Bipolar Disorders

Janiri, Delfina; Ambrosi, Elisa; Danese, Emanuela; Panaccione, Isabella; Simonetti, Alessio; Sani, Gabriele

doi:10.1007/978-1-4939-7647-8_20

Cited by 3 publications

(2 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The largest study of this association to-date compared 1710 individuals with BD to 2594 healthy controls (HC) and found that, amongst the limbic and diencephalic structures evaluated, lower total hippocampal volume was the finding with the largest effect size (Hibar et al, 2016). BD-related effects have been reported for all hippocampal subfields (Cao et al, 2017;Elvsåshagen et al, 2013;Haukvik et al, 2015b;Janiri et al, 2018a;Mathew et al, 2014), with the most pronounced effects reported to-date being on the cornu ammonis (CA) (Haukvik et al, 2015a;Mathew et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Hippocampal subfield volumes and childhood trauma in bipolar disorders

Janiri

Sani

Rossi

et al. 2019

Journal of Affective Disorders

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Hippocampal subfield volumes and childhood trauma in bipolar disorders

Janiri

Sani

Rossi

et al. 2019

Journal of Affective Disorders

Self Cite

View full text Add to dashboard Cite

“…Reduction in hippocampal volume is a consistent correlate of BD and has been hypothesized as a possible biological marker for these disorders . The largest study to date, comparing 1710 patients with BD to 2594 healthy individuals, found that, amongst all subcortical regions, reduced hippocampal volume was the finding with the largest effect size (Cohen's d = −0.23) .…”

Section: Introductionmentioning

confidence: 99%

Predominant polarity and hippocampal subfield volumes in Bipolar disorders

et al. 2019

Self Cite

View full text Add to dashboard Cite

Objectives Predominant polarity (PP) is a proposed course specifier for bipolar disorders (BD) based on patient lifetime mood episodes. Hippocampal subfield volumetric changes have been proposed as a neurobiological marker for BD and could be influenced by mood episodes. Our study aimed to test the hypothesis that patients with BD differ in hippocampal subfield volumes according to their PP. Methods We assessed 172 outpatients, diagnosed with BD according to DSM‐IV‐TR criteria, and 150 healthy control (HC) participants. High‐resolution magnetic resonance imaging was performed on all subjects and volumes of all hippocampal subfields were measured using FreeSurfer. Results Patients with depressive PP (BD‐DP) and with uncertain PP (BD‐UP) but not with manic/hypomanic PP (BD‐MP) showed a global reduction on all hippocampal subfield volumes with respect to HCs. When directly compared, BD‐DP presented with smaller bilateral presubiculum/subiculum volumes than BD‐MP. Conclusions Results support the potential utility of PP not only as a clinical but also as a neurobiological specifier of BD.

show abstract

predict bipolar disorder by using graph theory, cortical volume, and machine learning

Ruhi,

Hassani-Abharian

2024

Preprint

View full text Add to dashboard Cite

Bipolar disorder diagnosis(BPD) is associated with great imprecision and uncertainty and requires a reliable diagnostic measure. Recently, machine learning techniques, named support vector machine (SVM), random forest, and K-nearest neighbor (KNN), have been combined with neuroimaging methods to help diagnose BPD. This study aimed to predict BPD using SVM, RF, and KNN classifier models based on graph theory values of the whole brain's global function and gray matter volume using the data integration method. Methodology: In this study, we used data from 49 patients with bipolar disorder and 49 healthy. In this method, we used the global efficiency scale and brain gray matter volume for integration into the concatenation method. Results: For the combined dataset, the SVM model had an accuracy of 0.85, a sensitivity of 0.92, and a specificity of 0.78, The random forest model had an accuracy of 0.89, a sensitivity of 0.88, and a specificity of 0.91; the KNN model had an accuracy of 0.82, a sensitivity of 0.84, and a specificity of 0.80. In the global-efficiency dataset, the SVM model had an accuracy of 0.85, a sensitivity of 0.82, and a specificity of 0.87; The random forest model had an accuracy of 0.82 a sensitivity of 0.78, and a specificity of 0.86; The KNN model has an achieved of 0.78, a sensitivity of 0.79, and a specificity of 0.81. In the gray matter volume dataset, all three models (SVM, Random Forest, and KNN) performed similarly, with accuracies, sensitivities, and specificities ranging from 0.51 to 0.52. The results show that the combined gray matter and global-efficiency data group yielded the highest accuracy for all three models. The random forest model consistently performed well on all datasets and demonstrated robustness when handling brain imaging data. However, note that the performance of the models varies depending on the data type used. Therefore, model selection should be tailored to the specific characteristics of the given dataset.

show abstract

Bipolar Disorders

Cited by 3 publications

References 104 publications

Hippocampal subfield volumes and childhood trauma in bipolar disorders

Hippocampal subfield volumes and childhood trauma in bipolar disorders

Predominant polarity and hippocampal subfield volumes in Bipolar disorders

predict bipolar disorder by using graph theory, cortical volume, and machine learning

Contact Info

Product

Resources

About