Long COVID diagnostic with differentiation from chronic lyme disease using machine learning and cytokine hubs, 2024, Patterson et al

• Bruce K. Patterson,

• Jose Guevara-Coto,

• Javier Mora,

• Edgar B. Francisco,

• Ram Yogendra,

• Rodrigo A. Mora-Rodríguez,

• Christopher Beaty,

• Gwyneth Lemaster,

• Gary Kaplan DO,

• Amiram Katz &

• Joseph A. Bellanti

Abstract

The absence of a long COVID (LC) or post-acute sequelae of COVID-19 (PASC) diagnostic has profound implications for research and potential therapeutics given the lack of specificity with symptom-based identification of LC and the overlap of symptoms with other chronic inflammatory conditions. Here, we report a machine-learning approach to LC/PASC diagnosis on 347 individuals using cytokine hubs that are also capable of differentiating LC from chronic lyme disease (CLD).

We derived decision tree, random forest, and gradient-boosting machine (GBM) classifiers and compared their diagnostic capabilities on a dataset partitioned into training (178 individuals) and evaluation (45 individuals) sets. The GBM model generated 89% sensitivity and 96% specificity for LC with no evidence of overfitting. We tested the GBM on an additional random dataset (106 LC/PASC and 18 Lyme), resulting in high sensitivity (97%) and specificity (90%) for LC. We constructed a Lyme Index confirmatory algorithm to discriminate LC and CLD.

Open access: https://www.nature.com/articles/s41598-024-70929-y

 

So there's this:
"Considering the type of symptoms observed in CLD that share the common features of exacerbated central nervous system pain and sensory-processing mechanisms, CLD is included within the group of pathologies associated with central sensitivity syndrome (CSS)24. Pro-inflammatory cytokines such as TNF-α promote CSS inducing central sensitization and hyperalgesia via distinct and overlapping synaptic mechanisms in neurons either by increasing excitatory synaptic transmission or by decreasing inhibitory synaptic transmission29. Furthermore, TNF-α promotes CSS-associated neuroinflammation generating several adverse effects, such as chronic pain, neurodegeneration, and cognitive impairment30, common features of CLD. Additionally, immune cells promote peripheral or central nervous system sensitization through pro-inflammatory molecules such as TNF-α. Mast cells and astrocytes release TNF-α affecting neuronal function and promoting the development of chronic pain30,31. The effects of chronic inflammation and TNF-α, in particular, have been shown to lower levels of serotonin leading to depression32. Interestingly, a recent paper has suggested that low serotonin in LC could be alleviated by the use of Prozac™33. One can also speculate that effective treatment of chronic inflammation in LC and CLD might also be effective in addressing depression in these conditions."

Moreover, based on this:
"Presence of other tick-borne organisms was noted but not required for definition of CLD as previously described13."
and this:
"We also determined that altered levels of VEGF are associated with chronic CLD similar to Antonara et al.18",
I'm not sure that they are actually even measuring CLD. Elevated serum VEGF is a proxy for Bartonella. If they are more or less giving other TBDs a free pass into their CLD cohort. who knows what they are measuring?

Regardless, they lost me at CSS.