Immunological Mechanisms and Machine Learning Applications in Post-COVID-19 Syndrome: A Narrative Review.

ingentiumby ingentium

In Computing Literature.

Publication date: Jun 11, 2026

Post-COVID-19 syndrome (PCS), also referred to as post-acute sequelae of SARS-CoV-2 infection (PASC), represents a heterogeneous set of persistent clinical manifestations developing after acute infection. These conditions are associated with immune dysregulation, autonomic imbalance, impaired thymic function, and possible viral persistence. This study aims to systematically synthesise current evidence on the immunopathogenesis of PCS and to critically evaluate the application of artificial intelligence (AI) and machine learning (ML) approaches for its prediction and clinical stratification. A PRISMA 2020-informed systematic review was conducted using PubMed/MEDLINE, Scopus, Web of Science, elibrary. ru and Embase databases (January 2020-December 2025). Studies addressing immunopathological mechanisms and AI/ML applications in PCS were selected based on predefined eligibility criteria. Risk of bias in prediction studies was assessed using the PROBAST tool. Due to heterogeneity, a structured qualitative synthesis was performed. Current evidence indicates that PCS may result from sustained systemic inflammation, cytokine dysregulation, autoimmunity, and delayed restoration of T-cell homeostasis, including reduced thymic output of nacEFve T lymphocytes. Persistent thymic dysfunction may contribute to prolonged immune imbalance, increased susceptibility to secondary infections, and reactivation of latent viruses. AI/ML approaches-including gradient boosting, ensemble learning, deep neural networks, and natural language processing-have demonstrated promising performance across multimodal datasets. However, significant limitations were identified, including small sample sizes, overfitting, lack of external validation, and heterogeneity in outcome definitions. The integration of immunopathological insights with data-driven modelling highlights the potential of combined approaches for improving PCS risk stratification. However, current AI models remain insufficiently validated for clinical implementation. Future research should prioritise methodological standardisation, external validation, and incorporation of mechanistically informed biomarkers.

Open Access PDF

Concepts Keywords
December artificial intelligence
Immunopathogenesis autoimmunity
Models disease prediction
Viral long COVID
lymphocyte subsets
machine learning
neuroendocrine regulation
PRISMA
systematic review

Semantics

Type Source Name
disease MESH Post-COVID-19 Syndrome
disease MESH PCS
disease MESH infection
disease MESH inflammation
disease MESH secondary infections
drug DRUGBANK Flunarizine
disease MESH COVID 19
disease MESH Syndrome
disease MESH hypophysitis
disease MESH small fiber neuropathies
disease MESH arteritis
disease MESH atherogenesis
disease MESH adrenal insufficiency
drug DRUGBANK Indoleacetic acid
drug DRUGBANK Methionine
disease MESH Included
disease MESH ered
disease MESH chronic disease
disease MESH coronavirus infection
drug DRUGBANK Coenzyme M
disease MESH tic
disease MESH injury
disease MESH acute disease
disease MESH pathological processes
disease MESH cytokine storm
disease MESH shock
disease MESH metabolic syndrome
drug DRUGBANK Angiotensin II
pathway REACTOME Immune System
disease MESH lymphopenia
disease MESH acute respiratory distress syndrome
disease MESH convalescence
disease MESH pulmonary sarcoidosis
disease MESH granulomas
disease MESH systemic lupus erythematosus
pathway KEGG Systemic lupus erythematosus
disease MESH dis
disease MESH systemic sclerosis
disease MESH tar
disease MESH tachycardia
disease MESH orthostatic intolerance
disease MESH fatigue
drug DRUGBANK Rasagiline
drug DRUGBANK Omega-3 fatty acids
drug DRUGBANK Cardiolipin
disease MESH stroke
disease MESH pulmonary embolism
disease MESH arthralgia
disease MESH Neuroinflammation
disease MESH Cognitive impairment
disease MESH brain fog
disease MESH headaches
disease MESH rheumatoid arthritis
pathway KEGG Rheumatoid arthritis
disease MESH lung injury
disease MESH alopecia
disease MESH fac
disease MESH pulmonary fibrosis
drug DRUGBANK Phosphatidyl serine
drug DRUGBANK Prothrombin
disease MESH autoimmune diseases
disease MESH multiple sclerosis
disease MESH viral infection
disease MESH ger
disease MESH atrophy
drug DRUGBANK Isoxaflutole
pathway REACTOME Innate Immune System
pathway REACTOME Adaptive Immune System
disease MESH critically ill
drug DRUGBANK Oxytocin
disease MESH recurrent infections
disease MESH dysautonomia
disease MESH postural orthostatic tachycardia syndrome
disease MESH orthostatic hypotension
disease MESH MAE
drug DRUGBANK Oxygen
disease MESH CAM
disease MESH anosmia
disease MESH pain
disease MESH anxiety
disease MESH dys
disease MESH myalgia
disease MESH nausea
disease MESH fibrosis
drug DRUGBANK Ranitidine
disease MESH pneumonia
disease MESH char
drug DRUGBANK Trestolone
disease MESH Allergy
disease MESH Fibromyalgia
disease MESH Joint Hypermobility
disease MESH Heart Tumors
disease MESH Myalgic Encephalomyelitis
disease MESH Papilloma
disease MESH mental disorders
disease MESH Arthritis
drug DRUGBANK L-Arginine
drug DRUGBANK Gold
disease MESH sarcoidosis
disease MESH Heart Failure
drug DRUGBANK Creatinine
disease MESH respiratory infections
drug DRUGBANK Sulfasalazine
drug DRUGBANK Efavirenz
drug DRUGBANK (S)-Des-Me-Ampa
disease MESH Connective Tissue Disease
disease MESH rheumatic diseases
drug DRUGBANK Hexachlorophene
disease MESH Park
disease MESH immune thrombocytopenia
disease MESH Paralysis
pathway REACTOME Influenza Infection
disease MESH thyroiditis
disease MESH Death
drug DRUGBANK Guanosine
drug DRUGBANK Vorinostat
disease MESH Idiopathic pulmonary fibrosis
disease MESH myocarditis

Original Article

(Visited 3 times, 1 visits today)

Leave a Comment

Your email address will not be published. Required fields are marked *