Objective Social determinants of health (SDOH) impact health outcomes and are documented in the electronic health record (EHR) through structured data and unstructured clinical notes. However, clinical notes often contain more comprehensive SDOH information, detailing aspects such as status, severity, and temporality. This work has two primary objectives: (1) develop a natural language processing information extraction model to capture detailed SDOH information and (2) evaluate the information gain achieved by applying the SDOH extractor to clinical narratives and combining the extracted representations with existing structured data. Materials and Methods We developed a novel SDOH extractor using a deep learning entity and relation extraction architecture to characterize SDOH across various dimensions. In an EHR case study, we applied the SDOH extractor to a large clinical data set with 225 089 patients and 430 406 notes with social history sections and compared the extracted SDOH information with existing structured data. Results The SDOH extractor achieved 0.86 F1 on a withheld test set. In the EHR case study, we found extracted SDOH information complements existing structured data with 32% of homeless patients, 19% of current tobacco users, and 10% of drug users only having these health risk factors documented in the clinical narrative. Conclusions Utilizing EHR data to identify SDOH health risk factors and social needs may improve patient care and outcomes. Semantic representations of text-encoded SDOH information can augment existing structured data, and this more comprehensive SDOH representation can assist health systems in identifying and addressing these social needs.
Despite growing literature, there is still limited understanding of factors that can predict outcomes in coronavirus disease 2019 (COVID-19) patients who require intensive care. ObjectiveTo evaluate the characteristics of COVID-19 patients admitted to the intensive care unit (ICU) and identify their associations with outcomes.
Introduction: Thrombosis and bleeding are recognized complications of the novel coronavirus infection (COVID-19), with a higher incidence described particularly in the critically ill. Methods: A retrospective review of COVID-19 patients admitted to our intensive care units (ICU) between 1 January 2020 and 31 December 2020 was performed. Primary outcomes included clinically significant thrombotic and bleeding events (according to the ISTH definition) in the ICU. Secondary outcomes included mortality vis-a-vis the type of anticoagulation. Results: The cohort included 144 consecutive COVID-19 patients with a median age of 64 years (IQR 54.5–75). The majority were male (85 (59.0%)) and Caucasian (90 (62.5%)) with a median BMI of 30.5 kg/m2 (IQR 25.7–36.1). The median APACHE score at admission to the ICU was 12.5 (IQR 9.5–22). The coagulation parameters at admission were a d-dimer level of 109.2 mg/mL, a platelet count of 217.5 k/mcl, and an INR of 1.4. The anticoagulation strategy at admission included prophylactic anticoagulation for 97 (67.4%) patients and therapeutic anticoagulation for 35 (24.3%) patients, while 12 (8.3%) patients received no anticoagulation. A total of 29 patients (20.1%) suffered from thrombotic or major bleeding complications. These included 17 thrombus events (11.8%)—8 while on prophylactic anticoagulation (7 regular dose and 1 intermediate dose) and 9 while on therapeutic anticoagulation (p-value = 0.02)—and 19 major bleeding events (13.2%) (4 on no anticoagulation, 7 on prophylactic (6 regular dose and 1 intermediate dose), and 8 on therapeutic anticoagulation (p-value = 0.02)). A higher thrombosis risk among patients who received remdesivir (18.8% vs. 5.3% (p-value = 0.01)) and convalescent serum (17.3% vs. 5.8% (p-value = 0.03%)) was noted, but no association with baseline characteristics (age, sex, race, comorbidity), coagulation parameters, or treatments (steroids, mechanical ventilation) could be identified. There were 10 pulmonary embolism cases (6.9%). A total of 99 (68.8%) patients were intubated, and 66 patients (45.8%) died. Mortality was higher, but not statistically significant, in patients with thrombotic or bleeding complications—58.6% vs. 42.6% (p-value = 0.12)—and higher in the bleeding (21.2%) vs. thrombus group (12.1%), p-value = 0.06. It did not significantly differ according to the type of anticoagulation used or the coagulation parameters. Conclusions: This study describes a high incidence of thrombotic and bleeding complications among critically ill COVID-19 patients. The findings of thrombotic events in patients on anticoagulation and major bleeding events in patients on no or prophylactic anticoagulation pose a challenging clinical dilemma in the issue of anticoagulation for COVID-19 patients. The questions raised by this study and previous literature on this subject demonstrate that the role of anticoagulation in COVID-19 patients is worthy of further investigation.
Identifying patients’ social needs is a first critical step to address social determinants of health (SDoH)—the conditions in which people live, learn, work, and play that affect health. Addressing SDoH can improve health outcomes, population health, and health equity. Emerging SDoH reporting requirements call for health systems to implement efficient ways to identify and act on patients’ social needs. Automatic extraction of SDoH from clinical notes within the electronic health record through natural language processing offers a promising approach. However, such automated SDoH systems could have unintended consequences for patients, related to stigma, privacy, confidentiality, and mistrust. Using Floridi et al’s “AI4People” framework, we describe ethical considerations for system design and implementation that call attention to patient autonomy, beneficence, nonmaleficence, justice, and explicability. Based on our engagement of clinical and community champions in health equity work at University of Washington Medicine, we offer recommendations for integrating patient voices and needs into automated SDoH systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.