Health Care and Precision Medicine Research: Analysis of a Scalable Data Science Platform

Use of Electronic Health Records to Characterize Patients with Uncontrolled Hypertension in Two Large Health System Networks

Background

Improving hypertension control is a public health priority. However, consistent identification of uncontrolled hypertension using computable definitions in electronic health records (EHR) across health systems remains uncertain.

Methods

In this retrospective cohort study, we applied two computable definitions to the EHR data to identify patients with controlled and uncontrolled hypertension and to evaluate differences in characteristics, treatment, and clinical outcomes between these patient populations. We included adult patients (≥ 18 years) with hypertension receiving ambulatory care within Yale-New Haven Health System (YNHHS; a large US health system) and OneFlorida Clinical Research Consortium (OneFlorida; a Clinical Research Network comprised of 16 health systems) between October 2015 and December 2018. We identified patients with controlled and uncontrolled hypertension based on either a single blood pressure (BP) measurement from a randomly selected visit or all BP measurements recorded between hypertension identification and the randomly selected visit).

Results

Overall, 253,207 and 182,827 adults at YNHHS and OneFlorida were identified as having hypertension. Of these patients, 83.1% at YNHHS and 76.8% at OneFlorida were identified using ICD-10-CM codes, whereas 16.9% and 23.2%, respectively, were identified using elevated BP measurements (≥ 140/90 mmHg). Uncontrolled hypertension was observed among 32.5% and 43.7% of patients at YNHHS and OneFlorida, respectively. Uncontrolled hypertension was disproportionately higher among Black patients when compared with White patients (38.9% versus 31.5% in YNHHS; p < 0.001; 49.7% versus 41.2% in OneFlorida; p < 0.001). Medication prescription for hypertension management was more common in patients with uncontrolled hypertension when compared with those with controlled hypertension (overall treatment rate: 39.3% versus 37.3% in YNHHS; p = 0.04; 42.2% versus 34.8% in OneFlorida; p < 0.001). Patients with controlled and uncontrolled hypertension had similar rates of short-term (at 3 and 6 months) and long-term (at 12 and 24 months) clinical outcomes. The two computable definitions generated consistent results.

Conclusions

Our findings illustrate the potential of leveraging EHR data, employing computable definitions, to conduct effective digital population surveillance in the realm of hypertension management.

Use of Electronic Health Records to Characterize Patients with Uncontrolled Hypertension in Two Large Health System Networks

Background

Improving hypertension control is a public health priority. However, uncertainty remains regarding the optimal way to identify patients with uncontrolled hypertension using electronic health records (EHR) data.

Methods

In this retrospective cohort study, we applied computable definitions to the EHR data to identify patients with controlled and uncontrolled hypertension and to evaluate differences in characteristics, treatment, and clinical outcomes between these patient populations. We included adult patients (≥18 years) with hypertension receiving ambulatory care within Yale-New Haven Health System (YNHHS; a large US health system) and OneFlorida Clinical Research Consortium (OneFlorida; a Clinical Research Network comprised of 16 health systems) between October 2015 and December 2018. We identified patients with controlled and uncontrolled hypertension based on either a single blood pressure (BP) measurement from a randomly selected visit or all BP measurements recorded between hypertension identification and the randomly selected visit).

Results

Overall, 253,207 and 182,827 adults at YNHHS and OneFlorida were identified as having hypertension. Of these patients, 83.1% at YNHHS and 76.8% at OneFlorida were identified using ICD-10-CM codes, whereas 16.9% and 23.2%, respectively, were identified using elevated BP measurements (≥ 140/90 mmHg). Uncontrolled hypertension was observed among 32.5% and 43.7% of patients at YNHHS and OneFlorida, respectively. Uncontrolled hypertension was disproportionately higher among Black patients when compared with White patients (38.9% versus 31.5% in YNHHS; p<0.001; 49.7% versus 41.2% in OneFlorida; p<0.001). Medication prescription for hypertension management was more common in patients with uncontrolled hypertension when compared with those with controlled hypertension (overall treatment rate: 39.3% versus 37.3% in YNHHS; p=0.04; 42.2% versus 34.8% in OneFlorida; p<0.001). Patients with controlled and uncontrolled hypertension had similar rates of short-term (at 3 and 6 months) and long-term (at 12 and 24 months) clinical outcomes. The two computable definitions generated consistent results.

Conclusions

Computable definitions can be successfully applied to health system EHR data to conduct population surveillance for hypertension and identify patients with uncontrolled hypertension who may benefit from additional treatment.

A Case Study of Enhancing the Data Science Capacity of an RCMI Program at a Historically Black Medical College

As data grows exponentially across diverse fields, the ability to effectively leverage big data has become increasingly crucial. In the field of data science, however, minority groups, including African Americans, are significantly underrepresented. With the strategic role of minority-serving institutions to enhance diversity in the data science workforce and apply data science to health disparities, the National Institute for Minority Health Disparities (NIMHD) provided funding in September 2021 to six Research Centers in Minority Institutions (RCMI) to improve their data science capacity and foster collaborations with data scientists. Meharry Medical College (MMC), a historically Black College/University (HBCU), was among the six awardees. This paper summarizes the NIMHD-funded efforts at MMC, which include offering mini-grants to collaborative research groups, surveys to understand the needs of the community to guide project implementation, and data science training to enhance the data analytics skills of the RCMI investigators, staff, medical residents, and graduate students. This study is innovative as it addressed the urgent need to enhance the data science capacity of the RCMI program at MMC, build a diverse data science workforce, and develop collaborations between the RCMI and MMC's newly established School of Applied Computational Science. This paper presents the progress of this NIMHD-funded project, which clearly shows its positive impact on the local community.

Policy Preferences Regarding Health Data Sharing Among Patients With Cancer: Public Deliberations

BACKGROUND

Precision health offers the promise of advancing clinical care in data-driven, evidence-based, and personalized ways. However, complex data sharing infrastructures, for-profit (commercial) and nonprofit partnerships, and systems for data governance have been created with little attention to the values, expectations, and preferences of patients about how they want to be engaged in the sharing and use of their health information. We solicited patient opinions about institutional policy options using public deliberation methods to address this gap.

OBJECTIVE

We aimed to understand the policy preferences of current and former patients with cancer regarding the sharing of health information collected in the contexts of health information exchange and commercial partnerships and to identify the values invoked and perceived risks and benefits of health data sharing considered by the participants when formulating their policy preferences.

METHODS

We conducted 2 public deliberations, including predeliberation and postdeliberation surveys, with patients who had a current or former cancer diagnosis (n=61). Following informational presentations, the participants engaged in facilitated small-group deliberations to discuss and rank policy preferences related to health information sharing, such as the use of a patient portal, email or SMS text messaging, signage in health care settings, opting out of commercial data sharing, payment, and preservation of the status quo. The participants ranked their policy preferences individually, as small groups by mutual agreement, and then again individually in the postdeliberation survey.

RESULTS

After deliberation, the patient portal was ranked as the most preferred policy choice. The participants ranked no change in status quo as the least preferred policy option by a wide margin. Throughout the study, the participants expressed concerns about transparency and awareness, convenience, and accessibility of information about health data sharing. Concerns about the status quo centered around a lack of transparency, awareness, and control. Specifically, the patients were not aware of how, when, or why their data were being used and wanted more transparency in these regards as well as greater control and autonomy around the use of their health data. The deliberations suggested that patient portals would be a good place to provide additional information about data sharing practices but that over time, notifications should be tailored to patient preferences.

CONCLUSIONS

Our study suggests the need for increased disclosure of health information sharing practices. Describing health data sharing practices through patient portals or other mechanisms personalized to patient preferences would minimize the concerns expressed by patients about the extent of data sharing that occurs without their knowledge. Future research and policies should identify ways to increase patient control over health data sharing without reducing the societal benefits of data sharing.

Measuring the Impact of a Blood Supply Shortage Using Data Science

BACKGROUND

Transfusion medicine is the only section of the clinical laboratory that performs diagnostic testing and dispenses a drug (blood) on the basis of those results. However, not all of the testing that informs the clinical decision to prescribe a blood transfusion is performed in the blood bank. To form a holistic assessment of blood bank responsiveness to clinical needs, it is important to be able to merge blood bank data with datapoints from the hematology laboratory and the electronic medical record.

METHODS

We built an interactive visualization of the time from hemoglobin result availability to initiation of red blood cell (RBC) transfusion and monitored the result over a 2-year period that coincided with several severe blood shortages. The visualization runs entirely on free software and was designed to be feasibly deployed on a variety of hospital information technology platforms without the need for significant data science expertise.

RESULTS

Patient factors, such as hemoglobin concentration, blood type, and presence of minor blood group antibodies influenced the time to initiation of transfusion. Time to transfusion initiation did not appear to be significantly affected by periods of blood shortage.

CONCLUSION

Overall, we demonstrate a proof of concept that complex, but clinically important, blood bank quality metrics can be generated with the support of a free, user-friendly system that aggregates data from multiple sources.

Association between primary or booster COVID-19 mRNA vaccination and Omicron lineage BA.1 SARS-CoV-2 infection in people with a prior SARS-CoV-2 infection: A test-negative case-control analysis

BACKGROUND

The benefit of primary and booster vaccination in people who experienced a prior Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection remains unclear. The objective of this study was to estimate the effectiveness of primary (two-dose series) and booster (third dose) mRNA vaccination against Omicron (lineage BA.1) infection among people with a prior documented infection.

METHODS AND FINDINGS

We conducted a test-negative case-control study of reverse transcription PCRs (RT-PCRs) analyzed with the TaqPath (Thermo Fisher Scientific) assay and recorded in the Yale New Haven Health system from November 1, 2021, to April 30, 2022. Overall, 11,307 cases (positive TaqPath analyzed RT-PCRs with S-gene target failure [SGTF]) and 130,041 controls (negative TaqPath analyzed RT-PCRs) were included (median age: cases: 35 years, controls: 39 years). Among cases and controls, 5.9% and 8.1% had a documented prior infection (positive SARS-CoV-2 test record ≥90 days prior to the included test), respectively. We estimated the effectiveness of primary and booster vaccination relative to SGTF-defined Omicron (lineage BA.1) variant infection using a logistic regression adjusted for date of test, age, sex, race/ethnicity, insurance, comorbidities, social venerability index, municipality, and healthcare utilization. The effectiveness of primary vaccination 14 to 149 days after the second dose was 41.0% (95% confidence interval (CI): 14.1% to 59.4%, p 0.006) and 27.1% (95% CI: 18.7% to 34.6%, p < 0.001) for people with and without a documented prior infection, respectively. The effectiveness of booster vaccination (≥14 days after booster dose) was 47.1% (95% CI: 22.4% to 63.9%, p 0.001) and 54.1% (95% CI: 49.2% to 58.4%, p < 0.001) in people with and without a documented prior infection, respectively. To test whether booster vaccination reduced the risk of infection beyond that of the primary series, we compared the odds of infection among boosted (≥14 days after booster dose) and booster-eligible people (≥150 days after second dose). The odds ratio (OR) comparing boosted and booster-eligible people with a documented prior infection was 0.79 (95% CI: 0.54 to 1.16, p 0.222), whereas the OR comparing boosted and booster-eligible people without a documented prior infection was 0.54 (95% CI: 0.49 to 0.59, p < 0.001). This study's limitations include the risk of residual confounding, the use of data from a single system, and the reliance on TaqPath analyzed RT-PCR results.

CONCLUSIONS

In this study, we observed that primary vaccination provided significant but limited protection against Omicron (lineage BA.1) infection among people with and without a documented prior infection. While booster vaccination was associated with additional protection against Omicron BA.1 infection in people without a documented prior infection, it was not found to be associated with additional protection among people with a documented prior infection. These findings support primary vaccination in people regardless of documented prior infection status but suggest that infection history may impact the relative benefit of booster doses.

Lifting Hospital Electronic Health Record Data Treasures: Challenges and Opportunities

Electronic health records (EHRs) have been successfully used in data science and machine learning projects. However, most of these data are collected for clinical use rather than for retrospective analysis. This means that researchers typically face many different issues when attempting to access and prepare the data for secondary use. We aimed to investigate how raw EHRs can be accessed and prepared in retrospective data science projects in a disciplined, effective, and efficient way. We report our experience and findings from a large-scale data science project analyzing routinely acquired retrospective data from the Kepler University Hospital in Linz, Austria. The project involved data collection from more than 150,000 patients over a period of 10 years. It included diverse data modalities, such as static demographic data, irregularly acquired laboratory test results, regularly sampled vital signs, and high-frequency physiological waveform signals. Raw medical data can be corrupted in many unexpected ways that demand thorough manual inspection and highly individualized data cleaning solutions. We present a general data preparation workflow, which was shaped in the course of our project and consists of the following 7 steps: obtain a rough overview of the available EHR data, define clinically meaningful labels for supervised learning, extract relevant data from the hospital’s data warehouses, match data extracted from different sources, deidentify them, detect errors and inconsistencies therein through a careful exploratory analysis, and implement a suitable data processing pipeline in actual code. Only few of the data preparation issues encountered in our project were addressed by generic medical data preprocessing tools that have been proposed recently. Instead, highly individualized solutions for the specific data used in one’s own research seem inevitable. We believe that the proposed workflow can serve as a guidance for practitioners, helping them to identify and address potential problems early and avoid some common pitfalls.

Novel Machine-Learning Based Framework Using Electroretinography Data for the Detection of Early-Stage Glaucoma

Purpose

Early-stage glaucoma diagnosis has been a challenging problem in ophthalmology. The current state-of-the-art glaucoma diagnosis techniques do not completely leverage the functional measures' such as electroretinogram's immense potential; instead, focus is on structural measures like optical coherence tomography. The current study aims to take a foundational step toward the development of a novel and reliable predictive framework for early detection of glaucoma using machine-learning-based algorithm capable of leveraging medically relevant information that ERG signals contain.

Methods

ERG signals from 60 eyes of DBA/2 mice were grouped for binary classification based on age. The signals were also grouped based on intraocular pressure (IOP) for multiclass classification. Statistical and wavelet-based features were engineered and extracted. Important predictors (ERG tests and features) were determined, and the performance of five machine learning-based methods were evaluated.

Results

Random forest (bagged trees) ensemble classifier provided the best performance in both binary and multiclass classification of ERG signals. An accuracy of 91.7 and 80% was achieved for binary and multiclass classification, respectively, suggesting that machine-learning-based models can detect subtle changes in ERG signals if trained using advanced features such as those based on wavelet analyses.

Conclusions

The present study describes a novel, machine-learning-based method to analyze ERG signals providing additional information that may be used to detect early-stage glaucoma. Based on promising performance metrics obtained using the proposed machine-learning-based framework leveraging an established ERG data set, we conclude that the novel framework allows for detection of functional deficits of early/various stages of glaucoma in mice.

A multicenter evaluation of computable phenotyping approaches for SARS-CoV-2 infection and COVID-19 hospitalizations

Diagnosis codes are used to study SARS-CoV2 infections and COVID-19 hospitalizations in administrative and electronic health record (EHR) data. Using EHR data (April 2020–March 2021) at the Yale-New Haven Health System and the three hospital systems of the Mayo Clinic, computable phenotype definitions based on ICD-10 diagnosis of COVID-19 (U07.1) were evaluated against positive SARS-CoV-2 PCR or antigen tests. We included 69,423 patients at Yale and 75,748 at Mayo Clinic with either a diagnosis code or a positive SARS-CoV-2 test. The precision and recall of a COVID-19 diagnosis for a positive test were 68.8% and 83.3%, respectively, at Yale, with higher precision (95%) and lower recall (63.5%) at Mayo Clinic, varying between 59.2% in Rochester to 97.3% in Arizona. For hospitalizations with a principal COVID-19 diagnosis, 94.8% at Yale and 80.5% at Mayo Clinic had an associated positive laboratory test, with secondary diagnosis of COVID-19 identifying additional patients. These patients had a twofold higher inhospital mortality than based on principal diagnosis. Standardization of coding practices is needed before the use of diagnosis codes in clinical research and epidemiological surveillance of COVID-19.

Data Integration Challenges for Machine Learning in Precision Medicine

A main goal of Precision Medicine is that of incorporating and integrating the vast corpora on different databases about the molecular and environmental origins of disease, into analytic frameworks, allowing the development of individualized, context-dependent diagnostics, and therapeutic approaches. In this regard, artificial intelligence and machine learning approaches can be used to build analytical models of complex disease aimed at prediction of personalized health conditions and outcomes. Such models must handle the wide heterogeneity of individuals in both their genetic predisposition and their social and environmental determinants. Computational approaches to medicine need to be able to efficiently manage, visualize and integrate, large datasets combining structure, and unstructured formats. This needs to be done while constrained by different levels of confidentiality, ideally doing so within a unified analytical architecture. Efficient data integration and management is key to the successful application of computational intelligence approaches to medicine. A number of challenges arise in the design of successful designs to medical data analytics under currently demanding conditions of performance in personalized medicine, while also subject to time, computational power, and bioethical constraints. Here, we will review some of these constraints and discuss possible avenues to overcome current challenges.

Vertical integration in healthcare: What does literature say about improvements on quality, access, efficiency, and costs containment?

INTRODUCTION

Vertical integration models involve integrating services from different levels of care (e.g., primary care, acute care, post-acute care). Therefore, one of their main objectives is to increase continuity of care, potentially improving outcomes like efficiency, quality, and access or even enabling cost containment.

OBJECTIVES

This study conducts a literature review and aims at contributing to the contentious discussion regarding the effects of vertical integration reforms in terms of efficiency, costs containment, quality, and access.

METHODS

We performed a systematic search of the literature published until February 2020. The articles respecting the conceptual framework were included in an exhaustive analysis to study the impact of vertical integration on costs, prices of care, efficiency, quality, and access.

RESULTS

A sample of 64 papers resulted from the screening process. The impact of vertical integration on costs and prices of care appears to be negative. Decreases in technical efficiency upon vertical integration are practically out of the question. Nevertheless, there is no substantial inclination to visualise a positive influence. The same happens with the quality of care. Regarding access, the lack of available articles on this outcome limits conjectures.

CONCLUSIONS

In summary, it is not clear yet whether vertically integrated healthcare providers positively impact the overall delivery care system. Nevertheless, the recent growing trend in the number of studies suggests a promising future on the analysis of this topic.

Applications of Digital Microscopy and Densely Connected Convolutional Neural Networks for Automated Quantification of Babesia-Infected Erythrocytes

BACKGROUND

Clinical babesiosis is diagnosed, and parasite burden is determined, by microscopic inspection of a thick or thin Giemsa-stained peripheral blood smear. However, quantitative analysis by manual microscopy is subject to error. As such, methods for the automated measurement of percent parasitemia in digital microscopic images of peripheral blood smears could improve clinical accuracy, relative to the predicate method.

METHODS

Individual erythrocyte images were manually labeled as "parasite" or "normal" and were used to train a model for binary image classification. The best model was then used to calculate percent parasitemia from a clinical validation dataset, and values were compared to a clinical reference value. Lastly, model interpretability was examined using an integrated gradient to identify pixels most likely to influence classification decisions.

RESULTS

The precision and recall of the model during development testing were 0.92 and 1.00, respectively. In clinical validation, the model returned increasing positive signal with increasing mean reference value. However, there were 2 highly erroneous false positive values returned by the model. Further, the model incorrectly assessed 3 cases well above the clinical threshold of 10%. The integrated gradient suggested potential sources of false positives including rouleaux formations, cell boundaries, and precipitate as deterministic factors in negative erythrocyte images.

CONCLUSIONS

While the model demonstrated highly accurate single cell classification and correctly assessed most slides, several false positives were highly incorrect. This project highlights the need for integrated testing of machine learning-based models, even when models in the development phase perform well.

Predictors of diagnostic transition from major depressive disorder to bipolar disorder: a retrospective observational network study

Many patients with bipolar disorder (BD) are initially misdiagnosed with major depressive disorder (MDD) and are treated with antidepressants, whose potential iatrogenic effects are widely discussed. It is unknown whether MDD is a comorbidity of BD or its earlier stage, and no consensus exists on individual conversion predictors, delaying BD's timely recognition and treatment. We aimed to build a predictive model of MDD to BD conversion and to validate it across a multi-national network of patient databases using the standardization afforded by the Observational Medical Outcomes Partnership (OMOP) common data model. Five "training" US databases were retrospectively analyzed: IBM MarketScan CCAE, MDCR, MDCD, Optum EHR, and Optum Claims. Cyclops regularized logistic regression models were developed on one-year MDD-BD conversion with all standard covariates from the HADES PatientLevelPrediction package. Time-to-conversion Kaplan-Meier analysis was performed up to a decade after MDD, stratified by model-estimated risk. External validation of the final prediction model was performed across 9 patient record databases within the Observational Health Data Sciences and Informatics (OHDSI) network internationally. The model's area under the curve (AUC) varied 0.633-0.745 (µ = 0.689) across the five US training databases. Nine variables predicted one-year MDD-BD transition. Factors that increased risk were: younger age, severe depression, psychosis, anxiety, substance misuse, self-harm thoughts/actions, and prior mental disorder. AUCs of the validation datasets ranged 0.570-0.785 (µ = 0.664). An assessment algorithm was built for MDD to BD conversion that allows distinguishing as much as 100-fold risk differences among patients and validates well across multiple international data sources.

Neptune: an environment for the delivery of genomic medicine

PURPOSE

Genomic medicine holds great promise for improving health care, but integrating searchable and actionable genetic data into electronic health records (EHRs) remains a challenge. Here we describe Neptune, a system for managing the interaction between a clinical laboratory and an EHR system during the clinical reporting process.

METHODS

We developed Neptune and applied it to two clinical sequencing projects that required report customization, variant reanalysis, and EHR integration.

RESULTS

Neptune has been applied for the generation and delivery of over 15,000 clinical genomic reports. This work spans two clinical tests based on targeted gene panels that contain 68 and 153 genes respectively. These projects demanded customizable clinical reports that contained a variety of genetic data types including single-nucleotide variants (SNVs), copy-number variants (CNVs), pharmacogenomics, and polygenic risk scores. Two variant reanalysis activities were also supported, highlighting this important workflow.

CONCLUSION

Methods are needed for delivering structured genetic data to EHRs. This need extends beyond developing data formats to providing infrastructure that manages the reporting process itself. Neptune was successfully applied on two high-throughput clinical sequencing projects to build and deliver clinical reports to EHR systems. The software is open source and available at https://gitlab.com/bcm-hgsc/neptune .

Assessment of Inter-Institutional Post-Operative Hypoparathyroidism Status Using a Common Data Model

Post-thyroidectomy hypoparathyroidism may result in various transient or permanent symptoms, ranging from tingling sensation to severe breathing difficulties. Its incidence varies among surgeons and institutions, making it difficult to determine its actual incidence and associated factors. This study attempted to estimate the incidence of post-operative hypoparathyroidism in patients at two tertiary institutions that share a common data model, the Observational Health Data Sciences and Informatics. This study used the Common Data Model to extract explicitly specified encoding and relationships among concepts using standardized vocabularies. The EDI-codes of various thyroid disorders and thyroid operations were extracted from two separate tertiary hospitals between January 2013 and December 2018. Patients were grouped into no evidence of/transient/permanent hypoparathyroidism groups to analyze the likelihood of hypoparathyroidism occurrence related to operation types and diagnosis. Of the 4848 eligible patients at the two institutions who underwent thyroidectomy, 1370 (28.26%) experienced transient hypoparathyroidism and 251 (5.18%) experienced persistent hypoparathyroidism. Univariate logistic regression analysis predicted that, relative to total bilateral thyroidectomy, radical tumor resection was associated with a 48% greater likelihood of transient hypoparathyroidism and a 102% greater likelihood of persistent hypoparathyroidism. Moreover, multivariate logistic analysis found that radical tumor resection was associated with a 50% greater likelihood of transient hypoparathyroidism and a 97% greater likelihood of persistent hypoparathyroidism than total bilateral thyroidectomy. These findings, by integrating and analyzing two databases, suggest that this analysis could be expanded to include other large databases that share the same Observational Health Data Sciences and Informatics protocol.

Feasibility of capturing real-world data from health information technology systems at multiple centers to assess cardiac ablation device outcomes: A fit-for-purpose informatics analysis report

OBJECTIVE

The study sought to conduct an informatics analysis on the National Evaluation System for Health Technology Coordinating Center test case of cardiac ablation catheters and to demonstrate the role of informatics approaches in the feasibility assessment of capturing real-world data using unique device identifiers (UDIs) that are fit for purpose for label extensions for 2 cardiac ablation catheters from the electronic health records and other health information technology systems in a multicenter evaluation.

MATERIALS AND METHODS

We focused on data capture and transformation and data quality maturity model specified in the National Evaluation System for Health Technology Coordinating Center data quality framework. The informatics analysis included 4 elements: the use of UDIs for identifying device exposure data, the use of standardized codes for defining computable phenotypes, the use of natural language processing for capturing unstructured data elements from clinical data systems, and the use of common data models for standardizing data collection and analyses.

RESULTS

We found that, with the UDI implementation at 3 health systems, the target device exposure data could be effectively identified, particularly for brand-specific devices. Computable phenotypes for study outcomes could be defined using codes; however, ablation registries, natural language processing tools, and chart reviews were required for validating data quality of the phenotypes. The common data model implementation status varied across sites. The maturity level of the key informatics technologies was highly aligned with the data quality maturity model.

CONCLUSIONS

We demonstrated that the informatics approaches can be feasibly used to capture safety and effectiveness outcomes in real-world data for use in medical device studies supporting label extensions.

Social Determinants of Health and Cardiovascular Disease: Current State and Future Directions Towards Healthcare Equity

PURPOSE OF REVIEW

We sought to examine the role of social and environmental conditions that determine an individual's behaviors and risk of disease-collectively known as social determinants of health (SDOH)-in shaping cardiovascular (CV) health of the population and giving rise to disparities in risk factors, outcomes, and clinical care for cardiovascular disease (CVD), the leading cause of death in the United States (US).

RECENT FINDINGS

Traditional CV risk factors have been extensively targeted in existing CVD prevention and management paradigms, often with little attention to SDOH. Limited evidence suggests an association between individual SDOH (e.g., income, education) and CVD. However, inequities in CVD care, risk factors, and outcomes have not been studied using a broad SDOH framework. We examined existing evidence of the association between SDOH-organized into 6 domains, including economic stability, education, food, neighborhood and physical environment, healthcare system, and community and social context-and CVD. Greater social adversity, defined by adverse SDOH, was linked to higher burden of CVD risk factors and poor outcomes, such as stroke, myocardial infarction (MI), coronary heart disease, heart failure, and mortality. Conversely, favorable social conditions had protective effects on CVD. Upstream SDOH interact across domains to produce cumulative downstream effects on CV health, via multiple physiologic and behavioral pathways. SDOH are major drivers of sociodemographic disparities in CVD, with a disproportionate impact on socially disadvantaged populations. Efforts to achieve health equity should take into account the structural, institutional, and environmental barriers to optimum CV health in marginalized populations. In this review, we highlight major knowledge gaps for each SDOH domain and propose a set of actionable recommendations to inform CVD care, ensure equitable distribution of healthcare resources, and reduce observed disparities.

Longitudinal Assessment of SARS-CoV-2 Antinucleocapsid and Antispike-1-RBD Antibody Testing Following PCR-Detected SARS-CoV-2 Infection

Background

SARS-CoV-2 serologic assays are becoming increasingly available and may serve as a diagnostic aid in a multitude of settings relating to past infection status. However, there is limited literature detailing the longitudinal performance of EUA-cleared serologic assays in US populations, particularly in cohorts with a remote history of PCR-confirmed SARS-CoV-2 infection (e.g., > 2 months).

Methods

We evaluated the diagnostic sensitivities and specificities of the Elecsys® Anti-SARS-CoV-2 (anti-N) and Elecsys® Anti-SARS-CoV-2 S (anti-S1-RBD) assays, using 174 residual clinical samples up to 267 days post-PCR diagnosis of SARS-CoV-2 infection (n = 154) and a subset of samples obtained prior to the COVID-19 pandemic as negative controls (n = 20).

Results

The calculated diagnostic sensitivities for the anti-N and anti-S1-RBD assays were 89% and 93%, respectively. Of the 154 samples in the SARS-CoV-2-positive cohort, there were 6 discrepant results between the anti-N and anti-S1-RBD assays, 5 of which were specimens collected ≥ 200 days post-PCR positivity and only had detectable levels of anti-S1-RBD antibodies. When only considering specimens collected ≥ 100 days post-PCR positivity (n = 41), the sensitivities for the anti-N and anti-S1-RBD assays were 85% and 98%, respectively.

Conclusions

The anti-S1-RBD assay demonstrated superior sensitivity at time points more remote to the PCR detection date, with 6 more specimens from the SARS-CoV-2-positive cohort detected, 5 of which were collected more than 200 days post-PCR positivity. While analytical differences and reagent lot-to-lot variability are possible, this may indicate that, in some instances, anti-S1-RBD antibodies may persist longer in vivo and may be a better target for detecting remote SARS-CoV-2 infection.

Diverse functional autoantibodies in patients with COVID-19

COVID-19 manifests with a wide spectrum of clinical phenotypes that are characterized by exaggerated and misdirected host immune responses1-6. Although pathological innate immune activation is well-documented in severe disease1, the effect of autoantibodies on disease progression is less well-defined. Here we use a high-throughput autoantibody discovery technique known as rapid extracellular antigen profiling7 to screen a cohort of 194 individuals infected with SARS-CoV-2, comprising 172 patients with COVID-19 and 22 healthcare workers with mild disease or asymptomatic infection, for autoantibodies against 2,770 extracellular and secreted proteins (members of the exoproteome). We found that patients with COVID-19 exhibit marked increases in autoantibody reactivities as compared to uninfected individuals, and show a high prevalence of autoantibodies against immunomodulatory proteins (including cytokines, chemokines, complement components and cell-surface proteins). We established that these autoantibodies perturb immune function and impair virological control by inhibiting immunoreceptor signalling and by altering peripheral immune cell composition, and found that mouse surrogates of these autoantibodies increase disease severity in a mouse model of SARS-CoV-2 infection. Our analysis of autoantibodies against tissue-associated antigens revealed associations with specific clinical characteristics. Our findings suggest a pathological role for exoproteome-directed autoantibodies in COVID-19, with diverse effects on immune functionality and associations with clinical outcomes.

Accuracy of Computable Phenotyping Approaches for SARS-CoV-2 Infection and COVID-19 Hospitalizations from the Electronic Health Record

Objective:

Real-world data have been critical for rapid-knowledge generation throughout the COVID-19 pandemic. To ensure high-quality results are delivered to guide clinical decision making and the public health response, as well as characterize the response to interventions, it is essential to establish the accuracy of COVID-19 case definitions derived from administrative data to identify infections and hospitalizations.

Methods:

Electronic Health Record (EHR) data were obtained from the clinical data warehouse of the Yale New Haven Health System (Yale, primary site) and 3 hospital systems of the Mayo Clinic (validation site). Detailed characteristics on demographics, diagnoses, and laboratory results were obtained for all patients with either a positive SARS-CoV-2 PCR or antigen test or ICD-10 diagnosis of COVID-19 (U07.1) between April 1, 2020 and March 1, 2021. Various computable phenotype definitions were evaluated for their accuracy to identify SARS-CoV-2 infection and COVID-19 hospitalizations.

Results:

Of the 69,423 individuals with either a diagnosis code or a laboratory diagnosis of a SARS-CoV-2 infection at Yale, 61,023 had a principal or a secondary diagnosis code for COVID-19 and 50,355 had a positive SARS-CoV-2 test. Among those with a positive laboratory test, 38,506 (76.5%) and 3449 (6.8%) had a principal and secondary diagnosis code of COVID-19, respectively, while 8400 (16.7%) had no COVID-19 diagnosis. Moreover, of the 61,023 patients with a COVID-19 diagnosis code, 19,068 (31.2%) did not have a positive laboratory test for SARS-CoV-2 in the EHR. Of the 20 cases randomly sampled from this latter group for manual review, all had a COVID-19 diagnosis code related to asymptomatic testing with negative subsequent test results. The positive predictive value (precision) and sensitivity (recall) of a COVID-19 diagnosis in the medical record for a documented positive SARS-CoV-2 test were 68.8% and 83.3%, respectively. Among 5,109 patients who were hospitalized with a principal diagnosis of COVID-19, 4843 (94.8%) had a positive SARS-CoV-2 test within the 2 weeks preceding hospital admission or during hospitalization. In addition, 789 hospitalizations had a secondary diagnosis of COVID-19, of which 446 (56.5%) had a principal diagnosis consistent with severe clinical manifestation of COVID-19 (e.g., sepsis or respiratory failure). Compared with the cohort that had a principal diagnosis of COVID-19, those with a secondary diagnosis had a more than 2-fold higher in-hospital mortality rate (13.2% vs 28.0%, P<0.001). In the validation sample at Mayo Clinic, diagnosis codes more consistently identified SARS-CoV-2 infection (precision of 95%) but had lower recall (63.5%) with substantial variation across the 3 Mayo Clinic sites. Similar to Yale, diagnosis codes consistently identified COVID-19 hospitalizations at Mayo, with hospitalizations defined by secondary diagnosis code with 2-fold higher in-hospital mortality compared to those with a primary diagnosis of COVID-19.

Conclusions:

COVID-19 diagnosis codes misclassified the SARS-CoV-2 infection status of many people, with implications for clinical research and epidemiological surveillance. Moreover, the codes had different performance across two academic health systems and identified groups with different risks of mortality. Real-world data from the EHR can be used to in conjunction with diagnosis codes to improve the identification of people infected with SARS-CoV-2.

Clinical characteristics and outcomes for 7,995 patients with SARS-CoV-2 infection

OBJECTIVE

Severe acute respiratory syndrome virus (SARS-CoV-2) has infected millions of people worldwide. Our goal was to identify risk factors associated with admission and disease severity in patients with SARS-CoV-2.

DESIGN

This was an observational, retrospective study based on real-world data for 7,995 patients with SARS-CoV-2 from a clinical data repository.

SETTING

Yale New Haven Health (YNHH) is a five-hospital academic health system serving a diverse patient population with community and teaching facilities in both urban and suburban areas.

POPULATIONS

The study included adult patients who had SARS-CoV-2 testing at YNHH between March 1 and April 30, 2020.

MAIN OUTCOME AND PERFORMANCE MEASURES

Primary outcomes were admission and in-hospital mortality for patients with SARS-CoV-2 infection as determined by RT-PCR testing. We also assessed features associated with the need for respiratory support.

RESULTS

Of the 28605 patients tested for SARS-CoV-2, 7995 patients (27.9%) had an infection (median age 52.3 years) and 2154 (26.9%) of these had an associated admission (median age 66.2 years). Of admitted patients, 2152 (99.9%) had a discharge disposition at the end of the study period. Of these, 329 (15.3%) required invasive mechanical ventilation and 305 (14.2%) expired. Increased age and male sex were positively associated with admission and in-hospital mortality (median age 80.7 years), while comorbidities had a much weaker association with the risk of admission or mortality. Black race (OR 1.43, 95%CI 1.14-1.78) and Hispanic ethnicity (OR 1.81, 95%CI 1.50-2.18) were identified as risk factors for admission, but, among discharged patients, age-adjusted in-hospital mortality was not significantly different among racial and ethnic groups.

CONCLUSIONS

This observational study identified, among people testing positive for SARS-CoV-2 infection, older age and male sex as the most strongly associated risks for admission and in-hospital mortality in patients with SARS-CoV-2 infection. While minority racial and ethnic groups had increased burden of disease and risk of admission, age-adjusted in-hospital mortality for discharged patients was not significantly different among racial and ethnic groups. Ongoing studies will be needed to continue to evaluate these risks, particularly in the setting of evolving treatment guidelines.

Temporal relationship of computed and structured diagnoses in electronic health record data

Background

The electronic health record (EHR) holds the prospect of providing more complete and timely access to clinical information for biomedical research, quality assessments, and quality improvement compared to other data sources, such as administrative claims. In this study, we sought to assess the completeness and timeliness of structured diagnoses in the EHR compared to computed diagnoses for hypertension (HTN), hyperlipidemia (HLD), and diabetes mellitus (DM).

Methods

We determined the amount of time for a structured diagnosis to be recorded in the EHR from when an equivalent diagnosis could be computed from other structured data elements, such as vital signs and laboratory results. We used EHR data for encounters from January 1, 2012 through February 10, 2019 from an academic health system. Diagnoses for HTN, HLD, and DM were computed for patients with at least two observations above threshold separated by at least 30 days, where the thresholds were outpatient blood pressure of ≥ 140/90 mmHg, any low-density lipoprotein ≥ 130 mg/dl, or any hemoglobin A1c ≥ 6.5%, respectively. The primary measure was the length of time between the computed diagnosis and the time at which a structured diagnosis could be identified within the EHR history or problem list.

Results

We found that 39.8% of those with HTN, 21.6% with HLD, and 5.2% with DM did not receive a corresponding structured diagnosis recorded in the EHR. For those who received a structured diagnosis, a mean of 389, 198, and 166 days elapsed before the patient had the corresponding diagnosis of HTN, HLD, or DM, respectively, recorded in the EHR.

Conclusions

We found a marked temporal delay between when a diagnosis can be computed or inferred and when an equivalent structured diagnosis is recorded within the EHR. These findings demonstrate the continued need for additional study of the EHR to avoid bias when using observational data and reinforce the need for computational approaches to identify clinical phenotypes.

Diverse Functional Autoantibodies in Patients with COVID-19

COVID-19 manifests with a wide spectrum of clinical phenotypes that are characterized by exaggerated and misdirected host immune responses1-8. While pathological innate immune activation is well documented in severe disease1, the impact of autoantibodies on disease progression is less defined. Here, we used a high-throughput autoantibody discovery technique called Rapid Extracellular Antigen Profiling (REAP) to screen a cohort of 194 SARS-CoV-2 infected COVID-19 patients and healthcare workers for autoantibodies against 2,770 extracellular and secreted proteins (the "exoproteome"). We found that COVID-19 patients exhibit dramatic increases in autoantibody reactivities compared to uninfected controls, with a high prevalence of autoantibodies against immunomodulatory proteins including cytokines, chemokines, complement components, and cell surface proteins. We established that these autoantibodies perturb immune function and impair virological control by inhibiting immunoreceptor signaling and by altering peripheral immune cell composition, and found that murine surrogates of these autoantibodies exacerbate disease severity in a mouse model of SARS-CoV-2 infection. Analysis of autoantibodies against tissue-associated antigens revealed associations with specific clinical characteristics and disease severity. In summary, these findings implicate a pathological role for exoproteome-directed autoantibodies in COVID-19 with diverse impacts on immune functionality and associations with clinical outcomes.

Big Data and Digital Solutions: Laying the Foundation for Cardiovascular Population Management CME

There are huge gaps in evidence-based cardiovascular care at the national, organizational, practice, and provider level that can be attributed to variation in provider attitudes, lack of incentives for positive change and care standardization, and observed uncertainty in clinical decision making. Big data analytics and digital application platforms-such as patient care dashboards, clinical decision support systems, mobile patient engagement applications, and key performance indicators-offer unique opportunities for value-based healthcare delivery and efficient cardiovascular population management. Successful implementation of big data solutions must include a multidisciplinary approach, including investment in big data platforms, harnessing technology to create novel digital applications, developing digital solutions that can inform the actions of clinical and policy decision makers and relevant stakeholders, and optimizing engagement strategies with the public and information-empowered patients.

Clinical Characteristics and Outcomes for 7,995 Patients with SARS-CoV-2 Infection

OBJECTIVE

Severe acute respiratory syndrome virus (SARS-CoV-2) has infected millions of people worldwide. Our goal was to identify risk factors associated with admission and disease severity in patients with SARS-CoV-2.

DESIGN

This was an observational, retrospective study based on real-world data for 7,995 patients with SARS-CoV-2 from a clinical data repository.

SETTING

Yale New Haven Health (YNHH) is a five-hospital academic health system serving a diverse patient population with community and teaching facilities in both urban and suburban areas.

POPULATIONS

The study included adult patients who had SARS-CoV-2 testing at YNHH between March 1 and April 30, 2020.

MAIN OUTCOME AND PERFORMANCE MEASURES

Primary outcomes were admission and in-hospital mortality for patients with SARS-CoV-2 infection as determined by RT-PCR testing. We also assessed features associated with the need for respiratory support.

RESULTS

Of the 28605 patients tested for SARS-CoV-2, 7995 patients (27.9%) had an infection (median age 52.3 years) and 2154 (26.9%) of these had an associated admission (median age 66.2 years). Of admitted patients, 2152 (99.9%) had a discharge disposition at the end of the study period. Of these, 329 (15.3%) required invasive mechanical ventilation and 305 (14.2%) expired. Increased age and male sex were positively associated with admission and in-hospital mortality (median age 80.7 years), while comorbidities had a much weaker association with the risk of admission or mortality. Black race (OR 1.43, 95%CI 1.14-1.78) and Hispanic ethnicity (OR 1.81, 95%CI 1.50-2.18) were identified as risk factors for admission, but, among discharged patients, age-adjusted in-hospital mortality was not significantly different among racial and ethnic groups.

CONCLUSIONS

This observational study identified, among people testing positive for SARSCoV-2 infection, older age and male sex as the most strongly associated risks for admission and in-hospital mortality in patients with SARS-CoV-2 infection. While minority racial and ethnic groups had increased burden of disease and risk of admission, age-adjusted in-hospital mortality for discharged patients was not significantly different among racial and ethnic groups. Ongoing studies will be needed to continue to evaluate these risks, particularly in the setting of evolving treatment guidelines.

Association between coronary artery bypass graft center volume and year-to-year outcome variability: New York and California statewide analysis

OBJECTIVE

We evaluated whether volume-based, rather than time-based, annual reporting of center outcomes for coronary artery bypass grafting may improve inference of quality, assuming that large center-level year-to-year outcome variability is related to statistical noise.

METHODS

We analyzed 2012 to 2016 data on isolated coronary artery bypass grafting using statewide outcome reports from New York and California. Annual changes in center-level observed-to-expected mortality ratio represented stability of year-to-year outcomes. Cubic spline fit related the annual observed-to-expected ratio change and center volume. Volume above the inflection point of the spline curve indicated centers with low year-to-year change in outcome. We compared observed-to-expected ratio changes between centers below and above the volume threshold and observed-to-expected ratio changes between consecutive annual and biennial measurements.

RESULTS

There were 155 centers with median annual volume of 89 (interquartile range, 55-160) for isolated coronary artery bypass grafting. The inflection point of observed-to-expected ratio variability was observed at 111 cases/year. Median year-to-year observed-to-expected ratio change for centers performing less than 111 cases (62 centers) was greater at 0.83 (0.26-1.59) compared with centers performing 111 cases or more (93 centers) at 0.49 (022-0.87) (P < .001). By aggregating the outcome over 2 years, centers above the 111-case threshold increased from 93 centers (60%) to 118 centers (76%), but the median observed-to-expected change for all centers was similar between annual aggregates at 0.70 (0.26-1.22) compared with observed-to-expected change between biennial aggregates at 0.54 (0.23-1.02) (P = .095).

CONCLUSIONS

Center-level, risk-adjusted coronary artery bypass grafting mortality varies significantly from one year to the next. Reporting outcomes by specific case volume may complement annual reports.

Development and Validation of the Quick COVID-19 Severity Index: A Prognostic Tool for Early Clinical Decompensation

STUDY OBJECTIVE

The goal of this study is to create a predictive, interpretable model of early hospital respiratory failure among emergency department (ED) patients admitted with coronavirus disease 2019 (COVID-19).

METHODS

This was an observational, retrospective, cohort study from a 9-ED health system of admitted adult patients with severe acute respiratory syndrome coronavirus 2 (COVID-19) and an oxygen requirement less than or equal to 6 L/min. We sought to predict respiratory failure within 24 hours of admission as defined by oxygen requirement of greater than 10 L/min by low-flow device, high-flow device, noninvasive or invasive ventilation, or death. Predictive models were compared with the Elixhauser Comorbidity Index, quick Sequential [Sepsis-related] Organ Failure Assessment, and the CURB-65 pneumonia severity score.

RESULTS

During the study period, from March 1 to April 27, 2020, 1,792 patients were admitted with COVID-19, 620 (35%) of whom had respiratory failure in the ED. Of the remaining 1,172 admitted patients, 144 (12.3%) met the composite endpoint within the first 24 hours of hospitalization. On the independent test cohort, both a novel bedside scoring system, the quick COVID-19 Severity Index (area under receiver operating characteristic curve mean 0.81 [95% confidence interval {CI} 0.73 to 0.89]), and a machine-learning model, the COVID-19 Severity Index (mean 0.76 [95% CI 0.65 to 0.86]), outperformed the Elixhauser mortality index (mean 0.61 [95% CI 0.51 to 0.70]), CURB-65 (0.50 [95% CI 0.40 to 0.60]), and quick Sequential [Sepsis-related] Organ Failure Assessment (0.59 [95% CI 0.50 to 0.68]). A low quick COVID-19 Severity Index score was associated with a less than 5% risk of respiratory decompensation in the validation cohort.

CONCLUSION

A significant proportion of admitted COVID-19 patients progress to respiratory failure within 24 hours of admission. These events are accurately predicted with bedside respiratory examination findings within a simple scoring system.

Patient factors associated with SARS-CoV-2 in an admitted emergency department population

Background

The SARS-CoV-2 (COVID-19) virus has wide community spread. The aim of this study was to describe patient characteristics and to identify factors associated with COVID-19 among emergency department (ED) patients under investigation for COVID-19 who were admitted to the hospital.

Methods

This was a retrospective observational study from 8 EDs within a 9-hospital health system. Patients with COVID-19 testing around the time of hospital admission were included. The primary outcome measure was COVID-19 test result. Patient characteristics were described and a multivariable logistic regression model was used to identify factors associated with a positive COVID-19 test.

Results

During the study period from March 1, 2020 to April 8, 2020, 2182 admitted patients had a test resulted for COVID-19. Of these patients, 786 (36%) had a positive test result. For COVID-19-positive patients, 63 (8.1%) died during hospitalization. COVID-19-positive patients had lower pulse oximetry (0.91 [95% confidence interval, CI], [0.88-0.94]), higher temperatures (1.36 [1.26-1.47]), and lower leukocyte counts than negative patients (0.78 [0.75-0.82]). Chronic lung disease (odds ratio [OR] 0.68, [0.52-0.90]) and histories of alcohol (0.64 [0.42-0.99]) or substance abuse (0.39 [0.25-0.62]) were less likely to be associated with a positive COVID-19 result.

Conclusion

We observed a high percentage of positive results among an admitted ED cohort under investigation for COVID-19. Patient factors may be useful in early differentiation of patients with COVID-19 from similarly presenting respiratory illnesses although no single factor will serve this purpose.

Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study

Background

Successful integrations of machine learning into routine clinical care are exceedingly rare, and barriers to its adoption are poorly characterized in the literature.

Objective

This study aims to report a quality improvement effort to integrate a deep learning sepsis detection and management platform, Sepsis Watch, into routine clinical care.

Methods

In 2016, a multidisciplinary team consisting of statisticians, data scientists, data engineers, and clinicians was assembled by the leadership of an academic health system to radically improve the detection and treatment of sepsis. This report of the quality improvement effort follows the learning health system framework to describe the problem assessment, design, development, implementation, and evaluation plan of Sepsis Watch.

Results

Sepsis Watch was successfully integrated into routine clinical care and reshaped how local machine learning projects are executed. Frontline clinical staff were highly engaged in the design and development of the workflow, machine learning model, and application. Novel machine learning methods were developed to detect sepsis early, and implementation of the model required robust infrastructure. Significant investment was required to align stakeholders, develop trusting relationships, define roles and responsibilities, and to train frontline staff, leading to the establishment of 3 partnerships with internal and external research groups to evaluate Sepsis Watch.

Conclusions

Machine learning models are commonly developed to enhance clinical decision making, but successful integrations of machine learning into routine clinical care are rare. Although there is no playbook for integrating deep learning into clinical care, learnings from the Sepsis Watch integration can inform efforts to develop machine learning technologies at other health care delivery systems.

The Promise of Big Data and Digital Solutions in Building a Cardiovascular Learning System: Opportunities and Barriers

The learning health system is a conceptual model for continuous learning and knowledge generation rooted in the daily practice of medicine. While companies such as Google and Amazon use dynamic learning systems that learn iteratively through every customer interaction, this efficiency has not materialized on a comparable scale in health systems. An ideal learning health system would learn from every patient interaction to benefit the care for the next patient. Notable advances include the greater use of data generated in the course of clinical care, Common Data Models, and advanced analytics. However, many remaining barriers limit the most effective use of large and growing health care data assets. In this review, we explore the accomplishments, opportunities, and barriers to realizing the learning health system.

Publication Trends in Psychotherapy: Bibliometric Analysis of the Past 5 Decades

OBJECTIVE

Bibliometric analyses are commonly used to document publication trends over time; however, this methodology has not been used to investigate possible trends concerning publishing about psychotherapy brands. In this study, the authors sought to identify the publication trends of peer-reviewed articles about 30 psychotherapy brands.

METHODS

Analyses were focused on the past 50 years and on each decade from 1970 to 2019. All searches were performed between October 2018 and January 2019 on the EbscoHost platform. Two databases were selected for the searches: PsycINFO and PubMed.

RESULTS

In the 28,594 articles reviewed, most published articles concerned cognitive-behavioral therapy (CBT), and five brands accounted for almost 78% of all publications: CBT, psychoanalysis, family systems therapy, behavioral therapy, and cognitive therapy. Three trends were identified across decades: five therapies consistently yielded the largest number of publications, the number of publications focused on therapies with less research support declined from the 1970s to the 1990s, and publications about therapies with more of a research basis increased in the 1990s through the 2010s. Publications on meditation and mindfulness presented the most salient growth area for all psychotherapies across the 5 decades. A few psychotherapy brands have dominated the publishing realm during the past 50 years and across each decade.

CONCLUSIONS

Possible explanations for these publication trends were considered, including the emergence of the evidence-based therapy movement and various sociohistorical changes. Potential psychotherapy publications trends in the future are discussed.

Agile Health Care Analytics: Enabling Real-Time Disease Surveillance With a Computational Health Platform

The ongoing coronavirus disease outbreak demonstrates the need for novel applications of real-time data to produce timely information about incident cases. Using health information technology (HIT) and real-world data, we sought to produce an interface that could, in near real time, identify patients presenting with suspected respiratory tract infection and enable monitoring of test results related to specific pathogens, including severe acute respiratory syndrome coronavirus 2. This tool was built upon our computational health platform, which provides access to near real-time data from disparate HIT sources across our health system. This combination of technology allowed us to rapidly prototype, iterate, and deploy a platform to support a cohesive organizational response to a rapidly evolving outbreak. Platforms that allow for agile analytics are needed to keep pace with evolving needs within the health care system.

Bridging the Collaboration Gap: Real-time Identification of Clinical Specimens for Biomedical Research

INTRODUCTION

Biomedical and translational research often relies on the evaluation of patients or specimens that meet specific clinical or laboratory criteria. The typical approach used to identify biospecimens is a manual, retrospective process that exists outside the clinical workflow. This often makes biospecimen collection cost prohibitive and prevents the collection of analytes with short stability times. Emerging data architectures offer novel approaches to enhance specimen-identification practices. To this end, we present a new tool that can be deployed in a real-time environment to automate the identification and notification of available biospecimens for biomedical research.

METHODS

Real-time clinical and laboratory data from Cloverleaf (Infor, NY, NY) were acquired within our computational health platform, which is built on open-source applications. Study-specific filters were developed in NiFi (Apache Software Foundation, Wakefield, MA, USA) to identify the study-appropriate specimens in real time. Specimen metadata were stored in Elasticsearch (Elastic N. V., Mountain View, CA, USA) for visualization and automated alerting.

RESULTS

Between June 2018 and December 2018, we identified 2992 unique specimens belonging to 2815 unique patients, split between two different use cases. Based on laboratory policy for specimen retention and study-specific stability requirements, secure E-mail notifications were sent to investigators to automatically notify of availability. The assessment of throughput on commodity hardware demonstrates the ability to scale to approximately 2000 results per second.

CONCLUSION

This work demonstrates that real-world clinical data can be analyzed in real time to increase the efficiency of biospecimen identification with minimal overhead for the clinical laboratory. Future work will integrate additional data types, including the analysis of unstructured data, to enable more complex cases and biospecimen identification.

A practical approach to storage and retrieval of high-frequency physiological signals

OBJECTIVE

Storage of physiological waveform data for retrospective analysis presents significant challenges. Resultant data can be very large, and therefore becomes expensive to store and complicated to manage. Traditional database approaches are not appropriate for large scale storage of physiological waveforms. Our goal was to apply modern time series compression and indexing techniques to the problem of physiological waveform storage and retrieval.

APPROACH

We deployed a vendor-agnostic data collection system and developed domain-specific compression approaches that allowed long term storage of physiological waveform data and other associated clinical and medical device data. The database (called AtriumDB) also facilitates rapid retrieval of retrospective data for high-performance computing and machine learning applications.

MAIN RESULTS

A prototype system has been recording data in a 42-bed pediatric critical care unit at The Hospital for Sick Children in Toronto, Ontario since February 2016. As of December 2019, the database contains over 720,000 patient-hours of data collected from over 5300 patients, all with complete waveform capture. One year of full resolution physiological waveform storage from this 42-bed unit can be losslessly compressed and stored in less than 300 GB of disk space. Retrospective data can be delivered to analytical applications at a rate of up to 50 million time-value pairs per second.

SIGNIFICANCE

Stored data are not pre-processed or filtered. Having access to a large retrospective dataset with realistic artefacts lends itself to the process of anomaly discovery and understanding. Retrospective data can be replayed to simulate a realistic streaming data environment where analytical tools can be rapidly tested at scale.

Effect of Age on the Initiation of Biologic Agent Therapy in Patients With Inflammatory Bowel Disease: Korean Common Data Model Cohort Study

BACKGROUND

The Observational Health Data Sciences and Informatics (OHDSI) network is an international collaboration established to apply open-source data analytics to a large network of health databases, including the Korean common data model (K-CDM) network.

OBJECTIVE

The aim of this study is to analyze the effect that age at diagnosis has on the prognosis of inflammatory bowel disease (IBD) in Korea using a CDM network database.

METHODS

We retrospectively analyzed the K-CDM network database from 2005 to 2015. We transformed the electronic medical record into the CDM version 5.0 used in OHDSI. A worsened IBD prognosis was defined as the initiation of therapy with biologic agents, including infliximab and adalimumab. To evaluate the effect that age at diagnosis had on the prognosis of IBD, we divided the patients into an early-onset (EO) IBD group (age at diagnosis <40 years) and a late-onset (LO) IBD group (age at diagnosis ≥40 years) with the cutoff value of age at diagnosis as 40 years, which was calculated using the Youden index method. We then used the logrank test and Cox proportional hazards model to analyze the effect that age at diagnosis (EO group vs LO group) had on the prognosis in patients with IBD.

RESULTS

A total of 3480 patients were enrolled. There was 2017 patients with ulcerative colitis (UC) and 1463 with Crohn's disease (CD). The median follow up period was 109.5 weeks. The EO UC group was statistically significant and showed less event-free survival (ie, experiences of biologic agents) than the LO UC group (P<.001). In CD, the EO CD group showed less event-free survival (ie, experiences of biologic agents) than the LO CD group. In the Cox proportional hazard analysis, the odds ratio (OR) of the EO UC group on experiences of biologic agents compared with the LO UC group was 2.3 (95% CI 1.3-3.8, P=.002). The OR of the EO CD group on experiences of biologic agents compared with the LO CD group was 5.4 (95% CI 1.9-14.9, P=.001).

CONCLUSIONS

The EO IBD group showed a worse prognosis than the LO IBD group in Korean patients with IBD. In addition, this study successfully verified the CDM model in gastrointestinal research.

Intellectual Structure and Evolutionary Trends of Precision Medicine Research: Coword Analysis

BACKGROUND

Precision medicine (PM) is playing a more and more important role in clinical practice. In recent years, the scale of PM research has been growing rapidly. Many reviews have been published to facilitate a better understanding of the status of PM research. However, there is still a lack of research on the intellectual structure in terms of topics.

OBJECTIVE

This study aimed to identify the intellectual structure and evolutionary trends of PM research through the application of various social network analysis and visualization methods.

METHODS

The bibliographies of papers published between 2009 and 2018 were extracted from the Web of Science database. Based on the statistics of keywords in the papers, a coword network was generated and used to calculate network indicators of both the entire network and local networks. Communities were then detected to identify subdirections of PM research. Topological maps of networks, including networks between communities and within each community, were drawn to reveal the correlation structure. An evolutionary graph and a strategic graph were finally produced to reveal research venation and trends in discipline communities.

RESULTS

The results showed that PM research involves extensive themes and, overall, is not balanced. A minority of themes with a high frequency and network indicators, such as Biomarkers, Genomics, Cancer, Therapy, Genetics, Drug, Target Therapy, Pharmacogenomics, Pharmacogenetics, and Molecular, can be considered the core areas of PM research. However, there were five balanced theme directions with distinguished status and tendencies: Cancer, Biomarkers, Genomics, Drug, and Therapy. These were shown to be the main branches that were both focused and well developed. Therapy, though, was shown to be isolated and undeveloped.

CONCLUSIONS

The hotspots, structures, evolutions, and development trends of PM research in the past ten years were revealed using social network analysis and visualization. In general, PM research is unbalanced, but its subdirections are balanced. The clear evolutionary and developmental trend indicates that PM research has matured in recent years. The implications of this study involving PM research will provide reasonable and effective support for researchers, funders, policymakers, and clinicians.

Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Clinic NLP-as-a-service implementation

Data is foundational to high-quality artificial intelligence (AI). Given that a substantial amount of clinically relevant information is embedded in unstructured data, natural language processing (NLP) plays an essential role in extracting valuable information that can benefit decision making, administration reporting, and research. Here, we share several desiderata pertaining to development and usage of NLP systems, derived from two decades of experience implementing clinical NLP at the Mayo Clinic, to inform the healthcare AI community. Using a framework, we developed as an example implementation, the desiderata emphasize the importance of a user-friendly platform, efficient collection of domain expert inputs, seamless integration with clinical data, and a highly scalable computing infrastructure.

Blood utilisation and transfusion reactions in adult patients transfused with conventional or pathogen-reduced platelets

Pathogen-reduced (PR) platelets are routinely used in many countries. Some studies reported changes in platelet and red blood cell (RBC) transfusion requirements in patients who received PR platelets when compared to conventional (CONV) platelets. Over a 28-month period we retrospectively analysed platelet utilisation, RBC transfusion trends, and transfusion reaction rates data from all transfused adult patients transfused at the Yale-New Haven Hospital, New Haven, CT, USA. We determined the number of RBC and platelet components administered between 2 and 24, 48, 72 or 96 h. A total of 3767 patients received 21 907 platelet components (CONV = 8912; PR = 12 995); 1,087 patients received only CONV platelets (1578 components) and 1,466 patients received only PR platelets (2604 components). The number of subsequently transfused platelet components was slightly higher following PR platelet components (P < 0·05); however, fewer RBCs were transfused following PR platelet administration (P < 0·05). The mean time-to-next platelet component transfusion was slightly shorter following PR platelet transfusion (P = 0·002). The rate of non-septic transfusion reactions did not differ (all P > 0·05). Septic transfusion reactions (N = 5) were seen only after CONV platelet transfusions (P = 0·011). These results provide evidence for comparable clinical efficacy of PR and CONV platelets. PR platelets eliminated septic transfusion reactions without increased risk of other types of transfusions with only slight increase in platelet utilisation.