Search

Importance: A nonadjuvanted bivalent respiratory syncytial virus (RSV) prefusion F (RSVpreF [Pfizer]) protein subunit vaccine was newly approved and recommended for pregnant individuals at 32 0/7 to 36 6/7 weeks' gestation during the 2023 to 2024 RSV season; however, clinical vaccine data are lacking., Objective: To evaluate the association between prenatal RSV vaccination status and perinatal outcomes among patients who delivered during the vaccination season., Design, Setting, and Participants: This retrospective observational cohort study was conducted at 2 New York City hospitals within 1 health care system among patients who gave birth to singleton gestations at 32 weeks' gestation or later from September 22, 2023, to January 31, 2024., Exposure: Prenatal RSV vaccination with the RSVpreF vaccine captured from the health system's electronic health records., Main Outcome and Measures: The primary outcome is preterm birth (PTB), defined as less than 37 weeks' gestation. Secondary outcomes included hypertensive disorders of pregnancy (HDP), stillbirth, small-for-gestational age birth weight, neonatal intensive care unit (NICU) admission, neonatal respiratory distress with NICU admission, neonatal jaundice or hyperbilirubinemia, neonatal hypoglycemia, and neonatal sepsis. Logistic regression models were used to estimate odds ratios (ORs), and multivariable logistic regression models and time-dependent covariate Cox regression models were performed., Results: Of 2973 pregnant individuals (median [IQR] age, 34.9 [32.4-37.7] years), 1026 (34.5%) received prenatal RSVpreF vaccination. Fifteen patients inappropriately received the vaccine at 37 weeks' gestation or later and were included in the nonvaccinated group. During the study period, 60 patients who had evidence of prenatal vaccination (5.9%) experienced PTB vs 131 of those who did not (6.7%). Prenatal vaccination was not associated with an increased risk for PTB after adjusting for potential confounders (adjusted OR, 0.87; 95% CI, 0.62-1.20) and addressing immortal time bias (hazard ratio [HR], 0.93; 95% CI, 0.64-1.34). There were no significant differences in pregnancy and neonatal outcomes based on vaccination status in the logistic regression models, but an increased risk of HDP in the time-dependent model was seen (HR, 1.43; 95% CI, 1.16-1.77)., Conclusions and Relevance: In this cohort study of pregnant individuals who delivered at 32 weeks' gestation or later, the RSVpreF vaccine was not associated with an increased risk of PTB and perinatal outcomes. These data support the safety of prenatal RSVpreF vaccination, but further investigation into the risk of HDP is warranted.

Background: Patients with cirrhosis who have gastrointestinal bleeding have high short-term mortality, but the best modality for risk calculation remains in debate. Liver severity indices, such as Child-Turcotte-Pugh (CTP) and Model-for-End-Stage-Liver Disease (MELD) score, are well-studied in portal hypertensive bleeding, but there is a paucity of data confirming their accuracy in non-portal hypertensive bleeding and overall acute upper gastrointestinal bleeding (UGIB), unrelated to portal hypertension., Aims: This study aims to better understand the accuracy of current mortality risk calculators in predicting mortality for patients with any type of UGIB, which could allow for earlier risk stratification and targeted intervention prior to endoscopy to identify the bleeding source., Methods: In a large US single-center cohort, we investigated and recalibrated the model performance of CTP and MELD scores to predict six-week mortality risk for both sources of UGIB (portal hypertensive and non-portal hypertensive)., Results: Both CTP- and MELD-based models have excellent discrimination in predicting six-week mortality for all types of bleeding sources. However, only a CTP-based model demonstrates calibration for all bleeding, regardless of bleeding etiology. Median predicted 6-week mortality by CTP class A, B, and C estimates a risk of 1%, 7%, and 35% respectively., Conclusions: Our study corroborates findings in the literature that CTP- and MELD-based models have similar discriminative abilities for predicting 6-week mortality in hospitalized cirrhosis patients presenting with either portal hypertensive or non-portal hypertensive UGIB. CTP class is an effective clinical decision tool that can be used, even prior to endoscopy, to accurately risk stratify a patient with known cirrhosis presenting with any UGIB into low, moderate, and severe risk groupings., (© 2023 Indian National Association for Study of the Liver. Published by Elsevier B.V. All rights reserved.)

Background: Concerning data have revealed that viral hepatitis and hepatocellular carcinoma (HCC) disproportionally impact non-White patients and those from lower socioeconomic status. A recent study found that HCC clusters were more likely to be in high poverty areas in New York City., Aims: We aim to investigate the impacts of neighborhood characteristics on those with viral hepatitis and cirrhosis, particularly with advanced HCC diagnosis., Methods: Patients with cirrhosis and viral hepatitis admitted to a New York City health system between 2012 and 2019 were included. Those with prior liver transplants were excluded. Neighborhood characteristics were obtained from US Census. Our primary outcome was HCC and advanced HCC diagnosis., Results: This study included 348 patients; 209 without history of HCC, 20 with early HCC, 98 with advanced HCC, and 21 patients with HCC but no staging information. Patients with advanced HCC were more likely to be older, male, Asian, history of HBV, and increased mortality. They were more likely to live in areas with more foreign-born, limited English speakers, and less than high school education. After adjusting for age, sex, and payor type, Asian race and low income were independent risk factors for advanced HCC. Neighborhood factors were not associated with mortality or readmissions., Conclusion: We observed that in addition to age and sex, Asian race, lower household income, lower education, and lower English proficiency were associated with increased risk of advanced HCC. These disparities likely reflect suboptimal screening programs and linkage to care among vulnerable populations. Further efforts are crucial to validate and address these concerning disparities., (© 2023 Indian National Association for Study of the Liver. Published by Elsevier B.V. All rights reserved.)

Objective: The purpose of this study was to estimate the time to recovery of command-following and associations between hypoxemia with time to recovery of command-following., Methods: In this multicenter, retrospective, cohort study during the initial surge of the United States' pandemic (March-July 2020) we estimate the time from intubation to recovery of command-following, using Kaplan Meier cumulative-incidence curves and Cox proportional hazard models. Patients were included if they were admitted to 1 of 3 hospitals because of severe coronavirus disease 2019 (COVID-19), required endotracheal intubation for at least 7 days, and experienced impairment of consciousness (Glasgow Coma Scale motor score <6)., Results: Five hundred seventy-one patients of the 795 patients recovered command-following. The median time to recovery of command-following was 30 days (95% confidence interval [CI] = 27-32 days). Median time to recovery of command-following increased by 16 days for patients with at least one episode of an arterial partial pressure of oxygen (PaO 2 ) value ≤55 mmHg (p < 0.001), and 25% recovered ≥10 days after cessation of mechanical ventilation. The time to recovery of command-following  was associated with hypoxemia (PaO 2  ≤55 mmHg hazard ratio [HR] = 0.56, 95% CI = 0.46-0.68; PaO 2  ≤70 HR = 0.88, 95% CI = 0.85-0.91), and each additional day of hypoxemia decreased the likelihood of recovery, accounting for confounders including sedation. These findings were confirmed among patients without any imagining evidence of structural brain injury (n = 199), and in a non-overlapping second surge cohort (N = 427, October 2020 to April 2021)., Interpretation: Survivors of severe COVID-19 commonly recover consciousness weeks after cessation of mechanical ventilation. Long recovery periods are associated with more severe hypoxemia. This relationship is not explained by sedation or brain injury identified on clinical imaging and should inform decisions about life-sustaining therapies. ANN NEUROL 2022;91:740-755., (© 2022 The Authors. Annals of Neurology published by Wiley Periodicals LLC on behalf of American Neurological Association.)

Utilizing clinical texts in survival analysis is difficult because they are largely unstructured. Current automatic extraction models fail to capture textual information comprehensively since their labels are limited in scope. Furthermore, they typically require a large amount of data and high-quality expert annotations for training. In this work, we present a novel method of using BERT-based hidden layer representations of clinical texts as covariates for proportional hazards models to predict patient survival outcomes. We show that hidden layers yield notably more accurate predictions than predefined features, outperforming the previous baseline model by 5.7% on average across C-index and time-dependent AUC. We make our work publicly available at https://github.com/bionlplab/heart&#95;failure&#95;mortality.

Purpose: A new class of heart-rate sensing, closed-loop vagal nerve stimulator (VNS) devices for refractory epilepsy may improve seizure control by using pre-ictal autonomic changes as an indicator for stimulation. We compared our experience with closed- versus open-loop stimulator implantation at a single institution., Methods: We conducted a retrospective chart review of consecutive VNS implantations performed from 2004 to 2018. Bivariate and multivariable analyses were performed to compare changes in seizure frequency and clinical outcomes (Engel score) with closed- versus open-loop devices. Covariates included age, duration of seizure history, prior epilepsy surgery, depression, Lennox Gastaut Syndrome (LGS), tonic seizures, multiple seizure types, genetic etiology, and VNS settings. We examined early (9-month) and late (24-month) outcomes., Results: Seventy subjects received open-loop devices, and thirty-one received closed-loop devices. At a median of 8.5 months, there was a greater reduction of seizure frequency after use of closed-loop devices (median 75% [IQR 10-89%]) versus open-loop (50% [0-78%], p < 0.05), confirmed in multivariable analysis (odds ratio 2.72 [95% CI 1.02 - 7.4]). Similarly, Engel outcomes were better after closed-loop compared to open-loop confirmed in the multivariable analysis at the early timepoint (OR 0.26 [95% CI 0.09 - 0.69]). These differences did not persist at a median of 24.5 months., Conclusions: This retrospective single-center study suggests the use of closed-loop VNS devices is associated with greater seizure reduction and more favorable clinical outcomes than open-loop devices at 9-months though not at 24-months. Expansion of this study to other centers is warranted to increase the generalizability of our study., (Copyright © 2021 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.)

Objective: Electronic health record (EHR) data linked with address-based metrics using geographic information systems (GIS) are emerging data sources in population health studies. This study examined this approach through a case study on the associations between changes in ejection fraction (EF) and the built environment among heart failure (HF) patients., Materials and Methods: We identified 1287 HF patients with at least 2 left ventricular EF measurements that are minimally 1 year apart. EHR data were obtained at an academic medical center in New York for patients who visited between 2012 and 2017. Longitudinal clinical information was linked with address-based built environment metrics related to transportation, air quality, land use, and accessibility by GIS. The primary outcome is the increase in the severity of EF categories. Statistical analyses were performed using mixed-effects models, including a subgroup analysis of patients who initially had normal EF measurements., Results: Previously reported effects from the built environment among HF patients were identified. Increased daily nitrogen dioxide concentration was associated with the outcome while controlling for known HF risk factors including sex, comorbidities, and medication usage. In the subgroup analysis, the outcome was significantly associated with decreased distance to subway stops and increased distance to parks., Conclusions: Population health studies using EHR data may drive efficient hypothesis generation and enable novel information technology-based interventions. The availability of more precise outcome measurements and home locations, and frequent collection of individual-level social determinants of health may further drive the use of EHR data in population health studies., (© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

Background: Existing risk assessment tools for heart failure (HF) outcomes use structured databases with static, single-timepoint clinical data and have limited accuracy., Objective: The purpose of this study was to develop a comprehensive approach for accurate prediction of 30-day unplanned readmission and all-cause mortality (ACM) that integrates clinical and physiological data available in the electronic health record system., Methods: Three predictive models for 30-day unplanned readmissions or ACM were created using an extreme gradient boosting approach: (1) index admission model; (2) index discharge model; and (3) feature-aggregated model. Performance was assessed by the area under the curve (AUC) metric and compared with that of the HOSPITAL score, a widely used predictive model for hospital readmission., Results: A total of 3774 patients with a primary billing diagnosis of HF were included (614 experienced the primary outcome), with 796 variables used in the admission and discharge models, and 2032 in the feature-aggregated model. The index admission model had AUC = 0.723, the index discharge model had AUC = 0.754, and the feature-aggregated model had AUC = 0.756 for prediction of 30-day unplanned readmission or ACM. For comparison, the HOSPITAL score had AUC = 0.666 (admission model: P = .093; discharge model: P = .022; feature aggregated: P = .012)., Conclusion: These models predict risk of HF hospitalizations and ACM in patients admitted with HF and emphasize the importance of incorporating large numbers of variables in machine learning models to identify predictors for future investigation., (© 2020 The Authors.)

Myeloproliferative neoplasms (MPNs) are chronic hematologic malignancies that may progress over long disease courses. The original date of diagnosis is an important piece of information for patient care and research, but is not consistently documented. We describe an attempt to build a pipeline for extracting dates with natural language processing (NLP) tools and techniques and classifying them as relevant diagnoses or not. Inaccurate and incomplete date extraction and interpretation impacted the performance of the overall pipeline. Existing lightweight Python packages tended to have low specificity for identifying and interpreting partial and relative dates in clinical text. A rules-based regular expression (regex) approach achieved recall of 83.0% on dates manually annotated as diagnosis dates, and 77.4% on all annotated dates. With only 3.8% of annotated dates representing initial MPN diagnoses, additional methods of targeting candidate date instances may alleviate noise and class imbalance., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Background: Low-density lipoprotein cholesterol (LDL-C) is a target for cardiovascular prevention. Contemporary equations for LDL-C estimation have limited accuracy in certain scenarios (high triglycerides [TG], very low LDL-C)., Objectives: We derived a novel method for LDL-C estimation from the standard lipid profile using a machine learning (ML) approach utilizing random forests (the Weill Cornell model). We compared its correlation to direct LDL-C with the Friedewald and Martin-Hopkins equations for LDL-C estimation., Methods: The study cohort comprised a convenience sample of standard lipid profile measurements (with the directly measured components of total cholesterol [TC], high-density lipoprotein cholesterol [HDL-C], and TG) as well as chemical-based direct LDL-C performed on the same day at the New York-Presbyterian Hospital/Weill Cornell Medicine (NYP-WCM). Subsequently, an ML algorithm was used to construct a model for LDL-C estimation. Results are reported on the held-out test set, with correlation coefficients and absolute residuals used to assess model performance., Results: Between 2005 and 2019, there were 17,500 lipid profiles performed on 10,936 unique individuals (4,456 females; 40.8%) aged 1 to 103. Correlation coefficients between estimated and measured LDL-C values were 0.982 for the Weill Cornell model, compared to 0.950 for Friedewald and 0.962 for the Martin-Hopkins method. The Weill Cornell model was consistently better across subgroups stratified by LDL-C and TG values, including TG >500 and LDL-C <70., Conclusions: An ML model was found to have a better correlation with direct LDL-C than either the Friedewald formula or Martin-Hopkins equation, including in the setting of elevated TG and very low LDL-C., Competing Interests: Gurpreet Singh became affiliated with GlaxoSmithKline after working on this project. Benjamin C. Lee receives consulting fees from Cleerly Inc, but has not receive that consulting fee since 2019. Leslee J. Shaw reports having an equity interest in Cleerly Inc. There are no patents, products in development or marketed products associated with this research to declare This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Background: The 2019 novel coronavirus disease (COVID-19) has created unprecedented medical challenges. There remains a need for validated risk prediction models to assess short-term mortality risk among hospitalized patients with COVID-19. The objective of this study was to develop and validate a 7-day and 14-day mortality risk prediction model for patients hospitalized with COVID-19., Methods: We performed a multicenter retrospective cohort study with a separate multicenter cohort for external validation using two hospitals in New York, NY, and 9 hospitals in Massachusetts, respectively. A total of 664 patients in NY and 265 patients with COVID-19 in Massachusetts, hospitalized from March to April 2020., Results: We developed a risk model consisting of patient age, hypoxia severity, mean arterial pressure and presence of kidney dysfunction at hospital presentation. Multivariable regression model was based on risk factors selected from univariable and Chi-squared automatic interaction detection analyses. Validation was by receiver operating characteristic curve (discrimination) and Hosmer-Lemeshow goodness of fit (GOF) test (calibration). In internal cross-validation, prediction of 7-day mortality had an AUC of 0.86 (95%CI 0.74-0.98; GOF p = 0.744); while 14-day had an AUC of 0.83 (95%CI 0.69-0.97; GOF p = 0.588). External validation was achieved using 265 patients from an outside cohort and confirmed 7- and 14-day mortality prediction performance with an AUC of 0.85 (95%CI 0.78-0.92; GOF p = 0.340) and 0.83 (95%CI 0.76-0.89; GOF p = 0.471) respectively, along with excellent calibration. Retrospective data collection, short follow-up time, and development in COVID-19 epicenter may limit model generalizability., Conclusions: The COVID-AID risk tool is a well-calibrated model that demonstrates accuracy in the prediction of both 7-day and 14-day mortality risk among patients hospitalized with COVID-19. This prediction score could assist with resource utilization, patient and caregiver education, and provide a risk stratification instrument for future research trials., Competing Interests: The authors have declared that no competing interests exist.

Background: Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming., Purpose: We utilized a machine learning (ML)-based natural language processing (NLP) approach to extract clinical terms from unstructured radiology reports. Additionally, we investigate the prognostic value of the extracted data in predicting all-cause mortality (ACM) in HF patients., Materials and Methods: This observational cohort study utilized 122,025 thoracoabdominal computed tomography (CT) reports from 11,808 HF patients obtained between 2008 and 2018. 1,560 CT reports were manually annotated for the presence or absence of 14 radiographic findings, in addition to age and gender. Thereafter, a Convolutional Neural Network (CNN) was trained, validated and tested to determine the presence or absence of these features. Further, the ability of CNN to predict ACM was evaluated using Cox regression analysis on the extracted features., Results: 11,808 CT reports were analyzed from 11,808 patients (mean age 72.8 ± 14.8 years; 52.7% (6,217/11,808) male) from whom 3,107 died during the 10.6-year follow-up. The CNN demonstrated excellent accuracy for retrieval of the 14 radiographic findings with area-under-the-curve (AUC) ranging between 0.83-1.00 (F1 score 0.84-0.97). Cox model showed the time-dependent AUC for predicting ACM was 0.747 (95% confidence interval [CI] of 0.704-0.790) at 30 days., Conclusion: An ML-based NLP approach to unstructured CT reports demonstrates excellent accuracy for the extraction of predetermined radiographic findings, and provides prognostic value in HF patients., Competing Interests: The authors have declared that no competing interests exist. Gurpreet Singh is currently employed at GlaxoSmithKline but was not a part of GlaxoSmithKline during the conduct of this study. Gabriel Maliakal and James K. Min are currently employed at Cleerly Inc. but were not a part of Cleerly Inc. during the conduct of this study. Mohit Pandey is currently employed at Ipsos but was not a part of Ipsos during the conduct of this study. These commercial affiliations do not alter our adherence to PLOS ONE policies on sharing data and materials.

Objectives: Early hospital readmissions or deaths are key healthcare quality measures in pay-for-performance programs. Predictive models could identify patients at higher risk of readmission or death and target interventions. However, existing models usually do not incorporate social determinants of health (SDH) information, although this information is of great importance to address health disparities related to social risk factors. The objective of this study is to examine the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission., Methods: We extracted electronic health record data for 19,941 hospital admissions between January 2015 and November 2017 at an academic medical center in New York City. We applied the Simplified HOSPITAL score model to predict potentially avoidable 30-day readmission or death and examined if incorporating individual- and community-level SDH could improve the prediction using cross-validation. We calculated the C-statistic for discrimination, Brier score for accuracy, and Hosmer-Lemeshow test for calibration for each model using logistic regression. Analysis was conducted for all patients and three subgroups that may be disproportionately affected by social risk factors, namely Medicaid patients, patients who are 65 or older, and obese patients., Results: The Simplified HOSPITAL score model achieved similar performance in our sample compared to previous studies. Adding SDH did not improve the prediction among all patients. However, adding individual- and community-level SDH at the US census tract level significantly improved the prediction for all three subgroups. Specifically, C-statistics improved from 0.70 to 0.73 for Medicaid patients, from 0.66 to 0.68 for patients 65 or older, and from 0.70 to 0.73 for obese patients., Conclusions: Patients from certain subgroups may be more likely to be affected by social risk factors. Incorporating SDH into predictive models may be helpful to identify these patients and reduce health disparities associated with vulnerable social conditions., Competing Interests: The authors have declared that no competing interests exist.

Determining response status in patients with myeloproliferative neoplasms is a complex problem requiring the integration of both structured and unstructured data elements from disparate information systems. By applying multiple techniques, a collaborative team of informatics professionals and research personnel were able to determine which elements were amenable to automated extraction and which required expert adjudication. With this knowledge in mind, we were able to build a system that joins together programmatically-derived and manually-abstracted data elements to facilitate response assessment - an important end point in clinical and translational research in this disease area.