Machine Learning Models Identify Multimodal Measurements Highly Predictive of Transdiagnostic Symptom Severity for Mood, Anhedonia, and Anxiety.
Adult
Affect
/ physiology
Anhedonia
/ physiology
Anxiety
/ diagnosis
Attention Deficit Disorder with Hyperactivity
/ diagnosis
Bipolar Disorder
/ diagnosis
Brain
/ diagnostic imaging
Brain Mapping
/ methods
Female
Humans
Machine Learning
Magnetic Resonance Imaging
Male
Mental Disorders
/ diagnosis
Middle Aged
Schizophrenia
/ diagnosis
Severity of Illness Index
Young Adult
CNS
Depression
Elastic net
LASSO
Random forest
Regression
Journal
Biological psychiatry. Cognitive neuroscience and neuroimaging
ISSN: 2451-9030
Titre abrégé: Biol Psychiatry Cogn Neurosci Neuroimaging
Pays: United States
ID NLM: 101671285
Informations de publication
Date de publication:
01 2020
01 2020
Historique:
received:
17
12
2018
revised:
01
07
2019
accepted:
02
07
2019
pubmed:
24
9
2019
medline:
15
12
2020
entrez:
24
9
2019
Statut:
ppublish
Résumé
Insights from neuroimaging-based biomarker research have not yet translated into clinical practice. This translational gap may stem from a focus on diagnostic classification, rather than on prediction of transdiagnostic psychiatric symptom severity. Currently, no transdiagnostic, multimodal predictive models of symptom severity that include neurobiological characteristics have emerged. We built predictive models of 3 common symptoms in psychiatric disorders (dysregulated mood, anhedonia, and anxiety) from the Consortium for Neuropsychiatric Phenomics dataset (N = 272), which includes clinical scale assessments, resting-state functional magnetic resonance imaging (MRI), and structural MRI measures from patients with schizophrenia, bipolar disorder, and attention-deficit/hyperactivity disorder and healthy control subjects. We used an efficient, data-driven feature selection approach to identify the most predictive features from these high-dimensional data. This approach optimized modeling and explained 65% to 90% of variance across the 3 symptom domains, compared to 22% without using the feature selection approach. The top performing multimodal models retained a high level of interpretability that enabled several clinical and scientific insights. First, to our surprise, structural features did not substantially contribute to the predictive strength of these models. Second, the Temperament and Character Inventory scale emerged as a highly important predictor of symptom variation across diagnoses. Third, predictive resting-state functional MRI connectivity features were widely distributed across many intrinsic resting-state networks. Combining resting-state functional MRI with select questions from clinical scales enabled high prediction of symptom severity across diagnostically distinct patient groups and revealed that connectivity measures beyond a few intrinsic resting-state networks may carry relevant information for symptom severity.
Sections du résumé
BACKGROUND
Insights from neuroimaging-based biomarker research have not yet translated into clinical practice. This translational gap may stem from a focus on diagnostic classification, rather than on prediction of transdiagnostic psychiatric symptom severity. Currently, no transdiagnostic, multimodal predictive models of symptom severity that include neurobiological characteristics have emerged.
METHODS
We built predictive models of 3 common symptoms in psychiatric disorders (dysregulated mood, anhedonia, and anxiety) from the Consortium for Neuropsychiatric Phenomics dataset (N = 272), which includes clinical scale assessments, resting-state functional magnetic resonance imaging (MRI), and structural MRI measures from patients with schizophrenia, bipolar disorder, and attention-deficit/hyperactivity disorder and healthy control subjects. We used an efficient, data-driven feature selection approach to identify the most predictive features from these high-dimensional data.
RESULTS
This approach optimized modeling and explained 65% to 90% of variance across the 3 symptom domains, compared to 22% without using the feature selection approach. The top performing multimodal models retained a high level of interpretability that enabled several clinical and scientific insights. First, to our surprise, structural features did not substantially contribute to the predictive strength of these models. Second, the Temperament and Character Inventory scale emerged as a highly important predictor of symptom variation across diagnoses. Third, predictive resting-state functional MRI connectivity features were widely distributed across many intrinsic resting-state networks.
CONCLUSIONS
Combining resting-state functional MRI with select questions from clinical scales enabled high prediction of symptom severity across diagnostically distinct patient groups and revealed that connectivity measures beyond a few intrinsic resting-state networks may carry relevant information for symptom severity.
Identifiants
pubmed: 31543457
pii: S2451-9022(19)30200-9
doi: 10.1016/j.bpsc.2019.07.007
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
56-67Informations de copyright
Copyright © 2019 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.