A test of the adaptive network explanation of functional disorders using a machine learning analysis of symptoms

This study investigates the classification and etiology of functional disorders such as irritable bowel syndrome (IBS), fibromyalgia syndrome (FMS), and chronic fatigue syndrome (CFS). We examine two network models—the symptom network and the adaptive network—to explain symptom specificity and covariation. The adaptive network model, which posits that a network of biological mechanisms exhibits emergent properties and adaptation, uniquely accounts for the covariation of somatic symptoms in functional disorders. We conducted an internet survey with 1,751 participants diagnosed with IBS, FMS, or CFS, who completed a 61-item symptom questionnaire. Machine learning analysis identified eleven symptom clusters, revealing that differences between the disorder groups diminished as overall symptom frequency increased. Additionally, the strength of connections between symptom clusters varied based on symptom frequency and the presence of single versus multiple diagnoses. These findings suggest that functional disorder pathology involves increased activity and causal connections among various symptom-causing mechanisms, supporting the idea that the body can undergo complex adaptations leading to maladaptive changes in functional disorders.

Biosystems