Developing a Blood Cell-Based Diagnostic Test for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome Using Peripheral Blood Mononuclear Cells

Abstract

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is characterized by debilitating fatigue that profoundly impacts patients' lives. Diagnosis of ME/CFS remains challenging, with most patients relying on self-report, questionnaires, and subjective measures to receive a diagnosis, and many never receiving a clear diagnosis at all. In this study, a single-cell Raman platform and artificial intelligence are utilized to analyze blood cells from 98 human subjects, including 61 ME/CFS patients of varying disease severity and 37 healthy and disease controls. These results demonstrate that Raman profiles of blood cells can distinguish between healthy individuals, disease controls, and ME/CFS patients with high accuracy (91%), and can further differentiate between mild, moderate, and severe ME/CFS patients (84%). Additionally, specific Raman peaks that correlate with ME/CFS phenotypes and have the potential to provide insights into biological changes and support the development of new therapeutics are identified. This study presents a promising approach for aiding in the diagnosis and management of ME/CFS and can be extended to other unexplained chronic diseases such as long COVID and post-treatment Lyme disease syndrome, which share many of the same symptoms as ME/CFS.

Keywords: Raman microspectroscopy; machine learning; mitochondria; multiple sclerosis; myalgic encephalomyelitis/chronic fatigue syndrome; peripheral blood mononuclear cells; single cell.

Figure 1

Cohort clinical characteristics (n = 98). Symptom presence and intensity were determined for 63 variables obtained from the UKMEB symptoms assessment. Responses were recorded on an ordinal 4‐point scale, with 0 indicating “absent”, 1 indicating “mild”, 2 indicating “moderate”, and 3 indicating “severe”; gray boxes indicate missing data. Category inclusion was determined by calculating the relative mean ordinal weight/intensity for each variable, with a between‐group (severe ME compared to MS as the reference group) fold differentiation ≥1.5 mandated for analytical inclusion. Additionally, Fischer's Exact Test was calculated for severe ME versus MS comparison, with the Benjamini–Hochberg (BH) procedure applied to adjust for multiple comparisons (sig. p < 0.05).

Figure 2

SCRS differs among different cohorts (n = 98). Averaged Raman spectra of 2155 single cells obtained from 98 individual subjects, separating into A) three groups of HCs, ME, and MS, or B) five groups of HCs, Mild ME, Moderate ME, Severe ME, and MS. C) Differences between spectra of ME and HC and MS and HC; green line: subtracted HC baseline. Raman spectra from each group were shifted in intensity to aid visualization and the intensity is expressed in arbitrary units (a.u.). D–I) LDA clustering was used to visualize separations among three groups of HC, ME, and MS at the single‐cell level and the individual level, four groups of HC and different ME groups (mild, moderate, and severe) at the single‐cell level and the individual level, and five groups of HC, different ME groups (mild, moderate, and severe) and MS at the single‐cell level and the individual level.

Figure 3

Relative quantification of biomolecules in PBMCs of HC, ME (mild, moderate, and severe), and MS cohorts (n = 98), related to aromatic amino acids (AAAs) of A) tryptophan at 758 cm⁻¹, B) tyrosine at 860 cm⁻¹, and C) phenylalanine at 1003 cm⁻¹, lipid metabolism of D) glycerol at 1114 cm⁻¹, E) unsaturated fatty acids (FA) at 3010 cm⁻¹ and F) cholesterol/cholesteryl esters (CE) at 617 cm⁻¹, and energy metabolism of G) glycogen at 485 cm⁻¹ and H) glucose at 405 cm⁻¹. The quantification results were represented as box plots and the sample mean of each disease group was compared with healthy control (HC) by using Welch's two‐sample t‐test for unequal variance (ns: not significant; ^** p < 0.01; ^*** p < 0.001; and ^**** p < 0.0001).

Figure 4

Schematic illustration of the blood‐based Raman spectroscopic diagnostic test for ME/CFS and MS at a single‐cell level. A) PBMCs were isolated from blood samples. B) Raman spectra of single PBMCs from 98 individuals were measured. C) Around 5–7 spectra were measured in each cell which was then averaged to one spectrum for one cell; ≈30 spectra were obtained for each cell. D) SCRS at the single‐cell level from 98 individuals was then split into a train set (80%) and a test set (20%) with balanced subgroup distribution. The train set was used to train an ensemble learner and the independent test set was input into the trained learner for diagnosing the cell as HC, ME, or MS.

Figure 5

Ensemble learner performance on an independent test set breakdown by A) five classes with 84% overall accuracy and B) three classes with overall 91% accuracy. Matrix entries are shown as percentage values. The three‐class classification model shows a performance of diagnosing ME/CFS with 91% sensitivity and 93% specificity, MS with 90% sensitivity and 92% specificity, and an overall accuracy at 91% with 87–93% at 95% confidence interval.