Raw Electronic Health Record Data Research Articles

Augmented intelligence facilitates concept mapping across different electronic health records

IntroductionWith the advent of artificial intelligence, the secondary use of routinely collected medical data from electronic healthcare records (EHR) has become increasingly popular. However, different EHR systems typically use different names for the same medical concepts. This obviously hampers scalable model development and subsequent clinical implementation for decision support. Therefore, converting original parameter names to a so-called ontology, a standardized set of predefined concepts, is necessary but time-consuming and labor-intensive. We therefore propose an augmented intelligence approach to facilitate ontology alignment by predicting correct concepts based on parameter names from raw electronic health record data exports. MethodsWe used the manually mapped parameter names from the multicenter “Dutch ICU data warehouse against COVID-19” sourced from three types of EHR systems to train machine learning models for concept mapping. Data from 29 intensive care units on 38,824 parameters mapped to 1,679 relevant and unique concepts and 38,069 parameters labeled as irrelevant were used for model development and validation. We used the Natural Language Toolkit (NLTK) to preprocess the parameter names based on WordNet cognitive synonyms transformed by term-frequency inverse document frequency (TF-IDF), yielding numeric features. We then trained linear classifiers using stochastic gradient descent for multi-class prediction. Finally, we fine-tuned these predictions using information on distributions of the data associated with each parameter name through similarity score and skewness comparisons. ResultsThe initial model, trained using data from one hospital organization for each of three EHR systems, scored an overall top 1 precision of 0.744, recall of 0.771, and F1-score of 0.737 on a total of 58,804 parameters. Leave-one-hospital-out analysis returned an average top 1 recall of 0.680 for relevant parameters, which increased to 0.905 for the top 5 predictions. When reducing the training dataset to only include relevant parameters, top 1 recall was 0.811 and top 5 recall was 0.914 for relevant parameters. Performance improvement based on similarity score or skewness comparisons affected at most 5.23% of numeric parameters. ConclusionAugmented intelligence is a promising method to improve concept mapping of parameter names from raw electronic health record data exports. We propose a robust method for mapping data across various domains, facilitating the integration of diverse data sources. However, recall is not perfect, and therefore manual validation of mapping remains essential.

Constructing Epidemiologic Cohorts from Electronic Health Record Data.

In the United States, electronic health records (EHR) are increasingly being incorporated into healthcare organizations to document patient health and services rendered. EHRs serve as a vast repository of demographic, diagnostic, procedural, therapeutic, and laboratory test data generated during the routine provision of health care. The appeal of using EHR data for epidemiologic research is clear: EHRs generate large datasets on real-world patient populations in an easily retrievable form permitting the cost-efficient execution of epidemiologic studies on a wide array of topics. Constructing epidemiologic cohorts from EHR data involves as a defining feature the development of data machinery, which transforms raw EHR data into an epidemiologic dataset from which appropriate inference can be drawn. Though data machinery includes many features, the current report focuses on three aspects of machinery development of high salience to EHR-based epidemiology: (1) selecting study participants; (2) defining “baseline” and assembly of baseline characteristics; and (3) follow-up for future outcomes. For each, the defining features and unique challenges with respect to EHR-based epidemiology are discussed. An ongoing example illustrates key points. EHR-based epidemiology will become more prominent as EHR data sources continue to proliferate. Epidemiologists must continue to improve the methods of EHR-based epidemiology given the relevance of EHRs in today’s healthcare ecosystem.

Automated production of research data marts from a canonical fast healthcare interoperability resource data repository: applications to COVID-19 research

ObjectiveThe rapidly evolving COVID-19 pandemic has created a need for timely data from the healthcare systems for research. To meet this need, several large new data consortia have been developed that require frequent updating and sharing of electronic health record (EHR) data in different common data models (CDMs) to create multi-institutional databases for research. Traditionally, each CDM has had a custom pipeline for extract, transform, and load operations for production and incremental updates of data feeds to the networks from raw EHR data. However, the demands of COVID-19 research for timely data are far higher, and the requirements for updating faster than previous collaborative research using national data networks have increased. New approaches need to be developed to address these demands.MethodsIn this article, we describe the use of the Fast Healthcare Interoperability Resource (FHIR) data model as a canonical data model and the automated transformation of clinical data to the Patient-Centered Outcomes Research Network (PCORnet) and Observational Medical Outcomes Partnership (OMOP) CDMs for data sharing and research collaboration on COVID-19.ResultsFHIR data resources could be transformed to operational PCORnet and OMOP CDMs with minimal production delays through a combination of real-time and postprocessing steps, leveraging the FHIR data subscription feature.ConclusionsThe approach leverages evolving standards for the availability of EHR data developed to facilitate data exchange under the 21st Century Cures Act and could greatly enhance the availability of standardized datasets for research.

High-throughput phenotyping with temporal sequences.

High-throughput electronic phenotyping algorithms can accelerate translational research using data from electronic health record (EHR) systems. The temporal information buried in EHRs is often underutilized in developing computational phenotypic definitions. This study aims to develop a high-throughput phenotyping method, leveraging temporal sequential patterns from EHRs. We develop a representation mining algorithm to extract 5 classes of representations from EHR diagnosis and medication records: the aggregated vector of the records (aggregated vector representation), the standard sequential patterns (sequential pattern mining), the transitive sequential patterns (transitive sequential pattern mining), and 2 hybrid classes. Using EHR data on 10 phenotypes from the Mass General Brigham Biobank, we train and validate phenotyping algorithms. Phenotyping with temporal sequences resulted in a superior classification performance across all 10 phenotypes compared with the standard representations in electronic phenotyping. The high-throughput algorithm's classification performance was superior or similar to the performance of previously published electronic phenotyping algorithms. We characterize and evaluate the top transitive sequences of diagnosis records paired with the records of risk factors, symptoms, complications, medications, or vaccinations. The proposed high-throughput phenotyping approach enables seamless discovery of sequential record combinations that may be difficult to assume from raw EHR data. Transitive sequences offer more accurate characterization of the phenotype, compared with its individual components, and reflect the actual lived experiences of the patients with that particular disease. Sequential data representations provide a precise mechanism for incorporating raw EHR records into downstream machine learning. Our approach starts with user interpretability and works backward to the technology.

Early Sepsis Detection with Deep Learning on EHR Event Sequences

Background: Sepsis is a clinical condition involving an extreme inflammatory response to an infection, and is associated with high morbidity and mortality. Without intervention, this response can progress to septic shock, organ failure and death. Every hour that treatment is delayed mortality increases. Early identification of sepsis is therefore important for a positive outcome.
 Methods: We constructed predictive models for sepsis detection and performed a register-based cohort study on patients from four Danish municipalities. We used event-sequences of raw electronic health record (EHR) data from 2013 to 2017, where each event consists of three elements: a timestamp, an event category (e.g. medication code), and a value. In total, we consider 25.622 positive (SIRS criteria) sequences and 25.622 negative sequences with a total of 112 million events distributed across 64 different hospital units. The number of potential predictor variables in raw EHR data easily exceeds 10.000 and can be challenging for predictive modeling due to this large volume of sparse, heterogeneous events. Traditional approaches have dealt with this complexity by curating a limited number of variables of importance; a labor-intensive process that may discard a vast majority of information. In contrast, we consider a deep learning system constructed as a combination of a convolutional neural network (CNN) and long short-term memory (LSTM) network. Importantly, our system learns representations of the key factors and interactions from the raw event sequence data itself.
 Results: Our model predicts sepsis with an AUROC score of 0.8678, at 11 hours before actual treatment was started, outperforming all currently deployed approaches. At other prediction times, the model yields following AUROC scores. 15 min: 0.9058, 3 hours: 0.8803, 24 hours: 0.8073.
 Conclusion: We have presented a novel approach for early detection of sepsis that has more true positives and fewer false negatives than existing alarm systems without introducing domain knowledge into the model. Importantly, the model does not require changes in the daily workflow of healthcare professionals at hospitals, as the model is based on data that is routinely captured in the EHR. This also enables real-time prediction, as healthcare professionals enters the raw events in the EHR.

A hybrid neural network model for predicting kidney disease in hypertension patients based on electronic health records

BackgroundDisease prediction based on Electronic Health Records (EHR) has become one hot research topic in biomedical community. Existing work mainly focuses on the prediction of one target disease, and little work is proposed for multiple associated diseases prediction. Meanwhile, a piece of EHR usually contains two main information: the textual description and physical indicators. However, existing work largely adopts statistical models with discrete features from numerical physical indicators in EHR, and fails to make full use of textual description information.MethodsIn this paper, we study the problem of kidney disease prediction in hypertension patients by using neural network model. Specifically, we first model the prediction problem as a binary classification task. Then we propose a hybrid neural network which incorporates Bidirectional Long Short-Term Memory (BiLSTM) and Autoencoder networks to fully capture the information in EHR.ResultsWe construct a dataset based on a large number of raw EHR data. The dataset consists of totally 35,332 records from hypertension patients. Experimental results show that the proposed neural model achieves 89.7% accuracy for the task.ConclusionsA hybrid neural network model was presented. Based on the constructed dataset, the comparison results of different models demonstrated the effectiveness of the proposed neural model. The proposed model outperformed traditional statistical models with discrete features and neural baseline systems.

High-fidelity phenotyping: richness and freedom from bias.

Electronic health record phenotyping is the use of raw electronic health record data to assert characterizations about patients. Researchers have been doing it since the beginning of biomedical informatics, under different names. Phenotyping will benefit from an increasing focus on fidelity, both in the sense of increasing richness, such as measured levels, degree or severity, timing, probability, or conceptual relationships, and in the sense of reducing bias. Research agendas should shift from merely improving binary assignment to studying and improving richer representations. The field is actively researching new temporal directions and abstract representations, including deep learning. The field would benefit from research in nonlinear dynamics, in combining mechanistic models with empirical data, including data assimilation, and in topology. The health care process produces substantial bias, and studying that bias explicitly rather than treating it as merely another source of noise would facilitate addressing it.

Diagnosis Prediction from Electronic Health Records Using the Binary Diagnosis History Vector Representation.

Large amounts of rich, heterogeneous information nowadays routinely collected by healthcare providers across the world possess remarkable potential for the extraction of novel medical data and the assessment of different practices in real-world conditions. Specifically in this work, our goal is to use electronic health records (EHRs) to predict progression patterns of future diagnoses of ailments for a particular patient, given the patient's present diagnostic history. Following the highly promising results of a recently proposed approach that introduced the diagnosis history vector representation of a patient's diagnostic record, we introduce a series of improvements to the model and conduct thorough experiments that demonstrate its scalability, accuracy, and practicability in the clinical context. We show that the model is able to capture well the interaction between a large number of ailments that correspond to the most frequent diagnoses, show how the original learning framework can be adapted to increase its prediction specificity, and describe a principled, probabilistic method for incorporating explicit, human clinical knowledge to overcome semantic limitations of the raw EHR data.

Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records.

Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name “deep patient”. We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.

Big biomedical data and cardiovascular disease research: opportunities and challenges.

Electronic health records (EHRs), data generated and collected during normal clinical care, are increasingly being linked and used for translational cardiovascular disease research. Electronic health record data can be structured (e.g. coded diagnoses) or unstructured (e.g. clinical notes) and increasingly encapsulate medical imaging, genomic and patient-generated information. Large-scale EHR linkages enable researchers to conduct high-resolution observational and interventional clinical research at an unprecedented scale. A significant amount of preparatory work and research, however, is required to identify, obtain, and transform raw EHR data into research-ready variables that can be statistically analysed. This study critically reviews the opportunities and challenges that EHR data present in the field of cardiovascular disease clinical research and provides a series of recommendations for advancing and facilitating EHR research.

Incorporating patient-reported outcome measures into the electronic health record for research: application using the Patient Health Questionnaire (PHQ-9).

Electronic health records (EHRs) present an opportunity to access large stores of data for research, but mapping raw EHR data to clinical phenotypes is complex. We propose adding patient-reported data to the EHR to improve phenotyping performance and describe a retrospective cohort study demonstrating a test case in depressive disorder. We compared four EHR-phenotyping methods based on International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes, medication records, and the Patient Health Questionnaire 9 (PHQ-9) regarding the ability to identify cases with depression and characteristics of patients identified with depression. Our sample included 168,884 patients seen (2007-2013) at our neurological institute. We assessed the diagnostic performance in a subset of 225 patients who had a reference standard measurement available. ICD-9-CM codes identified the fewest number of patients as depressed (4,658), followed by PHQ-9 (46,565), and medication data (50,505). The presence of at least one of these criteria identified the largest number (78,322). The PHQ-9 identified a higher proportion of elderly, disabled, Medicaid, and rural patients, as compared to ICD-9-CM codes. ICD-9-CM codes were least sensitive (6.7% sensitivity), whereas the method using at least one of the criteria identified the highest number of truly depressed patients (93.3% sensitivity); however, specificity dropped from 97.7 to 58.1%. The choice of phenotyping method may disproportionately exclude patient groups from research. Patient-reported data hold potential to improve sensitivity while maintaining an acceptable loss of specificity, depending on the context. Researchers should consider including patient-reported data in EHR-driven phenotyping methods.