Neurological symptoms and comorbidity profile of hospitalized patients with COVID-19.

BACKGROUND: The neurological manifestations in COVID-19 adversely impact acute illness and post-disease quality of life. Limited data exist regarding the association of neurological symptoms and comorbid individuals. OBJECTIVE: To assess neurological symptoms in hospitalized patients with acute COVID-19 and multicomorbidities. METHODS: Between June 2020 and July 2020, inpatients aged 18 or older, with laboratory-confirmed COVID-19, admitted to the Hospital São Paulo (Federal University of São Paulo), a tertiary referral center for high complexity cases, were questioned about neurological symptoms. The Composite Autonomic Symptom Score 31 (COMPASS-31) questionnaire was used. The data were analyzed as a whole and whether subjective olfactory dysfunction was present or not. RESULTS: The mean age of the sample was 55 ± 15.12 years, and 58 patients were male. The neurological symptoms were mostly xerostomia (71%), ageusia/hypogeusia (50%), orthostatic intolerance (49%), anosmia/hyposmia (44%), myalgia (31%), dizziness (24%), xerophthalmia (20%), impaired consciousness (18%), and headache (16%). Furthermore, 91% of the patients had a premorbidity. The 44 patients with subjective olfactory dysfunction were more likely to have hypertension, diabetes, weakness, shortness of breath, ageusia/hypogeusia, dizziness, orthostatic intolerance, and xerophthalmia. The COMPASS-31 score was higher than that of previously published controls (14.85 ± 12.06 vs. 8.9 ± 8.7). The frequency of orthostatic intolerance was 49% in sample and 63.6% in those with subjective olfactory dysfunction (2.9-fold higher risk compared to those without). CONCLUSION: A total of 80% of inpatients with multimorbidity and acute COVID-19 had neurological symptoms. Chemical sense and autonomic symptoms stood out. Orthostatic intolerance occurred in around two-thirds of the patients with anosmia/hyposmia. Hypertension and diabetes were common, mainly in those with anosmia/hyposmia.

ANTECEDENTES: As manifestações neurológicas na COVID-19 impactam adversamente na enfermidade aguda e na qualidade de vida após a doença. Dados limitados existem em relação a associação de sintomas neurológicos e indivíduos com comorbidades. OBJETIVO: Avaliar os sintomas neurológicos em pacientes de hospitalizados com COVID-19 aguda e múltiplas comorbidades. MéTODOS: Entre junho e julho de 2020, pacientes de hospitais com idade 18 anos ou acima e COVID-19 laboratorialmente confirmada, admitidos no Hospital São Paulo (Universidade Federal de São Paulo), um centro de referência terciário para casos de alta complexidade, foram perguntados sobre sintomas neurológicos. O questionário Pontuação composta de sintoma autonômico (COMPASS-31) foi usado. Os dados foram analisados no geral e se a disfunção olfatória subjetiva estava presente ou não. RESULTADOS: A média de idade da amostra foi 55 ± 15.12 anos. 58 pacientes eram homens. Os sintomas neurológicos foram principalmente xerostomia (71%), ageusia/hipogeusia (50%), intolerância ortostática (49%), anosmia/hiposmia (44%), mialgia (31%), tontura (24%), xeroftalmia (20%), comprometimento na consciência (18%) e cefaleia (16%). Além disso, 91% dos pacientes tinham uma pré-morbidade. Os 44 pacientes com disfunção olfatória tinham maior chance de ter hipertensão, diabetes, fraqueza, falta de ar, ageusia/hipogeusia, tontura, intolerância ortostática e xeroftalmia. A pontuação do COMPASS-31 foi maior do que a de controles previamente publicados (14,85 ± 12,06 vs. 8,9 ± 8,7). A frequência de intolerância ortostática foi 49% na amostra e 63,6% naqueles com disfunção olfatória subjetiva (risco 2.9 vezes maior comparado com os sem). CONCLUSãO: Um total de 80% dos pacientes hospitalizados com múltiplas morbidades e COVID-19 aguda tinham sintomas neurológicos. Os sintomas do sentido químico e autonômicos se destacaram. A intolerância ortostática ocorreu em cerca de dois terços dos pacientes com anosmia/hiposmia. A hipertensão e o diabetes foram comuns, principalmente naqueles com anosmia/hiposmia.

A Machine Learning Model for Predicting Hospitalization in Patients with Respiratory Symptoms during the COVID-19 Pandemic.

A machine learning approach is a useful tool for risk-stratifying patients with respiratory symptoms during the COVID-19 pandemic, as it is still evolving. We aimed to verify the predictive capacity of a gradient boosting decision trees (XGboost) algorithm to select the most important predictors including clinical and demographic parameters in patients who sought medical support due to respiratory signs and symptoms (RAPID RISK COVID-19). A total of 7336 patients were enrolled in the study, including 6596 patients that did not require hospitalization and 740 that required hospitalization. We identified that patients with respiratory signs and symptoms, in particular, lower oxyhemoglobin saturation by pulse oximetry (SpO2) and higher respiratory rate, fever, higher heart rate, and lower levels of blood pressure, associated with age, male sex, and the underlying conditions of diabetes mellitus and hypertension, required hospitalization more often. The predictive model yielded a ROC curve with an area under the curve (AUC) of 0.9181 (95% CI, 0.9001 to 0.9361). In conclusion, our model had a high discriminatory value which enabled the identification of a clinical and demographic profile predictive, preventive, and personalized of COVID-19 severity symptoms.