Multimodal representation learning for predicting molecule-disease relations.

MOTIVATION: Predicting 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. METHODS: We 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. RESULTS: We 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 IMPLEMENTATION: The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task.

MOTIVATION: Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model's performance. RESULTS: We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets-BioASQ-7b, BioASQ-8b and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets. AVAILABILITY AND IMPLEMENTATION: BioADAPT-MRC is freely available as an open-source project at https://github.com/mmahbub/BioADAPT-MRC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Pharmacoepidemiology, Machine Learning, and COVID-19: An Intent-to-Treat Analysis of Hydroxychloroquine, With or Without Azithromycin, and COVID-19 Outcomes Among Hospitalized US Veterans.

Hydroxychloroquine (HCQ) was proposed as an early therapy for coronavirus disease 2019 (COVID-19) after in vitro studies indicated possible benefit. Previous in vivo observational studies have presented conflicting results, though recent randomized clinical trials have reported no benefit from HCQ among patients hospitalized with COVID-19. We examined the effects of HCQ alone and in combination with azithromycin in a hospitalized population of US veterans with COVID-19, using a propensity score-adjusted survival analysis with imputation of missing data. According to electronic health record data from the US Department of Veterans Affairs health care system, 64,055 US Veterans were tested for the virus that causes COVID-19 between March 1, 2020 and April 30, 2020. Of the 7,193 veterans who tested positive, 2,809 were hospitalized, and 657 individuals were prescribed HCQ within the first 48-hours of hospitalization for the treatment of COVID-19. There was no apparent benefit associated with HCQ receipt, alone or in combination with azithromycin, and there was an increased risk of intubation when HCQ was used in combination with azithromycin (hazard ratio = 1.55; 95% confidence interval: 1.07, 2.24). In conclusion, we assessed the effectiveness of HCQ with or without azithromycin in treatment of patients hospitalized with COVID-19, using a national sample of the US veteran population. Using rigorous study design and analytic methods to reduce confounding and bias, we found no evidence of a survival benefit from the administration of HCQ.

Question-answering system extracts information on injection drug use from clinical notes.

BACKGROUND: Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients' electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. METHODS: To address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model's ability to extract IDU-related information from temporally out-of-distribution data. RESULTS: Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. CONCLUSIONS: Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

There are many health risks associated with injection drug use (IDU). Identifying people who inject drugs early can reduce the likelihood of these issues arising. However, extracting information about any possible IDU from a person's electronic health records can be difficult because the information is often in text-based general clinical notes rather than provided in a particular section of the record or as numerical data. Manually extracting information from these notes is time-consuming and inefficient. We used a computational method to train computer software to be able to extract IDU details. Potentially, this approach could be used by healthcare providers to more efficiently and accurately identify people who inject drugs, and therefore provide better advice and medical care.

Accelerating Genome- and Phenome-Wide Association Studies using GPUs - A case study using data from the Million Veteran Program.

The expansion of biobanks has significantly propelled genomic discoveries yet the sheer scale of data within these repositories poses formidable computational hurdles, particularly in handling extensive matrix operations required by prevailing statistical frameworks. In this work, we introduce computational optimizations to the SAIGE (Scalable and Accurate Implementation of Generalized Mixed Model) algorithm, notably employing a GPU-based distributed computing approach to tackle these challenges. We applied these optimizations to conduct a large-scale genome-wide association study (GWAS) across 2,068 phenotypes derived from electronic health records of 635,969 diverse participants from the Veterans Affairs (VA) Million Veteran Program (MVP). Our strategies enabled scaling up the analysis to over 6,000 nodes on the Department of Energy (DOE) Oak Ridge Leadership Computing Facility (OLCF) Summit High-Performance Computer (HPC), resulting in a 20-fold acceleration compared to the baseline model. We also provide a Docker container with our optimizations that was successfully used on multiple cloud infrastructures on UK Biobank and All of Us datasets where we showed significant time and cost benefits over the baseline SAIGE model.

ARCH: Large-scale Knowledge Graph via Aggregated Narrative Codified Health Records Analysis.

Objective: Electronic 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 efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: The ARCH algorithm first derives embedding vectors from a co-occurrence matrix of all EHR concepts and then generates cosine similarities along with associated p-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. Results: ARCH 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 the p-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. Conclusions: The 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.

sciCAN: single-cell chromatin accessibility and gene expression data integration via cycle-consistent adversarial network.

The boom in single-cell technologies has brought a surge of high dimensional data that come from different sources and represent cellular systems from different views. With advances in these single-cell technologies, integrating single-cell data across modalities arises as a new computational challenge. Here, we present an adversarial approach, sciCAN, to integrate single-cell chromatin accessibility and gene expression data in an unsupervised manner. We benchmarked sciCAN with 5 existing methods in 5 scATAC-seq/scRNA-seq datasets, and we demonstrated that our method dealt with data integration with consistent performance across datasets and better balance of mutual transferring between modalities than the other 5 existing methods. We further applied sciCAN to 10X Multiome data and confirmed that the integrated representation preserves biological relationships within the hematopoietic hierarchy. Finally, we investigated CRISPR-perturbed single-cell K562 ATAC-seq and RNA-seq data to identify cells with related responses to different perturbations in these different modalities.

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients.

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.

Network-medicine framework for studying disease trajectories in U.S. veterans.

A better understanding of the sequential and temporal aspects in which diseases occur in patient's lives is essential for developing improved intervention strategies that reduce burden and increase the quality of health services. Here we present a network-based framework to study disease relationships using Electronic Health Records from > 9 million patients in the United States Veterans Health Administration (VHA) system. We create the Temporal Disease Network, which maps the sequential aspects of disease co-occurrence among patients and demonstrate that network properties reflect clinical aspects of the respective diseases. We use the Temporal Disease Network to identify disease groups that reflect patterns of disease co-occurrence and the flow of patients among diagnoses. Finally, we define a strategy for the identification of trajectories that lead from one disease to another. The framework presented here has the potential to offer new insights for disease treatment and prevention in large health care systems.

Visualizing novel connections and genetic similarities across diseases using a network-medicine based approach.

Understanding the genetic relationships between human disorders could lead to better treatment and prevention strategies, especially for individuals with multiple comorbidities. A common resource for studying genetic-disease relationships is the GWAS Catalog, a large and well curated repository of SNP-trait associations from various studies and populations. Some of these populations are contained within mega-biobanks such as the Million Veteran Program (MVP), which has enabled the genetic classification of several diseases in a large well-characterized and heterogeneous population. Here we aim to provide a network of the genetic relationships among diseases and to demonstrate the utility of quantifying the extent to which a given resource such as MVP has contributed to the discovery of such relations. We use a network-based approach to evaluate shared variants among thousands of traits in the GWAS Catalog repository. Our results indicate many more novel disease relationships that did not exist in early studies and demonstrate that the network can reveal clusters of diseases mechanistically related. Finally, we show novel disease connections that emerge when MVP data is included, highlighting methodology that can be used to indicate the contributions of a given biobank.

Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data.

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.

Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)-based ranking for concept normalization.

OBJECTIVE: Concept normalization, the task of linking phrases in text to concepts in an ontology, is useful for many downstream tasks including relation extraction, information retrieval, etc. We present a generate-and-rank concept normalization system based on our participation in the 2019 National NLP Clinical Challenges Shared Task Track 3 Concept Normalization. MATERIALS AND METHODS: The shared task provided 13 609 concept mentions drawn from 100 discharge summaries. We first design a sieve-based system that uses Lucene indices over the training data, Unified Medical Language System (UMLS) preferred terms, and UMLS synonyms to generate a list of possible concepts for each mention. We then design a listwise classifier based on the BERT (Bidirectional Encoder Representations from Transformers) neural network to rank the candidate concepts, integrating UMLS semantic types through a regularizer. RESULTS: Our generate-and-rank system was third of 33 in the competition, outperforming the candidate generator alone (81.66% vs 79.44%) and the previous state of the art (76.35%). During postevaluation, the model's accuracy was increased to 83.56% via improvements to how training data are generated from UMLS and incorporation of our UMLS semantic type regularizer. DISCUSSION: Analysis of the model shows that prioritizing UMLS preferred terms yields better performance, that the UMLS semantic type regularizer results in qualitatively better concept predictions, and that the model performs well even on concepts not seen during training. CONCLUSIONS: Our generate-and-rank framework for UMLS concept normalization integrates key UMLS features like preferred terms and semantic types with a neural network-based ranking model to accurately link phrases in text to UMLS concepts.

Standardized Architecture for a Mega-Biobank Phenomic Library: The Million Veteran Program (MVP).

Electronic health records (EHRs) provide a wealth of data for phenotype development in population health studies, and researchers invest considerable time to curate data elements and validate disease definitions. The ability to reproduce well-defined phenotypes increases data quality, comparability of results and expedites research. In this paper, we present a standardized approach to organize and capture phenotype definitions, resulting in the creation of an open, online repository of phenotypes. This resource captures phenotype development, provenance and process from the Million Veteran Program, a national mega-biobank embedded in the Veterans Health Administration (VHA). To ensure that the repository is searchable, extendable, and sustainable, it is necessary to develop both a proper digital catalog architecture and underlying metadata infrastructure to enable effective management of the data fields required to define each phenotype. Our methods provide a resource for VHA investigators and a roadmap for researchers interested in standardizing their phenotype definitions to increase portability.

JSONize: A Scalable Machine Learning Pipeline to Model Medical Notes as Semi-structured Documents.

The Department of Veteran's Affairs (VA) archives one of the largest corpora of clinical notes in their corporate data warehouse as unstructured text data. Unstructured text easily supports keyword searches and regular expressions. Often these simple searches do not adequately support the complex searches that need to be performed on notes. For example, a researcher may want all notes with a Duke Treadmill Score of less than five or people that smoke more than one pack per day. Range queries like this and more can be supported by modelling text as semi-structured documents. In this paper, we implement a scalable machine learning pipeline that models plain medical text as useful semi-structured documents. We improve on existing models and achieve an F1-score of 0.912 and scale our methods to the entire VA corpus.

A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier.

PURPOSE: Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage. METHODS: A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset. RESULTS: The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset. CONCLUSIONS: The use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.