Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children's diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence diabetic eye exam at the point of care), or control (scripted eye care provider referral and education) in an academic pediatric diabetes center. The primary outcome was diabetic eye exam completion rate within 6 months. The secondary outcome was the proportion of participants who completed follow-through with an eye care provider if deemed appropriate. Diabetic eye exam completion rate was significantly higher (100%, 95%CI: 95.5%, 100%) in the intervention group (n = 81) than the control group (n = 83) (22%, 95%CI: 14.2%, 32.4%)(p < 0.001). In the intervention arm, 25/81 participants had an abnormal result, of whom 64% (16/25) completed follow-through with an eye care provider, compared to 22% in the control arm (p < 0.001). Autonomous AI increases diabetic eye exam completion rates in youth with diabetes.

Advancing Toward a Common Data Model in Ophthalmology: Gap Analysis of General Eye Examination Concepts to Standard Observational Medical Outcomes Partnership (OMOP) Concepts.

Purpose: Evaluate the degree of concept coverage of the general eye examination in one widely used electronic health record (EHR) system using the Observational Health Data Sciences and Informatics Observational Medical Outcomes Partnership (OMOP) common data model (CDM). Design: Study of data elements. Participants: Not applicable. Methods: Data elements (field names and predefined entry values) from the general eye examination in the Epic foundation system were mapped to OMOP concepts and analyzed. Each mapping was given a Health Level 7 equivalence designation-equal when the OMOP concept had the same meaning as the source EHR concept, wider when it was missing information, narrower when it was overly specific, and unmatched when there was no match. Initial mappings were reviewed by 2 graders. Intergrader agreement for equivalence designation was calculated using Cohen's kappa. Agreement on the mapped OMOP concept was calculated as a percentage of total mappable concepts. Discrepancies were discussed and a final consensus created. Quantitative analysis was performed on wider and unmatched concepts. Main Outcome Measures: Gaps in OMOP concept coverage of EHR elements and intergrader agreement of mapped OMOP concepts. Results: A total of 698 data elements (210 fields, 488 values) from the EHR were analyzed. The intergrader kappa on the equivalence designation was 0.88 (standard error 0.03, P < 0.001). There was a 96% agreement on the mapped OMOP concept. In the final consensus mapping, 25% (1% fields, 31% values) of the EHR to OMOP concept mappings were considered equal, 50% (27% fields, 60% values) wider, 4% (8% fields, 2% values) narrower, and 21% (52% fields, 8% values) unmatched. Of the wider mapped elements, 46% were missing the laterality specification, 24% had other missing attributes, and 30% had both issues. Wider and unmatched EHR elements could be found in all areas of the general eye examination. Conclusions: Most data elements in the general eye examination could not be represented precisely using the OMOP CDM. Our work suggests multiple ways to improve the incorporation of important ophthalmology concepts in OMOP, including adding laterality to existing concepts. There exists a strong need to improve the coverage of ophthalmic concepts in source vocabularies so that the OMOP CDM can better accommodate vision research. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Associations between sleep health and obesity and weight change in adults: The Daily24 Multisite Cohort Study.

OBJECTIVES: To examine cross-sectional and longitudinal associations of individual sleep domains and multidimensional sleep health with current overweight or obesity and 5-year weight change in adults. METHODS: We estimated sleep regularity, quality, timing, onset latency, sleep interruptions, duration, and napping using validated questionnaires. We calculated multidimensional sleep health using a composite score (total number of "good" sleep health indicators) and sleep phenotypes derived from latent class analysis. Logistic regression was used to examine associations between sleep and overweight or obesity. Multinomial regression was used to examine associations between sleep and weight change (gain, loss, or maintenance) over a median of 1.66 years. RESULTS: The sample included 1016 participants with a median age of 52 (IQR = 37-65), who primarily identified as female (78%), White (79%), and college-educated (74%). We identified 3 phenotypes: good, moderate, and poor sleep. More regularity of sleep, sleep quality, and shorter sleep onset latency were associated with 37%, 38%, and 45% lower odds of overweight or obesity, respectively. The addition of each good sleep health dimension was associated with 16% lower adjusted odds of having overweight or obesity. The adjusted odds of overweight or obesity were similar between sleep phenotypes. Sleep, individual or multidimensional sleep health, was not associated with weight change. CONCLUSIONS: Multidimensional sleep health showed cross-sectional, but not longitudinal, associations with overweight or obesity. Future research should advance our understanding of how to assess multidimensional sleep health to understand the relationship between all aspects of sleep health and weight over time.

Strengths, weaknesses, opportunities, and threats for the nation's public health information systems infrastructure: synthesis of discussions from the 2022 ACMI Symposium.

OBJECTIVE: The annual American College of Medical Informatics (ACMI) symposium focused discussion on the national public health information systems (PHIS) infrastructure to support public health goals. The objective of this article is to present the strengths, weaknesses, threats, and opportunities (SWOT) identified by public health and informatics leaders in attendance. MATERIALS AND METHODS: The Symposium provided a venue for experts in biomedical informatics and public health to brainstorm, identify, and discuss top PHIS challenges. Two conceptual frameworks, SWOT and the Informatics Stack, guided discussion and were used to organize factors and themes identified through a qualitative approach. RESULTS: A total of 57 unique factors related to the current PHIS were identified, including 9 strengths, 22 weaknesses, 14 opportunities, and 14 threats, which were consolidated into 22 themes according to the Stack. Most themes (68%) clustered at the top of the Stack. Three overarching opportunities were especially prominent: (1) addressing the needs for sustainable funding, (2) leveraging existing infrastructure and processes for information exchange and system development that meets public health goals, and (3) preparing the public health workforce to benefit from available resources. DISCUSSION: The PHIS is unarguably overdue for a strategically designed, technology-enabled, information infrastructure for delivering day-to-day essential public health services and to respond effectively to public health emergencies. CONCLUSION: Most of the themes identified concerned context, people, and processes rather than technical elements. We recommend that public health leadership consider the possible actions and leverage informatics expertise as we collectively prepare for the future.

Effectiveness of artificial intelligence screening in preventing vision loss from diabetes: a policy model.

The effectiveness of using artificial intelligence (AI) systems to perform diabetic retinal exams ('screening') on preventing vision loss is not known. We designed the Care Process for Preventing Vision Loss from Diabetes (CAREVL), as a Markov model to compare the effectiveness of point-of-care autonomous AI-based screening with in-office clinical exam by an eye care provider (ECP), on preventing vision loss among patients with diabetes. The estimated incidence of vision loss at 5 years was 1535 per 100,000 in the AI-screened group compared to 1625 per 100,000 in the ECP group, leading to a modelled risk difference of 90 per 100,000. The base-case CAREVL model estimated that an autonomous AI-based screening strategy would result in 27,000 fewer Americans with vision loss at 5 years compared with ECP. Vision loss at 5 years remained lower in the AI-screened group compared to the ECP group, in a wide range of parameters including optimistic estimates biased toward ECP. Real-world modifiable factors associated with processes of care could further increase its effectiveness. Of these factors, increased adherence with treatment was estimated to have the greatest impact.

Healthcare utilization is a collider: an introduction to collider bias in EHR data reuse.

OBJECTIVES: Collider bias is a common threat to internal validity in clinical research but is rarely mentioned in informatics education or literature. Conditioning on a collider, which is a variable that is the shared causal descendant of an exposure and outcome, may result in spurious associations between the exposure and outcome. Our objective is to introduce readers to collider bias and its corollaries in the retrospective analysis of electronic health record (EHR) data. TARGET AUDIENCE: Collider bias is likely to arise in the reuse of EHR data, due to data-generating mechanisms and the nature of healthcare access and utilization in the United States. Therefore, this tutorial is aimed at informaticians and other EHR data consumers without a background in epidemiological methods or causal inference. SCOPE: We focus specifically on problems that may arise from conditioning on forms of healthcare utilization, a common collider that is an implicit selection criterion when one reuses EHR data. Directed acyclic graphs (DAGs) are introduced as a tool for identifying potential sources of bias during study design and planning. References for additional resources on causal inference and DAG construction are provided.

Human-Centered Design of a Clinical Decision Support for Anemia Screening in Children with Inflammatory Bowel Disease.

BACKGROUND: Inflammatory bowel disease (IBD) commonly leads to iron deficiency anemia (IDA). Rates of screening and treatment of IDA are often low. A clinical decision support system (CDSS) embedded in an electronic health record could improve adherence to evidence-based care. Rates of CDSS adoption are often low due to poor usability and fit with work processes. One solution is to use human-centered design (HCD), which designs CDSS based on identified user needs and context of use and evaluates prototypes for usefulness and usability. OBJECTIVES: this study aimed to use HCD to design a CDSS tool called the IBD Anemia Diagnosis Tool, IADx. METHODS: Interviews with IBD practitioners informed creation of a process map of anemia care that was used by an interdisciplinary team that used HCD principles to create a prototype CDSS. The prototype was iteratively tested with "Think Aloud" usability evaluation with clinicians as well as semi-structured interviews, a survey, and observations. Feedback was coded and informed redesign. RESULTS: Process mapping showed that IADx should function at in-person encounters and asynchronous laboratory review. Clinicians desired full automation of clinical information acquisition such as laboratory trends and analysis such as calculation of iron deficit, less automation of clinical decision selection such as laboratory ordering, and no automation of action implementation such as signing medication orders. Providers preferred an interruptive alert over a noninterruptive reminder. CONCLUSION: Providers preferred an interruptive alert, perhaps due to the low likelihood of noticing a noninterruptive advisory. High levels of desire for automation of information acquisition and analysis with less automation of decision selection and action may be generalizable to other CDSSs designed for chronic disease management. This underlines the ways in which CDSSs have the potential to augment rather than replace provider cognitive work.

Applicability Area: A novel utility-based approach for evaluating predictive models, beyond discrimination.

Translating prediction models into practice and supporting clinicians' decision-making demand demonstration of clinical value. Existing approaches to evaluating machine learning models emphasize discriminatory power, which is only a part of the medical decision problem. We propose the Applicability Area (ApAr), a decision-analytic utility-based approach to evaluating predictive models that communicate the range of prior probability and test cutoffs for which the model has positive utility; larger ApArs suggest a broader potential use of the model. We assess ApAr with simulated datasets and with three published medical datasets. ApAr adds value beyond the typical area under the receiver operating characteristic curve (AUROC) metric analysis. As an example, in the diabetes dataset, the top model by ApAr was ranked as the 23rd best model by AUROC. Decision makers looking to adopt and implement models can leverage ApArs to assess if the local range of priors and utilities is within the respective ApArs.

Electronic Health Record-Based Recruitment and Retention and Mobile Health App Usage: Multisite Cohort Study.

BACKGROUND: To address the obesity epidemic, there is a need for novel paradigms, including those that address the timing of eating and sleep in relation to circadian rhythms. Electronic health records (EHRs) are an efficient way to identify potentially eligible participants for health research studies. Mobile health (mHealth) apps offer available and convenient data collection of health behaviors, such as timing of eating and sleep. OBJECTIVE: The aim of this descriptive analysis was to report on recruitment, retention, and app use from a 6-month cohort study using a mobile app called Daily24. METHODS: Using an EHR query, adult patients from three health care systems in the PaTH clinical research network were identified as potentially eligible, invited electronically to participate, and instructed to download and use the Daily24 mobile app, which focuses on eating and sleep timing. Online surveys were completed at baseline and 4 months. We described app use and identified predictors of app use, defined as 1 or more days of use, versus nonuse and usage categories (ie, immediate, consistent, and sustained) using multivariate regression analyses. RESULTS: Of 70,661 patients who were sent research invitations, 1021 (1.44%) completed electronic consent forms and online baseline surveys; 4 withdrew, leaving a total of 1017 participants in the analytic sample. A total of 53.79% (n=547) of the participants were app users and, of those, 75.3% (n=412), 50.1% (n=274), and 25.4% (n=139) were immediate, consistent, and sustained users, respectively. Median app use was 28 (IQR 7-75) days over 6 months. Younger age, White race, higher educational level, higher income, having no children younger than 18 years, and having used 1 to 5 health apps significantly predicted app use (vs nonuse) in adjusted models. Older age and lower BMI predicted early, consistent, and sustained use. About half (532/1017, 52.31%) of the participants completed the 4-month online surveys. A total of 33.5% (183/547), 29.3% (157/536), and 27.1% (143/527) of app users were still using the app for at least 2 days per month during months 4, 5, and 6 of the study, respectively. CONCLUSIONS: EHR recruitment offers an efficient (ie, high reach, low touch, and minimal participant burden) approach to recruiting participants from health care settings into mHealth research. Efforts to recruit and retain less engaged subgroups are needed to collect more generalizable data. Additionally, future app iterations should include more evidence-based features to increase participant use.

Harmonizing units and values of quantitative data elements in a very large nationally pooled electronic health record (EHR) dataset.

OBJECTIVE: The goals of this study were to harmonize data from electronic health records (EHRs) into common units, and impute units that were missing. MATERIALS AND METHODS: The National COVID Cohort Collaborative (N3C) table of laboratory measurement data-over 3.1 billion patient records and over 19 000 unique measurement concepts in the Observational Medical Outcomes Partnership (OMOP) common-data-model format from 55 data partners. We grouped ontologically similar OMOP concepts together for 52 variables relevant to COVID-19 research, and developed a unit-harmonization pipeline comprised of (1) selecting a canonical unit for each measurement variable, (2) arriving at a formula for conversion, (3) obtaining clinical review of each formula, (4) applying the formula to convert data values in each unit into the target canonical unit, and (5) removing any harmonized value that fell outside of accepted value ranges for the variable. For data with missing units for all the results within a lab test for a data partner, we compared values with pooled values of all data partners, using the Kolmogorov-Smirnov test. RESULTS: Of the concepts without missing values, we harmonized 88.1% of the values, and imputed units for 78.2% of records where units were absent (41% of contributors' records lacked units). DISCUSSION: The harmonization and inference methods developed herein can serve as a resource for initiatives aiming to extract insight from heterogeneous EHR collections. Unique properties of centralized data are harnessed to enable unit inference. CONCLUSION: The pipeline we developed for the pooled N3C data enables use of measurements that would otherwise be unavailable for analysis.

Night eating, weight, and health behaviors in adults participating in the Daily24 study.

BACKGROUND: Night eating syndrome (NES) is associated with adverse health outcomes. This study evaluated the relationship between night eating severity, weight, and health behaviors. METHODS: Participants (N = 1017; 77.6% female, mean Body Mass Index (BMI) = 30.5, SD = 7.8 kg/m2, age = 51.1, SD = 15.0 years) were recruited from three health systems. Participants completed the Night Eating Questionnaire (NEQ) and questionnaires assessing sleep, chronotype, physical activity, diet, weight, and napping. RESULTS: In the overall sample, higher NEQ scores were associated with higher BMI (p < .001) and consumption of sugar-sweetened beverages (p < .001), as well as lower fruit/vegetable consumption (p = .001). Higher NEQ scores were associated with increased odds of having overweight/obesity (p < .001), eating fast food (p < .001), moderate-vigorous physical activity (p = .005), and smoking (p = .004). Participants who exceeded the screening threshold for NES (n = 48, 4.7%) reported elevated BMI (p = .014), an increased likelihood of overweight/obesity (p = .004), greater sugar-sweetened beverages consumption (p < .001), napping less than twice per week (p = .029), shorter sleep duration (p = .012), and a later chronotype (M = 4:55, SD = 2:45). CONCLUSION: Night eating severity was associated with obesity and intake of fast food and sugar-sweetened beverages. Interventions to address night eating and associated behaviors may enhance the efficacy of weight management interventions and promote engagement in positive health behaviors.

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.

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.

The National COVID Cohort Collaborative: Clinical Characterization and Early Severity Prediction.

Background: The majority of U.S. reports of COVID-19 clinical characteristics, disease course, and treatments are from single health systems or focused on one domain. Here we report the creation of the National COVID Cohort Collaborative (N3C), a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative U.S. cohort of COVID-19 cases and controls to date. This multi-center dataset supports robust evidence-based development of predictive and diagnostic tools and informs critical care and policy. Methods and Findings: In a retrospective cohort study of 1,926,526 patients from 34 medical centers nationwide, we stratified patients using a World Health Organization COVID-19 severity scale and demographics; we then evaluated differences between groups over time using multivariable logistic regression. We established vital signs and laboratory values among COVID-19 patients with different severities, providing the foundation for predictive analytics. The cohort included 174,568 adults with severe acute respiratory syndrome associated with SARS-CoV-2 (PCR >99% or antigen <1%) as well as 1,133,848 adult patients that served as lab-negative controls. Among 32,472 hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March/April 2020 to 8.6% in September/October 2020 (p = 0.002 monthly trend). In a multivariable logistic regression model, age, male sex, liver disease, dementia, African-American and Asian race, and obesity were independently associated with higher clinical severity. To demonstrate the utility of the N3C cohort for analytics, we used machine learning (ML) to predict clinical severity and risk factors over time. Using 64 inputs available on the first hospital day, we predicted a severe clinical course (death, discharge to hospice, invasive ventilation, or extracorporeal membrane oxygenation) using random forest and XGBoost models (AUROC 0.86 and 0.87 respectively) that were stable over time. The most powerful predictors in these models are patient age and widely available vital sign and laboratory values. The established expected trajectories for many vital signs and laboratory values among patients with different clinical severities validates observations from smaller studies, and provides comprehensive insight into COVID-19 characterization in U.S. patients. Conclusions: This is the first description of an ongoing longitudinal observational study of patients seen in diverse clinical settings and geographical regions and is the largest COVID-19 cohort in the United States. Such data are the foundation for ML models that can be the basis for generalizable clinical decision support tools. The N3C Data Enclave is unique in providing transparent, reproducible, easily shared, versioned, and fully auditable data and analytic provenance for national-scale patient-level EHR data. The N3C is built for intensive ML analyses by academic, industry, and citizen scientists internationally. Many observational correlations can inform trial designs and care guidelines for this new disease.

Applying Decision Science to the Prioritization of Healthcare-Associated Infection Initiatives.

OBJECTIVES: Improving patient quality remains a top priority from the perspectives of both patient outcomes and cost of care. The continuing threat to patient safety has resulted in an increasing number of options for patient safety initiatives, making choices more difficult because of competing priorities. This study provides a proof of concept for using low-cost decision science methods for prioritizing initiatives. METHODS: Using multicriteria decision analysis, we developed a decision support model for aiding the prioritization of the four most common types of healthcare-associated infections: surgical site infections, central line-associated bloodstream infections, ventilator-associated events, and catheter-associated urinary tract infections. In semistructured interviews, we elicited structure and parameter values of a candidate model, which was then validated by six participants with different roles across three urban teaching and nonteaching hospitals in the Baltimore, Maryland area. RESULTS: Participants articulated the following structural attributes of concern: patient harm, monetary costs, patient mortality, reputational effects, and patient satisfaction. A quantitative decision-making model with an associated uncertainty report for prioritizing initiatives related to the four most common types of healthcare-associated infections was then created. CONCLUSIONS: A decision support methodology such as our proof of concept could aid hospital executives in prioritizing the quality improvement initiatives within their hospital, with more complete data. Because hospitals continue to struggle in improving quality of care with tighter budgets, a formal decision support mechanism could be used to objectively prioritize patient safety and quality initiatives.

The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers. MATERIALS AND METHODS: The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics. RESULTS: Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access. CONCLUSIONS: The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.

Cost-effectiveness of Autonomous Point-of-Care Diabetic Retinopathy Screening for Pediatric Patients With Diabetes.

Importance: Screening for diabetic retinopathy is recommended for children with type 1 diabetes (T1D) and type 2 diabetes (T2D), yet screening rates remain low. Point-of-care diabetic retinopathy screening using autonomous artificial intelligence (AI) has become available, providing immediate results in the clinic setting, but the cost-effectiveness of this strategy compared with standard examination is unknown. Objective: To assess the cost-effectiveness of detecting and treating diabetic retinopathy and its sequelae among children with T1D and T2D using AI diabetic retinopathy screening vs standard screening by an eye care professional (ECP). Design, Setting, and Participants: In this economic evaluation, parameter estimates were obtained from the literature from 1994 to 2019 and assessed from March 2019 to January 2020. Parameters included out-of-pocket cost for autonomous AI screening, ophthalmology visits, and treating diabetic retinopathy; probability of undergoing standard retinal examination; relative odds of undergoing screening; and sensitivity, specificity, and diagnosability of the ECP screening examination and autonomous AI screening. Main Outcomes and Measures: Costs or savings to the patient based on mean patient payment for diabetic retinopathy screening examination and cost-effectiveness based on costs or savings associated with the number of true-positive results identified by diabetic retinopathy screening. Results: In this study, the expected true-positive proportions for standard ophthalmologic screening by an ECP were 0.006 for T1D and 0.01 for T2D, and the expected true-positive proportions for autonomous AI were 0.03 for T1D and 0.04 for T2D. The base case scenario of 20% adherence estimated that use of autonomous AI would result in a higher mean patient payment ($8.52 for T1D and $10.85 for T2D) than conventional ECP screening ($7.91 for T1D and $8.20 for T2D). However, autonomous AI screening was the preferred strategy when at least 23% of patients adhered to diabetic retinopathy screening. Conclusions and Relevance: These results suggest that point-of-care diabetic retinopathy screening using autonomous AI systems is effective and cost saving for children with diabetes and their caregivers at recommended adherence rates.