Search

SummaryObjectiveElectronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes, covering hundreds of thousands of clinical concepts available for research and clinical care. The complex, massive, heterogeneous, and noisy nature of EHR data imposes significant challenges for feature representation, information extraction, and uncertainty quantification. To address these challenges, we proposed an efficientAggregated naRrativeCodifiedHealth (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features.MethodsThe ARCH algorithm first derives embedding vectors from a co-occurrence matrix of all EHR concepts and then generates cosine similarities along with associatedp-values to measure the strength of relatedness between clinical features with statistical certainty quantification. In the final step, ARCH performs a sparse embedding regression to remove indirect linkage between entity pairs. We validated the clinical utility of the ARCH knowledge graph, generated from 12.5 million patients in the Veterans Affairs (VA) healthcare system, through downstream tasks including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer’s disease patients.ResultsARCH produces high-quality clinical embeddings and KG for over 60, 000 EHR concepts, as visualized in the R-shiny powered web-API (https://celehs.hms.harvard.edu/ARCH/). The ARCH embeddings attained an average area under the ROC curve (AUC) of 0.926 and 0.861 for detecting pairs of similar EHR concepts when the concepts are mapped to codified data and to NLP data; and 0.810 (codified) and 0.843 (NLP) for detecting related pairs. Based on thep-values computed by ARCH, the sensitivity of detecting similar and related entity pairs are 0.906 and 0.888 under false discovery rate (FDR) control of 5%. For detecting drug side effects, the cosine similarity based on the ARCH semantic representations achieved an AUC of 0.723 while the AUC improved to 0.826 after few-shot training via minimizing the loss function on the training data set. Incorporating NLP data substantially improved the ability to detect side effects in the EHR. For example, based on unsupervised ARCH embeddings, the power of detecting drug-side effects pairs when using codified data only was 0.15, much lower than the power of 0.51 when using both codified and NLP concepts. Compared to existing large-scale representation learning methods including PubmedBERT, BioBERT and SAPBERT, ARCH attains the most robust performance and substantially higher accuracy in detecting these relationships. Incorporating ARCH selected features in weakly supervised phenotyping algorithms can improve the robustness of algorithm performance, especially for diseases that benefit from NLP features as supporting evidence. For example, the phenotyping algorithm for depression attained an AUC of 0.927 when using ARCH selected features but only 0.857 when using codified features selected via the KESER network[1]. In addition, embeddings and knowledge graphs generated from the ARCH network were able to cluster AD patients into two subgroups, where the fast progression subgroup had a much higher mortality rate.ConclusionsThe proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

The International Classification of Diseases (ICD)-10 code (U09.9) for post-acute sequelae of COVID-19 (PASC) was introduced in October of 2021. As researchers seek to leverage this billing code for research purposes in large scale real-world studies of PASC, it is of utmost importance to understand the functional use of the code by healthcare providers and the clinical characteristics of patients who have been assigned this code. To this end, we operationalized clinical case definitions of PASC using World Health Organization and Centers for Disease Control guidelines. We then chart reviewed 300 patients with COVID-19 from three participating healthcare systems of the 4CE Consortium who were assigned the U09.9 code. Chart review results showed the average positive predictive value (PPV) of the U09.9 code ranged from 40.2% to 65.4% depending on which definition of PASC was used in the evaluation. The PPV of the U09.9 code also fluctuated significantly between calendar time periods. We demonstrated the potential utility of textual data extracted from natural language processing techniques to more comprehensively capture symptoms associated with PASC from electronic health records data. Finally, we investigated the utilization of long COVID clinics in the cohort of patients. We observed that only an average of 24.0% of patients with the U09.9 code visited a long COVID clinic. Among patients who met the WHO PASC definition, only an average of 35.6% visited a long COVID clinic.

MotivationPredicting molecule–disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule–molecule, molecule–disease and disease–disease semantic dependencies can potentially improve prediction performance.MethodsWe introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule–disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects.ResultsWe extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens.Availability and implementationThe code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/.Supplementary informationSupplementary data are available at Bioinformatics online.

UNSTRUCTURED Although randomized controlled trials (RCTs) are the gold standard for establishing the efficacy and safety of a medical treatment, real-world evidence (RWE) generated from real-world data has been vital in postapproval monitoring and is being promoted for the regulatory process of experimental therapies. An emerging source of real-world data is electronic health records (EHRs), which contain detailed information on patient care in both structured (eg, diagnosis codes) and unstructured (eg, clinical notes and images) forms. Despite the granularity of the data available in EHRs, the critical variables required to reliably assess the relationship between a treatment and clinical outcome are challenging to extract. To address this fundamental challenge and accelerate the reliable use of EHRs for RWE, we introduce an integrated data curation and modeling pipeline consisting of 4 modules that leverage recent advances in natural language processing, computational phenotyping, and causal modeling techniques with noisy data. Module 1 consists of techniques for data harmonization. We use natural language processing to recognize clinical variables from RCT design documents and map the extracted variables to EHR features with description matching and knowledge networks. Module 2 then develops techniques for cohort construction using advanced phenotyping algorithms to both identify patients with diseases of interest and define the treatment arms. Module 3 introduces methods for variable curation, including a list of existing tools to extract baseline variables from different sources (eg, codified, free text, and medical imaging) and end points of various types (eg, death, binary, temporal, and numerical). Finally, module 4 presents validation and robust modeling methods, and we propose a strategy to create gold-standard labels for EHR variables of interest to validate data curation quality and perform subsequent causal modeling for RWE. In addition to the workflow proposed in our pipeline, we also develop a reporting guideline for RWE that covers the necessary information to facilitate transparent reporting and reproducibility of results. Moreover, our pipeline is highly data driven, enhancing study data with a rich variety of publicly available information and knowledge sources. We also showcase our pipeline and provide guidance on the deployment of relevant tools by revisiting the emulation of the Clinical Outcomes of Surgical Therapy Study Group Trial on laparoscopy-assisted colectomy versus open colectomy in patients with early-stage colon cancer. We also draw on existing literature on EHR emulation of RCTs together with our own studies with the Mass General Brigham EHR.

While acute kidney injury (AKI) is a common complication in COVID-19, data on post-AKI kidney function recovery and the clinical factors associated with poor kidney function recovery is lacking.A retrospective multi-centre observational cohort study comprising 12,891 hospitalized patients aged 18 years or older with a diagnosis of SARS-CoV-2 infection confirmed by polymerase chain reaction from 1 January 2020 to 10 September 2020, and with at least one serum creatinine value 1-365 days prior to admission. Mortality and serum creatinine values were obtained up to 10 September 2021.Advanced age (HR 2.77, 95%CI 2.53-3.04, p 0.0001), severe COVID-19 (HR 2.91, 95%CI 2.03-4.17, p 0.0001), severe AKI (KDIGO stage 3: HR 4.22, 95%CI 3.55-5.00, p 0.0001), and ischemic heart disease (HR 1.26, 95%CI 1.14-1.39, p 0.0001) were associated with worse mortality outcomes. AKI severity (KDIGO stage 3: HR 0.41, 95%CI 0.37-0.46, p 0.0001) was associated with worse kidney function recovery, whereas remdesivir use (HR 1.34, 95%CI 1.17-1.54, p 0.0001) was associated with better kidney function recovery. In a subset of patients without chronic kidney disease, advanced age (HR 1.38, 95%CI 1.20-1.58, p 0.0001), male sex (HR 1.67, 95%CI 1.45-1.93, p 0.0001), severe AKI (KDIGO stage 3: HR 11.68, 95%CI 9.80-13.91, p 0.0001), and hypertension (HR 1.22, 95%CI 1.10-1.36, p = 0.0002) were associated with post-AKI kidney function impairment. Furthermore, patients with COVID-19-associated AKI had significant and persistent elevations of baseline serum creatinine 125% or more at 180 days (RR 1.49, 95%CI 1.32-1.67) and 365 days (RR 1.54, 95%CI 1.21-1.96) compared to COVID-19 patients with no AKI.COVID-19-associated AKI was associated with higher mortality, and severe COVID-19-associated AKI was associated with worse long-term post-AKI kidney function recovery.Authors are supported by various funders, with full details stated in the acknowledgement section.

The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems.The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems.With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks.The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

The increasing availability of electronic health record (EHR) systems has created enormous potential for translational research. However, it is difficult to know all the relevant codes related to a phenotype due to the large number of codes available. Traditional data mining approaches often require the use of patient-level data, which hinders the ability to share data across institutions. In this project, we demonstrate that multi-center large-scale code embeddings can be used to efficiently identify relevant features related to a disease of interest. We constructed large-scale code embeddings for a wide range of codified concepts from EHRs from two large medical centers. We developed knowledge extraction via sparse embedding regression (KESER) for feature selection and integrative network analysis. We evaluated the quality of the code embeddings and assessed the performance of KESER in feature selection for eight diseases. Besides, we developed an integrated clinical knowledge map combining embedding data from both institutions. The features selected by KESER were comprehensive compared to lists of codified data generated by domain experts. Features identified via KESER resulted in comparable performance to those built upon features selected manually or with patient-level data. The knowledge map created using an integrative analysis identified disease-disease and disease-drug pairs more accurately compared to those identified using single institution data. Analysis of code embeddings via KESER can effectively reveal clinical knowledge and infer relatedness among codified concepts. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data.

Accurately assigning phenotype information to individual patients via computational phenotyping using Electronic Health Records (EHRs) has been seen as the first step towards enabling EHRs for precision medicine research. Chart review labels annotated by clinical experts, also known as "gold standard" labels, are essential for the development and validation of computational phenotyping algorithms. However, given the complexity of EHR systems, the process of chart review is both labor intensive and time consuming. We propose a fully automated algorithm, referred to as pGUESS, to rank EHR notes according to their relevance to a given phenotype. By identifying the most relevant notes, pGUESS can greatly improve the efficiency and accuracy of chart reviews.pGUESS uses prior guided semantic similarity to measure the informativeness of a clinical note to a given phenotype. We first select candidate clinical concepts from a pool of comprehensive medical concepts using public knowledge sources and then derive the semantic embedding vector (SEV) for a reference article (SEVThe algorithm was validated against four sets of 200 notes that were manually annotated by clinical experts to assess their informativeness to one of three disease phenotypes. pGUESS algorithm substantially outperforms existing unsupervised approaches for classifying the relevance status with respect to both accuracy and scalability across phenotypes. Averaging over the three phenotypes, the rank correlation between the algorithm ranking and gold standard label was 0.64 for pGUESS, but only 0.47 and 0.35 for the next two best performing algorithms. pGUESS is also much more computationally scalable compared to existing algorithms.pGUESS algorithm can substantially reduce the burden of chart review and holds potential in improving the efficiency and accuracy of human annotation.

Objective Multimodal automated phenotyping (MAP) is a scalable, high-throughput phenotyping method, developed using electronic health record (EHR) data from an adult population. We tested transportability of MAP to a pediatric population. Materials and Methods Without additional feature engineering or supervised training, we applied MAP to a pediatric population enrolled in a biobank and evaluated performance against physician-reviewed medical records. We also compared performance of MAP at the pediatric institution and the original adult institution where MAP was developed, including for 6 phenotypes validated at both institutions against physician-reviewed medical records. Results MAP performed equally well in the pediatric setting (average AUC 0.98) as it did at the general adult hospital system (average AUC 0.96). MAP’s performance in the pediatric sample was similar across the 6 specific phenotypes also validated against gold-standard labels in the adult biobank. Conclusions MAP is highly transportable across diverse populations and has potential for wide-scale use.