a classifier that achieves an area under the curve of 0.94 on a held out test set. The classifier is used on 2,362,950 possible drug-disorder pairs comprised of 1602 unique drugs and 1475 unique disorders for which we had data, resulting in 240 high-confidence, well-supported drug-AE associations. Eighty-seven of them (36%) are supported in at least one of the resources that have information that was not available to the classifier., Conclusion: This method demonstrates the feasibility of systematic post-marketing surveillance for ADEs using electronic medical records, a key component of the learning healthcare system., (© The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)

Objective: The trade-off between the speed and simplicity of dictionary-based term recognition and the richer linguistic information provided by more advanced natural language processing (NLP) is an area of active discussion in clinical informatics. In this paper, we quantify this trade-off among text processing systems that make different trade-offs between speed and linguistic understanding. We tested both types of systems in three clinical research tasks: phase IV safety profiling of a drug, learning adverse drug-drug interactions, and learning used-to-treat relationships between drugs and indications., Materials: We first benchmarked the accuracy of the NCBO Annotator and REVEAL in a manually annotated, publically available dataset from the 2008 i2b2 Obesity Challenge. We then applied the NCBO Annotator and REVEAL to 9 million clinical notes from the Stanford Translational Research Integrated Database Environment (STRIDE) and used the resulting data for three research tasks., Results: There is no significant difference between using the NCBO Annotator and REVEAL in the results of the three research tasks when using large datasets. In one subtask, REVEAL achieved higher sensitivity with smaller datasets., Conclusions: For a variety of tasks, employing simple term recognition methods instead of advanced NLP methods results in little or no impact on accuracy when using large datasets. Simpler dictionary-based methods have the advantage of scaling well to very large datasets. Promoting the use of simple, dictionary-based methods for population level analyses can advance adoption of NLP in practice., (© The Author 2014. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

Objective: Mental illness is the leading cause of disability in the USA, but boundaries between different mental illnesses are notoriously difficult to define. Electronic medical records (EMRs) have recently emerged as a powerful new source of information for defining the phenotypic signatures of specific diseases. We investigated how EMR-based text mining and statistical analysis could elucidate the phenotypic boundaries of three important neuropsychiatric illnesses-autism, bipolar disorder, and schizophrenia., Methods: We analyzed the medical records of over 7000 patients at two facilities using an automated text-processing pipeline to annotate the clinical notes with Unified Medical Language System codes and then searching for enriched codes, and associations among codes, that were representative of the three disorders. We used dimensionality-reduction techniques on individual patient records to understand individual-level phenotypic variation within each disorder, as well as the degree of overlap among disorders., Results: We demonstrate that automated EMR mining can be used to extract relevant drugs and phenotypes associated with neuropsychiatric disorders and characteristic patterns of associations among them. Patient-level analyses suggest a clear separation between autism and the other disorders, while revealing significant overlap between schizophrenia and bipolar disorder. They also enable localization of individual patients within the phenotypic 'landscape' of each disorder., Conclusions: Because EMRs reflect the realities of patient care rather than idealized conceptualizations of disease states, we argue that automated EMR mining can help define the boundaries between different mental illnesses, facilitate cohort building for clinical and genomic studies, and reveal how clear expert-defined disease boundaries are in practice.

ObjectiveDepression is a prevalent disorder difficult to diagnose and treat. In particular, depressed patients exhibit largely unpredictable responses to treatment. Toward the goal of personalizing treatment for depression, we develop and evaluate computational models that use electronic health record (EHR) data for predicting the diagnosis and severity of depression, and response to treatment.Materials and methodsWe develop regression-based models for predicting depression, its severity, and response to treatment from EHR data, using structured diagnosis and medication codes as well as free-text clinical reports. We used two datasets: 35,000 patients (5000 depressed) from the Palo Alto Medical Foundation and 5651 patients treated for depression from the Group Health Research Institute.ResultsOur models are able to predict a future diagnosis of depression up to 12 months in advance (area under the receiver operating characteristic curve (AUC) 0.70-0.80). We can differentiate patients with severe baseline depression from those with minimal or mild baseline depression (AUC 0.72). Baseline depression severity was the strongest predictor of treatment response for medication and psychotherapy.ConclusionsIt is possible to use EHR data to predict a diagnosis of depression up to 12 months in advance and to differentiate between extreme baseline levels of depression. The models use commonly available data on diagnosis, medication, and clinical progress notes, making them easily portable. The ability to automatically determine severity can facilitate assembly of large patient cohorts with similar severity from multiple sites, which may enable elucidation of the moderators of treatment response in the future.

Background and objectiveElectronic health records (EHRs) are increasingly being used to complement the FDA Adverse Event Reporting System (FAERS) and to enable active pharmacovigilance. Over 30% of all adverse drug reactions are caused by drug-drug interactions (DDIs) and result in significant morbidity every year, making their early identification vital. We present an approach for identifying DDI signals directly from the textual portion of EHRs.MethodsWe recognize mentions of drug and event concepts from over 50 million clinical notes from two sites to create a timeline of concept mentions for each patient. We then use adjusted disproportionality ratios to identify significant drug-drug-event associations among 1165 drugs and 14 adverse events. To validate our results, we evaluate our performance on a gold standard of 1698 DDIs curated from existing knowledge bases, as well as with signaling DDI associations directly from FAERS using established methods.ResultsOur method achieves good performance, as measured by our gold standard (area under the receiver operator characteristic (ROC) curve >80%), on two independent EHR datasets and the performance is comparable to that of signaling DDIs from FAERS. We demonstrate the utility of our method for early detection of DDIs and for identifying alternatives for risky drug combinations. Finally, we publish a first of its kind database of population event rates among patients on drug combinations based on an EHR corpus.ConclusionsIt is feasible to identify DDI signals and estimate the rate of adverse events among patients on drug combinations, directly from clinical text; this could have utility in prioritizing drug interaction surveillance as well as in clinical decision support.

Introduction: Pharmacovigilance programs protect patient health and safety by identifying adverse event signals through postmarketing surveillance of claims data and spontaneous reports. Electronic health records (EHRs) provide new opportunities to address limitations of traditional approaches and promote discovery-oriented pharmacovigilance. Methods: To evaluate the current state of EHR-based medication safety signal identification, we conducted a scoping literature review of studies aimed at identifying safety signals from routinely collected patient-level EHR data. We extracted information on study design, EHR data elements utilized, analytic methods employed, drugs and outcomes evaluated, and key statistical and data analysis choices. Results: We identified 81 eligible studies. Disproportionality methods were the predominant analytic approach, followed by data mining and regression. Variability in study design makes direct comparisons difficult. Studies varied widely in terms of data, confounding adjustment, and statistical considerations. Conclusion: Despite broad interest in utilizing EHRs for safety signal identification, current efforts fail to leverage the full breadth and depth of available data or to rigorously control for confounding. The development of best practices and application of common data models would promote the expansion of EHR-based pharmacovigilance. [ABSTRACT FROM AUTHOR]

Chronic nonhealing wounds have a prevalence of 2% in the United States, and cost an estimated $50 billion annually. Accurate stratification of wounds for risk of slow healing may help guide treatment and referral decisions. We have applied modern machine learning methods and feature engineering to develop a predictive model for delayed wound healing that uses information collected during routine care in outpatient wound care centers. Patient and wound data was collected at 68 outpatient wound care centers operated by Healogics Inc. in 26 states between 2009 and 2013. The dataset included basic demographic information on 59,953 patients, as well as both quantitative and categorical information on 180,696 wounds. Wounds were split into training and test sets by randomly assigning patients to training and test sets. Wounds were considered delayed with respect to healing time if they took more than 15 weeks to heal after presentation at a wound care center. Eleven percent of wounds in this dataset met this criterion. Prognostic models were developed on training data available in the first week of care to predict delayed healing wounds. A held out subset of the training set was used for model selection, and the final model was evaluated on the test set to evaluate discriminative power and calibration. The model achieved an area under the curve of 0.842 (95% confidence interval 0.834-0.847) for the delayed healing outcome and a Brier reliability score of 0.00018. Early, accurate prediction of delayed healing wounds can improve patient care by allowing clinicians to increase the aggressiveness of intervention in patients most at risk. [ABSTRACT FROM AUTHOR]

Background: Peripheral arterial disease (PAD) is a growing problem with few available therapies. Cilostazol is the only FDA-approved medication with a class I indication for intermittent claudication, but carries a black box warning due to concerns for increased cardiovascular mortality. To assess the validity of this black box warning, we employed a novel text-analytics pipeline to quantify the adverse events associated with Cilostazol use in a clinical setting, including patients with congestive heart failure (CHF). Methods and Results: We analyzed the electronic medical records of 1.8 million subjects from the Stanford clinical data warehouse spanning 18 years using a novel text-mining/statistical analytics pipeline. We identified 232 PAD patients taking Cilostazol and created a control group of 1,160 PAD patients not taking this drug using 1∶5 propensity-score matching. Over a mean follow up of 4.2 years, we observed no association between Cilostazol use and any major adverse cardiovascular event including stroke (OR = 1.13, CI [0.82, 1.55]), myocardial infarction (OR = 1.00, CI [0.71, 1.39]), or death (OR = 0.86, CI [0.63, 1.18]). Cilostazol was not associated with an increase in any arrhythmic complication. We also identified a subset of CHF patients who were prescribed Cilostazol despite its black box warning, and found that it did not increase mortality in this high-risk group of patients. Conclusions: This proof of principle study shows the potential of text-analytics to mine clinical data warehouses to uncover ‘natural experiments’ such as the use of Cilostazol in CHF patients. We envision this method will have broad applications for examining difficult to test clinical hypotheses and to aid in post-marketing drug safety surveillance. Moreover, our observations argue for a prospective study to examine the validity of a drug safety warning that may be unnecessarily limiting the use of an efficacious therapy. [ABSTRACT FROM AUTHOR]