OneFlorida Clinical Research Consortium: Linking a Clinical and Translational Science Institute With a Community-Based Distributive Medical Education Model

Lessons on the use of real-world data in medical device research: findings from the National Evaluation System for Health Technology Test-Cases

Aim: Although the US FDA encourages manufacturers of medical devices to submit real-world evidence (RWE) to support regulatory decisions, the ability of real-world data (RWD) to generate evidence suitable for decision making remains unclear. The 2017 Medical Device User Fee Amendments (MDUFA IV), authorized the National Evaluation System for health Technology Coordinating Center (NESTcc) to conduct pilot projects, or 'Test-Cases', to assess whether current RWD captures the information needed to answer research questions proposed by industry stakeholders. We synthesized key lessons about the challenges conducting research with RWD and the strategies used by research teams to enhance their ability to generate evidence from RWD based on 18 Test-Cases conducted between 2020 and 2022. Materials & methods: We reviewed study protocols and reports from each Test-Case team and conducted 49 semi-structured interviews with representatives of participating organizations. Interview transcripts were coded and thematically analyzed. Results: Challenges that stakeholders encountered in working with RWD included the lack of unique device identifiers, capturing key data elements and their appropriate meaning in structured data, limited reliability of diagnosis and procedure codes in structured data, extracting information from unstructured electronic health record (EHR) data, limited capture of long-term study end points, missing data and data sharing. Successful strategies included using manufacturer and supply chain data, leveraging clinical registries and registry reporting processes to collect and aggregate data, querying standardized EHR data, implementing natural language processing algorithms and using multidisciplinary research teams. Conclusion: The Test-Cases identified numerous challenges working with RWD but also opportunities to address these challenges and improve researchers' ability to use RWD to generate evidence on medical devices.

Identification of risk factors of Long COVID and predictive modeling in the RECOVER EHR cohorts

BACKGROUND

SARS-CoV-2-infected patients may develop new conditions in the period after the acute infection. These conditions, the post-acute sequelae of SARS-CoV-2 infection (PASC, or Long COVID), involve a diverse set of organ systems. Limited studies have investigated the predictability of Long COVID development and its associated risk factors.

METHODS

In this retrospective cohort study, we used electronic healthcare records from two large-scale PCORnet clinical research networks, INSIGHT (~1.4 million patients from New York) and OneFlorida+ (~0.7 million patients from Florida), to identify factors associated with having Long COVID, and to develop machine learning-based models for predicting Long COVID development. Both SARS-CoV-2-infected and non-infected adults were analysed during the period of March 2020 to November 2021. Factors associated with Long COVID risk were identified by removing background associations and correcting for multiple tests.

RESULTS

We observed complex association patterns between baseline factors and a variety of Long COVID conditions, and we highlight that severe acute SARS-CoV-2 infection, being underweight, and having baseline comorbidities (e.g., cancer and cirrhosis) are likely associated with increased risk of developing Long COVID. Several Long COVID conditions, e.g., dementia, malnutrition, chronic obstructive pulmonary disease, heart failure, PASC diagnosis U099, and acute kidney failure are well predicted (C-index > 0.8). Moderately predictable conditions include atelectasis, pulmonary embolism, diabetes, pulmonary fibrosis, and thromboembolic disease (C-index 0.7-0.8). Less predictable conditions include fatigue, anxiety, sleep disorders, and depression (C-index around 0.6).

CONCLUSIONS

This observational study suggests that association patterns between investigated factors and Long COVID are complex, and the predictability of different Long COVID conditions varies. However, machine learning-based predictive models can help in identifying patients who are at risk of developing a variety of Long COVID conditions.

Autoencoder to Identify Sex-Specific Sub-phenotypes in Alzheimer's Disease Progression Using Longitudinal Electronic Health Records

Alzheimer's Disease (AD) is a complex neurodegenerative disorder significantly influenced by sex differences, with approximately two-thirds of AD patients being women. Characterizing the sex-specific AD progression and identifying its progression trajectory is a crucial step to developing effective risk stratification and prevention strategies. In this study, we developed an autoencoder to uncover sex-specific sub-phenotypes in AD progression leveraging longitudinal electronic health record (EHR) data from OneFlorida+ Clinical Research Consortium. Specifically, we first constructed temporal patient representation using longitudinal EHRs from a sex-stratified AD cohort. We used a long short-term memory (LSTM)-based autoencoder to extract and generate latent representation embeddings from sequential clinical records of patients. We then applied hierarchical agglomerative clustering to the learned representations, grouping patients based on their progression sub-phenotypes. The experimental results show we successfully identified five primary sex-based AD sub-phenotypes with corresponding progression pathways with high confidence. These sex-specific sub-phenotypes not only illustrated distinct AD progression patterns but also revealed differences in clinical characteristics and comorbidities between females and males in AD development. These findings could provide valuable insights for advancing personalized AD intervention and treatment strategies.

Identification of Parkinson's disease PACE subtypes and repurposing treatments through integrative analyses of multimodal data

Parkinson's disease (PD) is a serious neurodegenerative disorder marked by significant clinical and progression heterogeneity. This study aimed at addressing heterogeneity of PD through integrative analysis of various data modalities. We analyzed clinical progression data (≥5 years) of individuals with de novo PD using machine learning and deep learning, to characterize individuals' phenotypic progression trajectories for PD subtyping. We discovered three pace subtypes of PD exhibiting distinct progression patterns: the Inching Pace subtype (PD-I) with mild baseline severity and mild progression speed; the Moderate Pace subtype (PD-M) with mild baseline severity but advancing at a moderate progression rate; and the Rapid Pace subtype (PD-R) with the most rapid symptom progression rate. We found cerebrospinal fluid P-tau/α-synuclein ratio and atrophy in certain brain regions as potential markers of these subtypes. Analyses of genetic and transcriptomic profiles with network-based approaches identified molecular modules associated with each subtype. For instance, the PD-R-specific module suggested STAT3, FYN, BECN1, APOA1, NEDD4, and GATA2 as potential driver genes of PD-R. It also suggested neuroinflammation, oxidative stress, metabolism, PI3K/AKT, and angiogenesis pathways as potential drivers for rapid PD progression (i.e., PD-R). Moreover, we identified repurposable drug candidates by targeting these subtype-specific molecular modules using network-based approach and cell line drug-gene signature data. We further estimated their treatment effects using two large-scale real-world patient databases; the real-world evidence we gained highlighted the potential of metformin in ameliorating PD progression. In conclusion, this work helps better understand clinical and pathophysiological complexity of PD progression and accelerate precision medicine.

Excess burden of respiratory and abdominal conditions following COVID-19 infections during the ancestral and Delta variant periods in the United States: An EHR-based cohort study from the RECOVER program

IMPORTANCE

The frequency and characteristics of post-acute sequelae of SARS-CoV-2 infection (PASC) may vary by SARS-CoV-2 variant.

OBJECTIVE

To characterize PASC-related conditions among individuals likely infected by the ancestral strain in 2020 and individuals likely infected by the Delta variant in 2021.

DESIGN

Retrospective cohort study of electronic medical record data for approximately 27 million patients from March 1, 2020-November 30, 2021.

SETTING

Healthcare facilities in New York and Florida.

PARTICIPANTS

Patients who were at least 20 years old and had diagnosis codes that included at least one SARS-CoV-2 viral test during the study period.

EXPOSURE

Laboratory-confirmed COVID-19 infection, classified by the most common variant prevalent in those regions at the time.

MAIN OUTCOME(S) AND MEASURE(S)

Relative risk (estimated by adjusted hazard ratio [aHR]) and absolute risk difference (estimated by adjusted excess burden) of new conditions, defined as new documentation of symptoms or diagnoses, in persons between 31-180 days after a positive COVID-19 test compared to persons without a COVID-19 test or diagnosis during the 31-180 days after the last negative test.

RESULTS

We analyzed data from 560,752 patients. The median age was 57 years; 60.3% were female, 20.0% non-Hispanic Black, and 19.6% Hispanic. During the study period, 57,616 patients had a positive SARS-CoV-2 test; 503,136 did not. For infections during the ancestral strain period, pulmonary fibrosis, edema (excess fluid), and inflammation had the largest aHR, comparing those with a positive test to those without a COVID-19 test or diagnosis (aHR 2.32 [95% CI 2.09 2.57]), and dyspnea (shortness of breath) carried the largest excess burden (47.6 more cases per 1,000 persons). For infections during the Delta period, pulmonary embolism had the largest aHR comparing those with a positive test to a negative test (aHR 2.18 [95% CI 1.57, 3.01]), and abdominal pain carried the largest excess burden (85.3 more cases per 1,000 persons).

CONCLUSIONS AND RELEVANCE

We documented a substantial relative risk of pulmonary embolism and a large absolute risk difference of abdomen-related symptoms after SARS-CoV-2 infection during the Delta variant period. As new SARS-CoV-2 variants emerge, researchers and clinicians should monitor patients for changing symptoms and conditions that develop after infection.

Artificial intelligence and open science in discovery of disease-modifying medicines for Alzheimer's disease

The high failure rate of clinical trials in Alzheimer's disease (AD) and AD-related dementia (ADRD) is due to a lack of understanding of the pathophysiology of disease, and this deficit may be addressed by applying artificial intelligence (AI) to "big data" to rapidly and effectively expand therapeutic development efforts. Recent accelerations in computing power and availability of big data, including electronic health records and multi-omics profiles, have converged to provide opportunities for scientific discovery and treatment development. Here, we review the potential utility of applying AI approaches to big data for discovery of disease-modifying medicines for AD/ADRD. We illustrate how AI tools can be applied to the AD/ADRD drug development pipeline through collaborative efforts among neurologists, gerontologists, geneticists, pharmacologists, medicinal chemists, and computational scientists. AI and open data science expedite drug discovery and development of disease-modifying therapeutics for AD/ADRD and other neurodegenerative diseases.

Demographics, Trends, and Clinical Characteristics of HIV Pre-Exposure Prophylaxis Recipients and People Newly Diagnosed with HIV from Large Electronic Health Records in Florida

Florida is one of the HIV epicenters with high incidence and marked sociodemographic disparities. We analyzed a decade of statewide electronic health record/claims data-OneFlorida+-to identify and characterize pre-exposure prophylaxis (PrEP) recipients and newly diagnosed HIV cases in Florida. Refined computable phenotype algorithms were applied and a total of 2186 PrEP recipients and 7305 new HIV diagnoses were identified between January 2013 and April 2021. We examined patients' sociodemographic characteristics, stratified by self-reported sex, along with both frequency-driven and expert-selected descriptions of clinical conditions documented within 12 months before the first PrEP use or HIV diagnosis. PrEP utilization rate increased in both sexes; higher rates were observed among males with sex differences widening in recent years. HIV incidence peaked in 2016 and then decreased with minimal sex differences observed. Clinical characteristics were similar between the PrEP and new HIV diagnosis cohorts, characterized by a low prevalence of sexually transmitted infections (STIs) and a high prevalence of mental health and substance use conditions. Study limitations include the overrepresentation of Medicaid recipients, with over 96% of female PrEP users on Medicaid, and the inclusion of those engaged in regular health care. Although PrEP uptake increased in Florida, and HIV incidence decreased, sex disparity among PrEP recipients remained. Screening efforts beyond individuals with documented prior STI and high-risk behavior, especially for females, including integration of mental health care with HIV counseling and testing, are crucial to further equalize PrEP access and improve HIV prevention programs.

The role of health system penetration rate in estimating the prevalence of type 1 diabetes in children and adolescents using electronic health records

OBJECTIVE

Having sufficient population coverage from the electronic health records (EHRs)-connected health system is essential for building a comprehensive EHR-based diabetes surveillance system. This study aimed to establish an EHR-based type 1 diabetes (T1D) surveillance system for children and adolescents across racial and ethnic groups by identifying the minimum population coverage from EHR-connected health systems to accurately estimate T1D prevalence.

MATERIALS AND METHODS

We conducted a retrospective, cross-sectional analysis involving children and adolescents <20 years old identified from the OneFlorida+ Clinical Research Network (2018-2020). T1D cases were identified using a previously validated computable phenotyping algorithm. The T1D prevalence for each ZIP Code Tabulation Area (ZCTA, 5 digits), defined as the number of T1D cases divided by the total number of residents in the corresponding ZCTA, was calculated. Population coverage for each ZCTA was measured using observed health system penetration rates (HSPR), which was calculated as the ratio of residents in the corresponding ZTCA and captured by OneFlorida+ to the overall population in the same ZCTA reported by the Census. We used a recursive partitioning algorithm to identify the minimum required observed HSPR to estimate T1D prevalence and compare our estimate with the reported T1D prevalence from the SEARCH study.

RESULTS

Observed HSPRs of 55%, 55%, and 60% were identified as the minimum thresholds for the non-Hispanic White, non-Hispanic Black, and Hispanic populations. The estimated T1D prevalence for non-Hispanic White and non-Hispanic Black were 2.87 and 2.29 per 1000 youth, which are comparable to the reference study's estimation. The estimated prevalence of T1D for Hispanics (2.76 per 1000 youth) was higher than the reference study's estimation (1.48-1.64 per 1000 youth). The standardized T1D prevalence in the overall Florida population was 2.81 per 1000 youth in 2019.

CONCLUSION

Our study provides a method to estimate T1D prevalence in children and adolescents using EHRs and reports the estimated HSPRs and prevalence of T1D for different race and ethnicity groups to facilitate EHR-based diabetes surveillance.

High-throughput target trial emulation for Alzheimer's disease drug repurposing with real-world data

Target trial emulation is the process of mimicking target randomized trials using real-world data, where effective confounding control for unbiased treatment effect estimation remains a main challenge. Although various approaches have been proposed for this challenge, a systematic evaluation is still lacking. Here we emulated trials for thousands of medications from two large-scale real-world data warehouses, covering over 10 years of clinical records for over 170 million patients, aiming to identify new indications of approved drugs for Alzheimer's disease. We assessed different propensity score models under the inverse probability of treatment weighting framework and suggested a model selection strategy for improved baseline covariate balancing. We also found that the deep learning-based propensity score model did not necessarily outperform logistic regression-based methods in covariate balancing. Finally, we highlighted five top-ranked drugs (pantoprazole, gabapentin, atorvastatin, fluticasone, and omeprazole) originally intended for other indications with potential benefits for Alzheimer's patients.

Linking coastal environmental and health observations for human wellbeing

Coastal areas have long been attractive places to live, work, and recreate and remain so even in the face of growing threats from global environmental change. At any moment, a significant portion of the human population is exposed to both positive and negative health effects associated with coastal locations. Some locations may be "hotspots" of concern for human health due to ongoing climatic and other changes, accentuating the need for better understanding of coastal environment-human health linkages. This paper describes how environmental and health data could be combined to create a coastal environmental and human health observing system. While largely based on information from the US and Europe, the concept should be relevant to almost any coastal area. If implemented, a coastal health observing system would connect a variety of human health data and environmental observations for individuals and communities, and where possible cohorts. Health data would be derived from questionnaires and other personal sources, clinical examinations, electronic health records, wearable devices, and syndromic surveillance, plus information on vulnerability and health-relevant community characteristics, and social media observations. Environmental data sources would include weather and climate, beach and coastal conditions, sentinel species, occurrences of harmful organisms and substances, seafood safety advisories, and distribution, proximity, and characteristics of health-promoting green and blue spaces. Where available, information on supporting resources could be added. Establishment of a linked network of coastal health observatories could provide powerful tools for understanding the positive and negative health effects of coastal living, lead to better health protections and enhanced wellbeing, and provide significant benefits to coastal residents, including the historically disadvantaged, as well as the military, hospitals and emergency departments, academic medical, public health, and environmental health programs, and others. Early networks could provide best practices and lessons learned to assist later entries.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Evaluation of a Computable Phenotype for Successful Cognitive Aging

Objective

To establish, apply, and evaluate a computable phenotype for the recruitment of individuals with successful cognitive aging.

Participants and Methods

Interviews with 10 aging experts identified electronic health record (EHR)-available variables representing successful aging among individuals aged 85 years and older. On the basis of the identified variables, we developed a rule-based computable phenotype algorithm composed of 17 eligibility criteria. Starting September 1, 2019, we applied the computable phenotype algorithm to all living persons aged 85 years and older at the University of Florida Health, which identified 24,024 individuals. This sample was comprised of 13,841 (58%) women, 13,906 (58%) Whites, and 16,557 (69%) non-Hispanics. A priori permission to be contacted for research had been obtained for 11,898 individuals, of whom 470 responded to study announcements and 333 consented to evaluation. Then, we contacted those who consented to evaluate whether their cognitive and functional status clinically met out successful cognitive aging criteria of a modified Telephone Interview for Cognitive Status score of more than 27 and Geriatric Depression Scale of less than 6. The study was completed on December 31, 2022.

Results

Of the 45% of living persons aged 85 years and older included in the University of Florida Health EHR database identified by the computable phenotype as successfully aged, approximately 4% of these responded to study announcements and 333 consented, of which 218 (65%) met successful cognitive aging criteria through direct evaluation.

Conclusion

The study evaluated a computable phenotype algorithm for the recruitment of individuals for a successful aging study using large-scale EHRs. Our study provides proof of concept of using big data and informatics as aids for the recruitment of individuals for prospective cohort studies.

Adverse Cardiovascular Events Associated With Cyclin-Dependent Kinase 4/6 Inhibitors in Patients With Metastatic Breast Cancer

Background Cyclin-dependent kinase (CDK) 4 and 6 inhibitors have significantly improved survival in patients with hormone receptor-positive metastatic breast cancer. There are few data regarding the epidemiology of cardiovascular adverse events (CVAEs) with these therapies. Methods and Results Using the OneFlorida Data Trust, adult patients without prior cardiovascular disease who received at least 1 CDK4/6 inhibitor were included in the analysis. CVAEs identified from International Classification of Diseases, Ninth and Tenth Revisions (ICD-9/10) codes included hypertension, atrial fibrillation(AF)/atrial flutter (AFL), heart failure/cardiomyopathy, ischemic heart disease, and pericardial disease. Competing risk analysis (Fine-Gray model) was used to determine the association between CDK4/6 inhibitor therapy and incident CVAEs. The effect of CVAEs on all-cause death was studied using Cox proportional hazard models. Propensity-weight analyses were performed to compare these patients to a cohort of patients treated with anthracyclines. A total of 1376 patients treated with CDK4/6 inhibitors were included in the analysis. CVAEs occurred in 24% (35.9 per 100 person-years). CVAEs were slightly higher in patients who received CKD4/6 inhibitors compared with anthracyclines (P=0.063), with higher death rate associated with the development of AF/AFL or cardiomyopathy/heart failure in the CDK4/6 group. The development of cardiomyopathy/heart failure and AF/AFL was associated with increased all-cause death (adjusted hazard ratio [HR], 4.89 [95% CI, 2.98-8.05]; and 5.88 [95% CI, 3.56-9.73], respectively). Conclusions CVAEs may be more common with CDK4/6 inhibitors than previously recognized, with increased death rates in these patients who develop AF/AFL or heart failure. Further research is needed to definitively determine cardiovascular risk associated with these novel anticancer treatments.

Stratified split sampling of electronic health records

Although superficially similar to data from clinical research, data extracted from electronic health records may require fundamentally different approaches for model building and analysis. Because electronic health record data is designed for clinical, rather than scientific use, researchers must first provide clear definitions of outcome and predictor variables. Yet an iterative process of defining outcomes and predictors, assessing association, and then repeating the process may increase Type I error rates, and thus decrease the chance of replicability, defined by the National Academy of Sciences as the chance of "obtaining consistent results across studies aimed at answering the same scientific question, each of which has obtained its own data."[1] In addition, failure to account for subgroups may mask heterogeneous associations between predictor and outcome by subgroups, and decrease the generalizability of the findings. To increase chances of replicability and generalizability, we recommend using a stratified split sample approach for studies using electronic health records. A split sample approach divides the data randomly into an exploratory set for iterative variable definition, iterative analyses of association, and consideration of subgroups. The confirmatory set is used only to replicate results found in the first set. The addition of the word 'stratified' indicates that rare subgroups are oversampled randomly by including them in the exploratory sample at higher rates than appear in the population. The stratified sampling provides a sufficient sample size for assessing heterogeneity of association by testing for effect modification by group membership. An electronic health record study of the associations between socio-demographic factors and uptake of hepatic cancer screening, and potential heterogeneity of association in subgroups defined by gender, self-identified race and ethnicity, census-tract level poverty and insurance type illustrates the recommended approach.

Racial and Ethnic Differences in Cardiac Surveillance Evaluation of Patients Treated With Anthracycline-Based Chemotherapy

Background Anthracyclines remain a key treatment for many malignancies but can increase the risk of heart failure or cardiomyopathy. Specific guidelines recommend echocardiography and serum cardiac biomarkers such as BNP (B-type natriuretic peptide) or NT-proBNP (N-terminal proBNP) evaluation before and 6 to 12 months after treatment. Our objective was to evaluate associations between racial and ethnic groups in cardiac surveillance of survivors of cancer after exposure to anthracyclines. Methods and Results Adult patients in the OneFlorida Consortium without prior cardiovascular disease who received at least 2 cycles of anthracyclines were included in the analysis. Multivariable logistic regression was performed to estimate the odds ratios (ORs) and 95% CIs for receiving cardiac surveillance at baseline before anthracycline therapy, 6 months after, and 12 months after anthracycline exposure among different racial and ethnic groups. Among the entire cohort of 5430 patients, 63.4% had a baseline echocardiogram, with 22.3% receiving an echocardiogram at 6 months and 25% at 12 months. Non-Hispanic Black (NHB) patients had a lower likelihood of receiving a baseline echocardiogram than Non-Hispanic White (NHW) patients (OR, 0.75 [95% CI, 0.63-0.88]; P=0.0006) or any baseline cardiac surveillance (OR, 0.76 [95% CI, 0.64-0.89]; P=0.001). Compared with NHW patients, Hispanic patients received significantly less cardiac surveillance at the 6-month (OR, 0.84 [95% CI, 0.72-0.98]; P=0.03) and 12-month (OR, 0.85 [95% CI, 0.74-0.98]; P=0.03) time points, respectively. Conclusions There were significant racial and ethnic differences in cardiac surveillance among survivors of cancer at baseline and following anthracycline-based treatment in NHB and Hispanic cohorts. Health care providers need to be cognizant of these social inequities and initiate efforts to ensure recommended cardiac surveillance occurs following anthracyclines.

A spatial and contextual exposome-wide association study and polyexposomic score of COVID-19 hospitalization

Environmental exposures have been linked to COVID-19 severity. Previous studies examined very few environmental factors, and often only separately without considering the totality of the environment, or the exposome. In addition, existing risk prediction models of severe COVID-19 predominantly rely on demographic and clinical factors. To address these gaps, we conducted a spatial and contextual exposome-wide association study (ExWAS) and developed polyexposomic scores (PES) of COVID-19 hospitalization leveraging rich information from individuals' spatial and contextual exposome. Individual-level electronic health records of 50 368 patients aged 18 years and older with a positive SARS-CoV-2 PCR/Antigen lab test or a COVID-19 diagnosis between March 2020 and October 2021 were obtained from the OneFlorida+ Clinical Research Network. A total of 194 spatial and contextual exposome factors from 10 data sources were spatiotemporally linked to each patient based on geocoded residential histories. We used a standard two-phase procedure in the ExWAS and developed and validated PES using gradient boosting decision trees models. Four exposome measures significantly associated with COVID-19 hospitalization were identified, including 2-chloroacetophenone, low food access, neighborhood deprivation, and reduced access to fitness centers. The initial prediction model in all patients without considering exposome factors had a testing-area under the curve (AUC) of 0.778. Incorporation of exposome data increased the testing-AUC to 0.787. Similar findings were observed in subgroup analyses focusing on populations without comorbidities and aged 18-24 years old. This spatial and contextual exposome study of COVID-19 hospitalization confirmed previously reported risk factor but also generated novel predictors that warrant more focused evaluation.

Pediatric and adult asthma clinical phenotypes: a real world, big data study based on acute exacerbations

INTRODUCTION

Asthma is a heterogeneous disease with a range of observable phenotypes. To date, the characterization of asthma phenotypes is mostly limited to allergic versus non-allergic disease. Therefore, the aim of this big data study was to computationally derive asthma subtypes from the OneFlorida Clinical Research Consortium.

METHODS

We obtained data from 2012-2020 from the OneFlorida Clinical Research Consortium. Longitudinal data for patients greater than two years of age who met inclusion criteria for an asthma exacerbation based on International Classification of Diseases codes. We used matrix factorization to extract information and K-means clustering to derive subtypes. The distributions of demographics, comorbidities, and medications were compared using Chi-square statistics.

RESULTS

A total of 39,807 pediatric patients and 23,883 adult patients met inclusion criteria. We identified five distinct pediatric subtypes and four distinct adult subtypes. Pediatric subtype P1 had the highest proportion of black patients, but the lowest use of inhaled corticosteroids and allergy medications. Subtype P2 had a predominance of patients with gastroesophageal reflux disease, whereas P3 had a predominance of patients with allergic disorders. Adult subtype A2 was the most severe and all patients were on biologic agents. Most of subtype A3 patients were not taking controller medications, whereas most patients (>90%) in subtypes A2 and A4 were taking corticosteroids and allergy medications.

CONCLUSION

We found five distinct pediatric asthma subtypes and four distinct adult asthma subtypes. Future work should externally validate these subtypes and characterize response to treatment by subtype to better guide clinical treatment of asthma.

Cancer incidence after asthma diagnosis: Evidence from a large clinical research network in the United States

BACKGROUND

Prior studies on the association between asthma and cancer show inconsistent results. This study aimed to generate additional evidence on the association between asthma and cancer, both overall, and by cancer type, in the United States.

METHOD

We conducted a retrospective cohort study using 2012-2020 electronic health records and claims data in the OneFlorida+ clinical research network. Our study population included a cohort of adult patients with asthma (n = 90,021) and a matching cohort of adult patients without asthma (n = 270,063). We built Cox proportional hazards models to examine the association between asthma diagnosis and subsequent cancer risk.

RESULTS

Our results showed that asthma patients were more likely to develop cancer compared to patients without asthma in multivariable analysis (hazard ratio [HR] = 1.36, 99% confidence interval [CI] = 1.29-1.44). Elevated cancer risk was observed in asthma patients without (HR = 1.60; 99% CI: 1.50-1.71) or with (HR = 1.11; 99% CI: 1.03-1.21) inhaled steroid use. However, in analyses of specific cancer types, cancer risk was elevated for nine of 13 cancers in asthma patients without inhaled steroid use but only for two of 13 cancers in asthma patients with inhaled steroid use, suggesting a protective effect of inhaled steroid use on cancer.

CONCLUSION

This is the first study to report a positive association between asthma and overall cancer risk in the US population. More in-depth studies using real-word data are needed to further explore the causal mechanisms of asthma on cancer risk.

Impacts of Eligibility Criteria on Trial Participants' Age in Alzheimer's Disease Clinical Trials

Overly restricted and poorly designed eligibility criteria reduce the generalizability of the results from clinical trials. We conducted a study to identify and quantify the impacts of study traits extracted from eligibility criteria on the age of study populations in Alzheimer's Disease (AD) clinical trials. Using machine learning methods and SHapley Additive exPlanation (SHAP) values, we identified 30 and 34 study traits that excluded older patients from AD trials in our 2 generated target populations respectively. We also found that study traits had different magnitudes of impacts on the age distributions of the generated study populations across racial-ethnic groups. To our best knowledge, this was the first study that quantified the impact of eligibility criteria on the age of AD trial participants. Our research is a first step in addressing the overly restrictive eligibility criteria in AD clinical trials.

Data-driven analysis to understand long COVID using electronic health records from the RECOVER initiative

Recent studies have investigated post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) using real-world patient data such as electronic health records (EHR). Prior studies have typically been conducted on patient cohorts with specific patient populations which makes their generalizability unclear. This study aims to characterize PASC using the EHR data warehouses from two large Patient-Centered Clinical Research Networks (PCORnet), INSIGHT and OneFlorida+, which include 11 million patients in New York City (NYC) area and 16.8 million patients in Florida respectively. With a high-throughput screening pipeline based on propensity score and inverse probability of treatment weighting, we identified a broad list of diagnoses and medications which exhibited significantly higher incidence risk for patients 30-180 days after the laboratory-confirmed SARS-CoV-2 infection compared to non-infected patients. We identified more PASC diagnoses in NYC than in Florida regarding our screening criteria, and conditions including dementia, hair loss, pressure ulcers, pulmonary fibrosis, dyspnea, pulmonary embolism, chest pain, abnormal heartbeat, malaise, and fatigue, were replicated across both cohorts. Our analyses highlight potentially heterogeneous risks of PASC in different populations.

Identifying environmental risk factors for post-acute sequelae of SARS-CoV-2 infection: An EHR-based cohort study from the recover program

Post-acute sequelae of SARS-CoV-2 infection (PASC) affects a wide range of organ systems among a large proportion of patients with SARS-CoV-2 infection. Although studies have identified a broad set of patient-level risk factors for PASC, little is known about the association between "exposome"-the totality of environmental exposures and the risk of PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified environmental risk factors for 23 PASC symptoms and conditions from nearly 200 exposome factors. The three domains of exposome include natural environment, built environment, and social environment. We conducted a two-phase environment-wide association study. In Phase 1, we ran a mixed effects logistic regression with 5-digit ZIP Code tabulation area (ZCTA5) random intercepts for each PASC outcome and each exposome factor, adjusting for a comprehensive set of patient-level confounders. In Phase 2, we ran a mixed effects logistic regression for each PASC outcome including all significant (false positive discovery adjusted p-value < 0.05) exposome characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), particulate matter (PM2.5) compositions (e.g., ammonium), neighborhood deprivation, and built environment (e.g., food access) that were associated with increased risk of PASC conditions related to nervous, blood, circulatory, endocrine, and other organ systems. Specific environmental risk factors for each PASC condition and symptom were different across the New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular exposome characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.

Risk Factors and Predictive Modeling for Post-Acute Sequelae of SARS-CoV-2 Infection: Findings from EHR Cohorts of the RECOVER Initiative

Background

Patients who were SARS-CoV-2 infected could suffer from newly incidental conditions in their post-acute infection period. These conditions, denoted as the post-acute sequelae of SARS-CoV-2 infection (PASC), are highly heterogeneous and involve a diverse set of organ systems. Limited studies have investigated the predictability of these conditions and their associated risk factors.

Method

In this retrospective cohort study, we investigated two large-scale PCORnet clinical research networks, INSIGHT and OneFlorida+, including 11 million patients in the New York City area and 16.8 million patients from Florida, to develop machine learning prediction models for those who are at risk for newly incident PASC and to identify factors associated with newly incident PASC conditions. Adult patients aged 20 with SARS-CoV-2 infection and without recorded infection between March 1st, 2020, and November 30th, 2021, were used for identifying associated factors with incident PASC after removing background associations. The predictive models were developed on infected adults.

Results

We find several incident PASC, e.g., malnutrition, COPD, dementia, and acute kidney failure, were associated with severe acute SARS-CoV-2 infection, defined by hospitalization and ICU stay. Older age and extremes of weight were also associated with these incident conditions. These conditions were better predicted (C-index >0.8). Moderately predictable conditions included diabetes and thromboembolic disease (C-index 0.7-0.8). These were associated with a wider variety of baseline conditions. Less predictable conditions included fatigue, anxiety, sleep disorders, and depression (C-index around 0.6).

Conclusions

This observational study suggests that a set of likely risk factors for different PASC conditions were identifiable from EHRs, predictability of different PASC conditions was heterogeneous, and using machine learning-based predictive models might help in identifying patients who were at risk of developing incident PASC.

Excess burden of respiratory and abdominal conditions following COVID-19 infections during the ancestral and Delta variant periods in the United States: An EHR-based cohort study from the RECOVER Program

Importance

The frequency and characteristics of post-acute sequelae of SARS-CoV-2 infection (PASC) may vary by SARS-CoV-2 variant.

Objective

To characterize PASC-related conditions among individuals likely infected by the ancestral strain in 2020 and individuals likely infected by the Delta variant in 2021.

Design

Retrospective cohort study of electronic medical record data for approximately 27 million patients from March 1, 2020-November 30, 2021.

Setting

Healthcare facilities in New York and Florida.

Participants

Patients who were at least 20 years old and had diagnosis codes that included at least one SARS-CoV-2 viral test during the study period.

Exposure

Laboratory-confirmed COVID-19 infection, classified by the most common variant prevalent in those regions at the time.

Main Outcomes and Measures

Relative risk (estimated by adjusted hazard ratio [aHR]) and absolute risk difference (estimated by adjusted excess burden) of new conditions, defined as new documentation of symptoms or diagnoses, in persons between 31-180 days after a positive COVID-19 test compared to persons with only negative tests during the 31-180 days after the last negative test.

Results

We analyzed data from 560,752 patients. The median age was 57 years; 60.3% were female, 20.0% non-Hispanic Black, and 19.6% Hispanic. During the study period, 57,616 patients had a positive SARS-CoV-2 test; 503,136 did not. For infections during the ancestral strain period, pulmonary fibrosis, edema (excess fluid), and inflammation had the largest aHR, comparing those with a positive test to those with a negative test, (aHR 2.32 [95% CI 2.09 2.57]), and dyspnea (shortness of breath) carried the largest excess burden (47.6 more cases per 1,000 persons). For infections during the Delta period, pulmonary embolism had the largest aHR comparing those with a positive test to a negative test (aHR 2.18 [95% CI 1.57, 3.01]), and abdominal pain carried the largest excess burden (85.3 more cases per 1,000 persons).

Conclusions and Relevance

We documented a substantial relative risk of pulmonary embolism and large absolute risk difference of abdomen-related symptoms after SARS-CoV-2 infection during the Delta variant period. As new SARS-CoV-2 variants emerge, researchers and clinicians should monitor patients for changing symptoms and conditions that develop after infection.

Machine learning enabled subgroup analysis with real-world data to inform clinical trial eligibility criteria design

Overly restrictive eligibility criteria for clinical trials may limit the generalizability of the trial results to their target real-world patient populations. We developed a novel machine learning approach using large collections of real-world data (RWD) to better inform clinical trial eligibility criteria design. We extracted patients' clinical events from electronic health records (EHRs), which include demographics, diagnoses, and drugs, and assumed certain compositions of these clinical events within an individual's EHRs can determine the subphenotypes-homogeneous clusters of patients, where patients within each subgroup share similar clinical characteristics. We introduced an outcome-guided probabilistic model to identify those subphenotypes, such that the patients within the same subgroup not only share similar clinical characteristics but also at similar risk levels of encountering severe adverse events (SAEs). We evaluated our algorithm on two previously conducted clinical trials with EHRs from the OneFlorida+ Clinical Research Consortium. Our model can clearly identify the patient subgroups who are more likely to suffer or not suffer from SAEs as subphenotypes in a transparent and interpretable way. Our approach identified a set of clinical topics and derived novel patient representations based on them. Each clinical topic represents a certain clinical event composition pattern learned from the patient EHRs. Tested on both trials, patient subgroup (#SAE=0) and patient subgroup (#SAE>0) can be well-separated by k-means clustering using the inferred topics. The inferred topics characterized as likely to align with the patient subgroup (#SAE>0) revealed meaningful combinations of clinical features and can provide data-driven recommendations for refining the exclusion criteria of clinical trials. The proposed supervised topic modeling approach can infer the clinical topics from the subphenotypes with or without SAEs. The potential rules for describing the patient subgroups with SAEs can be further derived to inform the design of clinical trial eligibility criteria.

Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated or newly incident in the period after acute SARS-CoV-2 infection. Most studies have examined these conditions individually without providing evidence on co-occurring conditions. In this study, we leveraged the electronic health record data of two large cohorts, INSIGHT and OneFlorida+, from the national Patient-Centered Clinical Research Network. We created a development cohort from INSIGHT and a validation cohort from OneFlorida+ including 20,881 and 13,724 patients, respectively, who were SARS-CoV-2 infected, and we investigated their newly incident diagnoses 30-180 days after a documented SARS-CoV-2 infection. Through machine learning analysis of over 137 symptoms and conditions, we identified four reproducible PASC subphenotypes, dominated by cardiac and renal (including 33.75% and 25.43% of the patients in the development and validation cohorts); respiratory, sleep and anxiety (32.75% and 38.48%); musculoskeletal and nervous system (23.37% and 23.35%); and digestive and respiratory system (10.14% and 12.74%) sequelae. These subphenotypes were associated with distinct patient demographics, underlying conditions before SARS-CoV-2 infection and acute infection phase severity. Our study provides insights into the heterogeneity of PASC and may inform stratified decision-making in the management of PASC conditions.

PM2.5 Constituents and Onset of Gestational Diabetes Mellitus: Identifying Susceptible Exposure Windows

Fine particulate matter (PM_2.5) has been linked to gestational diabetes mellitus (GDM). However, PM_2.5 is a complex mixture with large spatiotemporal heterogeneities, and women with early-onset GDM (i.e., diagnosed before 24^th gestation week) have distinct maternal characteristics and a higher risk of worse health outcomes compared with those with late-onset GDM (i.e., diagnosed in or after 24^th gestation week). We aimed to examine differential impacts of PM_2.5 and its constituents on early- vs. late-onset GDM, and to identify corresponding susceptible exposure windows. We leveraged statewide linked electronic health records and birth records data in Florida in 2012-2017. Exposures to PM_2.5 and its constituents (i.e., sulfate [SO₄ ^2-], ammonium [NH₄ ⁺], nitrate [NO₃ ^-], organic matter [OM], black carbon [BC], mineral dust [DUST], and sea-salt [SS]) were spatiotemporally linked to pregnant women based on their residential histories. Cox proportional hazards models and multinomial logistic regression were used to examine the associations of PM_2.5 and its constituents with GDM and its onsets. Distributed non-linear lag models were implemented to identify susceptible exposure windows. Exposures to PM_2.5, SO₄ ^2-, NH₄ ⁺, and BC were statistically significantly associated with higher hazards of GDM. Exposures to PM_2.5 during weeks 1-12 of gestation were positively associated with GDM. Associations of early-onset GDM with PM_2.5 in the 1^st and 2^nd trimesters, SO₄ ^2- in the 1^st and 2^nd trimesters, and NO₃ ^- in the preconception and 1^st trimester were considerably stronger than observations for late-onset GDM. Our findings suggest there are differential associations of PM_2.5 and its constituents with early- vs. late-onset GDM, with different susceptible exposure windows. This study helps better understand the impacts of air pollution on GDM accounting for its physiological heterogeneity.

Medication-Related Osteonecrosis of the Jaw in Cancer Patients: Result from the OneFlorida Clinical Research Consortium

Medication-related osteonecrosis of the jaw (MRONJ) is a rare but severely debilitating drug-induced bone disorder in the jawbone region. The first MRONJ was reported in 2003 after bisphosphonate (BP) exposure. Recently, other drugs, such as receptor activator of NF-κB ligand (RANKL) inhibitor denosumab and antiangiogenic agents, were also associated with MRONJ. The purpose of this study was to evaluate the incidence and risk factors for MRONJ related to BPs or denosumab in cancer patients in real-world clinical settings using data from the OneFlorida Clinical Research Consortium. We queried the electronic health records of participants with prescriptions of intravenous (IV) BPs or denosumab between January 1, 2012, and September 1, 2021, in the OneFlorida Consortium. Time to MRONJ diagnosis was evaluated using the Kaplan-Meier method, and Cox regression analysis was performed to estimate the adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) for MRONJ. A total of 5689 participants had one or more prescriptions of IV BP or denosumab within this study period and were included in this study. Among these participants, 52 (0.9%) had a diagnosis of MRONJ. The overall rate of MRONJ was 0.73%, 0.86%, and 3.50% in the cancer patients treated with IV BPs, denosumab, and sequential IV BPs and denosumab, respectively. The risk of MRONJ was similar in participants treated with denosumab alone compared to those treated with IV BPs alone (HR: 1.25, 95% CI: 0.66-2.34, p = .49). Patients with sequential prescription of IV BP and denosumab were at much higher risk for MRONJ, with an adjusted HR of 4.49, 95% CI of 1.96-10.28, p = .0004. In conclusion, in real-world clinical settings, the rates of MRONJ associated with IV BPs and denosumab were similar, while the sequential treatment of these two drug classes was associated with a much higher risk of MRONJ. © 2022 American Society for Bone and Mineral Research (ASBMR).

Assessing the impact of privacy-preserving record linkage on record overlap and patient demographic and clinical characteristics in PCORnet®, the National Patient-Centered Clinical Research Network

OBJECTIVE

This article describes the implementation of a privacy-preserving record linkage (PPRL) solution across PCORnet®, the National Patient-Centered Clinical Research Network.

MATERIAL AND METHODS

Using a PPRL solution from Datavant, we quantified the degree of patient overlap across the network and report a de-duplicated analysis of the demographic and clinical characteristics of the PCORnet population.

RESULTS

There were ∼170M patient records across the responding Network Partners, with ∼138M (81%) of those corresponding to a unique patient. 82.1% of patients were found in a single partner and 14.7% were in 2. The percentage overlap between Partners ranged between 0% and 80% with a median of 0%. Linking patients' electronic health records with claims increased disease prevalence in every clinical characteristic, ranging between 63% and 173%.

DISCUSSION

The overlap between Partners was variable and depended on timeframe. However, patient data linkage changed the prevalence profile of the PCORnet patient population.

CONCLUSIONS

This project was one of the largest linkage efforts of its kind and demonstrates the potential value of record linkage. Linkage between Partners may be most useful in cases where there is geographic proximity between Partners, an expectation that potential linkage Partners will be able to fill gaps in data, or a longer study timeframe.

Establishing a framework for privacy-preserving record linkage among electronic health record and administrative claims databases within PCORnet®, the National Patient-Centered Clinical Research Network

OBJECTIVE

The aim of this study was to determine whether a secure, privacy-preserving record linkage (PPRL) methodology can be implemented in a scalable manner for use in a large national clinical research network.

RESULTS

We established the governance and technical capacity to support the use of PPRL across the National Patient-Centered Clinical Research Network (PCORnet^®). As a pilot, four sites used the Datavant software to transform patient personally identifiable information (PII) into de-identified tokens. We queried the sites for patients with a clinical encounter in 2018 or 2019 and matched their tokens to determine whether overlap existed. We described patient overlap among the sites and generated a "deduplicated" table of patient demographic characteristics. Overlapping patients were found in 3 of the 6 site-pairs. Following deduplication, the total patient count was 3,108,515 (0.11% reduction), with the largest reduction in count for patients with an "Other/Missing" value for Sex; from 198 to 163 (17.6% reduction). The PPRL solution successfully links patients across data sources using distributed queries without directly accessing patient PII. The overlap queries and analysis performed in this pilot is being replicated across the full network to provide additional insight into patient linkages among a distributed research network.

Identifying Contextual and Spatial Risk Factors for Post-Acute Sequelae of SARS-CoV-2 Infection: An EHR-based Cohort Study from the RECOVER Program

Post-acute sequelae of SARS-CoV-2 infection (PASC) affects a wide range of organ systems among a large proportion of patients with SARS-CoV-2 infection. Although studies have identified a broad set of patient-level risk factors for PASC, little is known about the contextual and spatial risk factors for PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified contextual and spatial risk factors from nearly 200 environmental characteristics for 23 PASC symptoms and conditions of eight organ systems. We conducted a two-phase environment-wide association study. In Phase 1, we ran a mixed effects logistic regression with 5-digit ZIP Code tabulation area (ZCTA5) random intercepts for each PASC outcome and each contextual and spatial factor, adjusting for a comprehensive set of patient-level confounders. In Phase 2, we ran a mixed effects logistic regression for each PASC outcome including all significant (false positive discovery adjusted p-value < 0.05) contextual and spatial characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), criteria air pollutants (e.g., sulfur dioxide), particulate matter (PM 2.5 ) compositions (e.g., ammonium), neighborhood deprivation, and built environment (e.g., food access) that were associated with increased risk of PASC conditions related to nervous, respiratory, blood, circulatory, endocrine, and other organ systems. Specific contextual and spatial risk factors for each PASC condition and symptom were different across New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular contextual and spatial characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.

Accurate long-term prediction of death for patients with cirrhosis

BACKGROUND AND AIMS

Cirrhosis is a major cause of death and is associated with extensive health care use. Patients with cirrhosis have complex treatment choices due to risks of morbidity and mortality. To optimally counsel and treat patients with cirrhosis requires tools to predict their longer-term liver-related survival. We sought to develop and validate a risk score to predict longer-term survival of patients with cirrhosis.

APPROACH AND RESULTS

We conducted a retrospective cohort study of adults with cirrhosis with no major life-limiting comorbidities. Adults with cirrhosis within the Veterans Health Administration were used for model training and internal validation, and external validation used the OneFlorida Clinical Research Consortium. We used four model-building approaches including variables predictive of cirrhosis-related mortality, focused on discrimination at key time points (1, 3, 5, and 10 years). Among 30,263 patients with cirrhosis ≤75 years old without major life-limiting comorbidities and complete laboratory data during the baseline period, the boosted survival tree models had the highest discrimination, with 1-year, 3-year, 5-year, and 10-year survival rates of 0.77, 0.81, 0.84, and 0.88, respectively. The 1-year, 3-year, and 5-year discrimination was nearly identical in external validation. Secondary analyses with imputation of missing data and subgroups by etiology of liver disease had similar results to the primary model.

CONCLUSIONS

We developed and validated (internally and externally) a risk score to predict longer-term survival of patients with cirrhosis. This score would transform management of patients with cirrhosis in terms of referral to specialty care and treatment decision-making for non-liver-related care.

Hepatitis C virus (HCV) seroprevalence, RNA detection, and genotype distribution across Florida, 2015-2018

Chronic hepatitis C virus (HCV) infection is a leading cause of hepatocellular carcinoma (HCC) in the U.S. Due to high rates of HCV among baby boomers (born 1945-1965), it was recommended they receive universal screening. This was expanded to all U.S. adults in 2020 due to evidence of increasing rates of chronic HCV in younger adults. An assessment of HCV burden across demographics is crucial to understand the future burden of HCC and target under-screened adults for HCV. Using the OneFlorida Clinical Research Consortium, of more than one million individuals in Florida, all HCV antibody and viral RNA tests completed from 2015 to 2018 were identified. HCV seroprevalence, HCV viral load (active infection), and HCV genotype distribution by risk groups were assessed. Overall, HCV seroprevalence and active infection were highest among White non-Hispanic individuals, males, and baby boomers. However, odds of a positive HCV antibody test were higher among Black non-Hispanic individuals born before 1945 (aOR: 2.74; 95% CI: 1.98-3.78) or 1945-1965 (aOR: 1.46; 95% CI: 1.36-1.56) compared to White non-Hispanic individuals. In contrast, among individuals born after 1965, Black non-Hispanics were less likely than White non-Hispanics to test HCV antibody positive (aOR of 0.5-0.28). A similar age/race pattern was observed for active HCV infection. There was a higher prevalence of genotype 1A and 3 and lower prevalence of 1B in younger adults. Patterns of HCV seroprevalence and active HCV infection identified in our study support the recent shift from age and risk-based screening guidelines to universal adult screening.

Simulating Colorectal Cancer Trials Using Real-World Data

PURPOSE

Using real-world data (RWD)-based trial simulation approach, we aim to simulate colorectal cancer (CRC) trials and examine both effectiveness and safety end points in different simulation scenarios.

METHODS

We identified five phase III trials comparing new treatment regimens with an US Food and Drug Administration-approved first-line treatment in patients with metastatic CRC (ie, fluorouracil, leucovorin, and irinotecan) as the standard-of-care (SOC) control arm. Using Electronic Health Record-derived data from the OneFlorida network, we defined the study populations and outcome measures using the protocols from the original trials. Our design scenarios were (1) simulation of the SOC fluorouracil, leucovorin, and irinotecan arm and (2) comparative effectiveness research (CER) simulation of the control and experimental arms. For each scenario, we adjusted for random assignment, sampling, and dropout. We used overall survival (OS) and severe adverse events (SAEs) to measure effectiveness and safety.

RESULTS

We conducted CER simulations for two trials, and SOC simulations for three trials. The effect sizes of our simulated trials were stable across all simulation runs. Compared with the original trials, we observed longer OS and higher mean number of SAEs in both CER and SOC simulation. In the two CER simulations, hazard ratios associated with death from simulations were similar to that reported in the original trials. Consistent with the original trials, we found higher risk ratios of SAEs in the experiment arm, suggesting potentially higher toxicities from the new treatment regimen. We also observed similar SAE rates across all simulations compared with the original trials.

CONCLUSION

In this study, we simulated five CRC trials, and tested two simulation scenarios with several different configurations demonstrated that our simulations can robustly generate effectiveness and safety outcomes comparable with the original trials using real-world data.

Multisite learning of high-dimensional heterogeneous data with applications to opioid use disorder study of 15,000 patients across 5 clinical sites

Integrating data across institutions can improve learning efficiency. To integrate data efficiently while protecting privacy, we propose A one-shot, summary-statistics-based, Distributed Algorithm for fitting Penalized (ADAP) regression models across multiple datasets. ADAP utilizes patient-level data from a lead site and incorporates the first-order (ADAP1) and second-order gradients (ADAP2) of the objective function from collaborating sites to construct a surrogate objective function at the lead site, where model fitting is then completed with proper regularizations applied. We evaluate the performance of the proposed method using both simulation and a real-world application to study risk factors for opioid use disorder (OUD) using 15,000 patient data from the OneFlorida Clinical Research Consortium. Our results show that ADAP performs nearly the same as the pooled estimator but achieves higher estimation accuracy and better variable selection than the local and average estimators. Moreover, ADAP2 successfully handles heterogeneity in covariate distributions.

Personalised Lung Cancer Screening (PLuS) study to assess the importance of coexisting chronic conditions to clinical practice and policy: protocol for a multicentre observational study

INTRODUCTION

Lung cancer is the leading cause of cancer death in the USA and worldwide, and lung cancer screening (LCS) with low-dose CT (LDCT) has the potential to improve lung cancer outcomes. A critical question is whether the ratio of potential benefits to harms found in prior LCS trials applies to an older and potentially sicker population. The Personalised Lung Cancer Screening (PLuS) study will help close this knowledge gap by leveraging real-world data to fully characterise LCS recipients. The principal goal of the PLuS study is to characterise the comorbidity burden of individuals undergoing LCS and quantify the benefits and harms of LCS to enable informed decision-making.

METHODS AND ANALYSIS

PLuS is a multicentre observational study designed to assemble an LCS cohort from the electronic health records of ~40 000 individuals undergoing annual LCS with LDCT from 2016 to 2022. Data will be integrated into a unified repository to (1) examine the burden of multimorbidity by race/ethnicity, socioeconomic status and age; (2) quantify potential benefits and harms; and (3) use the observational data with validated simulation models in the Cancer Intervention and Surveillance Modeling Network (CISNET) to provide LCS outcomes in the real-world US population. We will fit a multivariable logistic regression model to estimate the adjusted ORs of comorbidity, functional limitations and impaired pulmonary function adjusted for relevant covariates. We will also estimate the cumulative risk of LCS outcomes using discrete-time survival models. To our knowledge, this is the first study to combine observational data and simulation models to estimate the long-term impact of LCS with LDCT.

ETHICS AND DISSEMINATION

The study was approved by the Kaiser Permanente Southern California Institutional Review Board and VA Portland Health Care System. The results will be disseminated through publications and presentations at national and international conferences. Safety considerations include protection of patient confidentiality.

Machine Learning for Identifying Data-Driven Subphenotypes of Incident Post-Acute SARS-CoV-2 Infection Conditions with Large Scale Electronic Health Records: Findings from the RECOVER Initiative

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated, or newly incident in the post-acute SARS-CoV-2 infection period of COVID-19 patients. Most studies have examined these conditions individually without providing concluding evidence on co-occurring conditions. To answer this question, this study leveraged electronic health records (EHRs) from two large clinical research networks from the national Patient-Centered Clinical Research Network (PCORnet) and investigated patients' newly incident diagnoses that appeared within 30 to 180 days after a documented SARS-CoV-2 infection. Through machine learning, we identified four reproducible subphenotypes of PASC dominated by blood and circulatory system, respiratory, musculoskeletal and nervous system, and digestive system problems, respectively. We also demonstrated that these subphenotypes were associated with distinct patterns of patient demographics, underlying conditions present prior to SARS-CoV-2 infection, acute infection phase severity, and use of new medications in the post-acute period. Our study provides novel insights into the heterogeneity of PASC and can inform stratified decision-making in the treatment of COVID-19 patients with PASC conditions.

Allostatic load in the context of disasters

Environmental disasters, pandemics, and other major traumatic events such as the Covid-19 pandemic or war contribute to psychosocial stress which manifests in a wide range of mental and physical consequences. The increasing frequency and severity of such events suggest that the adverse effects of toxic stress are likely to become more widespread and pervasive in the future. The allostatic load (AL) model has important elements that lend themselves well for identifying adverse health effects of disasters. Here we examine several articulations of AL from the standpoint of using AL to gauge short- and long-term health effects of disasters and to provide predictive capacity that would enable mitigation or prevention of some disaster-related health consequences. We developed a transdisciplinary framework combining indices of psychosocial AL and physiological AL to produce a robust estimate of overall AL in people affected by disasters and other traumatic events. In conclusion, we urge researchers to consider the potential of using AL as a component in a proposed disaster-oriented human health observing system.

Central Nervous System Manifestations of COVID-19: A Critical Review and Proposed Research Agenda

OBJECTIVE

On March 11, 2020, the World Health Organization declared an outbreak of a new viral entity, coronavirus 2019 (COVID-19), to be a worldwide pandemic. The characteristics of this virus, as well as its short- and long-term implications, are not yet well understood. The objective of the current paper was to provide a critical review of the emerging literature on COVID-19 and its implications for neurological, neuropsychiatric, and cognitive functioning.

METHOD

A critical review of recently published empirical research, case studies, and reviews pertaining to central nervous system (CNS) complications of COVID-19 was conducted by searching PubMed, PubMed Central, Google Scholar, and bioRxiv.

RESULTS

After considering the available literature, areas thought to be most pertinent to clinical and research neuropsychologists, including CNS manifestations, neurologic symptoms/syndromes, neuroimaging, and potential long-term implications of COVID-19 infection, were reviewed.

CONCLUSION

Once thought to be merely a respiratory virus, the scientific and medical communities have realized COVID-19 to have broader effects on renal, vascular, and neurological body systems. The question of cognitive deficits is not yet well studied, but neuropsychologists will undoubtedly play an important role in the years to come.

Procedural complications associated with invasive diagnostic procedures after lung cancer screening with low-dose computed tomography

INTRODUCTION

Although the National Lung Screening Trial (NLST) has proven low-dose computed tomography (LDCT) is effective for lung cancer screening, little is known about complication rates from invasive diagnostic procedures (IDPs) after LDCT in real-world settings. In this study, we used the real-world data from a large clinical research network to estimate the complication rates associated with IDPs after LDCT.

METHODS

Using 2014-2021 electronic health records and claims data from the OneFlorida clinical research network, we identified case individuals who underwent an IDP (i.e., cytology or needle biopsy, bronchoscopy, thoracic surgery, and other surgery) within 12 months of their first LDCT. We matched each case with one control individual who underwent an LDCT but without any IDPs. We calculated 3-month incremental complication rates as the difference in the complication rate between the case and control groups by IDP and complication severity.

RESULTS

Among 7,041 individuals who underwent an LDCT, 301 (4.3%) subsequently had an IDP within 12 months following the LDCT. The overall 3-month incremental complication rate was 16.6% (95% confidence interval [CI]: 9.9% - 23.1%), higher than that reported in the NLST (9.4%). The overall incremental complication rate was 5.6% (95% CI: 1.9% - 9.6%) for major, 8.6% (95% CI: 3.1% - 14.1%) for intermediate, and 13.2% (95% CI: 8.1% - 18.5%) for minor complications.

CONCLUSIONS

It is important to ensure adherence to clinical guidelines for nodule management and downstream work-up to minimize potential harms from screening.

Environmental effects on acute exacerbations of respiratory diseases: A real-world big data study

BACKGROUND

The effects of weather periods, race/ethnicity, and sex on environmental triggers for respiratory exacerbations are not well understood. This study linked the OneFlorida network (~15 million patients) with an external exposome database to analyze environmental triggers for asthma, bronchitis, and COPD exacerbations while accounting for seasonality, sex, and race/ethnicity.

METHODS

This is a case-crossover study of OneFlorida database from 2012 to 2017 examining associations of asthma, bronchitis, and COPD exacerbations with exposures to heat index, PM 2.5 and O 3. We spatiotemporally linked exposures using patients' residential addresses to generate average exposures during hazard and control periods, with each case serving as its own control. We considered age, sex, race/ethnicity, and neighborhood deprivation index as potential effect modifiers in conditional logistic regression models.

RESULTS

A total of 1,148,506 exacerbations among 533,446 patients were included. Across all three conditions, hotter heat indices conferred increasing exacerbation odds, except during November to March, where the opposite was seen. There were significant differences when stratified by race/ethnicity (e.g., for asthma in April, May, and October, heat index quartile 4, odds were 1.49 (95% confidence interval (CI) 1.42-1.57) for Non-Hispanic Blacks and 2.04 (95% CI 1.92-2.17) for Hispanics compared to 1.27 (95% CI 1.19-1.36) for Non-Hispanic Whites). Pediatric patients' odds of asthma and bronchitis exacerbations were significantly lower than adults in certain circumstances (e.g., for asthma during June - September, pediatric odds 0.71 (95% CI 0.68-0.74) and adult odds 0.82 (95% CI 0.79-0.85) for the highest quartile of PM 2.5).

CONCLUSION

This study of acute exacerbations of asthma, bronchitis, and COPD found exacerbation risk after exposure to heat index, PM 2.5 and O 3 varies by weather period, age, and race/ethnicity. Future work can build upon these results to alert vulnerable populations to exacerbation triggers.

Temporal Subtyping of Alzheimer's Disease Using Medical Conditions Preceding Alzheimer's Disease Onset in Electronic Health Records

Subtyping of Alzheimer's disease (AD) can facilitate diagnosis, treatment, prognosis and disease management. It can also support the testing of new prevention and treatment strategies through clinical trials. In this study, we employed spectral clustering to cluster 29,922 AD patients in the OneFlorida Data Trust using their longitudinal EHR data of diagnosis and conditions into four subtypes. These subtypes exhibit different patterns of progression of other conditions prior to the first AD diagnosis. In addition, according to the results of various statistical tests, these subtypes are also significantly different with respect to demographics, mortality, and prescription medications after the AD diagnosis. This study could potentially facilitate early detection and personalized treatment of AD as well as data-driven generalizability assessment of clinical trials for AD.

HCV testing: Order and completion rates among baby boomers obtaining care from seven health systems in Florida, 2015-2017

Many U.S. residents infected with hepatitis C virus (HCV) are baby boomers (born 1945-1965), who remain undiagnosed. Past CDC and USPSTF guidelines recommended one-time HCV testing for all baby boomers, with newer guidelines recommending universal screening for all adults. This retrospective cohort study examined electronic medical records for patient visits from 2015 to 2017 within the OneFlorida Data Trust and University of South Florida Health system. We assessed percentages of HCV tests ordered and completed across four age groups (those born before 1945, 1945-1965, 1966-1985, and after 1985). In 2019, we used logistic regression to examine factors associated with HCV test ordering and completion among baby boomers, including age, race, sex, number of primary care visits, HIV status, hepatitis diagnosis, and liver cancer history. All age groups had low rates of HCV test orders. 4.4% of baby boomers had a test ordered in 2015, and 6.7% in 2016. Of those, 94.5% and 89.7% completed testing, respectively. All other races/ethnicities had lower likelihood of testing completion than Whites (Blacks (aOR 0.82, 95%, CI 0.75-0.91); Asians (0.69, 0.52-0.92); Hispanics (0.29, 0.26-0.32)), although test orders were higher for Asians (1.48, 1.37-1.61) and Blacks (1.78, 1.73-1.82). Tests ordered (11.42, 10.94-11.92) and completed (2.25, 1.94-2.60) were more likely among those with hepatitis history. Test orders were more likely for HIV-positive patients (3.68, 3.45-3.93), but completion was less likely (0.67, 0.57-0.78). Interventions are needed to increase testing rates so that HCV infections are treated early, mitigating HCV-related morbidity and mortality, especially related to liver cancer.

Accessing Artificial Intelligence for Clinical Decision-Making

Advancements in computing and data from the near universal acceptance and implementation of electronic health records has been formative for the growth of personalized, automated, and immediate patient care models that were not previously possible. Artificial intelligence (AI) and its subfields of machine learning, reinforcement learning, and deep learning are well-suited to deal with such data. The authors in this paper review current applications of AI in clinical medicine and discuss the most likely future contributions that AI will provide to the healthcare industry. For instance, in response to the need to risk stratify patients, appropriately cultivated and curated data can assist decision-makers in stratifying preoperative patients into risk categories, as well as categorizing the severity of ailments and health for non-operative patients admitted to hospitals. Previous overt, traditional vital signs and laboratory values that are used to signal alarms for an acutely decompensating patient may be replaced by continuously monitoring and updating AI tools that can pick up early imperceptible patterns predicting subtle health deterioration. Furthermore, AI may help overcome challenges with multiple outcome optimization limitations or sequential decision-making protocols that limit individualized patient care. Despite these tremendously helpful advancements, the data sets that AI models train on and develop have the potential for misapplication and thereby create concerns for application bias. Subsequently, the mechanisms governing this disruptive innovation must be understood by clinical decision-makers to prevent unnecessary harm. This need will force physicians to change their educational infrastructure to facilitate understanding AI platforms, modeling, and limitations to best acclimate practice in the age of AI. By performing a thorough narrative review, this paper examines these specific AI applications, limitations, and requisites while reviewing a few examples of major data sets that are being cultivated and curated in the US.

The OneFlorida Data Trust: a centralized, translational research data infrastructure of statewide scope

The OneFlorida Data Trust is a centralized research patient data repository created and managed by the OneFlorida Clinical Research Consortium ("OneFlorida"). It comprises structured electronic health record (EHR), administrative claims, tumor registry, death, and other data on 17.2 million individuals who received healthcare in Florida between January 2012 and the present. Ten healthcare systems in Miami, Orlando, Tampa, Jacksonville, Tallahassee, Gainesville, and rural areas of Florida contribute EHR data, covering the major metropolitan regions in Florida. Deduplication of patients is accomplished via privacy-preserving entity resolution (precision 0.97-0.99, recall 0.75), thereby linking patients' EHR, claims, and death data. Another unique feature is the establishment of mother-baby relationships via Florida vital statistics data. Research usage has been significant, including major studies launched in the National Patient-Centered Clinical Research Network ("PCORnet"), where OneFlorida is 1 of 9 clinical research networks. The Data Trust's robust, centralized, statewide data are a valuable and relatively unique research resource.

Optimizing Identification of People Living with HIV from Electronic Medical Records: Computable Phenotype Development and Validation

BACKGROUND

Electronic health record (EHR)-based computable phenotype algorithms allow researchers to efficiently identify a large virtual cohort of Human Immunodeficiency Virus (HIV) patients. Built upon existing algorithms, we refined, improved, and validated an HIV phenotype algorithm using data from the OneFlorida Data Trust, a repository of linked claims data and EHRs from its clinical partners, which provide care to over 15 million patients across all 67 counties in Florida.

METHODS

Our computable phenotype examined information from multiple EHR domains, including clinical encounters with diagnoses, prescription medications, and laboratory tests. To identify an HIV case, the algorithm requires the patient to have at least one diagnostic code for HIV and meet one of the following criteria: have 1+ positive HIV laboratory, have been prescribed with HIV medications, or have 3+ visits with HIV diagnostic codes. The computable phenotype was validated against a subset of clinical notes.

RESULTS

Among the 15+ million patients from OneFlorida, we identified 61,313 patients with confirmed HIV diagnosis. Among them, 8.05% met all four inclusion criteria, 69.7% met the 3+ HIV encounters criteria in addition to having HIV diagnostic code, and 8.1% met all criteria except for having positive laboratories. Our algorithm achieved higher sensitivity (98.9%) and comparable specificity (97.6%) relative to existing algorithms (77-83% sensitivity, 86-100% specificity). The mean age of the sample was 42.7 years, 58% male, and about half were Black African American. Patients' average follow-up period (the time between the first and last encounter in the EHRs) was approximately 4.6 years. The median number of all encounters and HIV-related encounters were 79 and 21, respectively.

CONCLUSION

By leveraging EHR data from multiple clinical partners and domains, with a considerably diverse population, our algorithm allows more flexible criteria for identifying patients with incomplete laboratory test results and medication prescribing history compared with prior studies.

Implementation context for addressing social needs in a learning health system: a qualitative study

INTRODUCTION

Unmet social needs contribute to growing health disparities and rising health care costs. Strategies to collect and integrate information on social needs into patients' electronic health records (EHRs) show promise for connecting patients with community resources. However, gaps remain in understanding the contextual factors that impact implementing these interventions in clinical settings.

METHODS

We conducted qualitative interviews with patients and focus groups with providers (January-September 2020) in two primary care clinics to inform the implementation of a module that collects and integrates patient-reported social needs information into the EHR. Questions addressed constructs within the Theoretical Framework for Acceptability and the Consolidated Framework for Implementation Research. Data were coded deductively using team-based framework analysis, followed by inductive coding and matrix analyses.

RESULTS

Forty patients participated in interviews, with 20 recruited at the clinics and 20 from home. Two focus groups were conducted with a total of 12 providers. Factors salient to acceptability and feasibility included patients' discomfort answering sensitive questions, concerns about privacy, difficulty reading/understanding module content, and technological literacy. Rapport with providers was a facilitator for patients to discuss social needs. Providers stressed that limited time with patients would be a barrier, and expressed concerns about the lack of available community resources.

CONCLUSION

Findings highlight the need for flexible approaches to assessing and discussing social needs with patients. Feasibility of the intervention is contingent upon support from the health system to facilitate social needs assessment and discussion. Further study of availability of community resources is needed to ensure intervention effectiveness.

Ambient heat and stillbirth in Northern and Central Florida

BACKGROUND

Elevated temperature is well-recognized as a health hazard, and may be particularly harmful to pregnant women, including increasing risk of stillbirth. We conducted a study in Northern and Central Florida, an area prone to periodic extreme heat but with significant seasonal variation, focusing on the most socioeconomically vulnerable populations least able to mitigate the impact of heat.

METHODS

We obtained electronic health records data from the OneFlorida Data Trust for the period 2012-2017, with 1876 stillbirths included in the analysis. We used a case-crossover design to examine the risk of stillbirth associated with acute exposures to elevated heat prior to the outcome, contrasting the case period (the week preceding the stillbirth) with a control period (the week prior to the case period and the week after the stillbirth). Average heat index and maximum warning level during the case and control periods of each woman were assigned by ZIP code. Conditional logistic regression models were used to assess the association between stillbirth and heat exposure, controlling for PM_2.5 and O₃.

RESULTS

The adjusted odds ratio showed no overall association with stillbirth except for a weak association for exposure above the 90th percentile which was larger among the most socioeconomically deprived and non-Hispanic Black women. In the hot months, there was a clear association for all indices of heat exposure, but largest again for the most socioeconomically deprived population (aOR = 2.4, 95% CI: 1.2-5.2 in the 4th vs. 1st quartile) and among non-Hispanic Black women (aOR = 1.8, 95% CI: 1.0-3.2 in the 4th vs. 1st quartile).

CONCLUSIONS

Our results provide further evidence that elevated ambient heat is related to stillbirth and encourage a focus on the most susceptible individuals and possible clinical pathways.

Testing the Use of Data Drawn from the Electronic Health Record to Compare Quality

Introduction

Health systems spend $1.5 billion annually reporting data on quality, but efficacy and utility for benchmarking are limited due, in part, to limitations of data sources. Our objective was to implement and evaluate measures of pediatric quality for three conditions using electronic health record (EHR)-derived data.

Methods

PCORnet networks standardized EHR-derived data to a common data model. In 13 health systems from 2 networks for 2015, we implemented the National Quality Forum measures: % children with sickle cell anemia who received a transcranial Doppler; % children on antipsychotics who had metabolic screening; and % pediatric acute otitis media with amoxicillin prescribed. Manual chart review assessed measure accuracy.

Results

Only 39% (N = 2,923) of 7,278 children on antipsychotics received metabolic screening (range: 20%-54%). If the measure indicated screening was performed, the chart agreed 88% of the time [95% confidence interval (CI): 81%-94%]; if it indicated screening was not done, the chart agreed 86% (95% CI: 78%-93%). Only 69% (N = 793) of 1,144 children received transcranial Doppler screening (range across sites: 49%-88%). If the measure indicated screening was performed, the chart agreed 98% of the time (95% CI: 94%-100%); if it indicated screening was not performed, the chart agreed 89% (95% CI: 82%-95%). For acute otitis media, chart review identified many qualifying cases missed by the National Quality Forum measure, which excluded a common diagnostic code.

Conclusions

Measures of healthcare quality developed using EHR-derived data were valid and identified wide variation among network sites. This data can facilitate the identification and spread of best practices.

Examination of Early CNS Symptoms and Severe Coronavirus Disease 2019: A Multicenter Observational Case Series

To determine if early CNS symptoms are associated with severe coronavirus disease 2019.

DESIGN

A retrospective, observational case series study design.

SETTING

Electronic health records were reviewed for patients from five healthcare systems across the state of Florida, United States.

PATIENTS

A clinical sample (n = 36,615) of patients with confirmed diagnosis of coronavirus disease 2019 were included. Twelve percent (n = 4,417) of the sample developed severe coronavirus disease 2019, defined as requiring critical care, mechanical ventilation, or diagnosis of acute respiratory distress syndrome, sepsis, or severe inflammatory response syndrome.

INTERVENTIONS

None.

MEASUREMENT AND MAIN RESULTS

We reviewed the electronic health record for diagnosis of early CNS symptoms (encephalopathy, headache, ageusia, anosmia, dizziness, acute cerebrovascular disease) between 14 days before the diagnosis of coronavirus disease 2019 and 8 days after the diagnosis of coronavirus disease 2019, or before the date of severe coronavirus disease 2019 diagnosis, whichever came first. Hierarchal logistic regression models were used to examine the odds of developing severe coronavirus disease 2019 based on diagnosis of early CNS symptoms. Severe coronavirus disease 2019 patients were significantly more likely to have early CNS symptoms (32.8%) compared with nonsevere patients (6.11%; χ2[1] = 3,266.08, p < 0.0001, φ = 0.29). After adjusting for demographic variables and pertinent comorbidities, early CNS symptoms were significantly associated with severe coronavirus disease 2019 (odds ratio = 3.21). Diagnosis of encephalopathy (odds ratio = 14.38) was associated with greater odds of severe coronavirus disease 2019; whereas diagnosis of anosmia (odds ratio = 0.45), ageusia (odds ratio = 0.46), and headache (odds ratio = 0.63) were associated with reduced odds of severe coronavirus disease 2019.

CONCLUSIONS

Early CNS symptoms, and specifically encephalopathy, are differentially associated with risk of severe coronavirus disease 2019 and may serve as an early marker for differences in clinical disease course. Therapies for early coronavirus disease 2019 are scarce, and further identification of subgroups at risk may help to advance understanding of the severity trajectories and enable focused treatment.