Measuring and controlling medical record abstraction (MRA) error rates in an observational study.

BACKGROUND: Studies have shown that data collection by medical record abstraction (MRA) is a significant source of error in clinical research studies relying on secondary use data. Yet, the quality of data collected using MRA is seldom assessed. We employed a novel, theory-based framework for data quality assurance and quality control of MRA. The objective of this work is to determine the potential impact of formalized MRA training and continuous quality control (QC) processes on data quality over time. METHODS: We conducted a retrospective analysis of QC data collected during a cross-sectional medical record review of mother-infant dyads with Neonatal Opioid Withdrawal Syndrome. A confidence interval approach was used to calculate crude (Wald's method) and adjusted (generalized estimating equation) error rates over time. We calculated error rates using the number of errors divided by total fields ("all-field" error rate) and populated fields ("populated-field" error rate) as the denominators, to provide both an optimistic and a conservative measurement, respectively. RESULTS: On average, the ACT NOW CE Study maintained an error rate between 1% (optimistic) and 3% (conservative). Additionally, we observed a decrease of 0.51 percentage points with each additional QC Event conducted. CONCLUSIONS: Formalized MRA training and continuous QC resulted in lower error rates than have been found in previous literature and a decrease in error rates over time. This study newly demonstrates the importance of continuous process controls for MRA within the context of a multi-site clinical research study.

User-centered design principles in the development of clinical research tools.

BACKGROUND: Increasing and sustaining the engagement of participants in clinical research studies is a goal for clinical investigators, especially for studies that require long-term or frequent involvement of participants. Technology can be used to reduce barriers to participation by providing multiple options for clinical data entry and form submission. However, electronic systems used in clinical research studies should be user-friendly while also ensuring data quality. Directly involving study participants in evaluating the effectiveness and usability of electronic tools may promote wider adoption, maintain involvement, and increase user satisfaction of the technology. While developers of healthcare applications have incorporated user-centered designs, these methods remain uncommon in the design of clinical study tools such as patient-reported outcome surveys or electronic data capture digital health tools. METHODS: Our study evaluated whether the clinical research setting may benefit from implementing user-centered design principles. Study participants were recruited to test the web-based form for the Measurement to Understand the Reclassification of Disease of Cabarrus/Kannapolis (MURDOCK) Study Community Translational Population Health Registry and Biorepository that would enable them to complete their study forms electronically. The study enrollment form collects disease history, conditions, smoking status, medications, and other information. The system was initially evaluated by the data management team through traditional user-acceptance testing methods. During the tool evaluation phase, a decision was made to incorporate a small-scale usability study to directly test the system. RESULTS: Results showed that a majority of participants found the system easy to use. Of the eight required tasks, 75% were completed successfully. Of the 72 heuristics violated, language was the most frequent violation. CONCLUSION: Our study showed that user-centered usability methods can identify important issues and capture information that can enhance the participant's experience and may improve the quality of study tools.

Evaluating common data models for use with a longitudinal community registry.

OBJECTIVE: To evaluate common data models (CDMs) to determine which is best suited for sharing data from a large, longitudinal, electronic health record (EHR)-based community registry. MATERIALS AND METHODS: Four CDMs were chosen from models in use for clinical research data: Sentinel v5.0 (referred to as the Mini-Sentinel CDM in previous versions), PCORnet v3.0 (an extension of the Mini-Sentinel CDM), OMOP v5.0, and CDISC SDTM v1.4. Each model was evaluated against 11 criteria adapted from previous research. The criteria fell into six categories: content coverage, integrity, flexibility, ease of querying, standards compatibility, and ease and extent of implementation. RESULTS: The OMOP CDM accommodated the highest percentage of our data elements (76%), fared well on other requirements, and had broader terminology coverage than the other models. Sentinel and PCORnet fell short in content coverage with 37% and 48% matches respectively. Although SDTM accommodated a significant percentage of data elements (55% true matches), 45% of the data elements mapped to SDTM's extension mechanism, known as Supplemental Qualifiers, increasing the number of joins required to query the data. CONCLUSION: The OMOP CDM best met the criteria for supporting data sharing from longitudinal EHR-based studies. Conclusions may differ for other uses and associated data element sets, but the methodology reported here is easily adaptable to common data model evaluation for other uses.

Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study.

BACKGROUND: Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. OBJECTIVE: The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. METHODS: Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. RESULTS: Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. CONCLUSIONS: This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.

Increased Incidence of Vestibular Disorders in Patients With SARS-CoV-2.

Objective: Determine the incidence of vestibular disorders in patients with SARS-CoV-2 compared to the control population. Study Design: Retrospective. Setting: Clinical data in the National COVID Cohort Collaborative database (N3C). Methods: Deidentified patient data from the National COVID Cohort Collaborative database (N3C) were queried based on variant peak prevalence (untyped, alpha, delta, omicron 21K, and omicron 23A) from covariants.org to retrospectively analyze the incidence of vestibular disorders in patients with SARS-CoV-2 compared to control population, consisting of patients without documented evidence of COVID infection during the same period. Results: Patients testing positive for COVID-19 were significantly more likely to have a vestibular disorder compared to the control population. Compared to control patients, the odds ratio of vestibular disorders was significantly elevated in patients with untyped (odds ratio [OR], 2.39; confidence intervals [CI], 2.29-2.50; P < 0.001), alpha (OR, 3.63; CI, 3.48-3.78; P < 0.001), delta (OR, 3.03; CI, 2.94-3.12; P < 0.001), omicron 21K variant (OR, 2.97; CI, 2.90-3.04; P < 0.001), and omicron 23A variant (OR, 8.80; CI, 8.35-9.27; P < 0.001). Conclusions: The incidence of vestibular disorders differed between COVID-19 variants and was significantly elevated in COVID-19-positive patients compared to the control population. These findings have implications for patient counseling and further research is needed to discern the long-term effects of these findings.

Leadership and administration to advance translational science: Environmental scan of adaptive capacity and preparedness of Clinical and Translational Science Award Program hubs.

COVID-19 reinforced the need for effective leadership and administration within Clinical and Translational Science Award (CTSA) program hubs in response to a public health crisis. The speed, scale, and persistent evolution of the pandemic forced CTSA hubs to act quickly and remain nimble. The switch to virtual environments paired with supporting program operations, while ensuring the safety and well-being of their team, highlight the critical support role provided by leadership and administration. The pandemic also illustrated the value of emergency planning in supporting organizations' ability to quickly pivot and adapt. Lessons learned from the pandemic and from other cases of adaptive capacity and preparedness can aid program hubs in promoting and sustaining the overall capabilities of their organizations to prepare for future events.

Harnessing consumer wearable digital biomarkers for individualized recognition of postpartum depression using the All of Us Research Program dataset.

Postpartum depression (PPD), afflicting one in seven women, poses a major challenge in maternal health. Existing approaches to detect PPD heavily depend on in-person postpartum visits, leading to cases of the condition being overlooked and untreated. We explored the potential of consumer wearable-derived digital biomarkers for PPD recognition to address this gap. Our study demonstrated that intra-individual machine learning (ML) models developed using these digital biomarkers can discern between pre-pregnancy, pregnancy, postpartum without depression, and postpartum with depression time periods (i.e., PPD diagnosis). When evaluating variable importance, calories burned from the basal metabolic rate (calories BMR) emerged as the digital biomarker most predictive of PPD. To confirm the specificity of our method, we demonstrated that models developed in women without PPD could not accurately classify the PPD-equivalent phase. Prior depression history did not alter model efficacy for PPD recognition. Furthermore, the individualized models demonstrated superior performance compared to a conventional cohort-based model for the detection of PPD, underscoring the effectiveness of our individualized ML approach. This work establishes consumer wearables as a promising avenue for PPD identification. More importantly, it also emphasizes the utility of individualized ML model methodology, potentially transforming early disease detection strategies.

Informatics infrastructure in a rural pediatric clinical trials network: Matching specific clinical research needs with best practices and industry guidelines.

Children have historically been underrepresented in randomized controlled trials and multi-center studies. This is particularly true for children who reside in rural and underserved areas. Conducting multi-center trials in rural areas presents unique informatics challenges. These challenges call for increased attention towards informatics infrastructure and the need for development and application of sound informatics approaches to the collection, processing, and management of data for clinical studies. By modifying existing local infrastructure and utilizing open source tools, we have been able to successfully deploy a multi-site data coordinating and operations center. We report our implementation decisions for data collection and management for the IDeA States Pediatric Clinical Trial Network (ISPCTN) based on the functionality needed for the ISPCTN, our synthesis of the extant literature in data collection and management methodology, and Good Clinical Data Management Practices.

Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review.

An increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP-assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP-derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP-assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.

Assessing clinical site readiness for electronic health record (EHR)-to-electronic data capture (EDC) automated data collection.

BACKGROUND: eSource software is used to automatically copy a patient's electronic health record data into a clinical study's electronic case report form. However, there is little evidence to assist sponsors in identifying the best sites for multi-center eSource studies. METHODS: We developed an eSource site readiness survey. The survey was administered to principal investigators, clinical research coordinators, and chief research information officers at Pediatric Trial Network sites. RESULTS: A total of 61 respondents were included in this study (clinical research coordinator, 22; principal investigator, 20; and chief research information officer, 19). Clinical research coordinators and principal investigators ranked medication administration, medication orders, laboratory, medical history, and vital signs data as having the highest priority for automation. While most organizations used some electronic health record research functions (clinical research coordinator, 77%; principal investigator, 75%; and chief research information officer, 89%), only 21% of sites were using Fast Healthcare Interoperability Resources standards to exchange patient data with other institutions. Respondents generally gave lower readiness for change ratings to organizations that did not have a separate research information technology group and where researchers practiced in hospitals not operated by their medical schools. CONCLUSIONS: Site readiness to participate in eSource studies is not merely a technical problem. While technical capabilities are important, organizational priorities, structure, and the site's support of clinical research functions are equally important considerations.

Comparing Medical Record Abstraction (MRA) Error Rates in an Observational Study to Pooled Rates Identified in the Data Quality Literature.

Background: Medical record abstraction (MRA) is a commonly used method for data collection in clinical research, but is prone to error, and the influence of quality control (QC) measures is seldom and inconsistently assessed during the course of a study. We employed a novel, standardized MRA-QC framework as part of an ongoing observational study in an effort to control MRA error rates. In order to assess the effectiveness of our framework, we compared our error rates against traditional MRA studies that had not reported using formalized MRA-QC methods. Thus, the objective of this study was to compare the MRA error rates derived from the literature with the error rates found in a study using MRA as the sole method of data collection that employed an MRA-QC framework. Methods: Using a moderator meta-analysis employed with Q-test, the MRA error rates from the meta-analysis of the literature were compared with the error rate from a recent study that implemented formalized MRA training and continuous QC processes. Results: The MRA process for data acquisition in clinical research was associated with both high and highly variable error rates (70 - 2,784 errors per 10,000 fields). Error rates for the study using our MRA-QC framework were between 1.04% (optimistic, all-field rate) and 2.57% (conservative, populated-field rate) (or 104 - 257 errors per 10,000 fields), 4.00 - 5.53 percentage points less than the observed rate from the literature (p<0.0001). Conclusions: Review of the literature indicated that the accuracy associated with MRA varied widely across studies. However, our results demonstrate that, with appropriate training and continuous QC, MRA error rates can be significantly controlled during the course of a clinical research study.

The N3C governance ecosystem: A model socio-technical partnership for the future of collaborative analytics at scale.

The National COVID Cohort Collaborative (N3C) is a public-private-government partnership established during the Coronavirus pandemic to create a centralized data resource called the "N3C data enclave." This resource contains individual-level health data from participating healthcare sites nationwide to support rapid collaborative analytics. N3C has enabled analytics within a cloud-based enclave of data from electronic health records from over 17 million people (with and without COVID-19) in the USA. To achieve this goal of a shared data resource, N3C implemented a shared governance strategy involving stakeholders in decision-making. The approach leveraged best practices in data stewardship and team science to rapidly enable COVID-19-related research at scale while respecting the privacy of data subjects and participating institutions. N3C balanced equitable access to data, team-based scientific productivity, and individual professional recognition - a key incentive for academic researchers. This governance approach makes N3C research sustainable and effective beyond the initial days of the pandemic. N3C demonstrated that shared governance can overcome traditional barriers to data sharing without compromising data security and trust. The governance innovations described herein are a helpful framework for other privacy-preserving data infrastructure programs and provide a working model for effective team science beyond COVID-19.

Error Rates of Data Processing Methods in Clinical Research: A Systematic Review and Meta-Analysis of Manuscripts Identified Through PubMed.

Background: In clinical research, prevention of systematic and random errors of data collected is paramount to ensuring reproducibility of trial results and the safety and efficacy of the resulting interventions. Over the last 40 years, empirical assessments of data accuracy in clinical research have been reported in the literature. Although there have been reports of data error and discrepancy rates in clinical studies, there has been little systematic synthesis of these results. Further, although notable exceptions exist, little evidence exists regarding the relative accuracy of different data processing methods. We aim to address this gap by evaluating error rates for 4 data processing methods. Methods: A systematic review of the literature identified through PubMed was performed to identify studies that evaluated the quality of data obtained through data processing methods typically used in clinical trials: medical record abstraction (MRA), optical scanning, single-data entry, and double-data entry. Quantitative information on data accuracy was abstracted from the manuscripts and pooled. Meta-analysis of single proportions based on the Freeman-Tukey transformation method and the generalized linear mixed model approach were used to derive an overall estimate of error rates across data processing methods used in each study for comparison. Results: A total of 93 papers (published from 1978 to 2008) meeting our inclusion criteria were categorized according to their data processing methods. The accuracy associated with data processing methods varied widely, with error rates ranging from 2 errors per 10,000 fields to 2,784 errors per 10,000 fields. MRA was associated with both high and highly variable error rates, having a pooled error rate of 6.57% (95% CI: 5.51, 7.72). In comparison, the pooled error rates for optical scanning, single-data entry, and double-data entry methods were 0.74% (0.21, 1.60), 0.29% (0.24, 0.35) and 0.14% (0.08, 0.20), respectively. Conclusions: Data processing and cleaning methods may explain a significant amount of the variability in data accuracy. MRA error rates, for example, were high enough to impact decisions made using the data and could necessitate increases in sample sizes to preserve statistical power. Thus, the choice of data processing methods can likely impact process capability and, ultimately, the validity of trial results.

Economic analysis of a single institutional review board data exchange standard in multisite clinical studies.

BACKGROUND: Single Institutional Review Boards (sIRB) are not achieving the benefits envisioned by the National Institutes of Health. The recently published Health Level Seven (HL7®) Fast Healthcare Interoperability Resources (FHIR®) data exchange standard seeks to improve sIRB operational efficiency. METHODS AND RESULTS: We conducted a study to determine whether the use of this standard would be economically attractive for sIRB workflows collectively and for Reviewing and Relying institutions. We examined four sIRB-associated workflows at a single institution: (1) Initial Study Protocol Application, (2) Site Addition for an Approved sIRB study, (3) Continuing Review, and (4) Medical and Non-Medical Event Reporting. Task-level information identified personnel roles and their associated hour requirements for completion. Tasks that would be eliminated by the data exchange standard were identified. Personnel costs were estimated using annual salaries by role. No tasks would be eliminated in the Initial Study Protocol Application or Medical and Non-Medical Event Reporting workflows through use of the proposed data exchange standard. Site Addition workflow hours would be reduced by 2.50 h per site (from 15.50 to 13.00 h) and Continuing Review hours would be reduced by 9.00 h per site per study year (from 36.50 to 27.50 h). Associated costs savings were $251 for the Site Addition workflow (from $1609 to $1358) and $1033 for the Continuing Review workflow (from $4110 to $3076). CONCLUSION: Use of the proposed HL7 FHIR® data exchange standard would be economically attractive for sIRB workflows collectively and for each entity participating in the new workflows.

Identifying who has long COVID in the USA: a machine learning approach using N3C data.

BACKGROUND: Post-acute sequelae of SARS-CoV-2 infection, known as long COVID, have severely affected recovery from the COVID-19 pandemic for patients and society alike. Long COVID is characterised by evolving, heterogeneous symptoms, making it challenging to derive an unambiguous definition. Studies of electronic health records are a crucial element of the US National Institutes of Health's RECOVER Initiative, which is addressing the urgent need to understand long COVID, identify treatments, and accurately identify who has it-the latter is the aim of this study. METHODS: Using the National COVID Cohort Collaborative's (N3C) electronic health record repository, we developed XGBoost machine learning models to identify potential patients with long COVID. We defined our base population (n=1 793 604) as any non-deceased adult patient (age ≥18 years) with either an International Classification of Diseases-10-Clinical Modification COVID-19 diagnosis code (U07.1) from an inpatient or emergency visit, or a positive SARS-CoV-2 PCR or antigen test, and for whom at least 90 days have passed since COVID-19 index date. We examined demographics, health-care utilisation, diagnoses, and medications for 97 995 adults with COVID-19. We used data on these features and 597 patients from a long COVID clinic to train three machine learning models to identify potential long COVID among all patients with COVID-19, patients hospitalised with COVID-19, and patients who had COVID-19 but were not hospitalised. Feature importance was determined via Shapley values. We further validated the models on data from a fourth site. FINDINGS: Our models identified, with high accuracy, patients who potentially have long COVID, achieving areas under the receiver operator characteristic curve of 0·92 (all patients), 0·90 (hospitalised), and 0·85 (non-hospitalised). Important features, as defined by Shapley values, include rate of health-care utilisation, patient age, dyspnoea, and other diagnosis and medication information available within the electronic health record. INTERPRETATION: Patients identified by our models as potentially having long COVID can be interpreted as patients warranting care at a specialty clinic for long COVID, which is an essential proxy for long COVID diagnosis as its definition continues to evolve. We also achieve the urgent goal of identifying potential long COVID in patients for clinical trials. As more data sources are identified, our models can be retrained and tuned based on the needs of individual studies. FUNDING: US National Institutes of Health and National Center for Advancing Translational Sciences through the RECOVER Initiative.

Characteristics, Outcomes, and Severity Risk Factors Associated With SARS-CoV-2 Infection Among Children in the US National COVID Cohort Collaborative.

Importance: Understanding of SARS-CoV-2 infection in US children has been limited by the lack of large, multicenter studies with granular data. Objective: To examine the characteristics, changes over time, outcomes, and severity risk factors of children with SARS-CoV-2 within the National COVID Cohort Collaborative (N3C). Design, Setting, and Participants: A prospective cohort study of encounters with end dates before September 24, 2021, was conducted at 56 N3C facilities throughout the US. Participants included children younger than 19 years at initial SARS-CoV-2 testing. Main Outcomes and Measures: Case incidence and severity over time, demographic and comorbidity severity risk factors, vital sign and laboratory trajectories, clinical outcomes, and acute COVID-19 vs multisystem inflammatory syndrome in children (MIS-C), and Delta vs pre-Delta variant differences for children with SARS-CoV-2. Results: A total of 1 068 410 children were tested for SARS-CoV-2 and 167 262 test results (15.6%) were positive (82 882 [49.6%] girls; median age, 11.9 [IQR, 6.0-16.1] years). Among the 10 245 children (6.1%) who were hospitalized, 1423 (13.9%) met the criteria for severe disease: mechanical ventilation (796 [7.8%]), vasopressor-inotropic support (868 [8.5%]), extracorporeal membrane oxygenation (42 [0.4%]), or death (131 [1.3%]). Male sex (odds ratio [OR], 1.37; 95% CI, 1.21-1.56), Black/African American race (OR, 1.25; 95% CI, 1.06-1.47), obesity (OR, 1.19; 95% CI, 1.01-1.41), and several pediatric complex chronic condition (PCCC) subcategories were associated with higher severity disease. Vital signs and many laboratory test values from the day of admission were predictive of peak disease severity. Variables associated with increased odds for MIS-C vs acute COVID-19 included male sex (OR, 1.59; 95% CI, 1.33-1.90), Black/African American race (OR, 1.44; 95% CI, 1.17-1.77), younger than 12 years (OR, 1.81; 95% CI, 1.51-2.18), obesity (OR, 1.76; 95% CI, 1.40-2.22), and not having a pediatric complex chronic condition (OR, 0.72; 95% CI, 0.65-0.80). The children with MIS-C had a more inflammatory laboratory profile and severe clinical phenotype, with higher rates of invasive ventilation (117 of 707 [16.5%] vs 514 of 8241 [6.2%]; P < .001) and need for vasoactive-inotropic support (191 of 707 [27.0%] vs 426 of 8241 [5.2%]; P < .001) compared with those who had acute COVID-19. Comparing children during the Delta vs pre-Delta eras, there was no significant change in hospitalization rate (1738 [6.0%] vs 8507 [6.2%]; P = .18) and lower odds for severe disease (179 [10.3%] vs 1242 [14.6%]) (decreased by a factor of 0.67; 95% CI, 0.57-0.79; P < .001). Conclusions and Relevance: In this cohort study of US children with SARS-CoV-2, there were observed differences in demographic characteristics, preexisting comorbidities, and initial vital sign and laboratory values between severity subgroups. Taken together, these results suggest that early identification of children likely to progress to severe disease could be achieved using readily available data elements from the day of admission. Further work is needed to translate this knowledge into improved outcomes.

Synergies between centralized and federated approaches to data quality: a report from the national COVID cohort collaborative.

OBJECTIVE: In response to COVID-19, the informatics community united to aggregate as much clinical data as possible to characterize this new disease and reduce its impact through collaborative analytics. The National COVID Cohort Collaborative (N3C) is now the largest publicly available HIPAA limited dataset in US history with over 6.4 million patients and is a testament to a partnership of over 100 organizations. MATERIALS AND METHODS: We developed a pipeline for ingesting, harmonizing, and centralizing data from 56 contributing data partners using 4 federated Common Data Models. N3C data quality (DQ) review involves both automated and manual procedures. In the process, several DQ heuristics were discovered in our centralized context, both within the pipeline and during downstream project-based analysis. Feedback to the sites led to many local and centralized DQ improvements. RESULTS: Beyond well-recognized DQ findings, we discovered 15 heuristics relating to source Common Data Model conformance, demographics, COVID tests, conditions, encounters, measurements, observations, coding completeness, and fitness for use. Of 56 sites, 37 sites (66%) demonstrated issues through these heuristics. These 37 sites demonstrated improvement after receiving feedback. DISCUSSION: We encountered site-to-site differences in DQ which would have been challenging to discover using federated checks alone. We have demonstrated that centralized DQ benchmarking reveals unique opportunities for DQ improvement that will support improved research analytics locally and in aggregate. CONCLUSION: By combining rapid, continual assessment of DQ with a large volume of multisite data, it is possible to support more nuanced scientific questions with the scale and rigor that they require.

Economic analysis of centralized vs. decentralized electronic data capture in multi-center clinical studies.

BACKGROUND: New data management models are emerging in multi-center clinical studies. We evaluated the incremental costs associated with decentralized vs. centralized models. METHODS: We developed clinical research network economic models to evaluate three data management models: centralized, decentralized with local software, and decentralized with shared database. Descriptive information from three clinical research studies served as inputs for these models. MAIN OUTCOME MEASURES: The primary outcome was total data management costs. Secondary outcomes included: data management costs for sites, local data centers, and central coordinating centers. RESULTS: Both decentralized models were more costly than the centralized model for each clinical research study: the decentralized with local software model was the most expensive. Decreasing the number of local data centers and case book pages reduced cost differentials between models. CONCLUSION: Decentralized vs. centralized data management in multi-center clinical research studies is associated with increases in data management costs.

Children with SARS-CoV-2 in the National COVID Cohort Collaborative (N3C).

IMPORTANCE: SARS-CoV-2. OBJECTIVE: To determine the characteristics, changes over time, outcomes, and severity risk factors of SARS-CoV-2 affected children within the National COVID Cohort Collaborative (N3C). DESIGN: Prospective cohort study of patient encounters with end dates before May 27th, 2021. SETTING: 45 N3C institutions. PARTICIPANTS: Children <19-years-old at initial SARS-CoV-2 testing. MAIN OUTCOMES AND MEASURES: Case incidence and severity over time, demographic and comorbidity severity risk factors, vital sign and laboratory trajectories, clinical outcomes, and acute COVID-19 vs MIS-C contrasts for children infected with SARS-CoV-2. RESULTS: 728,047 children in the N3C were tested for SARS-CoV-2; of these, 91,865 (12.6%) were positive. Among the 5,213 (6%) hospitalized children, 685 (13%) met criteria for severe disease: mechanical ventilation (7%), vasopressor/inotropic support (7%), ECMO (0.6%), or death/discharge to hospice (1.1%). Male gender, African American race, older age, and several pediatric complex chronic condition (PCCC) subcategories were associated with higher clinical severity (p ≤ 0.05). Vital signs (all p≤0.002) and many laboratory tests from the first day of hospitalization were predictive of peak disease severity. Children with severe (vs moderate) disease were more likely to receive antimicrobials (71% vs 32%, p<0.001) and immunomodulatory medications (53% vs 16%, p<0.001). Compared to those with acute COVID-19, children with MIS-C were more likely to be male, Black/African American, 1-to-12-years-old, and less likely to have asthma, diabetes, or a PCCC (p < 0.04). MIS-C cases demonstrated a more inflammatory laboratory profile and more severe clinical phenotype with higher rates of invasive ventilation (12% vs 6%) and need for vasoactive-inotropic support (31% vs 6%) compared to acute COVID-19 cases, respectively (p<0.03). CONCLUSIONS: In the largest U.S. SARS-CoV-2-positive pediatric cohort to date, we observed differences in demographics, pre-existing comorbidities, and initial vital sign and laboratory test values between severity subgroups. Taken together, these results suggest that early identification of children likely to progress to severe disease could be achieved using readily available data elements from the day of admission. Further work is needed to translate this knowledge into improved outcomes.

Clinical Characterization and Prediction of Clinical Severity of SARS-CoV-2 Infection Among US Adults Using Data From the US National COVID Cohort Collaborative.

Importance: The National COVID Cohort Collaborative (N3C) is a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools and inform clinical care and policy. Objectives: To evaluate COVID-19 severity and risk factors over time and assess the use of machine learning to predict clinical severity. Design, Setting, and Participants: In a retrospective cohort study of 1 926 526 US adults with SARS-CoV-2 infection (polymerase chain reaction >99% or antigen <1%) and adult patients without SARS-CoV-2 infection who served as controls from 34 medical centers nationwide between January 1, 2020, and December 7, 2020, patients were stratified using a World Health Organization COVID-19 severity scale and demographic characteristics. Differences between groups over time were evaluated using multivariable logistic regression. Random forest and XGBoost models were used to predict severe clinical course (death, discharge to hospice, invasive ventilatory support, or extracorporeal membrane oxygenation). Main Outcomes and Measures: Patient demographic characteristics and COVID-19 severity using the World Health Organization COVID-19 severity scale and differences between groups over time using multivariable logistic regression. Results: The cohort included 174 568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1 133 848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized, and 6565 (20.2%) of those had a severe clinical course (invasive ventilatory support, extracorporeal membrane oxygenation, death, or discharge to hospice). Of the hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March to April 2020 to 8.6% in September to October 2020 (P = .002 for monthly trend). Using 64 inputs available on the first hospital day, this study predicted a severe clinical course using random forest and XGBoost models (area under the receiver operating curve = 0.87 for both) that were stable over time. The factor most strongly associated with clinical severity was pH; this result was consistent across machine learning methods. In a separate multivariable logistic regression model built for inference, age (odds ratio [OR], 1.03 per year; 95% CI, 1.03-1.04), male sex (OR, 1.60; 95% CI, 1.51-1.69), liver disease (OR, 1.20; 95% CI, 1.08-1.34), dementia (OR, 1.26; 95% CI, 1.13-1.41), African American (OR, 1.12; 95% CI, 1.05-1.20) and Asian (OR, 1.33; 95% CI, 1.12-1.57) race, and obesity (OR, 1.36; 95% CI, 1.27-1.46) were independently associated with higher clinical severity. Conclusions and Relevance: This cohort study found that COVID-19 mortality decreased over time during 2020 and that patient demographic characteristics and comorbidities were associated with higher clinical severity. The machine learning models accurately predicted ultimate clinical severity using commonly collected clinical data from the first 24 hours of a hospital admission.