The development of long-term symptoms of coronavirus disease 2019 (COVID-19) more than four weeks after primary infection, termed “long COVID” or post-acute sequela of COVID-19 (PASC), can implicate persistent neurological complications in up to one third of patients and present as fatigue, “brain fog”, headaches, cognitive impairment, dysautonomia, neuropsychiatric symptoms, anosmia, hypogeusia, and peripheral neuropathy. Pathogenic mechanisms of these symptoms of long COVID remain largely unclear; however, several hypotheses implicate both nervous system and systemic pathogenic mechanisms such as SARS-CoV2 viral persistence and neuroinvasion, abnormal immunological response, autoimmunity, coagulopathies, and endotheliopathy. Outside of the CNS, SARS-CoV-2 can invade the support and stem cells of the olfactory epithelium leading to persistent alterations to olfactory function. SARS-CoV-2 infection may induce abnormalities in innate and adaptive immunity including monocyte expansion, T-cell exhaustion, and prolonged cytokine release, which may cause neuroinflammatory responses and microglia activation, white matter abnormalities, and microvascular changes. Additionally, microvascular clot formation can occlude capillaries and endotheliopathy, due to SARS-CoV-2 protease activity and complement activation, can contribute to hypoxic neuronal injury and blood–brain barrier dysfunction, respectively. Current therapeutics target pathological mechanisms by employing antivirals, decreasing inflammation, and promoting olfactory epithelium regeneration. Thus, from laboratory evidence and clinical trials in the literature, we sought to synthesize the pathophysiological pathways underlying neurological symptoms of long COVID and potential therapeutics.

In-hospital mortality after venoarterial extracorporeal membrane oxygenation (VA-ECMO) remains high. This study compared the performance of the Survival after Venoarterial ECMO (SAVE) score with machine learning (ML) models incorporating rich electronic medical record data to evaluate survival for patients on VA-ECMO support. We retrospectively reviewed adults undergoing VA-ECMO (2016–2022) at a single tertiary care center. The CatBoost algorithm was trained using leave-one-out cross-validation (LOOCV) on 74 extracted vital signs, laboratory values, and ventilator settings. Shapley Additive Explanations (SHAP) was used to identify key predictive features for logistic regression. Overall, 194 VA-ECMO patients (median age = 58 years, 36.6% female) were included, with 133 (69%) experiencing mortality. The SAVE score was compared to two predictive models: a pre-ECMO model (≤ 24 hours before cannulation) and an on-ECMO model (including up to the first 48 hours of ECMO). The LOOCV area under the receiver-operator characteristics curves (AUC) for the SAVE score, pre-ECMO, and on-ECMO models was 0.73, 0.77, and 0.83, respectively. Logistic regressions using ML-identified variables showed stepwise AUC improvements: 0.82 (pre-ECMO), 0.86 (on-ECMO), and 0.89 (combined). A novel, interpretable ML model predicted survival for VA-ECMO patients with accuracy comparable to the SAVE score. Incorporating on-ECMO variables significantly increased predictive performance and revealed novel variables associated with survival.