A Proposed Explainable Artificial Intelligence-Based Machine Learning Model for Discriminative Metabolites for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome

Abstract:

Background: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex and debilitating disease with a significant global prevalence of over 65 million individuals. It affects various systems, including the immune, neurological, gastrointestinal, and circulatory systems. Studies have shown abnormalities in immune cell types, increased inflammatory cytokines, and brain abnormalities. Further research is needed to identify consistent biomarkers and develop targeted therapies. A multidisciplinary approach is essential for diagnosing, treating, and managing this complex disease.

The current study aims at employing explainable artificial intelligence (XAI) and machine learning (ML) techniques to identify discriminative metabolites for ME/CFS.

Material and Methods: The present study used a metabolomics dataset of CFS patients and healthy controls, including 26 healthy controls and 26 ME/CFS patients aged 22-72. The dataset encapsulated 768 metabolites, classified into nine metabolic super-pathways: amino acids, carbohydrates, cofactors, vitamins, energy, lipids, nucleotides, peptides, and xenobiotics.

Random forest-based feature selection and Bayesian Approach based-hyperparameter optimization were implemented on the target data. Four different ML algorithms [Gaussian Naive Bayes (GNB), Gradient Boosting Classifier (GBC), Logistic regression (LR) and Random Forest Classifier (RFC)] were used to classify individuals as ME/CFS patients and healthy individuals. XAI approaches were applied to clinically explain the prediction decisions of the optimum model. Performance evaluation was performed using the indices of accuracy, precision, recall, F1 score, Brier score, and AUC.

Results: The metabolomics of C-glycosyltryptophan, oleoylcholine, cortisone, and 3-hydroxydecanoate were determined to be crucial for ME/CFS diagnosis.

The RFC learning model outperformed GNB, GBC, and LR in ME/CFS prediction using the 1000 iteration bootstrapping method, achieving 98% accuracy, precision, recall, F1 score, 0.01 Brier score, and 99% AUC.

Conclusion: RFC model proposed in this study correctly classified and evaluated ME/CFS patients through the selected biomarker candidate metabolites. The methodology combining ML and XAI can provide a clear interpretation of risk estimation for ME/CFS, helping physicians intuitively understand the impact of key metabolomics features in the model.

Source: Yagin, F.H., Alkhateeb, A., Raza, A., Samee, N.A., Mahmoud, N.F., Colak, C., & Yagin, B. (2023). A Proposed Explainable Artificial Intelligence-Based Machine Learning Model for Discriminative Metabolites for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome. Preprints. https://doi.org/10.20944/preprints202307.1585.v1 https://www.preprints.org/manuscript/202307.1585/v1 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10706650/ (Full text of completed study)

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) and COVID-19: is there a connection?

Abstract:

Objectives: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a chronic systemic disease that leads to neurological, immunological, autonomic, and energy metabolism dysfunction. COVID-19 has been reported to cause similar symptoms to ME/CFS. The study aims to investigate the prevalence of myalgic encephalomyelitis in patients post-COVID-19 infection by assessing acute and long-term COVID-19 symptoms.

Methods: A cross-sectional questionnaire was developed based on the ME/CFS diagnostic criteria, as specified by the IOM clinical diagnostic criteria, and administered to participants with confirmed COVID-19 who are more than 18 years old and have BMI below 40 Kg/m2. Data from 437 participants were completed.

Results: The current study results revealed that 8.1% of the study participants met the ME/CFS diagnostic criteria. Interestingly, 2.8 of the study participants were classified to have COVID-19 related to ME/CFS. While 4.6% of participants were determined to have disease-related fatigue, 0.7% of participants showed ME/CFS that was not related to COVID-19, and 3.7% of participants were considered to have long COVID-19. Almost one-fourth of the study participants had a family history of ME/CFS. The current study demonstrated that the prevalence of ME/CFS is similar to slightly higher than reported in the literature.

Conclusion: The presence of a relationship between ME/CFS and COVID-19 has been supported by the results of our study. Follow-up of COVID-19 patients is strongly recommended to ensure proper management of ME/CFS symptoms.

Source: Muhaissen SA, Abu Libdeh A, ElKhatib Y, Alshayeb R, Jaara A, Bardaweel SK. Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) and COVID-19: is there a connection? Curr Med Res Opin. 2023 Jul 28:1-24. doi: 10.1080/03007995.2023.2242244. Epub ahead of print. PMID: 37501626. https://pubmed.ncbi.nlm.nih.gov/37501626/

One-Year Follow-up of Young People with ME/CFS Following Infectious Mononucleosis by Epstein-Barr Virus

Abstract:

Background: Infectious mononucleosis, caused by the Epstein-Barr Virus (EBV-IM), has been linked to the development of myalgic encephalomyelitis/chronic fatigue-syndrome (ME/CFS) in children, adolescents, and young adults. Our study presents the first cohort of young individuals in Germany who were diagnosed with ME/CFS following EBV-IM.

Methods: We conducted a one-year follow-up of 25 young people diagnosed with ME/CFS at our specialized tertiary outpatient service by clinical criteria requiring post-exertional malaise and with documented EBV-IM as the triggering event. Demographic information, laboratory findings, frequency and severity of symptoms, physical functioning, and health-related quality of life (HRQoL) were assessed at first visit as well as 6 and 12 months later at follow-up visits.

Results: The physical functioning and HRQoL of the cohort were significantly impaired, with young adults displaying more severe symptoms, as well as worsening of fatigue, physical and mental functioning, and HRQoL throughout the study, compared to adolescents. After one year, we found that 6/12 (54%) adolescents no longer met the diagnostic criteria for ME/CFS, indicating partial remission, while all young adults continued to fulfill the Canadian consensus criteria. Improvement in children was evident in physical functioning, symptom frequency and severity, and HRQoL, while young adults had little improvement. EBV serology and EBV DNA load did not correlate with distinct clinical features of ME/CFS, and clinical chemistry showed no evidence of inflammation. Remarkably, the median time from symptom onset to ME/CFS diagnosis was 13.8 (IQR: 9.1-34.9) months.

Conclusions: ME/CFS following EBV-IM in young people is a severely debilitating disease with diagnoses protracted longer than one year in many patients and only limited responses to conventional symptom-oriented medical care. Although younger children may have a better prognosis, their condition can fluctuate and significantly impact their HRQoL. Our data emphasize that biomarkers and effective therapeutic options are also urgently needed for this very young age group to better manage their medical condition and pave the way to recovery.

Source: Rafael Pricoco, Paulina Meidel, Tim Hofberger, Hannah Zietemann, Yvonne Mueller, Katharina Wiehler, Kaja Michel, Johannes Paulick, Ariane Leone, Matthias Haegele, Sandra Mayer-Huber, Katrin Gerrer, Kirstin Mittelstrass, Carmen Scheibenbogen, Herbert Renz-Polster, Lorenz Mihatsch, Uta Behrends. One-Year Follow-up of Young People with ME/CFS Following Infectious Mononucleosis by Epstein-Barr Virus. medRxiv 2023.07.24.23293082; doi: https://doi.org/10.1101/2023.07.24.23293082 https://www.medrxiv.org/content/10.1101/2023.07.24.23293082v1 (Full text available as PDF file)

Clinical phenotypes and quality of life to define post-COVID-19 syndrome: a cluster analysis of the multinational, prospective ORCHESTRA cohort

Summary:

Background: Lack of specific definitions of clinical characteristics, disease severity, and risk and preventive factors of post-COVID-19 syndrome (PCS) severely impacts research and discovery of new preventive and therapeutics drugs.

Methods: This prospective multicenter cohort study was conducted from February 2020 to June 2022 in 5 countries, enrolling SARS-CoV-2 out- and in-patients followed at 3-, 6-, and 12-month from diagnosis, with assessment of clinical and biochemical features, antibody (Ab) response, Variant of Concern (VoC), and physical and mental quality of life (QoL). Outcome of interest was identification of risk and protective factors of PCS by clinical phenotype, setting, severity of disease, treatment, and vaccination status. We used SF-36 questionnaire to assess evolution in QoL index during follow-up and unsupervised machine learning algorithms (principal component analysis, PCA) to explore symptom clusters. Severity of PCS was defined by clinical phenotype and QoL. We also used generalized linear models to analyse the impact of PCS on QoL and associated risk and preventive factors. CT registration number: NCT05097677.

Findings: Among 1796 patients enrolled, 1030 (57%) suffered from at least one symptom at 12-month. PCA identified 4 clinical phenotypes: chronic fatigue-like syndrome (CFs: fatigue, headache and memory loss, 757 patients, 42%), respiratory syndrome (REs: cough and dyspnoea, 502, 23%); chronic pain syndrome (CPs: arthralgia and myalgia, 399, 22%); and neurosensorial syndrome (NSs: alteration in taste and smell, 197, 11%). Determinants of clinical phenotypes were different (all comparisons p < 0.05): being female increased risk of CPs, NSs, and CFs; chronic pulmonary diseases of REs; neurological symptoms at SARS-CoV-2 diagnosis of REs, NSs, and CFs; oxygen therapy of CFs and REs; and gastrointestinal symptoms at SARS-CoV-2 diagnosis of CFs. Early treatment of SARS-CoV-2 infection with monoclonal Ab (all clinical phenotypes), corticosteroids therapy for mild/severe cases (NSs), and SARS-CoV-2 vaccination (CPs) were less likely to be associated to PCS (all comparisons p < 0.05). Highest reduction in QoL was detected in REs and CPs (43.57 and 43.86 vs 57.32 in PCS-negative controls, p < 0.001). Female sex (p < 0.001), gastrointestinal symptoms (p = 0.034) and renal complications (p = 0.002) during the acute infection were likely to increase risk of severe PCS (QoL <50). Vaccination and early treatment with monoclonal Ab reduced the risk of severe PCS (p = 0.01 and p = 0.03, respectively).

Interpretation: Our study provides new evidence suggesting that PCS can be classified by clinical phenotypes with different impact on QoL, underlying possible different pathogenic mechanisms. We identified factors associated to each clinical phenotype and to severe PCS. These results might help in designing pathogenesis studies and in selecting high-risk patients for inclusion in therapeutic and management clinical trials.

Funding: The study received funding from the Horizon 2020 ORCHESTRA project, grant 101016167; from the Netherlands Organisation for Health Research and Development (ZonMw), grant 10430012010023; from Inserm, REACTing (REsearch & ACtion emergING infectious diseases) consortium and the French Ministry of Health, grant PHRC 20-0424.

Source: Elisa Gentilotti, Anna Górska, Adriana Tami, Roy Gusinow, Massimo Mirandola, Jesús Rodríguez Baño, et al. Clinical phenotypes and quality of life to define post-COVID-19 syndrome: a cluster analysis of the multinational, prospective ORCHESTRA cohort. Lancet,  “eClinicalMedicine” https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(23)00284-5/fulltext (Full text)

Post-acute sequelae of COVID-19: understanding and addressing the burden of multisystem manifestations

Abstract:

Individuals with SARS-CoV-2 infection can develop symptoms that persist well beyond the acute phase of COVID-19 or emerge after the acute phase, lasting for weeks or months after the initial acute illness. The post-acute sequelae of COVID-19, which include physical, cognitive, and mental health impairments, are known collectively as long COVID or post-COVID-19 condition.

The substantial burden of this multisystem condition is felt at individual, health-care system, and socioeconomic levels, on an unprecedented scale. Survivors of COVID-19-related critical illness are at risk of the well known sequelae of acute respiratory distress syndrome, sepsis, and chronic critical illness, and these multidimensional morbidities might be difficult to differentiate from the specific effects of SARS-CoV-2 and COVID-19.

We provide an overview of the manifestations of post-COVID-19 condition after critical illness in adults. We explore the effects on various organ systems, describe potential pathophysiological mechanisms, and consider the challenges of providing clinical care and support for survivors of critical illness with multisystem manifestations.

Research is needed to reduce the incidence of post-acute sequelae of COVID-19-related critical illness and to optimise therapeutic and rehabilitative care and support for patients.

Source: Parotto M, Gyöngyösi M, Howe K, Myatra SN, Ranzani O, Shankar-Hari M, Herridge MS. Post-acute sequelae of COVID-19: understanding and addressing the burden of multisystem manifestations. Lancet Respir Med. 2023 Jul 17:S2213-2600(23)00239-4. doi: 10.1016/S2213-2600(23)00239-4. Epub ahead of print. PMID: 37475125. https://www.thelancet.com/journals/lanres/article/PIIS2213-2600(23)00239-4/fulltext (Full text)

Mitigating neurological, cognitive, and psychiatric sequelae of COVID-19-related critical illness

Abstract:

Despite advances in the treatment and mitigation of critical illness caused by infection with SARS-CoV-2, millions of survivors have a devastating, post-acute infection syndrome known as long COVID. A large proportion of patients with long COVID have nervous system dysfunction, which is also seen in the distinct but overlapping condition of post-intensive care syndrome (PICS), putting survivors of COVID-19-related critical illness at high risk of long-lasting morbidity affecting multiple organ systems and, as a result, engendering measurable deficits in quality of life and productivity.

In this Series paper, we discuss neurological, cognitive, and psychiatric sequelae in patients who have survived critical illness due to COVID-19. We review current knowledge of the epidemiology and pathophysiology of persistent neuropsychological impairments, and outline potential preventive strategies based on safe, evidence-based approaches to the management of pain, agitation, delirium, anticoagulation, and ventilator weaning during critical illness. We highlight priorities for current and future research, including possible therapeutic approaches, and offer considerations for health services to address the escalating health burden of long COVID.

Source: Pandharipande P, Williams Roberson S, Harrison FE, Wilson JE, Bastarache JA, Ely EW. Mitigating neurological, cognitive, and psychiatric sequelae of COVID-19-related critical illness. Lancet Respir Med. 2023 Jul 17:S2213-2600(23)00238-2. doi: 10.1016/S2213-2600(23)00238-2. Epub ahead of print. PMID: 37475124. https://www.thelancet.com/journals/lanres/article/PIIS2213-2600(23)00238-2/fulltext (Full text)

Using Data Science and a Health Equity Lens to Identify Long-COVID Sequelae Among Medically Underserved Populations

Abstract:

Understanding how post-acute COVID-19 syndrome (PACS or long COVID) manifests among underserved populations, who experienced a disproportionate burden of acute COVID-19, can help providers and policymakers better address this ongoing crisis. To identify clinical sequelae of long COVID among underserved populations treated in the primary care safety net, we conducted a causal impact analysis with electronic health records (EHR) to compare symptoms among community health center patients who tested positive (n=4,091) and negative (n=7,118) for acute COVID-19.

We found 18 sequelae with statistical significance and causal dependence among patients who had a visit after 60 days or more following acute COVID-19. These sequelae encompass most organ systems and include breathing abnormalities, malaise and fatigue, and headache. This study adds to current knowledge about how long COVID manifests in a large, underserved population.

Source: Nasir M, Cook N, Parras D, Mukherjee S, Miller G, Ferres JL, Chung-Bridges K. Using Data Science and a Health Equity Lens to Identify Long-COVID Sequelae Among Medically Underserved Populations. J Health Care Poor Underserved. 2023;34(2):521-534. doi: 10.1353/hpu.2023.0047. PMID: 37464515. https://pubmed.ncbi.nlm.nih.gov/37464515/

Multisystem inflammatory syndrome in children (MIS-C): Implications for long COVID

Abstract:

The COVID-19 pandemic caused by the coronavirus 2 of the severe acute respiratory syndrome (SARS-CoV-2) has significantly affected people around the world, leading to substantial morbidity and mortality. Although the pandemic has affected people of all ages, there is increasing evidence that children are less susceptible to SARS-CoV-2 infection and are more likely to experience milder symptoms than adults. However, children with COVID-19 can still develop serious complications, such as multisystem inflammatory syndrome in children (MIS-C).

This narrative review of the literature provides an overview of the epidemiology and immune pathology of SARS-CoV-2 infection and MIS-C in children. The review also examines the genetics of COVID-19 and MIS-C in children, including the genetic factors that can influence the susceptibility and severity of the diseases and their implications for personalized medicine and vaccination strategies.

By examining current evidence and insights from the literature, this review aims to contribute to the development of effective prevention and treatment strategies for COVID-19, MIS-C, and long COVID syndromes in children.

Source: Constantin T, Pék T, Horváth Z, Garan D, Szabó AJ. Multisystem inflammatory syndrome in children (MIS-C): Implications for long COVID. Inflammopharmacology. 2023 Jul 17. doi: 10.1007/s10787-023-01272-3. Epub ahead of print. PMID: 37460909. https://link.springer.com/article/10.1007/s10787-023-01272-3 (Full text)

Chronic inflammation, neutrophil activity, and autoreactivity splits long COVID

Abstract:

While immunologic correlates of COVID-19 have been widely reported, their associations with post-acute sequelae of COVID-19 (PASC) remain less clear. Due to the wide array of PASC presentations, understanding if specific disease features associate with discrete immune processes and therapeutic opportunities is important.

Here we profile patients in the recovery phase of COVID-19 via proteomics screening and machine learning to find signatures of ongoing antiviral B cell development, immune-mediated fibrosis, and markers of cell death in PASC patients but not in controls with uncomplicated recovery. Plasma and immune cell profiling further allow the stratification of PASC into inflammatory and non-inflammatory types.

Inflammatory PASC, identifiable through a refined set of 12 blood markers, displays evidence of ongoing neutrophil activity, B cell memory alterations, and building autoreactivity more than a year post COVID-19. Our work thus helps refine PASC categorization to aid in both therapeutic targeting and epidemiological investigation of PASC.

Source: Woodruff MC, Bonham KS, Anam FA, Walker TA, Faliti CE, Ishii Y, Kaminski CY, Ruunstrom MC, Cooper KR, Truong AD, Dixit AN, Han JE, Ramonell RP, Haddad NS, Rudolph ME, Yalavarthi S, Betin V, Natoli T, Navaz S, Jenks SA, Zuo Y, Knight JS, Khosroshahi A, Lee FE, Sanz I. Chronic inflammation, neutrophil activity, and autoreactivity splits long COVID. Nat Commun. 2023 Jul 14;14(1):4201. doi: 10.1038/s41467-023-40012-7. PMID: 37452024; PMCID: PMC10349085. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10349085/ (Full text)

Post-COVID cognitive dysfunction: current status and research recommendations for high risk population

Abstract:

Post-COVID cognitive dysfunction (PCCD) is a condition in which patients with a history of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, usually three months from the onset, exhibit subsequent cognitive impairment in various cognitive domains, and cannot be explained by an alternative diagnosis.

While our knowledge of the risk factors and management strategy of PCCD is still incomplete, it is necessary to integrate current epidemiology, diagnosis and treatment evidence, and form consensus criteria to better understand this disease to improve disease management. Identifying the risk factors and vulnerable population of PCCD and providing reliable strategies for effective prevention and management is urgently needed.

In this paper, we reviewed epidemiology, diagnostic markers, risk factors and available treatments on the disease, formed research recommendation framework for vulnerable population, under the background of post-COVID period.

Source: Quan M, Wang X, Gong M, Wang Q, Li Y, Jia J. Post-COVID cognitive dysfunction: current status and research recommendations for high risk population. Lancet Reg Health West Pac. 2023 Jul 5;38:100836. doi: 10.1016/j.lanwpc.2023.100836. PMID: 37457901; PMCID: PMC10344681. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10344681/ (Full text)