ABSTRACT
The potential long-term neuropsychiatric effects of COVID-19 are of global concern. This study aimed to determine the prevalence and predictors of neuropsychiatric post-acute sequelae of COVID-19 among Egyptian COVID-19 survivors and to study the impact of full vaccination before COVID-19 infection on the occurrence and severity of these manifestations. Three months after getting COVID-19 infection, 1638 COVID-19 survivors were screened by phone for possible neuropsychiatric sequelae. Subjects suspected to suffer from these sequelae were invited to a face-to-face interview for objective evaluation. They were requested to rate the severity of their symptoms using visual analogue scales (VAS). The mean age of participants was 38.28 ± 13 years. Only 18.6% were fully vaccinated before COVID-19 infection. Neuropsychiatric post-acute sequelae of COVID-19 were documented in 598 (36.5%) subjects, fatigue was the most frequent one (24.6%), followed by insomnia (16.4%), depression (15.3%), and anxiety (14.4%). Moderate and severe COVID-19 infection and non-vaccination increased the odds of developing post-COVID-19 neuropsychiatric manifestations by 2 times (OR 1.95, 95% CI = 1.415-2.683), 3.86 times (OR 3.86, 95% CI = 2.358-6.329), and 1.67 times (OR 1.67, 95% CI = 1.253-2.216), respectively. Fully vaccinated subjects before COVID-19 infection (n = 304) had significantly lesser severity of post-COVID-19 fatigue, ageusia/hypogeusia, dizziness, tinnitus, and insomnia (P value = 0.001, 0.008, < 0.001, 0.025, and 0.005, respectively) than non-vaccinated subjects. This report declared neuropsychiatric sequelae in 36.5% of Egyptian COVID-19 survivors, fatigue being the most prevalent. The effectiveness of COVID-19 vaccines in reducing the severity of some post-COVID-19 neuropsychiatric manifestations may improve general vaccine acceptance.
ABSTRACT
OBJECTIVES: During the COVID-19 pandemic, a quick and reliable phone-triage system is critical for early care and efficient distribution of hospital resources. The study aimed to assess the accuracy of the traditional phone-triage system and phone triage-driven deep learning model in the prediction of positive COVID-19 patients. SETTING: This is a retrospective study conducted at the family medicine department, Cairo University. METHODS: The study included a dataset of 943 suspected COVID-19 patients from the phone triage during the first wave of the pandemic. The accuracy of the phone triaging system was assessed. PCR-dependent and phone triage-driven deep learning model for automated classifications of natural human responses was conducted. RESULTS: Based on the RT-PCR results, we found that myalgia, fever, and contact with a case with respiratory symptoms had the highest sensitivity among the symptoms/ risk factors that were asked during the phone calls (86.3%, 77.5%, and 75.1%, respectively). While immunodeficiency, smoking, and loss of smell or taste had the highest specificity (96.9%, 83.6%, and 74.0%, respectively). The positive predictive value (PPV) of phone triage was 48.4%. The classification accuracy achieved by the deep learning model was 66%, while the PPV was 70.5%. CONCLUSION: Phone triage and deep learning models are feasible and convenient tools for screening COVID-19 patients. Using the deep learning models for symptoms screening will help to provide the proper medical care as early as possible for those at a higher risk of developing severe illness paving the way for a more efficient allocation of the scanty health resources.