Objective: Early and accurate prediction of patients at risk of readmission is key to reducing costs and improving outcomes. LACE is a widely used score to predict 30-day readmissions. We examine whether adding social determinants of health (SDOH) to LACE can improve its predictive performance. Methods: This is a retrospective study that included all inpatient encounters in the state of Maryland in 2019. We constructed predictive models by fitting Logistic Regression (LR) on LACE and different sets of SDOH predictors. We used the area under the curve (AUC) to evaluate discrimination and SHapley Additive exPlanations values to assess feature importance. Results: Our study population included 316 558 patients of whom 35 431 (11.19%) patients were readmitted after 30 days. Readmitted patients had more challenges with individual-level SDOH and were more likely to reside in communities with poor SDOH conditions. Adding a combination of individual and community-level SDOH improved LACE performance from AUC = 0.698 (95% CI [0.695–0.7]; ref) to AUC = 0.708 (95% CI [0.705–0.71]; P < .001). The increase in AUC was highest in black patients (+1.6), patients aged 65 years or older (+1.4), and male patients (+1.4). Discussion: We demonstrated the value of SDOH in improving the LACE index. Further, the additional predictive value of SDOH on readmission risk varies by subpopulations. Vulnerable populations like black patients and the elderly are likely to benefit more from the inclusion of SDOH in readmission prediction. Conclusion: These findings provide potential SDOH factors that health systems and policymakers can target to reduce overall readmissions.

Significant strides have been made in utilizing data, information, and knowledge to enhance neonatal outcomes. This review examines how data informatics, encompassing electronic health records (EHRs), data standards, and artificial intelligence (AI), has facilitated advancements in neonatal care and research. Vast amounts of data, structured and unstructured, have been produced from clinical care. In turn AI stands to improve patient care, safety, and quality improvement initiatives. Facilitated by AI, clinicians' interaction with neonatal informatic tools is transitioning from reactive to real-time, proactive care. Historically, necrotizing enterocolitis, sepsis, medical imaging, and neonatal mortality have been the targets of AI-integrated neonatal care. While much progress has been made in developing state-of-the-art AI tools, their development and implementation must consider optimization of patient care, clinical workflows, and aim to decrease clinician burnout. Employing a sociotechnical framework to assess both technical and human factors is key to effectively evaluating clinical utility, promoting adoption, and facilitating successful deployment. Beyond technical concerns, ethical considerations such as trust in AI, data security, and model transparency are critical to the responsible deployment of informatics tools. Ongoing advancements in neonatal care coupled with informatics, multi-omics, AI, and federated learning expands the possibilities of personalized care for neonates.

Background: In the United States, >3.6 million deliveries occur annually. Among them, up to 20% (approximately 700,000) of women experience postpartum depression (PPD) according to the Centers for Disease Control and Prevention. Absence of accurate reporting and diagnosis has made phenotyping of patients with PPD difficult. Existing literature has shown that factors such as race, socioeconomic status, and history of substance abuse are associated with the differential risks of PPD. However, limited research has considered differential temporal associations with the outcome. Objective: This study aimed to estimate the disparities in the risk of PPD and time to diagnosis for patients of different racial and socioeconomic backgrounds. Methods: This is a longitudinal retrospective study using the statewide hospital discharge data from Maryland. We identified 160,066 individuals who had a hospital delivery from 2017 to 2019. We applied logistic regression and Cox regression to study the risk of PPD across racial and socioeconomic strata. Multinomial regression was used to estimate the risk of PPD at different postpartum stages. Results: The cumulative incidence of PPD diagnosis was highest for White patients (8779/65,028, 13.5%) and lowest for Asian and Pacific Islander patients (248/10,760, 2.3%). Compared with White patients, PPD diagnosis was less likely to occur for Black patients (odds ratio [OR] 0.31, 95% CI 0.30-0.33), Asian or Pacific Islander patients (OR 0.17, 95% CI 0.15-0.19), and Hispanic patients (OR 0.21, 95% CI 0.19-0.22). Similar findings were observed from the Cox regression analysis. Multinomial regression showed that compared with White patients, Black patients (relative risk 2.12, 95% CI 1.73-2.60) and Asian and Pacific Islander patients (relative risk 2.48, 95% CI 1.46-4.21) were more likely to be diagnosed with PPD after 8 weeks of delivery. Conclusions: Compared with White patients, PPD diagnosis is less likely to occur in individuals of other races. We found disparate timing in PPD diagnosis across different racial groups and socioeconomic backgrounds. Our findings serve to enhance intervention strategies and policies for phenotyping patients at the highest risk of PPD and to highlight needs in data quality to support future work on racial disparities in PPD.

Background: Increasing and substantial reliance on electronic health records (EHRs) and data types (ie, diagnosis, medication, and laboratory data) demands assessment of their data quality as a fundamental approach, especially since there is a need to identify appropriate denominator populations with chronic conditions, such as type 2 diabetes (T2D), using commonly available computable phenotype definitions (ie, phenotypes). Objective: To bridge this gap, our study aims to assess how issues of EHR data quality and variations and robustness (or lack thereof) in phenotypes may have potential impacts in identifying denominator populations. Methods: Approximately 208,000 patients with T2D were included in our study, which used retrospective EHR data from the Johns Hopkins Medical Institution (JHMI) during 2017‐2019. Our assessment included 4 published phenotypes and 1 definition from a panel of experts at Hopkins. We conducted descriptive analyses of demographics (ie, age, sex, race, and ethnicity), use of health care (inpatient and emergency room visits), and the average Charlson Comorbidity Index score of each phenotype. We then used different methods to induce or simulate data quality issues of completeness, accuracy, and timeliness separately across each phenotype. For induced data incompleteness, our model randomly dropped diagnosis, medication, and laboratory codes independently at increments of 10%; for induced data inaccuracy, our model randomly replaced a diagnosis or medication code with another code of the same data type and induced 2% incremental change from −100% to +10% in laboratory result values; and lastly, for timeliness, data were modeled for induced incremental shift of date records by 30 days to 365 days. Results: Less than a quarter (n=47,326, 23%) of the population overlapped across all phenotypes using EHRs. The population identified by each phenotype varied across all combinations of data types. Induced incompleteness identified fewer patients with each increment; for example, at 100% diagnostic incompleteness, the Chronic Conditions Data Warehouse phenotype identified zero patients, as its phenotypic characteristics included only diagnosis codes. Induced inaccuracy and timeliness similarly demonstrated variations in performance of each phenotype, therefore resulting in fewer patients being identified with each incremental change. Conclusions: We used EHR data with diagnosis, medication, and laboratory data types from a large tertiary hospital system to understand T2D phenotypic differences and performance. We used induced data quality methods to learn how data quality issues may impact identification of the denominator populations upon which clinical (eg, clinical research and trials, population health evaluations) and financial or operational decisions are made. The novel results from our study may inform future approaches to shaping a common T2D computable phenotype definition that can be applied to clinical informatics, managing chronic conditions, and additional industry-wide efforts in health care.

Background: The Observational Health Data Sciences and Informatics (OHDSI) community has emerged as a leader in observational research on real-world clinical data for promoting evidence for healthcare and decision-making. The community has seen rapid growth in publications, citations, and the number of authors. Components of its successful uptake have been attributed to an open science and collaborative culture for research and development. Investigating the adoption of OHDSI as a field of study provides an opportunity to understand how communities embrace new ideas, onboard new members, and enhance their impact. Objective: To track, study, and evaluate an open scientific community’s growth and impact. Method: We present a modern architecture leveraging open application programming interfaces to capture publicly available data (PubMed, YouTube, and EHDEN) on open science activities (publication, teaching, and engagement). Results: Three interactive dashboard were implemented for each publicly available artifact (PubMed, YouTube, and EHDEN). Each dashboard provides longitudinal summary analysis and has a searchable table, which differs in the available features related to each public artifact. Conclusion: We discuss the insights enabled by our approach to monitor the growth and impact of the OHDSI community by capturing artifacts of learning, teaching, and creation. We share the implications for different users based on their functional needs. As other scientific networks adopt open-source frameworks, our framework serves as a model for tracking the growth of their community, driving the perception of their development, engaging their members, and attaining higher impact.

Objective: Significant variations exist in computable phenotype definitions to identify patients with type 2 diabetes (T2D) using electronic health records (EHRs). These variations cause challenges in identifying T2D populations for clinical research. To address these challenges, this study compares the variations in common phenotypes in identifying patients with T2D using EHRs. Methods: A retrospective data analysis was performed using clinical data extracted from EHRs of 207 813 adult patients captured 2017–2019. Multiple T2D phenotypes were used: (1) Surveillance, Prevention and Management of Diabetes Mellitus, (2) Centers for Medicare and Medicaid Services Chronic Conditions Data Warehouse (CCW), (3) eMERGE Northwestern Group, (4) Durham Diabetes Coalition (DDC) and (5) a definition developed by a panel of experts at Johns Hopkins. Results: Each phenotype definition identified a different T2D population with a unique composition of demographics and clinical features. Although the identified patients overlapped across phenotypes, only 22.7% (47 326) of the population was commonly identified across all definitions. Of the phenotypes, DDC identified the greatest number of patients with T2D (139 832, 67.3%), while CCW had the highest mean age (65.3 years), the highest percentage of black patients (35%) and the highest mean Charlson comorbidity score of 2.96. DDC identified patients with T2D with the lowest means of inpatient (0.64) and emergency room (1.06) visits. Conclusion: Our study highlights the complexity of computable T2D phenotypes in translating commonly agreed T2D clinical definitions when applied against retrospective EHR data. Our findings provide an understanding of using appropriate phenotypes to identify, enrol and analyse T2D populations of interest using EHR data.