Identifying who has long COVID in the USA: a machine learning approach using N3C data.

BACKGROUND: Post-acute sequelae of SARS-CoV-2 infection, known as long COVID, have severely affected recovery from the COVID-19 pandemic for patients and society alike. Long COVID is characterised by evolving, heterogeneous symptoms, making it challenging to derive an unambiguous definition. Studies of electronic health records are a crucial element of the US National Institutes of Health's RECOVER Initiative, which is addressing the urgent need to understand long COVID, identify treatments, and accurately identify who has it-the latter is the aim of this study. METHODS: Using the National COVID Cohort Collaborative's (N3C) electronic health record repository, we developed XGBoost machine learning models to identify potential patients with long COVID. We defined our base population (n=1 793 604) as any non-deceased adult patient (age ≥18 years) with either an International Classification of Diseases-10-Clinical Modification COVID-19 diagnosis code (U07.1) from an inpatient or emergency visit, or a positive SARS-CoV-2 PCR or antigen test, and for whom at least 90 days have passed since COVID-19 index date. We examined demographics, health-care utilisation, diagnoses, and medications for 97 995 adults with COVID-19. We used data on these features and 597 patients from a long COVID clinic to train three machine learning models to identify potential long COVID among all patients with COVID-19, patients hospitalised with COVID-19, and patients who had COVID-19 but were not hospitalised. Feature importance was determined via Shapley values. We further validated the models on data from a fourth site. FINDINGS: Our models identified, with high accuracy, patients who potentially have long COVID, achieving areas under the receiver operator characteristic curve of 0·92 (all patients), 0·90 (hospitalised), and 0·85 (non-hospitalised). Important features, as defined by Shapley values, include rate of health-care utilisation, patient age, dyspnoea, and other diagnosis and medication information available within the electronic health record. INTERPRETATION: Patients identified by our models as potentially having long COVID can be interpreted as patients warranting care at a specialty clinic for long COVID, which is an essential proxy for long COVID diagnosis as its definition continues to evolve. We also achieve the urgent goal of identifying potential long COVID in patients for clinical trials. As more data sources are identified, our models can be retrained and tuned based on the needs of individual studies. FUNDING: US National Institutes of Health and National Center for Advancing Translational Sciences through the RECOVER Initiative.

Association between Sleep Quality and Mental Health among Patients at a Post-COVID-19 Recovery Clinic.

A growing body of research documents the persistence of physical and neuropsychiatric symptoms following the resolution of acute COVID-19 infection. To the best of our knowledge, no published study has examined the interaction between insomnia and mental health. Accordingly, we proposed to examine new diagnoses of insomnia, and referrals to pulmonary and sleep medicine clinics for treatment of sleep disorders, in patients presenting to one post-acute COVID-19 recovery clinic. Additionally, we aimed to examine the relationship between poor sleep quality, depression, anxiety, and post-traumatic stress. Patients presented to the clinic on average 2 months following COVID-19 infection; 51.9% (n = 41) were hospitalized, 11.4% (n = 9) were in the intensive care unit, 2.5% (n = 2) were on a mechanical ventilator, and 38.0% (n = 30) were discharged on oxygen. The most commonly reported symptom was fatigue (88%, n = 70), with worse sleep following a COVID-19 infection reported in 50.6% (n = 40). The mean PSQI score was 9.7 (82.3%, n = 65 with poor sleep quality). The mean GAD-7 score was 8.3 (22.8%, n = 14 with severe depression). The mean PHQ-9 was 10.1 (17.8%, n = 18 with severe anxiety). The mean IES-6 was 2.1 (54.4%, n = 43 with post-traumatic stress). Poor sleep quality was significantly associated with increased severity of depression, anxiety, and post-traumatic stress. Future work should follow patients longitudinally to examine if sleep, fatigue, and mental health symptoms improve over time.

Impact of COVID-19 Infection and Persistent Lingering Symptoms on Patient Reported Indicators of Nutritional Risk and Malnutrition.

Persistent malnutrition after COVID-19 infection may worsen outcomes, including delayed recovery and increased risk of rehospitalization. This study aimed to determine dietary intakes and nutrient distribution patterns after acute COVID-19 illness. Findings were also compared to national standards for intake of energy, protein, fruit, and vegetables, as well as protein intake distribution recommendations. Participants (≥18 years old, n = 92) were enrolled after baseline visit at the Post-COVID Recovery Clinic. The broad screening battery included nutritional assessment and 24-h dietary recall. Participants were, on average, 53 years old, 63% female, 69% non-Hispanic White, and 59% obese/morbidly obese. Participants at risk for malnutrition (48%) experienced significantly greater symptoms, such as gastric intestinal issues, loss of smell, loss of taste, or shortness of breath; in addition, they consumed significantly fewer calories. Most participants did not meet recommendations for fruit or vegetables. Less than 39% met the 1.2 g/kg/day proposed optimal protein intake for recovery from illness. Protein distribution throughout the day was skewed; only 3% met the recommendation at all meals, while over 30% never met the threshold at any meal. Our findings highlight the need for nutritional education and support for patients to account for lingering symptoms and optimize recovery after COVID-19 infection.

Characterizing Long COVID: Deep Phenotype of a Complex Condition.

BACKGROUND: Numerous publications describe the clinical manifestations of post-acute sequelae of SARS-CoV-2 (PASC or "long COVID"), but they are difficult to integrate because of heterogeneous methods and the lack of a standard for denoting the many phenotypic manifestations. Patient-led studies are of particular importance for understanding the natural history of COVID-19, but integration is hampered because they often use different terms to describe the same symptom or condition. This significant disparity in patient versus clinical characterization motivated the proposed ontological approach to specifying manifestations, which will improve capture and integration of future long COVID studies. METHODS: The Human Phenotype Ontology (HPO) is a widely used standard for exchange and analysis of phenotypic abnormalities in human disease but has not yet been applied to the analysis of COVID-19. FUNDING: We identified 303 articles published before April 29, 2021, curated 59 relevant manuscripts that described clinical manifestations in 81 cohorts three weeks or more following acute COVID-19, and mapped 287 unique clinical findings to HPO terms. We present layperson synonyms and definitions that can be used to link patient self-report questionnaires to standard medical terminology. Long COVID clinical manifestations are not assessed consistently across studies, and most manifestations have been reported with a wide range of synonyms by different authors. Across at least 10 cohorts, authors reported 31 unique clinical features corresponding to HPO terms; the most commonly reported feature was Fatigue (median 45.1%) and the least commonly reported was Nausea (median 3.9%), but the reported percentages varied widely between studies. INTERPRETATION: Translating long COVID manifestations into computable HPO terms will improve analysis, data capture, and classification of long COVID patients. If researchers, clinicians, and patients share a common language, then studies can be compared/pooled more effectively. Furthermore, mapping lay terminology to HPO will help patients assist clinicians and researchers in creating phenotypic characterizations that are computationally accessible, thereby improving the stratification, diagnosis, and treatment of long COVID. FUNDING: U24TR002306; UL1TR001439; P30AG024832; GBMF4552; R01HG010067; UL1TR002535; K23HL128909; UL1TR002389; K99GM145411.