Using Electronic Health Records To Generate Phenotypes For Research

Machine-Learned Codes from EHR Data Predict Hard Outcomes Better than Human-Assigned ICD Codes

We used machine learning (ML) to characterize 894,154 medical records of outpatient visits from the Veterans Administration Central Data Warehouse (VA CDW) by the likelihood of assignment of 200 International Classification of Diseases (ICD) code blocks. Using four different predictive models, we found the ML-derived predictions for the code blocks were consistently more effective in predicting death or 90-day rehospitalization than the assigned code block in the record. We reviewed records of ICD chapter assignments. The review revealed that the ML-predicted chapter assignments were consistently better than those humanly assigned. Impact factor analysis, a method of explanation of AI findings that was developed in our group, demonstrated little effect on any one assigned ICD code block but a marked impact on the ML-derived code blocks of kidney disease as well as several other morbidities. In this study, machine learning was much better than human code assignment at predicting the relatively rare outcomes of death or rehospitalization. Future work will address generalizability using other datasets, as well as addressing coding that is more nuanced than that of the categorization provided by code blocks.

Automating assignment of HIV+ patients into phenogroups from demography bound phenotype attack rates

Evidence based medicine and health data for policy should update statistical data modeling methods to take advantage of at-scale data. One challenge with at-scale data is information segmentation for clinical presentation discovery and cohort assignment. We use gradient boosting machine (GBM) to segment 94,379,175,015 diagnostic clinical events attributable to 283,632,789 Centers for Medicare and Medicaid Services beneficiaries over 22 observation years. Diagnostic events were aggregated into attack rates by demography and Phenome-wide association studies (PheWas) codes. Resulting attack rates were then segmented within a user defined clinical status of interest, in this case HIV status. 1,753,647 HIV+ beneficiaries were considered. The GBM model assigned 19,651,408 PheWas attack rates from 69,133,296 ICD attack rates into phenogroups/nodes.

Opportunities and Challenges of Cardiovascular Disease Risk Prediction for Primary Prevention Using Machine Learning and Electronic Health Records: A Systematic Review

Background

Cardiovascular disease (CVD) remains the foremost cause of morbidity and mortality worldwide. Recent advancements in machine learning (ML) have demonstrated substantial potential in augmenting risk stratification for primary prevention, surpassing conventional statistical models in predictive performance. Thus, integrating ML with Electronic Health Records (EHRs) enables refined risk estimation by leveraging the granularity and breadth of longitudinal individual patient data. However, fundamental barriers persist, including limited generalizability, challenges in interpretability, and the absence of rigorous external validation, all of which impede widespread clinical deployment.

Methods

This review adheres to the methodological rigor of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Scale for the Assessment of Narrative Review Articles (SANRA) guidelines. A systematic literature search was performed in March 2024, encompassing the Medline and Embase databases, to identify studies published since 2010. Supplementary references were retrieved from the Institute for Scientific Information (ISI) Web of Science, and manual searches were curated. The selection process, conducted via Rayyan, focused on systematic and narrative reviews evaluating ML-driven models for long-term CVD risk prediction within primary prevention contexts utilizing EHR data. Studies investigating short-term prognostication, highly specific comorbid cohorts, or conventional models devoid of ML components were excluded.

Results

Following an exhaustive screening of 1757 records, 22 studies met the inclusion criteria. Of these, 10 were systematic reviews (four incorporating meta-analyses), while 12 constituted narrative reviews, with the majority published post-2020. The synthesis underscores the superiority of ML in modeling intricate EHR-derived risk factors, facilitating precision-driven cardiovascular risk assessment. Nonetheless, salient challenges endure heterogeneity in CVD outcome definitions, undermine comparability, data incompleteness and inconsistency compromise model robustness, and a dearth of external validation constrains clinical translatability. Moreover, ethical and regulatory considerations, including algorithmic opacity, equity in predictive performance, and the absence of standardized evaluation frameworks, pose formidable obstacles to seamless integration into clinical workflows.

Conclusions

Despite the transformative potential of ML-based CVD risk prediction, it remains encumbered by methodological, technical, and regulatory impediments that hinder its full-scale adoption into real-world healthcare settings. This review underscores the imperative circumstances for standardized validation protocols, stringent regulatory oversight, and interdisciplinary collaboration to bridge the translational divide. Our findings established an integrative framework for developing, validating, and applying ML-based CVD risk prediction algorithms, addressing both clinical and technical dimensions. To further advance this field, we propose a standardized, transparent, and regulated EHR platform that facilitates fair model evaluation, reproducibility, and clinical translation by providing a high-quality, representative dataset with structured governance and benchmarking mechanisms. Meanwhile, future endeavors must prioritize enhancing model transparency, mitigating biases, and ensuring adaptability to heterogeneous clinical populations, fostering equitable and evidence-based implementation of ML-driven predictive analytics in cardiovascular medicine.

Sepsis in silico: definition, development and application of an electronic phenotype for sepsis

Repurposing electronic health record (EHR) or electronic medical record (EMR) data holds significant promise for evidence-based epidemic intelligence and research. Key challenges include sepsis recognition by physicians and issues with EHR and EMR data. Recent advances in data-driven techniques, alongside initiatives like the Surviving Sepsis Campaign and the Severe Sepsis and Septic Shock Management Bundle (SEP-1), have improved sepsis definition, early detection, subtype characterization, prognostication and personalized treatment. This includes identifying potential biomarkers or digital signatures to enhance diagnosis, guide therapy and optimize clinical management. Machine learning applications play a crucial role in identifying biomarkers and digital signatures associated with sepsis and its sub-phenotypes. Additionally, electronic phenotyping, leveraging EHR and EMR data, has emerged as a valuable tool for evidence-based sepsis identification and management. This review examines methods for identifying sepsis cohorts, focusing on two main approaches: utilizing health administrative data with standardized diagnostic coding via the International Classification of Diseases and integrating clinical data. This overview provides a comprehensive analysis of current cohort identification and electronic phenotyping strategies for sepsis, highlighting their potential applications and challenges. The accuracy of an electronic phenotype or signature is pivotal for precision medicine, enabling a shift from subjective clinical descriptions to data-driven insights.

Transforming liver transplant allocation with artificial intelligence and machine learning: a systematic review

BACKGROUND

The principles of urgency, utility, and benefit are fundamental concepts guiding the ethical and practical decision-making process for organ allocation; however, LT allocation still follows an urgency model.

AIM

To identify and analyze data elements used in Machine Learning (ML) and Artificial Intelligence (AI) methods, data sources, and their focus on urgency, utility, or benefit in LT.

METHODS

A comprehensive search across Ovid Medline and Scopus was conducted for studies published from 2002 to June 2023. Inclusion criteria targeted quantitative studies using ML/AI for candidates, donors, or recipients. Two reviewers assessed eligibility and extracted data, following PRISMA guidelines.

RESULTS

A total of 20 papers were included, synthesizing results into five major categories. Eight studies were led by a Spanish team, focusing on donor-recipient matching and proposing machine learning models to predict post- LT survival. Other international studies addressed organ supply-demand issues and developed predictive models to optimize LT outcomes. The studies highlight the potential of ML/AI to enhance LT allocation and outcomes. Despite advancements, limitations included the lack of robust transplant-related benefit models and improvements in urgency models compared to MELD.

DISCUSSION

This review highlighted the potential of AI and ML to enhance liver transplant allocation and outcomes. Significant advancements were noted, but limitations such as the need for better urgency models and the absence of a transplant-related benefit model remain. Most studies emphasized utility, focusing on survival outcomes. Future research should address the interpretability and generalizability of these models to improve organ allocation and post-LT survival predictions.

Assessing the capture of sociodemographic information in electronic medical records to inform clinical decision making

There is a growing need to document sociodemographic factors in electronic medical records to produce representative cohorts for medical research and to perform focused research for potentially vulnerable populations. The objective of this work was to assess the content of family physicians' electronic medical records and characterize the quality of the documentation of sociodemographic characteristics. Descriptive statistics were reported for each sociodemographic characteristic. The association between the completeness rates of the sociodemographic data and the various clinics, electronic medical record vendors, and physician characteristics was analyzed. Supervised machine learning models were used to determine the absence or presence of each characteristic for all adult patients over the age of 18 in the database. Documentation of marital status (51.0%) and occupation (47.2%) were significantly higher compared to the rest of the variables. Race (1.4%), sexual orientation (2.5%), and gender identity (0.8%) had the lowest documentation rates with a 97.5% missingness rate or higher. The correlation analysis for vendor type demonstrated that there was significant variation in the availability of marital and occupation information between vendors (χ2 > 6.0, P < 0.05). Variability in documentation between clinics indicated that the majority of characteristics exhibited high variation in completeness rates with the highest variation for occupation (median: 47.2, interquartile range: 60.6%) and marital status (median: 45.6, interquartile: 59.7%). Finally, physician sex, years since a physician graduated, and whether a physician was a foreign vs a Canadian medical graduate were significantly associated with documentation rates of place of birth, citizenship status, occupation, and education in the electronic medical records. Our findings suggest a crucial need to implement better documentation strategies for sociodemographic information in the healthcare setting. To improve completeness rates, healthcare systems should monitor, encourage, enforce, or incentivize sociodemographic data collection standards.

Implementation of a genotyped African population cohort, with virtual follow-up: A feasibility study in the Western Cape Province, South Africa

Background

There is limited knowledge regarding African genetic drivers of disease due to prohibitive costs of large-scale genomic research in Africa.

Methods

We piloted a scalable virtual genotyped cohort in South Africa that was affordable in this resource-limited context, cost-effective, scalable virtual genotyped cohort in South Africa, with participant recruitment using a tiered informed consent model and DNA collection by buccal swab. Genotype data was generated using the H3Africa Illumina micro-array, and phenotype data was derived from routine health data of participants. We demonstrated feasibility of nested case control genome wide association studies using these data for phenotypes type 2 diabetes mellitus (T2DM) and severe COVID-19.

Results

2267346 variants were analysed in 459 participant samples, of which 229 (66.8%) are female. 78.6% of SNPs and 74% of samples passed quality control (QC). Principal component analysis showed extensive ancestry admixture in study participants. Of the 343 samples that passed QC, 93 participants had T2DM and 63 had severe COVID-19. For 1780 previously published COVID-19-associated variants, 3 SNPs in the pre-imputation data and 23 SNPS in the imputed data were significantly associated with severe COVID-19 cases compared to controls (p<0.05). For 2755 published T2DM associated variants, 69 SNPs in the pre-imputation data and 419 SNPs in the imputed data were significantly associated with T2DM cases when compared to controls (p<0.05).

Conclusions

The results shown here are illustrative of what will be possible as the cohort expands in the future. Here we demonstrate the feasibility of this approach, recognising that the findings presented here are preliminary and require further validation once we have a sufficient sample size to improve statistical significance of findings.We implemented a genotyped population cohort with virtual follow up data in a resource-constrained African environment, demonstrating feasibility for scale up and novel health discoveries through nested case-control studies.

A Dynamic Time Warping Extension to Consensus Weight-Based Cachexia Criteria Improves Prediction of Cancer Patient Outcomes

Background

Cachexia is a complex syndrome that impacts up to half of patients with cancer. Criteria systems have been developed for the purpose of diagnosing and grading cachexia severity in clinical settings. One of the most widely known is those developed by Fearon et al. in 2011, which utilizes body mass loss and body mass index (BMI) to determine the presence and extent of cachexia. One limitation of this system and other clinical cachexia scales is the lack of systematic methods for assessing cachexia severity longitudinally. We sought to develop an extension to the 2011 consensus criteria that categorizes cancer patients with respect to their temporal cachexia progression and assess its predictive capacity relative to the current time-agnostic system.

Methods

Two cancer cohorts were identified in electronic health record data: lung cancer and glioblastoma. We extracted weight and BMI measures from the time of cancer diagnosis until death or loss to follow-up and computed cachexia severity according to the consensus criteria. Subgroups of cachexia progression were uncovered using dynamic time warping (DTW) followed by unsupervised clustering. This system and baseline consensus criteria measurements were each assessed for their ability to stratify patient outcomes utilizing Kaplan-Meier curves and Cox proportional hazards and subsequently compared with model concordance and inverse probability of censoring weighting (IPCW).

Results

Significant differences were observed in overall survival Kaplan-Meier curves of 1023 patients with lung cancer when stratified by baseline cachexia classification (p = 0.0002, N events = 592) but not in a cohort of 545 patients with glioblastoma (p = 0.16, N events = 353). DTW uncovered three patterns of cachexia progression in each subgroup with features described as 'smouldering', 'rapid with recovery' or 'persistent/recurrent'. Significant differences were observed in Kaplan-Meier curves when stratified by cachexia longitudinal patterns in lung cancer (p < 0.0001) and glioblastoma (p < 0.0001). Adjusted hazards ratios comparing the 'persistent/recurrent' cluster to referent subgroups in Cox models were 4.8 (4.1-5.8, p < 0.05) and 1.9 (1.4-2.4, p < 0.05) among patients with lung cancer and glioblastoma, respectively. Areas under the curve at multiple time points and Cox model concordances were greater when patients were stratified by progression pattern compared with baseline consensus criteria.

Conclusions

Our results suggest that accounting for cachexia's longitudinal progression in a systematic way can improve upon the prognostic capacity of a widely used consensus criteria set. These findings are important for the future development of systems that recognize concerning patterns of cachexia progression in clinical settings and aid clinicians in cachexia-related decision making.

Pharmacogenetics: Opportunities for the All of Us Research Program and Other Large Data Sets to Advance the Field

Pharmacogenetic variation is common and an established driver of response for many drugs. There has been tremendous progress in pharmacogenetics knowledge over the last 30 years and in clinical implementation of that knowledge over the last 15 years. But there have also been many examples where translation has stalled because of the lack of available data sets for discovery or validation research. The recent availability of data from very large cohorts with linked genetic, electronic health record, and other data promises new opportunities to advance pharmacogenetics research. This review presents the stages from pharmacogenetics discovery to widespread clinical adoption using prominent gene-drug pairs that have been implemented into clinical practice as examples. We discuss the opportunities that the All of Us Research Program and other large biorepositories with genomic and linked electronic health record data present in advancing and accelerating the translation of pharmacogenetics into clinical practice.

With big data comes big responsibility: Strategies for utilizing aggregated, standardized, de-identified electronic health record data for research

Electronic health records (EHRs), though they are maintained and utilized for clinical and billing purposes, may provide a wealth of information for research. Currently, sources are available that offer insight into the health histories of well over a quarter of a billion people. Their use, however, is fraught with hazards, including introduction or reinforcement of biases, clarity of disease definitions, protection of patient privacy, definitions of covariates or confounders, accuracy of medication usage compared with prescriptions, the need to introduce other data sources such as vaccination or death records and the ensuing potential for inaccuracy, duplicative records, and understanding and interpreting the outcomes of data queries. On the other hand, the possibility of study of rare disorders or the ability to link apparently disparate events are extremely valuable. Strategies for avoiding the worst pitfalls and hewing to conservative interpretations are essential. This article summarizes many of the approaches that have been used to avoid the most common pitfalls and extract the maximum information from aggregated, standardized, and de-identified EHR data. This article describes 26 topics broken into three major areas: (1) 14 topics related to design issues for observational study using EHR data, (2) 7 topics related to analysis issues when analyzing EHR data, and (3) 5 topics related to reporting studies using EHR data.

Multisource representation learning for pediatric knowledge extraction from electronic health records

Electronic Health Record (EHR) systems are particularly valuable in pediatrics due to high barriers in clinical studies, but pediatric EHR data often suffer from low content density. Existing EHR code embeddings tailored for the general patient population fail to address the unique needs of pediatric patients. To bridge this gap, we introduce a transfer learning approach, MUltisource Graph Synthesis (MUGS), aimed at accurate knowledge extraction and relation detection in pediatric contexts. MUGS integrates graphical data from both pediatric and general EHR systems, along with hierarchical medical ontologies, to create embeddings that adaptively capture both the homogeneity and heterogeneity between hospital systems. These embeddings enable refined EHR feature engineering and nuanced patient profiling, proving particularly effective in identifying pediatric patients similar to specific profiles, with a focus on pulmonary hypertension (PH). MUGS embeddings, resistant to negative transfer, outperform other benchmark methods in multiple applications, advancing evidence-based pediatric research.

Development and validation of an electronic health record-based algorithm for identifying TBI in the VA: A VA Million Veteran Program study

The purpose of this study was to develop and validate an algorithm for identifying Veterans with a history of traumatic brain injury (TBI) in the Veterans Affairs (VA) electronic health record using VA Million Veteran Program (MVP) data. Manual chart review (n = 200) was first used to establish 'gold standard' diagnosis labels for TBI ('Yes TBI' vs. 'No TBI'). To develop our algorithm, we used PheCAP, a semi-supervised pipeline that relied on the chart review diagnosis labels to train and create a prediction model for TBI. Cross-validation was used to train and evaluate the proposed algorithm, 'TBI-PheCAP.' TBI-PheCAP performance was compared to existing TBI algorithms and phenotyping methods, and the final algorithm was run on all MVP participants (n = 702,740) to assign a predicted probability for TBI and a binary classification status choosing specificity = 90%. The TBI-PheCAP algorithm had an area under the receiver operating characteristic curve of 0.92, sensitivity of 84%, and positive predictive value (PPV) of 98% at specificity = 90%. TBI-PheCAP generally performed better than other classification methods, with equivalent or higher sensitivity and PPV than existing rules-based TBI algorithms and MVP TBI-related survey data. Given its strong classification metrics, the TBI-PheCAP algorithm is recommended for use in future population-based TBI research.

A retrospective analysis using comorbidity detecting algorithmic software to determine the incidence of International Classification of Diseases (ICD) code omissions and appropriateness of Diagnosis-Related Group (DRG) code modifiers

BACKGROUND

The mechanism for recording International Classification of Diseases (ICD) and diagnosis related groups (DRG) codes in a patient's chart is through a certified medical coder who manually reviews the medical record at the completion of an admission. High-acuity ICD codes justify DRG modifiers, indicating the need for escalated hospital resources. In this manuscript, we demonstrate that value of rules-based computer algorithms that audit for omission of administrative codes and quantifying the downstream effects with regard to financial impacts and demographic findings did not indicate significant disparities.

METHODS

All study data were acquired via the UCLA Department of Anesthesiology and Perioperative Medicine's Perioperative Data Warehouse. The DataMart is a structured reporting schema that contains all the relevant clinical data entered into the EPIC (EPIC Systems, Verona, WI) electronic health record. Computer algorithms were created for eighteen disease states that met criteria for DRG modifiers. Each algorithm was run against all hospital admissions with completed billing from 2019. The algorithms scanned for the existence of disease, appropriate ICD coding, and DRG modifier appropriateness. Secondarily, the potential financial impact of ICD omissions was estimated by payor class and an analysis of ICD miscoding was done by ethnicity, sex, age, and financial class.

RESULTS

Data from 34,104 hospital admissions were analyzed from January 1, 2019, to December 31, 2019. 11,520 (32.9%) hospital admissions were algorithm positive for a disease state with no corresponding ICD code. 1,990 (5.8%) admissions were potentially eligible for DRG modification/upgrade with an estimated lost revenue of $22,680,584.50. ICD code omission rates compared against reference groups (private payors, Caucasians, middle-aged patients) demonstrated significant p-values < 0.05; similarly significant p-value where demonstrated when comparing patients of opposite sexes.

CONCLUSIONS

We successfully used rules-based algorithms and raw structured EHR data to identify omitted ICD codes from inpatient medical record claims. These missing ICD codes often had downstream effects such as inaccurate DRG modifiers and missed reimbursement. Embedding augmented intelligence into this problematic workflow has the potential for improvements in administrative data, but more importantly, improvements in administrative data accuracy and financial outcomes.

Genetic architecture of routinely acquired blood tests in a British South Asian cohort

Understanding the genetic basis of routinely-acquired blood tests can provide insights into several aspects of human physiology. We report a genome-wide association study of 42 quantitative blood test traits defined using Electronic Healthcare Records (EHRs) of ~50,000 British Bangladeshi and British Pakistani adults. We demonstrate a causal variant within the PIEZO1 locus which was associated with alterations in red cell traits and glycated haemoglobin. Conditional analysis and within-ancestry fine mapping confirmed that this signal is driven by a missense variant - chr16-88716656-G-TT - which is common in South Asian ancestries (MAF 3.9%) but ultra-rare in other ancestries. Carriers of the T allele had lower mean HbA1c values, lower HbA1c values for a given level of random or fasting glucose, and delayed diagnosis of Type 2 Diabetes Mellitus. Our results shed light on the genetic basis of clinically-relevant traits in an under-represented population, and emphasise the importance of ancestral diversity in genetic studies.

Phenome-wide association study in 25,639 pregnant Chinese women reveals loci associated with maternal comorbidities and child health

Phenome-wide association studies (PheWAS) have been less focused on maternal diseases and maternal-newborn comorbidities, especially in the Chinese population. To enhance our understanding of the genetic basis of these related diseases, we conducted a PheWAS on 25,639 pregnant women and 14,151 newborns in the Chinese Han population using ultra-low-coverage whole-genome sequence (ulcWGS). We identified 2,883 maternal trait-associated SNPs associated with 26 phenotypes, among which 99.5% were near established genome-wide association study (GWAS) loci. Further refinement delineated these SNPs to 442 unique trait-associated loci (TALs) predicated on linkage disequilibrium R2 > 0.8, revealing that 75.6% demonstrated pleiotropy and 50.9% were located in genes implicated in analogous phenotypes. Notably, we discovered 21 maternal SNPs associated with 35 neonatal phenotypes, including two SNPs associated with identical complications in both mothers and children. These findings underscore the importance of integrating ulcWGS data to enrich the discoveries derived from traditional PheWAS approaches.

Derivation and validation of generalized sepsis-induced acute respiratory failure phenotypes among critically ill patients: a retrospective study

BACKGROUND

Septic patients who develop acute respiratory failure (ARF) requiring mechanical ventilation represent a heterogenous subgroup of critically ill patients with widely variable clinical characteristics. Identifying distinct phenotypes of these patients may reveal insights about the broader heterogeneity in the clinical course of sepsis, considering multi-organ dynamics. We aimed to derive novel phenotypes of sepsis-induced ARF using observational clinical data and investigate the generalizability of the derived phenotypes.

METHODS

We performed a multi-center retrospective study of ICU patients with sepsis who required mechanical ventilation for ≥ 24 h. Data from two different high-volume academic hospital centers were used, where all phenotypes were derived in MICU of Hospital-I (N = 3225). The derived phenotypes were validated in MICU of Hospital-II (N = 848), SICU of Hospital-I (N = 1112), and SICU of Hospital-II (N = 465). Clinical data from 24 h preceding intubation was used to derive distinct phenotypes using an explainable machine learning-based clustering model interpreted by clinical experts.

RESULTS

Four distinct ARF phenotypes were identified: A (severe multi-organ dysfunction (MOD) with a high likelihood of kidney injury and heart failure), B (severe hypoxemic respiratory failure [median P/F = 123]), C (mild hypoxia [median P/F = 240]), and D (severe MOD with a high likelihood of hepatic injury, coagulopathy, and lactic acidosis). Patients in each phenotype showed differences in clinical course and mortality rates despite similarities in demographics and admission co-morbidities. The phenotypes were reproduced in external validation utilizing the MICU of Hospital-II and SICUs from Hospital-I and -II. Kaplan-Meier analysis showed significant difference in 28-day mortality across the phenotypes (p < 0.01) and consistent across MICU and SICU of both Hospital-I and -II. The phenotypes demonstrated differences in treatment effects associated with high positive end-expiratory pressure (PEEP) strategy.

CONCLUSION

The phenotypes demonstrated unique patterns of organ injury and differences in clinical outcomes, which may help inform future research and clinical trial design for tailored management strategies.

Clinical risk prediction using language models: benefits and considerations

OBJECTIVE

The use of electronic health records (EHRs) for clinical risk prediction is on the rise. However, in many practical settings, the limited availability of task-specific EHR data can restrict the application of standard machine learning pipelines. In this study, we investigate the potential of leveraging language models (LMs) as a means to incorporate supplementary domain knowledge for improving the performance of various EHR-based risk prediction tasks.

METHODS

We propose two novel LM-based methods, namely "LLaMA2-EHR" and "Sent-e-Med." Our focus is on utilizing the textual descriptions within structured EHRs to make risk predictions about future diagnoses. We conduct a comprehensive comparison with previous approaches across various data types and sizes.

RESULTS

Experiments across 6 different methods and 3 separate risk prediction tasks reveal that employing LMs to represent structured EHRs, such as diagnostic histories, results in significant performance improvements when evaluated using standard metrics such as area under the receiver operating characteristic (ROC) curve and precision-recall (PR) curve. Additionally, they offer benefits such as few-shot learning, the ability to handle previously unseen medical concepts, and adaptability to various medical vocabularies. However, it is noteworthy that outcomes may exhibit sensitivity to a specific prompt.

CONCLUSION

LMs encompass extensive embedded knowledge, making them valuable for the analysis of EHRs in the context of risk prediction. Nevertheless, it is important to exercise caution in their application, as ongoing safety concerns related to LMs persist and require continuous consideration.

The role of blockchain to secure internet of medical things

This study explores integrating blockchain technology into the Internet of Medical Things (IoMT) to address security and privacy challenges. Blockchain's transparency, confidentiality, and decentralization offer significant potential benefits in the healthcare domain. The research examines various blockchain components, layers, and protocols, highlighting their role in IoMT. It also explores IoMT applications, security challenges, and methods for integrating blockchain to enhance security. Blockchain integration can be vital in securing and managing this data while preserving patient privacy. It also opens up new possibilities in healthcare, medical research, and data management. The results provide a practical approach to handling a large amount of data from IoMT devices. This strategy makes effective use of data resource fragmentation and encryption techniques. It is essential to have well-defined standards and norms, especially in the healthcare sector, where upholding safety and protecting the confidentiality of information are critical. These results illustrate that it is essential to follow standards like HIPAA, and blockchain technology can help ensure these criteria are met. Furthermore, the study explores the potential benefits of blockchain technology for enhancing inter-system communication in the healthcare industry while maintaining patient privacy protection. The results highlight the effectiveness of blockchain's consistency and cryptographic techniques in combining identity management and healthcare data protection, protecting patient privacy and data integrity. Blockchain is an unchangeable distributed ledger system. In short, the paper provides important insights into how blockchain technology may transform the healthcare industry by effectively addressing significant challenges and generating legal, safe, and interoperable solutions. Researchers, doctors, and graduate students are the audience for our paper.

Using electronic health records for clinical pharmacology research: Challenges and considerations

Electronic health records (EHRs) contain a vast array of phenotypic data on large numbers of individuals, often collected over decades. Due to the wealth of information, EHR data have emerged as a powerful resource to make first discoveries and identify disparities in our healthcare system. While the number of EHR-based studies has exploded in recent years, most of these studies are directed at associations with disease rather than pharmacotherapeutic outcomes, such as drug response or adverse drug reactions. This is largely due to challenges specific to deriving drug-related phenotypes from the EHR. There is great potential for EHR-based discovery in clinical pharmacology research, and there is a critical need to address specific challenges related to accurate and reproducible derivation of drug-related phenotypes from the EHR. This review provides a detailed evaluation of challenges and considerations for deriving drug-related data from EHRs. We provide an examination of EHR-based computable phenotypes and discuss cutting-edge approaches to map medication information for clinical pharmacology research, including medication-based computable phenotypes and natural language processing. We also discuss additional considerations such as data structure, heterogeneity and missing data, rare phenotypes, and diversity within the EHR. By further understanding the complexities associated with conducting clinical pharmacology research using EHR-based data, investigators will be better equipped to design thoughtful studies with more reproducible results. Progress in utilizing EHRs for clinical pharmacology research should lead to significant advances in our ability to understand differential drug response and predict adverse drug reactions.

Variations in Electronic Health Record-Based Definitions of Diabetic Retinopathy Cohorts: A Literature Review and Quantitative Analysis

Purpose

Use of the electronic health record (EHR) has motivated the need for data standardization. A gap in knowledge exists regarding variations in existing terminologies for defining diabetic retinopathy (DR) cohorts. This study aimed to review the literature and analyze variations regarding codified definitions of DR.

Design

Literature review and quantitative analysis.

Subjects

Published manuscripts.

Methods

Four graders reviewed PubMed and Google Scholar for peer-reviewed studies. Studies were included if they used codified definitions of DR (e.g., billing codes). Data elements such as author names, publication year, purpose, data set type, and DR definitions were manually extracted. Each study was reviewed by ≥ 2 authors to validate inclusion eligibility. Quantitative analyses of the codified definitions were then performed to characterize the variation between DR cohort definitions.

Main Outcome Measures

Number of studies included and numeric counts of billing codes used to define codified cohorts.

Results

In total, 43 studies met the inclusion criteria. Half of the included studies used datasets based on structured EHR data (i.e., data registries, institutional EHR review), and half used claims data. All but 1 of the studies used billing codes such as the International Classification of Diseases 9th or 10th edition (ICD-9 or ICD-10), either alone or in addition to another terminology for defining disease. Of the 27 included studies that used ICD-9 and the 20 studies that used ICD-10 codes, the most common codes used pertained to the full spectrum of DR severity. Diabetic retinopathy complications (e.g., vitreous hemorrhage) were also used to define some DR cohorts.

Conclusions

Substantial variations exist among codified definitions for DR cohorts within retrospective studies. Variable definitions may limit generalizability and reproducibility of retrospective studies. More work is needed to standardize disease cohorts.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Identifying prehospital trauma patients from ambulance patient care records; comparing two methods using linked data in New South Wales, Australia

BACKGROUND

Linked datasets for trauma system monitoring should ideally follow patients from the prehospital scene to hospital admission and post-discharge. Having a well-defined cohort when using administrative datasets is essential because they must capture the representative population. Unlike hospital electronic health records (EHR), ambulance patient-care records lack access to sources beyond immediate clinical notes. Relying on a limited set of variables to define a study population might result in missed patient inclusion. We aimed to compare two methods of identifying prehospital trauma patients: one using only those documented under a trauma protocol and another incorporating additional data elements from ambulance patient care records.

METHODS

We analyzed data from six routinely collected administrative datasets from 2015 to 2018, including ambulance patient-care records, aeromedical data, emergency department visits, hospitalizations, rehabilitation outcomes, and death records. Three prehospital trauma cohorts were created: an Extended-T-protocol cohort (patients transported under a trauma protocol and/or patients with prespecified criteria from structured data fields), T-protocol cohort (only patients documented as transported under a trauma protocol) and non-T-protocol (extended-T-protocol population not in the T-protocol cohort). Patient-encounter characteristics, mortality, clinical and post-hospital discharge outcomes were compared. A conservative p-value of 0.01 was considered significant RESULTS: Of 1 038 263 patient-encounters included in the extended-T-population 814 729 (78.5 %) were transported, with 438 893 (53.9 %) documented as a T-protocol patient. Half (49.6 %) of the non-T-protocol sub-cohort had an International Classification of Disease 10th edition injury or external cause code, indicating 79644 missed patients when a T-protocol-only definition was used. The non-T-protocol sub-cohort also identified additional patients with intubation, prehospital blood transfusion and positive eFAST. A higher proportion of non-T protocol patients than T-protocol patients were admitted to the ICU (4.6% vs 3.6 %), ventilated (1.8% vs 1.3 %), received in-hospital transfusion (7.9 vs 6.8 %) or died (1.8% vs 1.3 %). Urgent trauma surgery was similar between groups (1.3% vs 1.4 %).

CONCLUSION

The extended-T-population definition identified 50 % more admitted patients with an ICD-10-AM code consistent with an injury, including patients with severe trauma. Developing an EHR phenotype incorporating multiple data fields of ambulance-transported trauma patients for use with linked data may avoid missing these patients.

Optimising the use of electronic medical records for large scale research in psychiatry

The explosion and abundance of digital data could facilitate large-scale research for psychiatry and mental health. Research using so-called "real world data"-such as electronic medical/health records-can be resource-efficient, facilitate rapid hypothesis generation and testing, complement existing evidence (e.g. from trials and evidence-synthesis) and may enable a route to translate evidence into clinically effective, outcomes-driven care for patient populations that may be under-represented. However, the interpretation and processing of real-world data sources is complex because the clinically important 'signal' is often contained in both structured and unstructured (narrative or "free-text") data. Techniques for extracting meaningful information (signal) from unstructured text exist and have advanced the re-use of routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey the opportunities, risks and progress made in the use of electronic medical record (real-world) data for psychiatric research.

Clarifying Chronic Obstructive Pulmonary Disease Genetic Associations Observed in Biobanks via Mediation Analysis of Smoking

Varying case definitions of COPD have heterogenous genetic risk profiles, potentially reflective of disease subtypes or classification bias (e.g., smokers more likely to be diagnosed with COPD). To better understand differences in genetic loci associated with ICD-defined versus spirometry-defined COPD we contrasted their GWAS results with those for heavy smoking among 337,138 UK Biobank participants. Overlapping risk loci were found in/near the genes ZEB2, FAM136B, CHRNA3, and CHRNA4, with the CHRNA3 locus shared across all three traits. Mediation analysis to estimate the effects of lead genotyped variants mediated by smoking found significant indirect effects for the FAM136B, CHRNA3, and CHRNA4 loci for both COPD definitions. Adjustment for mediator-outcome confounders modestly attenuated indirect effects, though in the CHRNA4 locus for spirometry-defined COPD the proportion mediated increased an additional 8.47%. Our results suggest that differences between ICD-defined and spirometry-defined COPD associated genetic loci are not a result of smoking biasing classification.

Overview and Clinical Applications of Artificial Intelligence and Machine Learning in Cardiac Anesthesiology

Artificial intelligence- (AI) and machine learning (ML)-based applications are becoming increasingly pervasive in the healthcare setting. This has in turn challenged clinicians, hospital administrators, and health policymakers to understand such technologies and develop frameworks for safe and sustained clinical implementation. Within cardiac anesthesiology, challenges and opportunities for AI/ML to support patient care are presented by the vast amounts of electronic health data, which are collected rapidly, interpreted, and acted upon within the periprocedural area. To address such challenges and opportunities, in this article, the authors review 3 recent applications relevant to cardiac anesthesiology, including depth of anesthesia monitoring, operating room resource optimization, and transthoracic/transesophageal echocardiography, as conceptual examples to explore strengths and limitations of AI/ML within healthcare, and characterize this evolving landscape. Through reviewing such applications, the authors introduce basic AI/ML concepts and methodologies, as well as practical considerations and ethical concerns for initiating and maintaining safe clinical implementation of AI/ML-based algorithms for cardiac anesthesia patient care.

A novel method for multiple phenotype association studies based on genotype and phenotype network

Joint analysis of multiple correlated phenotypes for genome-wide association studies (GWAS) can identify and interpret pleiotropic loci which are essential to understand pleiotropy in diseases and complex traits. Meanwhile, constructing a network based on associations between phenotypes and genotypes provides a new insight to analyze multiple phenotypes, which can explore whether phenotypes and genotypes might be related to each other at a higher level of cellular and organismal organization. In this paper, we first develop a bipartite signed network by linking phenotypes and genotypes into a Genotype and Phenotype Network (GPN). The GPN can be constructed by a mixture of quantitative and qualitative phenotypes and is applicable to binary phenotypes with extremely unbalanced case-control ratios in large-scale biobank datasets. We then apply a powerful community detection method to partition phenotypes into disjoint network modules based on GPN. Finally, we jointly test the association between multiple phenotypes in a network module and a single nucleotide polymorphism (SNP). Simulations and analyses of 72 complex traits in the UK Biobank show that multiple phenotype association tests based on network modules detected by GPN are much more powerful than those without considering network modules. The newly proposed GPN provides a new insight to investigate the genetic architecture among different types of phenotypes. Multiple phenotypes association studies based on GPN are improved by incorporating the genetic information into the phenotype clustering. Notably, it might broaden the understanding of genetic architecture that exists between diagnoses, genes, and pleiotropy.

Derivation and Validation of Generalized Sepsis-induced Acute Respiratory Failure Phenotypes Among Critically Ill Patients: A Retrospective Study

Background

Septic patients who develop acute respiratory failure (ARF) requiring mechanical ventilation represent a heterogenous subgroup of critically ill patients with widely variable clinical characteristics. Identifying distinct phenotypes of these patients may reveal insights about the broader heterogeneity in the clinical course of sepsis. We aimed to derive novel phenotypes of sepsis-induced ARF using observational clinical data and investigate their generalizability across multi-ICU specialties, considering multi-organ dynamics.

Methods

We performed a multi-center retrospective study of ICU patients with sepsis who required mechanical ventilation for ≥24 hours. Data from two different high-volume academic hospital systems were used as a derivation set with N=3,225 medical ICU (MICU) patients and a validation set with N=848 MICU patients. For the multi-ICU validation, we utilized retrospective data from two surgical ICUs at the same hospitals (N=1,577). Clinical data from 24 hours preceding intubation was used to derive distinct phenotypes using an explainable machine learning-based clustering model interpreted by clinical experts.

Results

Four distinct ARF phenotypes were identified: A (severe multi-organ dysfunction (MOD) with a high likelihood of kidney injury and heart failure), B (severe hypoxemic respiratory failure [median P/F=123]), C (mild hypoxia [median P/F=240]), and D (severe MOD with a high likelihood of hepatic injury, coagulopathy, and lactic acidosis). Patients in each phenotype showed differences in clinical course and mortality rates despite similarities in demographics and admission co-morbidities. The phenotypes were reproduced in external validation utilizing an external MICU from second hospital and SICUs from both centers. Kaplan-Meier analysis showed significant difference in 28-day mortality across the phenotypes (p<0.01) and consistent across both centers. The phenotypes demonstrated differences in treatment effects associated with high positive end-expiratory pressure (PEEP) strategy.

Conclusion

The phenotypes demonstrated unique patterns of organ injury and differences in clinical outcomes, which may help inform future research and clinical trial design for tailored management strategies.

Classifying early infant feeding status from clinical notes using natural language processing and machine learning

The objective of this study is to develop and evaluate natural language processing (NLP) and machine learning models to predict infant feeding status from clinical notes in the Epic electronic health records system. The primary outcome was the classification of infant feeding status from clinical notes using Medical Subject Headings (MeSH) terms. Annotation of notes was completed using TeamTat to uniquely classify clinical notes according to infant feeding status. We trained 6 machine learning models to classify infant feeding status: logistic regression, random forest, XGBoost gradient descent, k-nearest neighbors, and support-vector classifier. Model comparison was evaluated based on overall accuracy, precision, recall, and F1 score. Our modeling corpus included an even number of clinical notes that was a balanced sample across each class. We manually reviewed 999 notes that represented 746 mother-infant dyads with a mean gestational age of 38.9 weeks and a mean maternal age of 26.6 years. The most frequent feeding status classification present for this study was exclusive breastfeeding [n = 183 (18.3%)], followed by exclusive formula bottle feeding [n = 146 (14.6%)], and exclusive feeding of expressed mother's milk [n = 102 (10.2%)], with mixed feeding being the least frequent [n = 23 (2.3%)]. Our final analysis evaluated the classification of clinical notes as breast, formula/bottle, and missing. The machine learning models were trained on these three classes after performing balancing and down sampling. The XGBoost model outperformed all others by achieving an accuracy of 90.1%, a macro-averaged precision of 90.3%, a macro-averaged recall of 90.1%, and a macro-averaged F1 score of 90.1%. Our results demonstrate that natural language processing can be applied to clinical notes stored in the electronic health records to classify infant feeding status. Early identification of breastfeeding status using NLP on unstructured electronic health records data can be used to inform precision public health interventions focused on improving lactation support for postpartum patients.

Trends in publication and levels of social determinants of health reporting in Journal of Clinical and Translational Science from 2017 to 2023

Social determinants of health affect clinical and translational research processes and outcomes but remain underreported in empirical studies. This scoping review examined the rate and types of social determinants of health (SDoH) variables included in the JCTS translational research studies published between 2017 and 2023 and included 129 studies. Most papers (91.7%) reported at least one SDoH variable with age, race and ethnicity, and sex included most often. Future studies to inform the role of SDoH data in translational research and science are recommended, and a draft SDoH data checklist is provided.

Biases in Electronic Health Records Data for Generating Real-World Evidence: An Overview

Electronic Health Records (EHR) are increasingly being perceived as a unique source of data for clinical research as they provide unprecedentedly large volumes of real-time data from real-world settings. In this review of the secondary uses of EHR, we identify the anticipated breadth of opportunities, pointing out the data deficiencies and potential biases that are likely to limit the search for true causal relationships. This paper provides a comprehensive overview of the types of biases that arise along the pathways that generate real-world evidence and the sources of these biases. We distinguish between two levels in the production of EHR data where biases are likely to arise: (i) at the healthcare system level, where the principal source of bias resides in access to, and provision of, medical care, and in the acquisition and documentation of medical and administrative data; and (ii) at the research level, where biases arise from the processes of extracting, analyzing, and interpreting these data. Due to the plethora of biases, mainly in the form of selection and information bias, we conclude with advising extreme caution about making causal inferences based on secondary uses of EHRs.

Performance Characteristics of a Rule-Based Electronic Health Record Algorithm to Identify Patients with Gross and Microscopic Hematuria

BACKGROUND

Two million patients per year are referred to urologists for hematuria, or blood in the urine. The American Urological Association recently adopted a risk-stratified hematuria evaluation guideline to limit multi-phase computed tomography to individuals at highest risk of occult malignancy.

OBJECTIVES

To understand population-level hematuria evaluations, we developed an algorithm to accurately identify hematuria cases from electronic health records (EHRs).

METHODS

We used International Classification of Diseases (ICD)-9/ICD-10 diagnosis codes, urine color, and urine microscopy values to identify hematuria cases and to differentiate between gross and microscopic hematuria. Using an iterative process, we refined the ICD-9 algorithm on a gold standard, chart-reviewed cohort of 3,094 hematuria cases, and the ICD-10 algorithm on a 300 patient cohort. We applied the algorithm to Geisinger patients ≥35 years (n = 539,516) and determined performance by conducting chart review (n = 500).

RESULTS

After applying the hematuria algorithm, we identified 51,500 hematuria cases and 488,016 clean controls. Of the hematuria cases, 11,435 were categorized as gross, 26,658 as microscopic, 12,562 as indeterminate, and 845 were uncategorized. The positive predictive value (PPV) of identifying hematuria cases using the algorithm was 100% and the negative predictive value (NPV) was 99%. The gross hematuria algorithm had a PPV of 100% and NPV of 99%. The microscopic hematuria algorithm had lower PPV of 78% and NPV of 100%.

CONCLUSION

We developed an algorithm utilizing diagnosis codes and urine laboratory values to accurately identify hematuria and categorize as gross or microscopic in EHRs. Applying the algorithm will help researchers to understand patterns of care for this common condition.

OMICmAge: An integrative multi-omics approach to quantify biological age with electronic medical records

Biological aging is a multifactorial process involving complex interactions of cellular and biochemical processes that is reflected in omic profiles. Using common clinical laboratory measures in ~30,000 individuals from the MGB-Biobank, we developed a robust, predictive biological aging phenotype, EMRAge, that balances clinical biomarkers with overall mortality risk and can be broadly recapitulated across EMRs. We then applied elastic-net regression to model EMRAge with DNA-methylation (DNAm) and multiple omics, generating DNAmEMRAge and OMICmAge, respectively. Both biomarkers demonstrated strong associations with chronic diseases and mortality that outperform current biomarkers across our discovery (MGB-ABC, n=3,451) and validation (TruDiagnostic, n=12,666) cohorts. Through the use of epigenetic biomarker proxies, OMICmAge has the unique advantage of expanding the predictive search space to include epigenomic, proteomic, metabolomic, and clinical data while distilling this in a measure with DNAm alone, providing opportunities to identify clinically-relevant interconnections central to the aging process.

Association Between Fuchs Endothelial Corneal Dystrophy, Diabetes Mellitus, and Multimorbidity

PURPOSE

The aim of this study was to assess risk for demographic variables and other health conditions that are associated with Fuchs endothelial corneal dystrophy (FECD).

METHODS

We developed a FECD case-control algorithm based on structured electronic health record data and confirmed accuracy by individual review of charts at 3 Veterans Affairs (VA) Medical Centers. This algorithm was applied to the Department of VA Million Veteran Program cohort from whom sex, genetic ancestry, comorbidities, diagnostic phecodes, and laboratory values were extracted. Single-variable and multiple variable logistic regression models were used to determine the association of these risk factors with FECD diagnosis.

RESULTS

Being a FECD case was associated with female sex, European genetic ancestry, and a greater number of comorbidities. Of 1417 diagnostic phecodes evaluated, 213 had a significant association with FECD, falling in both ocular and nonocular conditions, including diabetes mellitus (DM). Five of 69 laboratory values were associated with FECD, with the direction of change for 4 being consistent with DM. Insulin dependency and type 1 DM raised risk to a greater degree than type 2 DM, like other microvascular diabetic complications.

CONCLUSIONS

Female sex, European ancestry, and multimorbidity increased FECD risk. Endocrine/metabolic clinic encounter codes and altered patterns of laboratory values support DM increasing FECD risk. Our results evoke a threshold model in which the FECD phenotype is intensified by DM and potentially other health conditions that alter corneal physiology. Further studies to better understand the relationship between FECD and DM are indicated and may help identify opportunities for slowing FECD progression.

Evaluating construct validity of computable acute respiratory distress syndrome definitions in adults hospitalized with COVID-19: an electronic health records based approach

BACKGROUND

Evolving ARDS epidemiology and management during COVID-19 have prompted calls to reexamine the construct validity of Berlin criteria, which have been rarely evaluated in real-world data. We developed a Berlin ARDS definition (EHR-Berlin) computable in electronic health records (EHR) to (1) assess its construct validity, and (2) assess how expanding its criteria affected validity.

METHODS

We performed a retrospective cohort study at two tertiary care hospitals with one EHR, among adults hospitalized with COVID-19 February 2020-March 2021. We assessed five candidate definitions for ARDS: the EHR-Berlin definition modeled on Berlin criteria, and four alternatives informed by recent proposals to expand criteria and include patients on high-flow oxygen (EHR-Alternative 1), relax imaging criteria (EHR-Alternatives 2-3), and extend timing windows (EHR-Alternative 4). We evaluated two aspects of construct validity for the EHR-Berlin definition: (1) criterion validity: agreement with manual ARDS classification by experts, available in 175 patients; (2) predictive validity: relationships with hospital mortality, assessed by Pearson r and by area under the receiver operating curve (AUROC). We assessed predictive validity and timing of identification of EHR-Berlin definition compared to alternative definitions.

RESULTS

Among 765 patients, mean (SD) age was 57 (18) years and 471 (62%) were male. The EHR-Berlin definition classified 171 (22%) patients as ARDS, which had high agreement with manual classification (kappa 0.85), and was associated with mortality (Pearson r = 0.39; AUROC 0.72, 95% CI 0.68, 0.77). In comparison, EHR-Alternative 1 classified 219 (29%) patients as ARDS, maintained similar relationships to mortality (r = 0.40; AUROC 0.74, 95% CI 0.70, 0.79, Delong test P = 0.14), and identified patients earlier in their hospitalization (median 13 vs. 15 h from admission, Wilcoxon signed-rank test P < 0.001). EHR-Alternative 3, which removed imaging criteria, had similar correlation (r = 0.41) but better discrimination for mortality (AUROC 0.76, 95% CI 0.72, 0.80; P = 0.036), and identified patients median 2 h (P < 0.001) from admission.

CONCLUSIONS

The EHR-Berlin definition can enable ARDS identification with high criterion validity, supporting large-scale study and surveillance. There are opportunities to expand the Berlin criteria that preserve predictive validity and facilitate earlier identification.

Leveraging electronic health record data for endometriosis research

Endometriosis is a chronic, complex disease for which there are vast disparities in diagnosis and treatment between sociodemographic groups. Clinical presentation of endometriosis can vary from asymptomatic disease-often identified during (in)fertility consultations-to dysmenorrhea and debilitating pelvic pain. Because of this complexity, delayed diagnosis (mean time to diagnosis is 1.7-3.6 years) and misdiagnosis is common. Early and accurate diagnosis of endometriosis remains a research priority for patient advocates and healthcare providers. Electronic health records (EHRs) have been widely adopted as a data source in biomedical research. However, they remain a largely untapped source of data for endometriosis research. EHRs capture diverse, real-world patient populations and care trajectories and can be used to learn patterns of underlying risk factors for endometriosis which, in turn, can be used to inform screening guidelines to help clinicians efficiently and effectively recognize and diagnose the disease in all patient populations reducing inequities in care. Here, we provide an overview of the advantages and limitations of using EHR data to study endometriosis. We describe the prevalence of endometriosis observed in diverse populations from multiple healthcare institutions, examples of variables that can be extracted from EHRs to enhance the accuracy of endometriosis prediction, and opportunities to leverage longitudinal EHR data to improve our understanding of long-term health consequences for all patients.

Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms

OBJECTIVE

Automated algorithms to identify individuals with type 1 diabetes using electronic health records are increasingly used in biomedical research. It is not known whether the accuracy of these algorithms differs by self-reported race. We investigated whether polygenic scores improve identification of individuals with type 1 diabetes.

RESEARCH DESIGN AND METHODS

We investigated two large hospital-based biobanks (Mass General Brigham [MGB] and BioMe) and identified individuals with type 1 diabetes using an established automated algorithm. We performed medical record reviews to validate the diagnosis of type 1 diabetes. We implemented two published polygenic scores for type 1 diabetes (developed in individuals of European or African ancestry). We assessed the classification algorithm before and after incorporating polygenic scores.

RESULTS

The automated algorithm was more likely to incorrectly assign a diagnosis of type 1 diabetes in self-reported non-White individuals than in self-reported White individuals (odds ratio 3.45; 95% CI 1.54-7.69; P = 0.0026). After incorporating polygenic scores into the MGB Biobank, the positive predictive value of the type 1 diabetes algorithm increased from 70 to 97% for self-reported White individuals (meaning that 97% of those predicted to have type 1 diabetes indeed had type 1 diabetes) and from 53 to 100% for self-reported non-White individuals. Similar results were found in BioMe.

CONCLUSIONS

Automated phenotyping algorithms may exacerbate health disparities because of an increased risk of misclassification of individuals from underrepresented populations. Polygenic scores may be used to improve the performance of phenotyping algorithms and potentially reduce this disparity.

Association of step counts over time with the risk of chronic disease in the All of Us Research Program

The association between physical activity and human disease has not been examined using commercial devices linked to electronic health records. Using the electronic health records data from the All of Us Research Program, we show that step count volumes as captured by participants' own Fitbit devices were associated with risk of chronic disease across the entire human phenome. Of the 6,042 participants included in the study, 73% were female, 84% were white and 71% had a college degree, and participants had a median age of 56.7 (interquartile range 41.5-67.6) years and body mass index of 28.1 (24.3-32.9) kg m-2. Participants walked a median of 7,731.3 (5,866.8-9,826.8) steps per day over the median activity monitoring period of 4.0 (2.2-5.6) years with a total of 5.9 million person-days of monitoring. The relationship between steps per day and incident disease was inverse and linear for obesity (n = 368), sleep apnea (n = 348), gastroesophageal reflux disease (n = 432) and major depressive disorder (n = 467), with values above 8,200 daily steps associated with protection from incident disease. The relationships with incident diabetes (n = 156) and hypertension (n = 482) were nonlinear with no further risk reduction above 8,000-9,000 steps. Although validation in a more diverse sample is needed, these findings provide a real-world evidence-base for clinical guidance regarding activity levels that are necessary to reduce disease risk.

Developing a risk stratification tool for predicting opioid-related respiratory depression after non-cardiac surgery: a retrospective study

OBJECTIVES

Accurately assessing the probability of significant respiratory depression following opioid administration can potentially enhance perioperative risk assessment and pain management. We developed and validated a risk prediction tool to estimate the probability of significant respiratory depression (indexed by naloxone administration) in patients undergoing noncardiac surgery.

DESIGN

Retrospective cohort study.

SETTING

Single academic centre.

PARTICIPANTS

We studied n=63 084 patients (mean age 47.1±18.2 years; 50% men) who underwent emergency or elective non-cardiac surgery between 1 January 2007 and 30 October 2017.

INTERVENTIONS

A derivation subsample reflecting two-thirds of available patients (n=42 082) was randomly selected for model development, and associations were identified between predictor variables and naloxone administration occurring within 5 days following surgery. The resulting probability model for predicting naloxone administration was then cross-validated in a separate validation cohort reflecting the remaining one-third of patients (n=21 002).

RESULTS

The rate of naloxone administration was identical in the derivation (n=2720 (6.5%)) and validation (n=1360 (6.5%)) cohorts. The risk prediction model identified female sex (OR: 3.01; 95% CI: 2.73 to 3.32), high-risk surgical procedures (OR: 4.16; 95% CI: 3.78 to 4.58), history of drug abuse (OR: 1.81; 95% CI: 1.52 to 2.16) and any opioids being administered on a scheduled rather than as-needed basis (OR: 8.31; 95% CI: 7.26 to 9.51) as risk factors for naloxone administration. Advanced age (OR: 0.971; 95% CI: 0.968 to 0.973), opioids administered via patient-controlled analgesia pump (OR: 0.55; 95% CI: 0.49 to 0.62) and any scheduled non-opioids (OR: 0.63; 95% CI: 0.58 to 0.69) were associated with decreased risk of naloxone administration. An overall risk prediction model incorporating the common clinically available variables above displayed excellent discriminative ability in both the derivation and validation cohorts (c-index=0.820 and 0.814, respectively).

CONCLUSION

Our cross-validated clinical predictive model accurately estimates the risk of serious opioid-related respiratory depression requiring naloxone administration in postoperative patients.

Comparing medical history data derived from electronic health records and survey answers in the All of Us Research Program

OBJECTIVE

A participant's medical history is important in clinical research and can be captured from electronic health records (EHRs) and self-reported surveys. Both can be incomplete, EHR due to documentation gaps or lack of interoperability and surveys due to recall bias or limited health literacy. This analysis compares medical history collected in the All of Us Research Program through both surveys and EHRs.

MATERIALS AND METHODS

The All of Us medical history survey includes self-report questionnaire that asks about diagnoses to over 150 medical conditions organized into 12 disease categories. In each category, we identified the 3 most and least frequent self-reported diagnoses and retrieved their analogues from EHRs. We calculated agreement scores and extracted participant demographic characteristics for each comparison set.

RESULTS

The 4th All of Us dataset release includes data from 314 994 participants; 28.3% of whom completed medical history surveys, and 65.5% of whom had EHR data. Hearing and vision category within the survey had the highest number of responses, but the second lowest positive agreement with the EHR (0.21). The Infectious disease category had the lowest positive agreement (0.12). Cancer conditions had the highest positive agreement (0.45) between the 2 data sources.

DISCUSSION AND CONCLUSION

Our study quantified the agreement of medical history between 2 sources-EHRs and self-reported surveys. Conditions that are usually undocumented in EHRs had low agreement scores, demonstrating that survey data can supplement EHR data. Disagreement between EHR and survey can help identify possible missing records and guide researchers to adjust for biases.

Strengthening Causal Inference in Exposomics Research: Application of Genetic Data and Methods

Advances in technologies to measure a broad set of exposures have led to a range of exposome research efforts. Yet, these efforts have insufficiently integrated methods that incorporate genetic data to strengthen causal inference, despite evidence that many exposome-associated phenotypes are heritable. Objective: We demonstrate how integration of methods and study designs that incorporate genetic data can strengthen causal inference in exposomics research by helping address six challenges: reverse causation and unmeasured confounding, comprehensive examination of phenotypic effects, low efficiency, replication, multilevel data integration, and characterization of tissue-specific effects. Examples are drawn from studies of biomarkers and health behaviors, exposure domains where the causal inference methods we describe are most often applied. Discussion: Technological, computational, and statistical advances in genotyping, imputation, and analysis, combined with broad data sharing and cross-study collaborations, offer multiple opportunities to strengthen causal inference in exposomics research. Full application of these opportunities will require an expanded understanding of genetic variants that predict exposome phenotypes as well as an appreciation that the utility of genetic variants for causal inference will vary by exposure and may depend on large sample sizes. However, several of these challenges can be addressed through international scientific collaborations that prioritize data sharing. Ultimately, we anticipate that efforts to better integrate methods that incorporate genetic data will extend the reach of exposomics research by helping address the challenges of comprehensively measuring the exposome and its health effects across studies, the life course, and in varied contexts and diverse populations. https://doi.org/10.1289/EHP9098.

Concept Libraries for Repeatable and Reusable Research: Qualitative Study Exploring the Needs of Users

Background

Big data research in the field of health sciences is hindered by a lack of agreement on how to identify and define different conditions and their medications. This means that researchers and health professionals often have different phenotype definitions for the same condition. This lack of agreement makes it difficult to compare different study findings and hinders the ability to conduct repeatable and reusable research.

Objective

This study aims to examine the requirements of various users, such as researchers, clinicians, machine learning experts, and managers, in the development of a data portal for phenotypes (a concept library).

Methods

This was a qualitative study using interviews and focus group discussion. One-to-one interviews were conducted with researchers, clinicians, machine learning experts, and senior research managers in health data science (N=6) to explore their specific needs in the development of a concept library. In addition, a focus group discussion with researchers (N=14) working with the Secured Anonymized Information Linkage databank, a national eHealth data linkage infrastructure, was held to perform a SWOT (strengths, weaknesses, opportunities, and threats) analysis for the phenotyping system and the proposed concept library. The interviews and focus group discussion were transcribed verbatim, and 2 thematic analyses were performed.

Results

Most of the participants thought that the prototype concept library would be a very helpful resource for conducting repeatable research, but they specified that many requirements are needed before its development. Although all the participants stated that they were aware of some existing concept libraries, most of them expressed negative perceptions about them. The participants mentioned several facilitators that would stimulate them to share their work and reuse the work of others, and they pointed out several barriers that could inhibit them from sharing their work and reusing the work of others. The participants suggested some developments that they would like to see to improve reproducible research output using routine data.

Conclusions

The study indicated that most interviewees valued a concept library for phenotypes. However, only half of the participants felt that they would contribute by providing definitions for the concept library, and they reported many barriers regarding sharing their work on a publicly accessible platform. Analysis of interviews and the focus group discussion revealed that different stakeholders have different requirements, facilitators, barriers, and concerns about a prototype concept library.

Performance of a Computational Phenotyping Algorithm for Sarcoidosis Using Diagnostic Codes in Electronic Medical Records: Case Validation Study From 2 Veterans Affairs Medical Centers

BACKGROUND

Electronic medical records (EMRs) offer the promise of computationally identifying sarcoidosis cases. However, the accuracy of identifying these cases in the EMR is unknown.

OBJECTIVE

The aim of this study is to determine the statistical performance of using the International Classification of Diseases (ICD) diagnostic codes to identify patients with sarcoidosis in the EMR.

METHODS

We used the ICD diagnostic codes to identify sarcoidosis cases by searching the EMRs of the San Francisco and Palo Alto Veterans Affairs medical centers and randomly selecting 200 patients. To improve the diagnostic accuracy of the computational algorithm in cases where histopathological data are unavailable, we developed an index of suspicion to identify cases with a high index of suspicion for sarcoidosis (confirmed and probable) based on clinical and radiographic features alone using the American Thoracic Society practice guideline. Through medical record review, we determined the positive predictive value (PPV) of diagnosing sarcoidosis by two computational methods: using ICD codes alone and using ICD codes plus the high index of suspicion.

RESULTS

Among the 200 patients, 158 (79%) had a high index of suspicion for sarcoidosis. Of these 158 patients, 142 (89.9%) had documentation of nonnecrotizing granuloma, confirming biopsy-proven sarcoidosis. The PPV of using ICD codes alone was 79% (95% CI 78.6%-80.5%) for identifying sarcoidosis cases and 71% (95% CI 64.7%-77.3%) for identifying histopathologically confirmed sarcoidosis in the EMRs. The inclusion of the generated high index of suspicion to identify confirmed sarcoidosis cases increased the PPV significantly to 100% (95% CI 96.5%-100%). Histopathology documentation alone was 90% sensitive compared with high index of suspicion.

CONCLUSIONS

ICD codes are reasonable classifiers for identifying sarcoidosis cases within EMRs with a PPV of 79%. Using a computational algorithm to capture index of suspicion data elements could significantly improve the case-identification accuracy.

Advances in mass cytometry and its applicability to digital pathology in clinical-translational cancer research

The development and subsequent adaptation of mass cytometry for the histological analysis of tissue sections has allowed the simultaneous spatial characterization of multiple components. This is useful to find the correlation between the genotypic and phenotypic profile of tumor cells and their environment in clinical-translational studies. In this revision, we provide an overview of the most relevant hallmarks in the development, implementation and application of multiplexed imaging in the study of cancer and other conditions. A special focus is placed on studies based on imaging mass cytometry (IMC) and multiplexed ion beam imaging (MIBI). The purpose of this review is to help our readers become familiar with the verification techniques employed on this tool and outline the multiple applications reported in the literature. This review will also provide guidance on the use of IMC or MIBI in any field of biomedical research.

Facilitating cancer systems epidemiology research

Systems epidemiology offers a more comprehensive and holistic approach to studies of cancer in populations by considering high dimensionality measures from multiple domains, assessing the inter-relationships among risk factors, and considering changes over time. These approaches offer a framework to account for the complexity of cancer and contribute to a broader understanding of the disease. Therefore, NCI sponsored a workshop in February 2019 to facilitate discussion about the opportunities and challenges of the application of systems epidemiology approaches for cancer research. Eight key themes emerged from the discussion: transdisciplinary collaboration and a problem-based approach; methods and modeling considerations; interpretation, validation, and evaluation of models; data needs and opportunities; sharing of data and models; enhanced training practices; dissemination of systems models; and building a systems epidemiology community. This manuscript summarizes these themes, highlights opportunities for cancer systems epidemiology research, outlines ways to foster this research area, and introduces a collection of papers, "Cancer System Epidemiology Insights and Future Opportunities" that highlight findings based on systems epidemiology approaches.

Machine learning can identify patients at risk of hyperparathyroidism without known calcium and intact parathyroid hormone

BACKGROUND

To prove the concept of diagnosing primary hyperparathyroidism (pHPT) without calcium and parathyroid hormone (PTH) values and identifying potential risk factors for pHPT.

METHODS

Data were extracted from the clinical data warehouse (CDW) at the University of Arkansas for Medical Sciences (UAMS) Epic EHR (2014-2019).

RESULTS

1737 patients with over 185 000 rows of clinical data were provided in a relational structure and processed/flattened to facilitate modeling. Phenotype elements were identified for pHPT without advance knowledge of calcium and PTH levels. The area under the curve (AUC) for the prediction of pHPT using our model was 0.86 with sensitivity and specificity of 0.8953 and 0.6686, respectively, using a 0.45 probability threshold.

CONCLUSION

Primary hyperparathyroidism was predicted from a dataset excluding calcium and PTH data with 86% accuracy. This approach needs to be validated/refined on larger samples of data and plans are in place to do this with other regional/national datasets.

A Digital Case-Finding Algorithm for Diagnosed but Untreated Hepatitis C: A Tool for Increasing Linkage to Treatment and Cure

BACKGROUND AND AIMS

Although chronic HCV infection increases mortality, thousands of patients remain diagnosed-but-untreated (DBU). We aimed to (1) develop a DBU phenotyping algorithm, (2) use it to facilitate case finding and linkage to care, and (3) identify barriers to successful treatment.

APPROACH AND RESULTS

We developed a phenotyping algorithm using Java and SQL and applied it to ~2.5 million EPIC electronic medical records (EMRs; data entered January 2003 to December 2017). Approximately 72,000 EMRs contained an HCV International Classification of Diseases code and/or diagnostic test. The algorithm classified 10,614 cases as DBU (HCV-RNA positive and alive). Its positive and negative predictive values were 88% and 97%, respectively, as determined by manual review of 500 EMRs randomly selected from the ~72,000. Navigators reviewed the charts of 6,187 algorithm-defined DBUs and they attempted to contact potential treatment candidates by phone. By June 2020, 30% (n = 1,862) had completed an HCV-related appointment. Outcomes analysis revealed that DBU patients enrolled in our care coordination program were more likely to complete treatment (72% [n = 219] vs. 54% [n = 256]; P < 0.001) and to have a verified sustained virological response (67% vs. 46%; P < 0.001) than other patients. Forty-eight percent (n = 2,992) of DBU patients could not be reached by phone, which was a major barrier to engagement. Nearly half of these patients had Fibrosis-4 scores ≥ 2.67, indicating significant fibrosis. Multivariable logistic regression showed that DBUs who could not be contacted were less likely to have private insurance than those who could (18% vs. 50%; P < 0.001).

CONCLUSIONS

The digital DBU case-finding algorithm efficiently identified potential HCV treatment candidates, freeing resources for navigation and coordination. The algorithm is portable and accelerated HCV elimination when incorporated in our comprehensive program.

Exploring the Use of Genomic and Routinely Collected Data: Narrative Literature Review and Interview Study

Background

Advancing the use of genomic data with routinely collected health data holds great promise for health care and research. Increasing the use of these data is a high priority to understand and address the causes of disease.

Objective

This study aims to provide an outline of the use of genomic data alongside routinely collected data in health research to date. As this field prepares to move forward, it is important to take stock of the current state of play in order to highlight new avenues for development, identify challenges, and ensure that adequate data governance models are in place for safe and socially acceptable progress.

Methods

We conducted a literature review to draw information from past studies that have used genomic and routinely collected data and conducted interviews with individuals who use these data for health research. We collected data on the following: the rationale of using genomic data in conjunction with routinely collected data, types of genomic and routinely collected data used, data sources, project approvals, governance and access models, and challenges encountered.

Results

The main purpose of using genomic and routinely collected data was to conduct genome-wide and phenome-wide association studies. Routine data sources included electronic health records, disease and death registries, health insurance systems, and deprivation indices. The types of genomic data included polygenic risk scores, single nucleotide polymorphisms, and measures of genetic activity, and biobanks generally provided these data. Although the literature search showed that biobanks released data to researchers, the case studies revealed a growing tendency for use within a data safe haven. Challenges of working with these data revolved around data collection, data storage, technical, and data privacy issues.

Conclusions

Using genomic and routinely collected data holds great promise for progressing health research. Several challenges are involved, particularly in terms of privacy. Overcoming these barriers will ensure that the use of these data to progress health research can be exploited to its full potential.

Concept libraries for automatic electronic health record based phenotyping: A review

Introduction

Electronic health records (EHR) are linked together to examine disease history and to undertake research into the causes and outcomes of disease. However, the process of constructing algorithms for phenotyping (e.g., identifying disease characteristics) or health characteristics (e.g., smoker) is very time consuming and resource costly. In addition, results can vary greatly between researchers. Reusing or building on algorithms that others have created is a compelling solution to these problems. However, sharing algorithms is not a common practice and many published studies do not detail the clinical code lists used by the researchers in the disease/characteristic definition. To address these challenges, a number of centres across the world have developed health data portals which contain concept libraries (e.g., algorithms for defining concepts such as disease and characteristics) in order to facilitate disease phenotyping and health studies.

Objectives

This study aims to review the literature of existing concept libraries, examine their utilities, identify the current gaps, and suggest future developments.

Methods

The five-stage framework of Arksey and O'Malley was used for the literature search. This approach included defining the research questions, identifying relevant studies through literature review, selecting eligible studies, charting and extracting data, and summarising and reporting the findings.

Results

This review identified seven publicly accessible Electronic Health data concept libraries which were developed in different countries including UK, USA, and Canada. The concept libraries (n = 7) investigated were either general libraries that hold phenotypes of multiple specialties (n = 4) or specialized libraries that manage only certain specialities such as rare diseases (n = 3). There were some clear differences between the general libraries such as archiving data from different electronic sources, and using a range of different types of coding systems. However, they share some clear similarities such as enabling users to upload their own code lists, and allowing users to use/download the publicly accessible code. In addition, there were some differences between the specialized libraries such as difference in ability to search, and if it was possible to use different searching queries such as simple or complex searches. Conversely, there were some similarities between the specialized libraries such as enabling users to upload their own concepts into the libraries and to show where they were published, which facilitates assessing the validity of the concepts. All the specialized libraries aimed to encourage the reuse of research methods such as lists of clinical code and/or metadata.

Conclusion

The seven libraries identified have been developed independently and appear to replicate similar concepts but in different ways. Collaboration between similar libraries would greatly facilitate the use of these libraries for the user. The process of building code lists takes time and effort. Access to existing code lists increases consistency and accuracy of definitions across studies. Concept library developers should collaborate with each other to raise awareness of their existence and of their various functions, which could increase users’ contributions to those libraries and promote their wide-ranging adoption.

Combining structured and unstructured data in EMRs to create clinically-defined EMR-derived cohorts

Background

There have been few studies describing how production EMR systems can be systematically queried to identify clinically-defined populations and limited studies utilising free-text in this process. The aim of this study is to provide a generalisable methodology for constructing clinically-defined EMR-derived patient cohorts using structured and unstructured data in EMRs.

Methods

Patients with possible acute coronary syndrome (ACS) were used as an exemplar. Cardiologists defined clinical criteria for patients presenting with possible ACS. These were mapped to data tables within the production EMR system creating seven inclusion criteria comprised of structured data fields (orders and investigations, procedures, scanned electrocardiogram (ECG) images, and diagnostic codes) and unstructured clinical documentation. Data were extracted from two local health districts (LHD) in Sydney, Australia. Outcome measures included examination of the relative contribution of individual inclusion criteria to the identification of eligible encounters, comparisons between inclusion criterion and evaluation of consistency of data extracts across years and LHDs.

Results

Among 802,742 encounters in a 5 year dataset (1/1/13–30/12/17), the presence of an ECG image (54.8% of encounters) and symptoms and keywords in clinical documentation (41.4–64.0%) were used most often to identify presentations of possible ACS. Orders and investigations (27.3%) and procedures (1.4%), were less often present for identified presentations. Relevant ICD-10/SNOMED CT codes were present for 3.7% of identified encounters. Similar trends were seen when the two LHDs were examined separately, and across years.

Conclusions

Clinically-defined EMR-derived cohorts combining structured and unstructured data during cohort identification is a necessary prerequisite for critical validation work required for development of real-time clinical decision support and learning health systems.

Automated Phenotyping Tool for Identifying Developmental Language Disorder Cases in Health Systems Data (APT-DLD): A New Research Algorithm for Deployment in Large-Scale Electronic Health Record Systems

Purpose Data mining algorithms using electronic health records (EHRs) are useful in large-scale population-wide studies to classify etiology and comorbidities (Casey et al., 2016). Here, we apply this approach to developmental language disorder (DLD), a prevalent communication disorder whose risk factors and epidemiology remain largely undiscovered. Method We first created a reliable system for manually identifying DLD in EHRs based on speech-language pathologist (SLP) diagnostic expertise. We then developed and validated an automated algorithmic procedure, called, Automated Phenotyping Tool for identifying DLD cases in health systems data (APT-DLD), that classifies a DLD status for patients within EHRs on the basis of ICD (International Statistical Classification of Diseases and Related Health Problems) codes. APT-DLD was validated in a discovery sample (N = 973) using expert SLP manual phenotype coding as a gold-standard comparison and then applied and further validated in a replication sample of N = 13,652 EHRs. Results In the discovery sample, the APT-DLD algorithm correctly classified 98% (concordance) of DLD cases in concordance with manually coded records in the training set, indicating that APT-DLD successfully mimics a comprehensive chart review. The output of APT-DLD was also validated in relation to independently conducted SLP clinician coding in a subset of records, with a positive predictive value of 95% of cases correctly classified as DLD. We also applied APT-DLD to the replication sample, where it achieved a positive predictive value of 90% in relation to SLP clinician classification of DLD. Conclusions APT-DLD is a reliable, valid, and scalable tool for identifying DLD cohorts in EHRs. This new method has promising public health implications for future large-scale epidemiological investigations of DLD and may inform EHR data mining algorithms for other communication disorders. Supplemental Material https://doi.org/10.23641/asha.12753578.