Brain structure, cognition, and brain age in schizophrenia, bipolar disorder, and healthy controls

Shahab, Saba; Mulsant, Benoit H.; Lévesque, Mélissa L.; Calarco, Navona; Nazeri, Arash; Wheeler, Anne L.; Foussias, George; Rajji, Tarek K.; Voineskos, Aristotle N.

doi:10.1038/s41386-018-0298-z

Cited by 126 publications

(133 citation statements)

References 56 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…These findings are aligned with the range of the brainPAD scores in patients with schizophrenia reported in previous studies (range = 2.6-8 years). 16,[18][19][20][21] However, our finding underscore the importance of algorithm selection given that variation in brainPAD was observed despite all analyses being undertaken on the same dataset.…”

Section: Discussionmentioning

confidence: 62%

“…17 Five further brain structural studies have focused on estimating the years of brain-age acceleration in schizophrenia using various machine learning algorithms. 16,[18][19][20][21] Koutsouleris and colleagues used a support vector regression (SVR) algorithm trained on data from 800 healthy individuals, and found that patients with schizophrenia (n=141) had a mean brainPAD of 5.5 years. 18 Schnack and colleagues also used SVR trained on a sample of 386 healthy individuals, and showed that discovery (n=341) and validation sample (n=60) of patients with schizophrenia had a mean brainPAD of 3.8 years and 5.6 years, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…20 Using random forest regression trained on data from 50 healthy individuals, Shahab and colleagues showed that patients with schizophrenia (n=81) had a mean brainPAD of 7.8 years. 21 Other regression algorithms commonly used to estimate brain-age in neuropsychiatric conditions include ordinary least squares (OLS) regression, 22,23 least absolute shrinkage and selection operator regression (Lasso), 24,25 ridge regression, 26,27 and elastic-net regression. 28 At present, it is unclear whether the performance of these machine learning approaches is comparable when estimating brainPAD.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

Lee

Antoniades

Schnack

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundSchizophrenia has been associated with lifelong deviations in the normative trajectories of brain structure. These deviations can be captured using the brain-predicted age difference (brainPAD), which is the difference between the biological age of an individual’s brain, as inferred from neuroimaging data, and their chronological age. Various machine learning algorithms are currently used for this purpose but their comparative performance has yet to be systematically evaluated.MethodsSix linear regression algorithms, ordinary least squares (OLS) regression, ridge regression, least absolute shrinkage and selection operator (Lasso) regression, elastic-net regression, linear support vector regression (SVR), and relevance vector regression (RVR), were applied to brain structural data acquired on the same 3T scanner using identical sequences from patients with schizophrenia (n=90) and healthy individuals (n=200). The performance of each algorithm was quantified by the mean absolute error (MAE) and the correlation (R) between predicted brain-age and chronological age. The inter-algorithm similarity in predicted brain-age, brain regional regression weights and brainPAD were compared using correlation analyses and hierarchical clustering.ResultsIn patients with schizophrenia, ridge regression, Lasso regression, elastic-net regression, and RVR performed very similarly and showed a high degree of correlation in predicted brain-age (R>0.94) and brain regional regression weights (R>0.66). By contrast, OLS regression, which was the only algorithm without a penalty term, performed markedly worse and showed a lower similarity with the other algorithms. The mean brainPAD was higher in patients than in healthy individuals but varied by algorithm from 3.8 to 5.2 years although all analyses were performed on the same dataset.ConclusionsLinear machine learning algorithms, with the exception of OLS regression, have comparable performance for age prediction on the basis of a combination of cortical and subcortical structural measures. However, algorithm choice introduced variation in brainPAD estimation, and therefore represents an important source of inter-study variability.

show abstract

Section: Discussionmentioning

confidence: 62%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

Lee

Antoniades

Schnack

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…RewP magnitude shows a negative association with age among HC (9), and a depression-focused meta-analysis found that RewP blunting was most pronounced in younger depressed samples (42). Beyond reward processing, growing evidence supports hypotheses of accelerated brain aging in SZ (43)(44)(45)(46)(47), particularly early in the illness course (44,46), which may be due to abnormal brain maturation (48).…”

Section: Introductionmentioning

confidence: 98%

Reward processing electrophysiology in schizophrenia: Effects of age and illness phase

Abram

Roach

Holroyd

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Reward processing abnormalities may underlie characteristic pleasure and motivational impairments in schizophrenia. Some neural measures of reward processing show strong age-related modulation, highlighting the importance of considering age effects on reward sensitivity. We compared event-related potentials (ERPs) reflecting reward anticipation (stimulus-preceding negativity, SPN) and evaluation (reward positivity, RewP; late-positive potential, LPP) across individuals with schizophrenia (SZ) and healthy controls (HC), with an emphasis on examining effects of chronological age, brain age (i.e., predicted age based on neurobiological measures), and illness phase.Methods: Subjects underwent EEG while completing a slot-machine task for which rewards were not dependent on performance accuracy, speed, or other preparatory demands. Slot-machine task EEG responses were compared between 54 SZ and 54 HC individuals, ages 19 to 65. Reward-related ERPs were analyzed with respect to chronological age, categorically-defined illness phase (early; ESZ versus chronic schizophrenia; CSZ), and were used to model brain age relative to chronological age.Results: Illness phase-focused analyses indicated there were no group differences in average SPN or RewP amplitudes. However, a group x reward outcome interaction revealed that ESZ differed from HC in later outcome processing, reflected by greater LPP responses following loss versus reward (a reversal of the HC pattern). While brain age estimates did not differ among groups, depressive symptoms in SZ were associated with older brain age estimates while controlling for negative symptoms.Conclusions: ESZ and CSZ did not differ from HC in reward anticipation or early outcome processing during a cognitively undemanding reward task, highlighting areas of preserved functioning. However, ESZ showed altered later reward outcome evaluation, pointing to selective reward deficits during the early illness phase of schizophrenia. Further, an association between ERP-derived brain age and depressive symptoms in SZ extends prior findings linking depression with reward-related ERP blunting. Taken together, both illness phase and age may impact reward processing in SZ, and brain aging may offer a promising, novel marker of reward dysfunction that warrants further study.

show abstract

“…SZ has the highest prevalence of all mental illnesses and is very difficult to treat. Over the last few decades, many neuroimaging studies have demonstrated that schizophrenia is a disorder involving widespread abnormalities in the brain structure [1][2][3][4][5]. However, the specific mechanisms involved in producing these structural deficits remain incompletely understood.…”

Section: Introductionmentioning

confidence: 99%

Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Chen

Yan

Wang

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Utilizing neuroimaging and machine learning (ML) to differentiate schizophrenia (SZ) patients from normal controls (NCs) and for detecting abnormal brain regions in schizophrenia has several benefits and can provide a reference for the clinical diagnosis of schizophrenia. In this study, structural magnetic resonance images (sMRIs) from SZ patients and NCs were used for discriminative analysis. is study proposed an ML framework based on coarse-to-fine feature selection. e proposed framework used two-sample t-tests to extract the differences between groups first, then further eliminated the nonrelevant and redundant features with recursive feature elimination (RFE), and finally utilized the support vector machine (SVM) to learn the decision models with selected gray matter (GM) and white matter (WM) features. Previous studies have tended to report differences at the group level instead of at the individual level and cannot be widely applied. e method proposed in this study extends the diagnosis to the individual level and has a higher recognition rate than previous methods. e experimental results of this study demonstrate that the proposed framework distinguishes SZ patients from NCs, with the highest classification accuracy reaching over 85%. e identified biomarkers are also consistent with previous literature findings. As a universal method, the proposed framework can be extended to diagnose other diseases.

show abstract

Brain structure, cognition, and brain age in schizophrenia, bipolar disorder, and healthy controls

Cited by 126 publications

References 56 publications

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

Reward processing electrophysiology in schizophrenia: Effects of age and illness phase

Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Contact Info

Product

Resources

About