Search

Clinical notes present a wealth of information for applications in the clinical domain, but heterogeneity across clinical institutions and settings presents challenges for their processing. The clinical natural language processing field has made strides in overcoming domain heterogeneity, while pretrained deep learning models present opportunities to transfer knowledge from one task to another. Pretrained models have performed well when transferred to new tasks; however, it is not well understood if these models generalize across differences in institutions and settings within the clinical domain. We explore if institution or setting specific pretraining is necessary for pretrained models to perform well when transferred to new tasks. We find no significant performance difference between models pretrained across institutions and settings, indicating that clinically pretrained models transfer well across such boundaries. Given a clinically pretrained model, clinical natural language processing researchers may forgo the time-consuming pretraining step without a significant performance drop.

IntroductionThe opioid epidemic is a modern public health emergency. Common interventions to alleviate the opioid epidemic aim to discourage excessive prescription of opioids. However, these methods often take place over large municipal areas (state-level) and may fail to address the diversity that exists within each opioid case (individual-level). An intervention to combat the opioid epidemic that takes place at the individual-level would be preferable.MethodsThis research leverages computational tools and methods to characterize the opioid epidemic at the individual-level using the electronic health record data from a large, academic medical center. To better understand the characteristics of patients with opioid use disorder (OUD) we leveraged a self-controlled analysis to compare the healthcare encounters before and after an individual’s first overdose event recorded within the data. We further contrast these patients with matched, non-OUD controls to demonstrate the unique qualities of the OUD cohort.ResultsOur research confirms that the rate of opioid overdoses in our hospital significantly increased between 2006 and 2015 (P ConclusionsInformatics-based methodologies, like those presented here, may play a role in better understanding those individuals who suffer from opioid dependency and overdose, and may lead to future research and interventions that could successfully prevent morbidity and mortality associated with this epidemic.

Objective We sought to assess the quality of race and ethnicity information in observational health databases, including electronic health records (EHRs), and to propose patient self-recording as an improvement strategy. Materials and Methods We assessed completeness of race and ethnicity information in large observational health databases in the United States (Healthcare Cost and Utilization Project and Optum Labs), and at a single healthcare system in New York City serving a racially and ethnically diverse population. We compared race and ethnicity data collected via administrative processes with data recorded directly by respondents via paper surveys (National Health and Nutrition Examination Survey and Hospital Consumer Assessment of Healthcare Providers and Systems). Respondent-recorded data were considered the gold standard for the collection of race and ethnicity information. Results Among the 160 million patients from the Healthcare Cost and Utilization Project and Optum Labs datasets, race or ethnicity was unknown for 25%. Among the 2.4 million patients in the single New York City healthcare system’s EHR, race or ethnicity was unknown for 57%. However, when patients directly recorded their race and ethnicity, 86% provided clinically meaningful information, and 66% of patients reported information that was discrepant with the EHR. Discussion Race and ethnicity data are critical to support precision medicine initiatives and to determine healthcare disparities; however, the quality of this information in observational databases is concerning. Patient self-recording through the use of patient-facing tools can substantially increase the quality of the information while engaging patients in their health. Conclusions Patient self-recording may improve the completeness of race and ethnicity information.

Survival analysis models the distribution of time until an event of interest, such as discharge from the hospital or admission to the ICU. When a model’s predicted number of events within any time interval is similar to the observed number, it is called well-calibrated. A survival model’s calibration can be measured using, for instance, distributional calibration (D-CALIBRATION) [Haider et al., 2020] which computes the squared difference between the observed and predicted number of events within different time intervals. Classically, calibration is addressed in post-training analysis. We develop explicit calibration (X-CAL), which turns D-CALIBRATION into a differentiable objective that can be used in survival modeling alongside maximum likelihood estimation and other objectives. X-CAL allows practitioners to directly optimize calibration and strike a desired balance between predictive power and calibration. In our experiments, we fit a variety of shallow and deep models on simulated data, a survival dataset based on MNIST, on length-of-stay prediction using MIMIC-III data, and on brain cancer data from The Cancer Genome Atlas. We show that the models we study can be miscalibrated. We give experimental evidence on these datasets that X-CAL improves D-CALIBRATION without a large decrease in concordance or likelihood.

Causal inference relies on two fundamental assumptions: ignorability and positivity. We study causal inference when the true confounder value can be expressed as a function of the observed data; we call this setting estimation with functional confounders (EFC). In this setting ignorability is satisfied, however positivity is violated, and causal inference is impossible in general. We consider two scenarios where causal effects are estimable. First, we discuss interventions on a part of the treatment called functional interventions and a sufficient condition for effect estimation of these interventions called functional positivity. Second, we develop conditions for nonparametric effect estimation based on the gradient fields of the functional confounder and the true outcome function. To estimate effects under these conditions, we develop Level-set Orthogonal Descent Estimation (LODE). Further, we prove error bounds on LODE’s effect estimates, evaluate our methods on simulated and real data, and empirically demonstrate the value of EFC.

Background: The extent to which Point-of-care of ultrasound (POCUS) is used in different European helicopter EMS (HEMS) is unknown. We aimed to study the availability, perception, and future aspects of POCUS in the European HEMS. Methods: A survey about the use of POCUS in HEMS was conducted by a multinational steering expert committee and was carried out from November 30, 2020 to December 30, 2020 via an online web portal. Invitations for participation were sent via email to the medical directors of the European HEMS organizations including two reminders. Results: During the study period, 69 participants from 25 countries and 41 different HEMS providers took part in the survey. 96% (n=66) completed the survey. POCUS was available in 75% of the responding HEMS organizations when needed (56% always, and 19% occasionally). 17% were planning to establish POCUS in the near future. Responders who provided POCUS used it in approximately 15% of the patients. Participants thought that POCUS is important in both trauma and non-trauma-patients (73%, n=46). The extended focused assessment sonography for trauma (eFAST) protocol (77%) was the most common used protocol. A POCUS credentialing process including documented examinations was requested in less than one third of the HEMS organizations.Conclusions: The majority of the HEMS organizations in Europe are able to provide different POCUS protocols in their services. The most used POCUS protocols were eFAST, FATE and RUSH. Despite the enthusiasm for POCUS, comprehensive training and clear credentialing processes are lacking in about two thirds of the European HEMS organizations.

Objective We introduce Medical evidence Dependency (MD)–informed attention, a novel neuro-symbolic model for understanding free-text clinical trial publications with generalizability and interpretability. Materials and Methods We trained one head in the multi-head self-attention model to attend to the Medical evidence Ddependency (MD) and to pass linguistic and domain knowledge on to later layers (MD informed). This MD-informed attention model was integrated into BioBERT and tested on 2 public machine reading comprehension benchmarks for clinical trial publications: Evidence Inference 2.0 and PubMedQA. We also curated a small set of recently published articles reporting randomized controlled trials on COVID-19 (coronavirus disease 2019) following the Evidence Inference 2.0 guidelines to evaluate the model’s robustness to unseen data. Results The integration of MD-informed attention head improves BioBERT substantially in both benchmark tasks—as large as an increase of +30% in the F1 score—and achieves the new state-of-the-art performance on the Evidence Inference 2.0. It achieves 84% and 82% in overall accuracy and F1 score, respectively, on the unseen COVID-19 data. Conclusions MD-informed attention empowers neural reading comprehension models with interpretability and generalizability via reusable domain knowledge. Its compositionality can benefit any transformer-based architecture for machine reading comprehension of free-text medical evidence.

Introduction A large proportion of patients with COVID-19 develop acute kidney injury (AKI). While the most severe of these cases require renal replacement therapy (RRT), little is known about their clinical course. Methods We describe the clinical characteristics of COVID-19 patients in the ICU with AKI requiring RRT at an academic medical center in New York City and followed patients for outcomes of death and renal recovery using time-to-event analyses. Results Our cohort of 115 patients represented 23% of all ICU admissions at our center, with a peak prevalence of 29%. Patients were followed for a median of 29 days (2542 total patient-RRT-days; median 54 days for survivors). Mechanical ventilation and vasopressor use were common (99% and 84%, respectively), and the median Sequential Organ Function Assessment (SOFA) score was 14. By the end of follow-up 51% died, 41% recovered kidney function (84% of survivors), and 8% still needed RRT (survival probability at 60 days: 0.46 [95% CI: 0.36–0.56])). In an adjusted Cox model, coronary artery disease and chronic obstructive pulmonary disease were associated with increased mortality (HRs: 3.99 [95% CI 1.46–10.90] and 3.10 [95% CI 1.25–7.66]) as were angiotensin-converting-enzyme inhibitors (HR 2.33 [95% CI 1.21–4.47]) and a SOFA score >15 (HR 3.46 [95% CI 1.65–7.25). Conclusions and relevance Our analysis demonstrates the high prevalence of AKI requiring RRT among critically ill patients with COVID-19 and is associated with a high mortality, however, the rate of renal recovery is high among survivors and should inform shared-decision making.

Background Cardiovascular involvement in coronavirus disease 2019 (COVID‐19) is common and leads to worsened mortality. Diagnostic cardiovascular studies may be helpful for resource appropriation and identifying patients at increased risk for death. Methods and Results We analyzed 887 patients (aged 64±17 years) admitted with COVID‐19 from March 1 to April 3, 2020 in New York City with 12 lead electrocardiography within 2 days of diagnosis. Demographics, comorbidities, and laboratory testing, including high sensitivity cardiac troponin T (hs‐cTnT), were abstracted. At 30 days follow‐up, 556 patients (63%) were living without requiring mechanical ventilation, 123 (14%) were living and required mechanical ventilation, and 203 (23%) had expired. Electrocardiography findings included atrial fibrillation or atrial flutter (AF/AFL) in 46 (5%) and ST‐T wave changes in 306 (38%). 27 (59%) patients with AF/AFL expired as compared to 181 (21%) of 841 with other non‐life‐threatening rhythms ( P Conclusions Myocardial injury with hs‐cTnT ≥20 ng/L, in addition to cardiac conduction perturbations, especially AF/AFL, upon hospital admission for COVID‐19 infection is associated with markedly increased risk for mortality than either diagnostic abnormality alone.