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

Abstract

The classification and etiology of functional disorders is controversial. Evidence supports both psychological and biological (disease) models that show, respectively, that functional disorders should be classified as one (bodily distress syndrome) and many (e.g., irritable bowel syndrome (IBS), fibromyalgia syndrome (FMS), and chronic fatigue syndrome (CFS)). Two network models (symptom network and adaptive network) can explain the specificity and covariation of symptomatology, but only the adaptive network model can explain the covariation of the somatic symptoms of functional disorders. The adaptive network model is based on the premise that a network of biological mechanisms has emergent properties and can exhibit adaptation. The purpose of this study was to test the predictions that symptom similarity increases with pathology and that network connection strengths vary with pathology, as this would be consistent with the notion that functional disorder pathology arises from network adaptation. We conducted a symptom internet survey followed by machine learning analysis. Participants were 1751 people reporting IBS, FMS or CFS diagnosis who completed a 61-item symptom questionnaire. Eleven symptom clusters were identified. Differences in symptom clusters between IBS, FMS and CFS groups decreased as overall symptom frequency increased. The strength of outgoing connections between clusters varied as a function of symptom frequency and single versus multiple diagnoses. The findings suggest that the pathology of functional disorders involves an increase in the activity and causal connections between several symptom causing mechanisms. The data provide support for the proposal that the body is capable of complex adaptation and that functional disorders result when rules that normally improve adaptation create maladaptive change.

Evidence for similarity in symptoms and mechanism: The extra‐pulmonary symptoms of severe asthma and the polysymptomatic presentation of fibromyalgia

“…Network theory suggests that similarity between groups should increase with severity because increased severity is associated with increased pathology over the whole network. Therefore symptom patterns within different diagnostic groups should converge as severity increases, consistent with evidence elsewhere that people diagnosed with IBS or CFS become more similar to the more severe group of FMS as the frequency of IBS and CFS symptoms increases . We found that people reporting a diagnosis of FMS report the most frequent symptoms compared with IBS and CFS (see Table ).…”

“…In a network of mutually activating nodes, increase in one part of the network activates increases activity across the whole network, such that differentiation between the original activating site and elsewhere becomes lost as severity increases. This prediction has been confirmed using a machine learning form of analysis with the additional finding that the connection strengths between the outgoing connections also increased with severity, showing that the underlying network structure (and therefore adaptation) varies with severity …”

“…The questionnaire for assessing extra‐pulmonary symptoms in asthma was selected so as to be able to provide a comparison with an existing data set obtained from a separate study . The questionnaire was based on an established general population symptom questionnaire but with items added that are indicative of functional disorders such as FMS and CFS (See online Appendix 1 for more details).…”

“…This prediction has been confirmed using a machine learning form of analysis with the additional finding that the connection strengths between the outgoing connections also increased with severity, showing that the underlying network structure (and therefore adaptation) varies with severity. 29 If the polysymptomatic presentation of IBS, FMS, and CFS is due to a causal network of biological, symptom causing mechanisms, then it is plausible that the asthma causing mechanisms as well as systemic effects of treatment could be causally linked to this network to a greater or lesser extent. If the extra-pulmonary symptoms of asthma have the same network aetiology as IBS, FMS and CFS then the symptomatology should exhibit the same properties.…”

“…Previous research shows that as symptom frequency increases, the pattern of symptoms (ie, relative frequency of symptoms) in functional disorder groups become more similar to those with fibromyalgia. 29 Therefore, the extra-pulmonary symptoms of people with severe asthma should approximate more to the symptom pattern of fibromyalgia as the number of extra-pulmonary symptoms increases.…”