Reconciling Dimensional and Categorical Models of Autism Heterogeneity: a Brain Connectomics &amp; Behavioral Study

Tang, Siyi; Sun, Nanbo; Floris, Dorothea L.; Zhang, Xiuming; Martino, Adriana Di; Yeo, B.T. Thomas

doi:10.1101/692772

Cited by 21 publications

(21 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding is reminiscent of previous reports, where even hard clustering solutions often sorted patients into broad disease severity categories [20,24,48,49,79]. Indeed, recent studies have taken an explicitly dimensional approach, attempting to find low-dimensional projections of clinical-behavioral and neuroimaging data [39,41,71,78]. In clinical practice, methods like SNF situate individual patients in a biologically-comprehensive feature space that can then guide more objective clinical decisions about diagnosis and prognosis.…”

Section: Biotypes or Dimensions?supporting

confidence: 56%

Multimodal phenotypic axes of Parkinson’s disease

Markello¹,

Shafiei²,

Tremblay³

et al. 2020

Preprint

View full text Add to dashboard Cite

Individuals with Parkinson's disease present with a complex clinical phenotype, encompassing sleep, motor, cognitive, and affective disturbances. However, characterizations of PD are typically made for the "average" patient, ignoring patient heterogeneity and obscuring important individual differences. Modern large-scale data sharing efforts provide a unique opportunity to precisely investigate individual patient characteristics, but there exists no analytic framework for comprehensively integrating data modalities. Here we apply an unsupervised learning method-similarity network fusion-to objectively integrate MRI morphometry, dopamine active transporter binding, protein assays, and clinical measurements from n = 186 individuals with de novo Parkinson's disease from the Parkinson's Progression Markers Initiative. We show that multimodal fusion captures inter-dependencies among data modalities that would otherwise be overlooked by field standard techniques like data concatenation. We then examine how patient subgroups derived from fused data map onto clinical phenotypes, and how neuroimaging data is critical to this delineation. Finally, we identify a compact set of phenotypic axes that span the patient population, demonstrating that this continuous, low-dimensional projection of individual patients presents a more parsimonious representation of heterogeneity in the sample compared to discrete biotypes. Altogether, these findings showcase the potential of similarity network fusion for combining multimodal data in heterogeneous patient populations.

show abstract

Section: Biotypes or Dimensions?supporting

confidence: 56%

Multimodal phenotypic axes of Parkinson’s disease

Markello¹,

Shafiei²,

Tremblay³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This finding is reminiscent of previous reports, where even hard clustering solutions often sorted patients into broad disease severity categories 5,[41][42][43][44] . Indeed, recent studies have taken an explicitly dimensional approach, attempting to find low-dimensional projections of clinical-behavioral and neuroimaging data 45,[52][53][54] . In clinical practice, methods like SNF situate individual patients in a biologically-comprehensive feature space that can then guide more objective clinical decisions about diagnosis and prognosis.…”

Section: Discussionmentioning

confidence: 99%

Multimodal phenotypic axes of Parkinson’s disease

Markello

Shafiei

Tremblay

et al. 2021

npj Parkinsons Dis.

View full text Add to dashboard Cite

Individuals with Parkinson’s disease present with a complex clinical phenotype, encompassing sleep, motor, cognitive, and affective disturbances. However, characterizations of PD are typically made for the “average” patient, ignoring patient heterogeneity and obscuring important individual differences. Modern large-scale data sharing efforts provide a unique opportunity to precisely investigate individual patient characteristics, but there exists no analytic framework for comprehensively integrating data modalities. Here we apply an unsupervised learning method—similarity network fusion—to objectively integrate MRI morphometry, dopamine active transporter binding, protein assays, and clinical measurements from n = 186 individuals with de novo Parkinson’s disease from the Parkinson’s Progression Markers Initiative. We show that multimodal fusion captures inter-dependencies among data modalities that would otherwise be overlooked by field standard techniques like data concatenation. We then examine how patient subgroups derived from the fused data map onto clinical phenotypes, and how neuroimaging data is critical to this delineation. Finally, we identify a compact set of phenotypic axes that span the patient population, demonstrating that this continuous, low-dimensional projection of individual patients presents a more parsimonious representation of heterogeneity in the sample compared to discrete biotypes. Altogether, these findings showcase the potential of similarity network fusion for combining multimodal data in heterogeneous patient populations.

show abstract

“…The present ASD neurosubtyping literature is in its infancy with a total of 12 studies in humans, 92% published since 2018 (60)(61)(62)(63)(64)(65)(66)(67)(68)(69)(70)(71). Studies vary in methodology (FIGURE 1, TABLE 1).…”

Section: Data-driven Asd Neurosubtypingmentioning

confidence: 99%

“…Others indirectly validate the subtype solutions by assessing their stability, either across independent subtyping algorithms or via bootstrapping. So far, only two ASD neurosubtyping studies have assessed the convergence of findings from different algorithms(61,71) and four have used bootstrapping(60,65,66,71), all reported within-study stability.…”

mentioning

confidence: 99%