RESUMO
Electronic health records offer great promise for early disease detection, treatment evaluation, information discovery, and other important facets of precision health. Clinical notes, in particular, may contain nuanced information about a patient's condition, treatment plans, and history that structured data may not capture. As a result, and with advancements in natural language processing, clinical notes have been increasingly used in supervised prediction models. To predict long-term outcomes such as chronic disease and mortality, it is often advantageous to leverage data occurring at multiple time points in a patient's history. However, these data are often collected at irregular time intervals and varying frequencies, thus posing an analytical challenge. Here, we propose the use of large language models (LLMs) for robust temporal harmonization of clinical notes across multiple visits. We compare multiple state-of-the-art LLMs in their ability to generate useful information during time gaps, and evaluate performance in supervised deep learning models for clinical prediction.
RESUMO
Electronic health records (EHRs) contain a wealth of information that can be used to further precision health. One particular data element in EHRs that is not only under-utilized but oftentimes unaccounted for is missing data. However, missingness can provide valuable information about comorbidities and best practices for monitoring patients, which could save lives and reduce burden on the healthcare system. We characterize patterns of missing data in laboratory measurements collected at the University of Pennsylvania Hospital System from long-term COVID-19 patients and focus on the changes in these patterns between 2020 and 2021. We investigate how these patterns are associated with comorbidities such as acute respiratory distress syndrome (ARDS), and 90-day mortality in ARDS patients. This work displays how knowledge and experience can change the way clinicians and hospitals manage a novel disease. It can also provide insight into best practices when it comes to patient monitoring to improve outcomes.
RESUMO
Electronic health records (EHRs) contain a wealth of information that can be used to further precision health. One particular data element in EHRs that is not only under-utilized but oftentimes unaccounted for is missing data. However, missingness can provide valuable information about comorbidities and best practices for monitoring patients, which could save lives and reduce burden on the healthcare system. We characterize patterns of missing data in laboratory measurements collected at the University of Pennsylvania Hospital System from long-term COVID-19 patients and focus on the changes in these patterns between 2020 and 2021. We investigate how these patterns are associated with comorbidities such as acute respiratory distress syndrome (ARDS), and 90-day mortality in ARDS patients. This work displays how knowledge and experience can change the way clinicians and hospitals manage a novel disease. It can also provide insight into best practices when it comes to patient monitoring to improve outcomes.
Assuntos
COVID-19 , Síndrome do Desconforto Respiratório , Humanos , COVID-19/epidemiologia , SARS-CoV-2 , PandemiasRESUMO
PURPOSE: Head and neck surgeons are among the highest risk for COVID-19 exposure, which also brings great risk to their mental wellbeing. In this study, we aim to evaluate mental health symptoms among head and neck surgeons in Brazil surrounding the time it was declared the epicenter of the virus. MATERIALS AND METHODS: A cross-sectional, survey-based study evaluating burnout, anxiety, distress, and depression among head and neck surgeons in Brazil, assessed through the single-item Mini-Z burnout assessment, 7-item Generalized Anxiety Disorder scale, 22-item Impact of Event Scale-Revised, and 2-item Patient Health Questionnaire, respectively. RESULTS: 163 physicians completed the survey (74.2% males). Anxiety, distress, burnout, and depression symptoms were reported in 74 (45.5%), 43 (26.3%), 24 (14.7%), and 26 (16.0%) physicians, respectively. On multivariable analysis, female physicians were more likely to report a positive screening for burnout compared to males (OR 2.88, CI [1.07-7.74]). Physicians 45 years or older were less likely to experience anxiety symptoms than those younger than 45 years (OR 0.40, CI [0.20-0.81]). Physicians with no self-reported prior psychiatric conditions were less likely to have symptoms of distress compared to those with such history (OR 0.11, CI [0.33-0.38]). CONCLUSION: Head and neck surgeons in Brazil reported symptoms of burnout, anxiety, distress and depression during our study period within the COVID-19 pandemic. Institutions should monitor these symptoms throughout the pandemic. Further study is required to assess the long-term implications for physician wellness.