Background: Changes in autonomic nervous system function, characterized by heart rate variability (HRV), have been associated with infection and observed prior to its clinical identification. Objective: We performed an evaluation of HRV collected by a wearable device to identify and predict COVID-19 and its related symptoms. Methods: Health care workers in the Mount Sinai Health System were prospectively followed in an ongoing observational study using the custom Warrior Watch Study app, which was downloaded to their smartphones. Participants wore an Apple Watch for the duration of the study, measuring HRV throughout the follow-up period. Surveys assessing infection and symptom-related questions were obtained daily. Results: Using a mixed-effect cosinor model, the mean amplitude of the circadian pattern of the standard deviation of the interbeat interval of normal sinus beats (SDNN), an HRV metric, differed between subjects with and without COVID-19 (P=.006). The mean amplitude of this circadian pattern differed between individuals during the 7 days before and the 7 days after a COVID-19 diagnosis compared to this metric during uninfected time periods (P=.01). Significant changes in the mean and amplitude of the circadian pattern of the SDNN was observed between the first day of reporting a COVID-19–related symptom compared to all other symptom-free days (P=.01). Conclusions: Longitudinally collected HRV metrics from a commonly worn commercial wearable device (Apple Watch) can predict the diagnosis of COVID-19 and identify COVID-19–related symptoms. Prior to the diagnosis of COVID-19 by nasal swab polymerase chain reaction testing, significant changes in HRV were observed, demonstrating the predictive ability of this metric to identify COVID-19 infection.

Background: Acute and chronic low back pain (LBP) are different conditions with different treatments. However, they are coded in electronic health records with the same International Classification of Diseases, 10th revision (ICD-10) code (M54.5) and can be differentiated only by retrospective chart reviews. This prevents an efficient definition of data-driven guidelines for billing and therapy recommendations, such as return-to-work options.Objective: The objective of this study was to evaluate the feasibility of automatically distinguishing acute LBP episodes by analyzing free-text clinical notes.Methods: We used a dataset of 17,409 clinical notes from different primary care practices; of these, 891 documents were manually annotated as acute LBP and 2973 were generally associated with LBP via the recorded ICD-10 code. We compared different supervised and unsupervised strategies for automated identification: keyword search, topic modeling, logistic regression with bag of n-grams and manual features, and deep learning (a convolutional neural network-based architecture [ConvNet]). We trained the supervised models using either manual annotations or ICD-10 codes as positive labels.Results: ConvNet trained using manual annotations obtained the best results with an area under the receiver operating characteristic curve of 0.98 and an F score of 0.70. ConvNet’s results were also robust to reduction of the number of manually annotated documents. In the absence of manual annotations, topic models performed better than methods trained using ICD-10 codes, which were unsatisfactory for identifying LBP acuity.Conclusions: This study uses clinical notes to delineate a potential path toward systematic learning of therapeutic strategies, billing guidelines, and management options for acute LBP at the point of care.

Persistent symptoms are common after acute COVID-19, often referred to as long COVID. Long COVID may affect the ability to perform activities of daily living, including work. Long COVID occurs more frequently in those with severe acute COVID-19. This guidance statement reviews the pathophysiology of severe acute COVID-19 and long COVID and provides pragmatic approaches to long COVID symptoms, syndromes, and conditions in the occupational setting. Disability laws and workers’ compensation are also addressed. Export

Objective: To examine associations of workers’ compensation, chronic conditions, age, sex, and race/ethnicity with primary prescription of long-acting opioids (LAO) among working-age patients in ambulatory care. Methods: Using the National Ambulatory Medical Care Survey (2010 to 2016), we conducted descriptive, bivariate, and multivariate logistic regression analyses of patients aged 18 to 64 with an LAO as their primary medication. Results: Those prescribed an LAO were more likely to be men (adjusted odds ratio [aOR] = 1.48, 95% CI 1.13, 1.91), have workers’ compensation (aOR = 2.00, 95% CI 1.12, 3.57), or have diagnoses of lower back pain (aOR = 4.70, 95% CI 3.51, 6.29), arthritis (aOR = 1.53, 95% CI 1.11, 2.09), or depression (aOR = 1.69; 95% CI 1.24, 2.31). Hispanic ethnicity/race had a lower likelihood of LAO use compared with non-Hispanic White (aOR = 0.58; 95% CI 0.37, 0.90). Conclusions: Male sex, workers’ compensation, and diagnoses of lower back pain, arthritis, or depression were independently associated with increased LAO prescription odds.

Context: Low back pain (LBP) is a common cause of disability in adults and primary care physicians (PCPs) are commonly the first medical practitioners to assess these patients. Despite this, PCPs often feel unprepared to make return to work (RTW) recommendations. Aims: The purpose of our project was to develop RTW guidelines for patients with LBP in the form of an accessible and adaptable electronic medical records (EMR) integrated tool. Settings and Design: All licensed physicians and physician extenders who see patients over the age of 18 years, presenting with acute LBP who are currently employed were eligible for participation. PCPs were randomized with and without the RTW guidelines and charts were reviewed to assess if PCPs made RTW recommendations. Subjects and Methods: RTW guidelines were developed using the Oswestry LBP Disability Questionnaire and the Official Disability Guidelines and integrated into the EMR. Statistical Analysis Used: A Chi-square analysis was used to compare physicians in the interventional and control groups. Results: Forty-four PCPs were randomized into the intervention group and 37 into the control group. In the intervention group, 301 patient encounters met the inclusion criteria for acute LBP. Of these, RTW recommendations were used in 7.3% encounters. Comparatively, there were 256 cases of LBP in the control group and RTW recommendations were offered in 1.6% of encounters (P < 0.001). Conclusion: This study showed that PCPs with access to the RTW guidelines in an EMR-integrated tool were significantly more likely to make such recommendations.

Background: Acute and chronic low back pain (LBP) are different conditions with different treatments. However, they are coded in electronic health records with the same ICD-10 code (M54.5) and can be differentiated only by retrospective chart reviews. This prevents efficient definition of data-driven guidelines for billing and therapy recommendations, such as return-to-work options. Objective: To solve this issue, we evaluate the feasibility of automatically distinguishing acute LBP episodes by analyzing free text clinical notes. Methods: We used a dataset of 17,409 clinical notes from different primary care practices; of these, 891 documents were manually annotated as “acute LBP” and 2,973 were generally associated with LBP via the recorded ICD-10 code. We compared different supervised and unsupervised strategies for automated identification: keyword search; topic modeling; logistic regression with bag-of-n-grams and manual features; and deep learning (ConvNet). We trained the supervised models using either manual annotations or ICD-10 codes as positive labels. Results: ConvNet trained using manual annotations obtained the best results with an AUC-ROC of 0.97 and F-score of 0.69. ConvNet’s results were also robust to reduction of the number of manually annotated documents. In the absence of manual annotations, topic models performed better than methods trained using ICD-10 codes, which were unsatisfactory for identifying LBP acuity. Conclusions: This study uses clinical notes to delineate a potential path toward systematic learning of therapeutic strategies, billing guidelines, and management options for acute LBP at the point of care.