Neurological Manifestations and Long-term Sequelae in Hospitalized Patients with COVID-19

Delayed encephalopathy after COVID-19: A case series of six patients

RATIONALE

Acute encephalopathy is a severe neurological complication of coronavirus disease 2019 (COVID-19). Most cases of acute encephalopathy associated with COVID-19 occur within several weeks of COVID-19 onset. We describe a case series of 6 patients who developed delayed encephalopathy (DE) after COVID-19.

PATIENT CONCERNS AND DIAGNOSES

We evaluated patients who recovered from COVID-19 and showed acute disturbance of consciousness or focal neurological deficits without recurrence of pneumonitis. Six patients, 2 females and 4 males, with ages ranging from 65 to 83 years were included. Durations of hospitalization due to COVID-19 were between 25 and 44 days. The severity of COVID-19 was moderate in 5 and severe in 1 patient. Patients were rehospitalized for acute disturbance of consciousness concomitant with postural tremor and, abnormal behavior, hemiplegia, aphasia, or apraxia between 34 and 67 days after the onset of COVID-19. Chest computed tomography showed no exacerbation of pneumonitis. Brain magnetic resonance imaging showed no specific findings except in 1 patient with an acute lacunar infarction. Electroencephalogram demonstrated diffuse slowing in all patients. Repeat electroencephalogram after recovery from encephalopathy demonstrated normal in all patients. One of the 6 patients had cerebrospinal fluid (CSF) pleocytosis. CSF protein levels were elevated in all patients, ranging from 51 to 115 mg/dL. CSF interleukin-6 levels ranged from 2.9 to 10.9 pg/mL. The immunoglobulin index was 0.39 to 0.44. Qlim(alb) < QAlb indicating dysfunction of the blood-brain barrier was observed in all patients. Severe acute respiratory syndrome coronavirus 2 reverse transcription polymerase chain reaction of CSF was negative in all patients. Neuronal autoantibodies were absent in serum and CSF.

INTERVENTIONS AND OUTCOMES

Immunotherapy including steroid pulses was administered to 3 patients; however, symptoms of encephalopathy resolved within several days in all patients, regardless of treatment with immunotherapy, and their consciousness levels were recovered fully. Notably, postural tremor remained for 2 weeks to 7 months.

LESSONS

In our patients, DE after COVID-19 was characterized by symptoms of acute encephalopathy accompanied with tremor in the absence of worsening pneumonitis after the fourth week of COVID-19 onset. Our findings indicate blood-brain barrier dysfunction may contribute to the pathogenesis of DE after COVID-19.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson's Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Catastrophic Neurological Complications in 2 Patients With Sickle Cell Disease and COVID-19

Severe acute respiratory syndrome coronavirus (SARS-CoV-2) infection is commonly associated with neurological complications. Patients with sickle cell disease are at increased risk of developing neurologic complications throughout their lifetimes and often have underlying cardiopulmonary comorbidities that may predispose them to poor outcomes during serious infections. In this case series, we describe 2 patients with sickle cell disease who developed devastating neurologic complications following SARS-CoV-2 infection, which ultimately led to brain edema and death. We highlight the unusual manifestations of coronavirus disease 2019 in patients with sickle cell disease and address the risk of these patients to develop catastrophic neurologic injury due to COVID-19, if not recognized promptly.