Preprint: Neurophenotypes of COVID-19: risk factors and recovery trajectories 2023 Prabhakaran et al

Coronavirus disease 2019 (COVID-19) infection is associated with risk of persistent neurocognitive and neuropsychiatric complications, termed “long COVID”. It is unclear whether the neuropsychological manifestations of COVID-19 present as a uniform syndrome or as distinct neurophenotypes with differing risk factors and recovery trajectories.

We examined post-acute outcomes following SARS-CoV-2 infection in 205 patients recruited from inpatient and outpatient populations, using an unsupervised machine learning cluster analysis, with objective and subjective neuropsychological measures as input features.

This resulted in three distinct post-COVID clusters. In the largest cluster (69%), cognitive functions were within normal limits (“normal cognition” neurophenotype), although mild subjective attention and memory complaints were reported. Cognitive impairment was present in the remaining 31% of the sample but clustered into two differentially impaired groups.

In 16% of participants, memory deficits, slowed processed speed, and fatigue were predominant. Risk factors for membership in the “memory-speed impaired” neurophenotype included anosmia and more severe COVID-19 infection. In the remaining 15% of participants, executive dysfunction was predominant. Risk factors for membership in this milder “dysexecutive” neurophenotype included disease-nonspecific factors such as neighborhood deprivation and obesity. Recovery trajectories at 6-month follow-up differed across neurophenotypes, with the normal cognition group showing stability, the dysexecutive group showing improvement, and the memory-speed impaired group showing persistent processing speed deficits and fatigue, as well as worse functional outcomes.

These results indicate that there are multiple post-acute neurophenotypes of long COVID, with different etiological pathways and recovery trajectories. This information may inform phenotype-specific approaches to treatment.

https://www.researchsquare.com/article/rs-2363210/v1

 

3 years of entry-level studies really don't amount to much when they stick to nothing but massively redundant entry-level stuff that only looks at the same things over and over. Running out the clock except the clock keeps turning faster. At this rate we'll have comprehensive studies about to start a possible planning phase by the 2050's.

No idea why they clown around with machine learning that adds nothing when you get the same information straight from the patients. I guess just adding "machine learning", even if it's completely superfluous, is a good way to get funded.

Any clever research could have made better progress on this topic a solid 80 years ago, all you have to do is pay attention and treat patients as a source of information.