Tag: diagnosis

Development of an expert system for the classification of myalgic encephalomyelitis/chronic fatigue syndrome

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a severe condition with an uncertain origin and a dismal prognosis. There is presently no precise diagnostic test for ME/CFS, and the diagnosis is determined primarily by the presence of certain symptoms. The current study presents an explainable artificial intelligence (XAI) integrated machine learning (ML) framework that identifies and classifies potential metabolic biomarkers of ME/CFS.

Metabolomic data from blood samples from 19 controls and 32 ME/CFS patients, all female, who were between age and body mass index (BMI) frequency-matched groups, were used to develop the XAI-based model. The dataset contained 832 metabolites, and after feature selection, the model was developed using only 50 metabolites, meaning less medical knowledge is required, thus reducing diagnostic costs and improving prognostic time. The computational method was developed using six different ML algorithms before and after feature selection. The final classification model was explained using the XAI approach, SHAP.

The best-performing classification model (XGBoost) achieved an area under the receiver operating characteristic curve (AUCROC) value of 98.85%. SHAP results showed that decreased levels of alpha-CEHC sulfate, hypoxanthine, and phenylacetylglutamine, as well as increased levels of N-delta-acetylornithine and oleoyl-linoloyl-glycerol (18:1/18:2)[2], increased the risk of ME/CFS. Besides the robustness of the methodology used, the results showed that the combination of ML and XAI could explain the biomarker prediction of ME/CFS and provided a first step toward establishing prognostic models for ME/CFS.

Source: Yagin FH, Shateri A, Nasiri H, Yagin B, Colak C, Alghannam AF. Development of an expert system for the classification of myalgic encephalomyelitis/chronic fatigue syndrome. PeerJ Comput Sci. 2024 Mar 20;10:e1857. doi: 10.7717/peerj-cs.1857. PMID: 38660205; PMCID: PMC11041999. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11041999/ (Full text)

Machine learning algorithms for detection of visuomotor neural control differences in individuals with PASC and ME

Abstract:

The COVID-19 pandemic has affected millions worldwide, giving rise to long-term symptoms known as post-acute sequelae of SARS-CoV-2 (PASC) infection, colloquially referred to as long COVID. With an increasing number of people experiencing these symptoms, early intervention is crucial. In this study, we introduce a novel method to detect the likelihood of PASC or Myalgic Encephalomyelitis (ME) using a wearable four-channel headband that collects Electroencephalogram (EEG) data. The raw EEG signals are processed using Continuous Wavelet Transform (CWT) to form a spectrogram-like matrix, which serves as input for various machine learning and deep learning models. We employ models such as CONVLSTM (Convolutional Long Short-Term Memory), CNN-LSTM, and Bi-LSTM (Bidirectional Long short-term memory). Additionally, we test the dataset on traditional machine learning models for comparative analysis.

Our results show that the best-performing model, CNN-LSTM, achieved an accuracy of 83%. In addition to the original spectrogram data, we generated synthetic spectrograms using Wasserstein Generative Adversarial Networks (WGANs) to augment our dataset. These synthetic spectrograms contributed to the training phase, addressing challenges such as limited data volume and patient privacy. Impressively, the model trained on synthetic data achieved an average accuracy of 93%, significantly outperforming the original model.

These results demonstrate the feasibility and effectiveness of our proposed method in detecting the effects of PASC and ME, paving the way for early identification and management of the condition. The proposed approach holds significant potential for various practical applications, particularly in the clinical domain. It can be utilized for evaluating the current condition of individuals with PASC or ME, and monitoring the recovery process of those with PASC, or the efficacy of any interventions in the PASC and ME populations. By implementing this technique, healthcare professionals can facilitate more effective management of chronic PASC or ME effects, ensuring timely intervention and improving the quality of life for those experiencing these conditions.

Source: Harit Ahuja, Smriti Badhwar, Heather Edgell, Lauren E. Sergio, Marin Litoiu. Machine learning algorithms for detection of visuomotor neural control differences in individuals with PASC and ME. Front. Hum. Neurosci. Sec. Brain-Computer Interfaces, Volume 18 – 2024 | doi: 10.3389/fnhum.2024.1359162 https://www.frontiersin.org/articles/10.3389/fnhum.2024.1359162/full (Full text)

NICE guideline on ME/CFS: robust advice based on a thorough review of the evidence

Abstract:

In 2021, the National Institute for Health and Care Excellence produced an evidence-based guideline on the diagnosis and management of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), a disabling long-term condition of unknown cause. The guideline provides clear support for people living with ME/CFS, their families and carers, and for clinicians. A recent opinion piece published in the journal suggested that there were anomalies in the processing and interpretation of the evidence when developing the guideline and proposed eight areas where these anomalies were thought to have occurred. We outline how these opinions are based on a misreading or misunderstanding of the guideline process or the guideline, which provides a balanced and reasoned approach to the diagnosis and management of this challenging condition.

Source: Barry PW, Kelley K, Tan T, et al. NICE guideline on ME/CFS: robust advice based on a thorough review of the evidence. Journal of Neurology, Neurosurgery & Psychiatry Published Online First: 28 February 2024. doi: 10.1136/jnnp-2023-332731 https://jnnp.bmj.com/content/early/2024/02/28/jnnp-2023-332731 (Full text)

Psychometric evaluation of the DePaul Symptom Questionnaire-Short Form (DSQ-SF) among adults with Long COVID, ME/CFS, and healthy controls: A machine learning approach

Abstract:

Long COVID shares a number of clinical features with myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), including post-exertional malaise, severe fatigue, and neurocognitive deficits. Utilizing validated assessment tools that accurately and efficiently screen for these conditions can facilitate diagnostic and treatment efforts, thereby improving patient outcomes.

In this study, we generated a series of random forest machine learning algorithms to evaluate the psychometric properties of the DePaul Symptom Questionnaire-Short Form (DSQ-SF) in classifying large groups of adults with Long COVID, ME/CFS (without Long COVID), and healthy controls.

We demonstrated that the DSQ-SF can accurately classify these populations with high degrees of sensitivity and specificity. In turn, we identified the particular DSQ-SF symptom items that best distinguish Long COVID from ME/CFS, as well as those that differentiate these illness groups from healthy controls.

Source: McGarrigle WJ, Furst J, Jason LA. Psychometric evaluation of the DePaul Symptom Questionnaire-Short Form (DSQ-SF) among adults with Long COVID, ME/CFS, and healthy controls: A machine learning approach. J Health Psychol. 2024 Jan 28:13591053231223882. doi: 10.1177/13591053231223882. Epub ahead of print. PMID: 38282368. https://pubmed.ncbi.nlm.nih.gov/38282368/

Systems thinking, subjective findings and diagnostic “pigeonholing” in ME/CFS: A mainly qualitative public health study from a patient perspective

Abstract:

in English, German

Background: ME/CFS (Myalgic encephalomyelitis/chronic fatigue syndrome) is an illness that is predominantly viewed as a neuroimmunological multisystem disease, which is still unknown to many doctors in Germany or which they classify as a psychosomatic disease. From their perspective, ME/CFS patients report significant deficits in terms of medical treatment and a doctor-patient relationship (DP relationship) that is perceived as problematic. The aim of the present study is to more precisely analyse the process of finding a diagnosis as an influencing factor on the DP relationship in ME/CFS from the point of view of those affected.

Method: As part of an explorative qualitative survey, 544 ME/CFS patients (> 20 years; 455 ♀, 89 ♂) with a medical diagnosis of ME/CFS were asked in writing about their experiences with regard to the process of finding a diagnosis. The sampling was previously done by self-activation and via the snowball principle. The questionnaire to be answered was structured analogously to a focused, standardized guideline interview. The evaluation was carried out as part of a qualitative content analysis according to Mayring. Some of the results were subsequently quantified.

Results: The participants described what they saw as the inadequate process of making a diagnosis as a central factor in a problematic DP relationship in ME/CFS. From their point of view, many doctors deny the existence of ME/CFS or classify it as a solely psychosomatic illness, insist on their level of knowledge, ignore patient knowledge and disregard scientific information provided. They follow the standard program, think in “pigeonholes” and are incapable of systemic thinking. This has a significant impact on the DP relationship.

Discussion: From the point of view of ME/CFS patients, the process of making a diagnosis and the recognition of ME/CFS as a neuroimmunological multisystem disease are the central aspects of a DP relationship that they experience as problematic. In the past, findings classified as “subjective” and thus ignored, the pigeonholing that is characteristic of biomedically oriented medicine and a healthcare system that opposes systemic thinking when making a diagnosis have all been identified as factors that may have a significant impact on the DP relationship.

Source: Habermann-Horstmeier L, Horstmeier LM. Systemisches Denken, subjektive Befunde und das diagnostische „Schubladendenken“ bei ME/CFS – Eine vorwiegend qualitative Public-Health-Studie aus Patientensicht [Systems thinking, subjective findings and diagnostic “pigeonholing” in ME/CFS: A mainly qualitative public health study from a patient perspective]. Dtsch Med Wochenschr. 2023 Dec 14. German. doi: 10.1055/a-2197-6479. Epub ahead of print. PMID: 38096913. https://pubmed.ncbi.nlm.nih.gov/38096913/

IgG Antibody Responses to Epstein-Barr Virus in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Their Effective Potential for Disease Diagnosis and Pathological Antigenic Mimicry

Abstract:

The diagnosis and the pathology of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) remain under debate. However, there is a growing body of evidence for an autoimmune component in ME/CFS caused by the Epstein-Barr virus (EBV) and other viral infections.
In this work, we took advantage of a large public dataset on the IgG antibodies to 3,054 EBV peptides to understand whether these immune responses could be used as putative biomarkers for disease diagnosis and triggers of pathological autoimmunity in ME/CFS patients using healthy controls (HCs) as a comparator cohort. We then aimed at predicting disease status of study participants using a Super Learner algorithm targeting an accuracy of 85% when splitting data into train and test datasets.
When we compared data of all ME/CFS patients or data of a subgroup of these patients with non-infectious or unknown disease trigger to the dataset of HC, we could not find an antibody-based classifier that would meet the desired accuracy in the test dataset. In contrast, we could identify a 26-antibody classifier that could distinguish ME/CFS patients with an infectious disease trigger from HCs with 100% and 90% accuracies on the train and test sets, respectively.
We finally performed a bioinformatic analysis of the EBV peptides associated with these 26 antibodies. We found no correlation between the importance metric of the selected antibodies in the classifier and the maximal sequence homology between human proteins and each EBV peptide recognized by these antibodies.
In conclusion, these 26 antibodies against EBV have an effective potential for disease diagnosis of a subset of patients, but they are less likely to trigger pathological autoimmune responses that could explain the pathogenesis of ME/CFS.
Source: Fonseca, A.; Szysz, M.; Ly, H.T.; Cordeiro, C.; Sepúlveda, N. IgG Antibody Responses to Epstein-Barr Virus in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Their Effective Potential for Disease Diagnosis and Pathological Antigenic Mimicry. Preprints 2023, 2023111523. https://doi.org/10.20944/preprints202311.1523.v1 https://www.preprints.org/manuscript/202311.1523/v1 (Full text available as PDF file)

Bioimpedance spectroscopy characterization of Myalgic Encephalomyelitis/ Chronic Fatigue Syndrome (ME/CFS) peripheral blood mononuclear cells

Abstract:

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a disabling and chronic disease, importantly related to the current COVID-19 pandemic. Currently, there are no specific laboratory tests to directly diagnose ME/CFS. In this work, the use of impedance spectroscopy is studied as a potential technique for the diagnosis of ME/CFS. A specific device for the electrical characterization of peripheral blood mononuclear cells was designed and implemented.

Impedance spectroscopy measurements in the range from 1 Hz to 500 MHz were carried out after the osmotic stress of the samples with sodium chloride solution at 1M concentration. The evolution in time after the osmotic stress at two specific frequencies (1.36 kHz and 154 kHz) was analyzed.

The device showed its sensitivity to the presence of cells and the evolution of the osmotic processes. Higher values of impedance (around 15% for both the real and imaginary part) were measured at 1.36 kHz in ME/CFS patients compared to control samples. No significant difference was found between patient samples and control samples at 154 kHz. Results help to further understand the diagnosis of ME/CFS patients and the relation of their blood samples with bioimpedance measurements.

Source: Sara Martinez Rodriguez, Alberto Olmo Fernandez, Daniel Martin Fernandez, Isabel Martin-Garrido. Bioimpedance spectroscopy characterization of Myalgic Encephalomyelitis/ Chronic Fatigue Syndrome (ME/CFS) peripheral blood mononuclear cells. Biomedical Letters, Volume 9, Issue 2: 121-128. http://thesciencepublishers.com/biomed_lett/v9i2abstract6.html (Full text available as PDF file)

Diagnosis and Management of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic neurologic disease often preceded by infection. There has been increased interest in ME/CFS recently because of its significant overlap with the post-COVID syndrome (long COVID or post-acute sequelae of COVID), with several studies estimating that half of patients with post-COVID syndrome fulfill ME/CFS criteria. Our concise review describes a generalist approach to ME/CFS, including diagnosis, evaluation, and management strategies.

Source: Grach SL, Seltzer J, Chon TY, Ganesh R. Diagnosis and Management of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome. Mayo Clin Proc. 2023 Oct;98(10):1544-1551. doi: 10.1016/j.mayocp.2023.07.032. PMID: 37793728. https://www.mayoclinicproceedings.org/article/S0025-6196(23)00402-0/fulltext (Full text)

Developing and validating a brief screening scale for ME/CFS

Abstract:

Objective: The purpose of the current study was to develop and evaluate a brief screening instrument for ME/CFS. The current study identified 4 symptom items that identify those positive for the IOM ME/CFS case definition.

Study Design: A data set of over 2,000 patients with Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) and over 350 controls were assessed for the 4-item DePaul Symptom Questionnaire-Brief (DSQ-Brief). All respondents also completed the longer 54-item DePaul Symptom Questionnaire (DSQ-1) as well as the 14-item DePaul Symptom Questionnaire-Short Form (DSQ-SF). These data sets were collected from multiple countries.

We also examined the DSQ-Brief, DSQ-1, and DSQ-SF with other chronic illness groups [Multiple Sclerosis (MS) and Post-Polio Syndrome (PPS)] and those with Long COVID. Random Forest comparisons were employed in these analyses.

Results: When contrasting ME/CFS from controls, high levels of accuracy occurred using the DSQ-1, DSQ-SF, and DSQ-Brief. High accuracy again occurred for differentiating those with ME/CFS from MS, PPS, and Long COVID using the DSQ-1 and DSQ-SF, but accuracy was less for the DSQ-Brief.

Conclusions: The DSQ-Brief had high sensitivity, meaning it could identify those with ME/CFS versus controls, whereas accuracy dropped with other chronic illnesses. However, it was possible to achieve better accuracy and identify those cases where misidentification occurred by administering the DSQ-SF or DSQ-1 following the DSQ-Brief. It is now possible to screen individuals for ME/CFS using the DSQ-Brief and in so doing, identify those who are most likely to have ME/CFS.

Source: Leonard A. Jason, Sage Benner, Jacob Furst & Paul Cathey (2023) Developing and validating a brief screening scale for ME/CFS, Fatigue: Biomedicine, Health & Behavior, 11:2-4, 176-187, DOI: 10.1080/21641846.2023.2252613 https://www.tandfonline.com/doi/abs/10.1080/21641846.2023.2252613

Myalgic Encephalomyelitis-Chronic Fatigue Syndrome Common Data Element item content analysis

Abstract:

Introduction: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a multisystem chronic disease estimated to affect 836,000-2.5 million individuals in the United States. Persons with ME/CFS have a substantial reduction in their ability to engage in pre-illness levels of activity. Multiple symptoms include profound fatigue, post-exertional malaise, unrefreshing sleep, cognitive impairment, orthostatic intolerance, pain, and other symptoms persisting for more than 6 months. Diagnosis is challenging due to fluctuating and complex symptoms. ME/CFS Common Data Elements (CDEs) were identified in the National Institutes of Health (NIH) National Institute of Neurological Disorders and Stroke (NINDS) Common Data Element Repository. This study reviewed ME/CFS CDEs item content.

Methods: Inclusion criteria for CDEs (measures recommended for ME/CFS) analysis: 1) assesses symptoms; 2) developed for adults; 3) appropriate for patient reported outcome measure (PROM); 4) does not use visual or pictographic responses. Team members independently reviewed CDEs item content using the World Health Organization International Classification of Functioning, Disability and Health (ICF) framework to link meaningful concepts.

Results: 119 ME/CFS CDEs (measures) were reviewed and 38 met inclusion criteria, yielding 944 items linked to 1503 ICF meaningful concepts. Most concepts linked to ICF Body Functions component (b-codes; n = 1107, 73.65%) as follows: Fatiguability (n = 220, 14.64%), Energy Level (n = 166, 11.04%), Sleep Functions (n = 137, 9.12%), Emotional Functions (n = 131, 8.72%) and Pain (n = 120, 7.98%). Activities and Participation concepts (d codes) accounted for a smaller percentage of codes (n = 385, 25.62%). Most d codes were linked to the Mobility category (n = 69, 4.59%) and few items linked to Environmental Factors (e codes; n = 11, 0.73%).

Discussion: Relatively few items assess the impact of ME/CFS symptoms on Activities and Participation. Findings support development of ME/CFS-specific PROMs, including items that assess activity limitations and participation restrictions. Development of psychometrically-sound, symptom-based item banks administered as computerized adaptive tests can provide robust assessments to assist primary care providers in the diagnosis and care of patients with ME/CFS.

Source: Slavin MD, Bailey HM, Hickey EJ, Vasudevan A, Ledingham A, Tannenbaum L, Bateman L, Kaufman DL, Peterson DL, Ruhoy IS, Systrom DM, Felsenstein D, Kazis LE. Myalgic Encephalomyelitis-Chronic Fatigue Syndrome Common Data Element item content analysis. PLoS One. 2023 Sep 12;18(9):e0291364. doi: 10.1371/journal.pone.0291364. PMID: 37698999. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0291364 (Full text)