Differentiating weight-restored anorexia nervosa and body dysmorphic disorder using neuroimaging and psychometric markers

Abstract

Anorexia nervosa (AN) and body dysmorphic disorder (BDD) are potentially life-threatening conditions whose partially overlapping phenomenology—distorted perception of appearance, obsessions/compulsions, and limited insight—can make diagnostic distinction difficult in some cases. Accurate diagnosis is crucial, as the effective treatments for AN and BDD differ. To improve diagnostic accuracy and clarify the contributions of each of the multiple underlying factors, we developed a two-stage machine learning model that uses multimodal, neurobiology-based, and symptom-based quantitative data as features: task-based functional magnetic resonance imaging data using body visual stimuli, graph theory metrics of white matter connectivity from diffusor tensor imaging, and anxiety, depression, and insight psychometric scores. In a sample of unmedicated adults with BDD (n = 29), unmedicated adults with weight-restored AN (n = 24), and healthy controls (n = 31), the resulting model labeled individuals with an accuracy of 76%, significantly better than the chance accuracy of 35% ( ). In the multivariate model, reduced white matter global efficiency and better insight were associated more with AN than with BDD. These results improve our understanding of the relative contributions of the neurobiological characteristics and symptoms of these disorders. Moreover, this approach has the potential to aid clinicians in diagnosis, thereby leading to more tailored therapy.

Distinguishing between depression in bipolar disorder and unipolar depression using magnetic resonance imaging: a systematic review

“…Finally, to our knowledge, although investigators have separately tested neurofunctional or psychometric classifiers (e.g., self‐reported measures that predict the onset of bipolar disorder in adolescents 136,137 ), no studies have yet combined these classifiers in bipolar depression. Combining psychometric and neurofunctional classifiers in other mental health conditions has been shown to increase the accuracy of classification 138‐140 . It would also be useful to investigate how neurofunctional classifiers improve diagnostic accuracy in addition to standard clinical diagnostic metrics 4,132,141 …”

“…Combining psychometric and neurofunctional classifiers in other mental health conditions has been shown to increase the accuracy of classification. [138][139][140] It would also be useful to investigate how neurofunctional classifiers improve diagnostic accuracy in addition to standard clinical diagnostic metrics. 4,132,141 Studies included in this review applied well-validated and standardized mood disorder diagnostic measures, but clinical measures are ultimately subjective.…”

Brain networks in eating disorders: a systematic review of graph theory studies

“…In HC, this community comprised the right caudate, right accumbens, right ACC, right posterior cingulate, and right pallidum, while in AN-wr it included the right caudate, right accumbens, right rostral ACC, right medial and lateral OFC, and right frontal pole (the BDD-a module shared some elements with each of other groups, see Table 2 for details). Based on these results, the second study [ 26 ] implemented a two-step machine learning model using DTI-based NPL as a feature in conjunction with other measures (i.e. task-related FC, anxiety, depression, and insight).…”

Exploring the impact of multisensory integration and episodic memory with machine learning: a proof-of-concept study in anorexia nervosa

“…For instance, (Serino et al, 2016) and colleagues showed that with immersive virtual reality is possible to modify the body memory in AN. Again, the combined use of neuroscientific measures and innovative methods like ML can be useful for diagnosis and prognosis of this complex psychiatric disorder (Haynos et al, 2020;Lavagnino et al, 2018;Vaughn et al, 2019).…”