Bian, Jiang

Abstract Hypertensive disorders of pregnancy (HDP) are a leading cause of maternal and perinatal morbidity, yet modifiable environmental risk factors remain poorly characterized. Prior studies typically have only examined a limited number of exposures and have rarely distinguished HDP subtypes (ie, gestational hypertension, preeclampsia, eclampsia, and chronic hypertension with or without superimposed preeclampsia) or accounted for residential mobility during pregnancy. To address these gaps, we conducted a spatial and contextual exposome study of HDP using linked electronic health records (EHR) and vital statistics data in Florida. We analyzed 686 412 singleton pregnancies conceived between 2013 and 2018, using computable phenotyping to distinguish HDP subtypes. A total of 245 spatial and contextual exposome measures spanning natural, built, and social environments were linked to residential histories from conception through gestational week 19. Using a two-phase double machine learning (DML) framework with exposure-specific, directed acyclic graph-guided confounder adjustment, we conducted discovery and replication analyses, followed by multi-treatment DML to estimate effect sizes. In Phase 1, 26 exposome measures replicated for gestational hypertension and 34 for overall HDP. In Phase 2, 12 measures remained associated with gestational hypertension and 11 with overall HDP, including air toxicants, meteorological factors, ultraviolet radiation, neighborhood crime indicators, environmental noise, and proximity to coastline. No exposures passed multiple-comparison thresholds for preeclampsia or eclampsia. These findings demonstrate that the spatial and contextual exposome contributes to HDP in a subtype-specific manner. Integrating EHR-linked phenotyping, residential mobility, and causal machine-learning methods offers a scalable framework for identifying environmental factors relevant to HDP prevention.

Background The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug‐eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. Methods and Results We developed and validated a new AI‐based pipeline using retrospective data of drug‐eluting stent‐treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de‐identified Clinformatics Data Mart Database (n=9978). The 36 months following drug‐eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI‐DAPT model. The AI‐DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%–92%] for ischemia and 84% [95% CI, 82%–87%] for bleeding predictions. Conclusions Our AI‐DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.

Abstract Objective Social determinants of health (SDoH) are nonclinical dispositions that impact patient health risks and clinical outcomes. Leveraging SDoH in clinical decision-making can potentially improve diagnosis, treatment planning, and patient outcomes. Despite increased interest in capturing SDoH in electronic health records (EHRs), such information is typically locked in unstructured clinical notes. Natural language processing (NLP) is the key technology to extract SDoH information from clinical text and expand its utility in patient care and research. This article presents a systematic review of the state-of-the-art NLP approaches and tools that focus on identifying and extracting SDoH data from unstructured clinical text in EHRs. Materials and Methods A broad literature search was conducted in February 2021 using 3 scholarly databases (ACL Anthology, PubMed, and Scopus) following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 6402 publications were initially identified, and after applying the study inclusion criteria, 82 publications were selected for the final review. Results Smoking status (n = 27), substance use (n = 21), homelessness (n = 20), and alcohol use (n = 15) are the most frequently studied SDoH categories. Homelessness (n = 7) and other less-studied SDoH (eg, education, financial problems, social isolation and support, family problems) are mostly identified using rule-based approaches. In contrast, machine learning approaches are popular for identifying smoking status (n = 13), substance use (n = 9), and alcohol use (n = 9). Conclusion NLP offers significant potential to extract SDoH data from narrative clinical notes, which in turn can aid in the development of screening tools, risk prediction models, and clinical decision support systems.

Abstract Carfilzomib was approved for the treatment of multiple myeloma in 2012 and since then there have been concerns for cardiovascular toxicity from its use. With this study, we aim to further study the hazards and underlying risk factors for cardiovascular adverse events associated with carfilzomib. This study was conducted using Surveillance, Epidemiology, and End Results (SEER)‐Medicare data set of multiple myeloma from 2001 to 2015. Data were analyzed for hazards ratio of cardiovascular adverse events between carfilzomib users and nonusers. We identified 7330 patients with multiple myeloma of whom 815 were carfilzomib users. Carfilzomib users had a statistically significant hazard ratio of 1.41 with p < 0.0001 for all cardiovascular adverse events as compared to nonusers. Carfilzomib use was significantly associated with increased risk of heart failure (HR 1.47, p = 0.0002), ischemic heart disease (HR 1.45, p = 0.0002), and hypertension (HR 3.33, p < 0.0001), whereas there was no association between carfilzomib use and cardiac conduction disorders (arrhythmia and heart blocks). Carfilzomib users were at higher risk of new‐onset edema (HR 5.09, p < 0.0001), syncope (HR 4.27, p < 0.0001), dyspnea (HR 1.33, p < 0.0001), and chest pain (HR 1.18, p < 0.0001) as compared to carfilzomib nonusers. Age above 75 years, preexisting cardiovascular disease, obesity, and twice a week carfilzomib schedule were significant risk factors associated with cardiovascular adverse events in carfilzomib users. The median time of the onset for all cardiovascular adverse events was 3.1 months. This study has identified a significantly higher likelihood of cardiovascular adverse events in elderly Medicare patients receiving carfilzomib.

Abstract The words cure and hope are important terms in oncology, reflecting a balance of aspirations and realism for physicians and patients. Yet, some have suggested that oncologists are reluctant to use these terms. We tested this hypothesis by performing a bibliometric analysis of the frequency of use of these words in JAMA Oncology (JAMA Oncol) and the Journal of Clinical Oncology (JCO). The text of all articles in 3 categories—primary research, editorials, and narrative essays—appearing in JCO from 2000 to 2018 and in JAMA Oncol from 2015 to 2019 was analyzed. These analyses compared, across these categories, the proportion of articles containing the words cure and hope, as well as the proportion of total sentences containing these words. There were statistically significant differences in frequency of the use of the terms cure and hope as a function of the type of article published in the JCO and JAMA Oncol (2-sided P values ranging from .005 to &lt;.001). Results were similar for both journals, with minor exceptions. Both hope and cure were used in a greater number of articles and sentences in the narrative and editorial categories than in primary research. Moreover, hope was used more often in narrative essays than in editorials. The relative reluctance to use these terms in more scientifically oriented original reports, despite concomitant improvements in oncologic outcomes, may reflect a bias worthy of future exploration.

AbstractLarge observational data networks that leverage routine clinical practice data in electronic health records (EHRs) are critical resources for research on coronavirus disease 2019 (COVID-19). Data normalization is a key challenge for the secondary use of EHRs for COVID-19 research across institutions. In this study, we addressed the challenge of automating the normalization of COVID-19 diagnostic tests, which are critical data elements, but for which controlled terminology terms were published after clinical implementation. We developed a simple but effective rule-based tool called COVID-19 TestNorm to automatically normalize local COVID-19 testing names to standard LOINC (Logical Observation Identifiers Names and Codes) codes. COVID-19 TestNorm was developed and evaluated using 568 test names collected from 8 healthcare systems. Our results show that it could achieve an accuracy of 97.4% on an independent test set. COVID-19 TestNorm is available as an open-source package for developers and as an online Web application for end users (https://clamp.uth.edu/covid/loinc.php). We believe that it will be a useful tool to support secondary use of EHRs for research on COVID-19.

Background PCSK9 (proprotein convertase subtilisin/kexin type 9) inhibitors effectively lower LDL (low‐density lipoprotein) cholesterol and have been shown to reduce cardiovascular outcomes in high‐risk patients. We used real‐world electronic health record data to characterize use of PCSK9 inhibitors, in addition to standard therapies, according to cardiovascular risk status. Methods and Results Data were obtained from 18 health systems with data marts within the National Patient‐Centered Clinical Research Network (PCORnet) using a common data model. Participating sites identified >17.5 million adults, of whom 3.6 million met study criteria. Patients were categorized into 3 groups: (1) dyslipidemia, (2) untreated LDL ≥130 mg/dL, and (3) coronary artery disease or coronary heart disease. Demographics, comorbidities, estimated 10‐year atherosclerotic cardiovascular disease risk, and lipid‐lowering pharmacotherapies were summarized for each group. Participants’ average age was 62 years, 50% were female, and 11% were black. LDL cholesterol ranged from 85 to 151 mg/dL. Among patients in groups 1 and 3, 54% received standard lipid‐lowering therapies and a PCSK9 inhibitor was prescribed in <1%. PCSK9 inhibitor prescribing was greatest for patients with coronary artery disease or coronary heart disease and, although prescribing increased during the study period, overall PCSK9 inhibitor prescribing was low. Conclusions We successfully used electronic health record data from 18 PCORnet data marts to identify >3.6 million patients meeting criteria for 3 patient groups. Approximately half of patients had been prescribed lipid‐lowering medication, but <1% were prescribed PCSK9 inhibitors. PCSK9 inhibitor prescribing increased over time for patients with coronary artery disease or coronary heart disease but not for those with dyslipidemia.