Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

Abstract Background: Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD.Methods: In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed.Results: After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5-95.3%), sensitivity of 86.4% (95%CI: 64.0-96.4%), and specificity of 88.9% (95%CI: 63.9-98.0%) in the test data (p=0.0022). Conclusions: A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Download Full-text

Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

10.21203/rs.3.rs-15480/v3 ◽

2020 ◽

Author(s):

Hao Li ◽

Liqian Cui ◽

Liping Cao ◽

Yizhi Zhang ◽

Yueheng Liu ◽

...

Keyword(s):

Machine Learning ◽

Bipolar Disorder ◽

Functional Mri ◽

Added Value ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Accurate Identification ◽

Learning Techniques ◽

Svm Model

Abstract Background: Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD.Methods: In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed.Results: After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5-95.3%), sensitivity of 86.4% (95%CI: 64.0-96.4%), and specificity of 88.9% (95%CI: 63.9-98.0%) in the test data (p=0.0022). Limitations: The sample size was small, and we were unable to eliminate the potential effects of medications. Conclusions: A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Download Full-text

Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

BMC Psychiatry ◽

10.1186/s12888-020-02886-5 ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Hao Li ◽

Liqian Cui ◽

Liping Cao ◽

Yizhi Zhang ◽

Yueheng Liu ◽

...

Keyword(s):

Machine Learning ◽

Bipolar Disorder ◽

Functional Mri ◽

Added Value ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Accurate Identification ◽

Learning Techniques ◽

Svm Model

Abstract Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD. Methods In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed. Results After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5–95.3%), sensitivity of 86.4% (95%CI: 64.0–96.4%), and specificity of 88.9% (95%CI: 63.9–98.0%) in the test data (p = 0.0022). Conclusions A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Download Full-text

Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

10.21203/rs.3.rs-15480/v2 ◽

2020 ◽

Author(s):

Hao Li ◽

Liqian Cui ◽

Liping Cao ◽

Yizhi Zhang ◽

Yueheng Liu ◽

...

Keyword(s):

Machine Learning ◽

Bipolar Disorder ◽

Functional Mri ◽

Added Value ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Accurate Identification ◽

Learning Techniques ◽

Svm Model

Abstract Background: Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed for years. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD.Methods: In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, voxel-based morphometry (VBM), and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed.Results: After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5%, sensitivity of 86.4%, and specificity of 88.9% in the test data (p=0.0022).Conclusions: A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Download Full-text

Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques

10.21203/rs.3.rs-15480/v1 ◽

2020 ◽

Author(s):

Hao Li ◽

Liqian Cui ◽

Liping Cao ◽

Yizhi Zhang ◽

Yueheng Liu ◽

...

Keyword(s):

Machine Learning ◽

Bipolar Disorder ◽

Functional Mri ◽

Added Value ◽

Classification Model ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Learning Techniques ◽

Svm Model

Abstract Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD. Methods In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, voxel-based morphometry (VBM), and ReHo analyses were performed. The grey matter volumes or ReHo values of the clusters showed significant differences as discriminant features in the SVM classification model. Based on extracted features, the SVM model was established, and discriminant analysis was performed. Results After using the two-sample t-test with multiple comparisons, 12 clusters with significant differences were extracted from the data. Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 90% in the test data (p=0.0014). Limitations The sample size was small, and we were unable to eliminate the potential effects of medications. Conclusions A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Download Full-text

Review on Machine Learning Techniques to predict Bipolar Disorder

10.36227/techrxiv.14346050 ◽

2021 ◽

Author(s):

Nisha Agnihotri

Keyword(s):

Mental Health ◽

Machine Learning ◽

Bipolar Disorder ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

K Nearest Neighbor ◽

Brain Disorder ◽

Research Papers ◽

Learning Techniques

<i>Bipolar disorder, a complex disorder in brain has affected many millions of people around the world. This brain disorder is identified by the occurrence of the oscillations of the patient’s changing mood. The mood swing between two states i.e. depression and mania. This is a result of different psychological and physical features. A set of psycholinguistic features like behavioral changes, mood swings and mental illness are observed to provide feedback on health and wellness. The study is an objective measure of identifying the stress level of human brain that could improve the harmful effects associated with it considerably. In the paper, we present the study prediction of symptoms and behavior of a commonly known mental health illness, bipolar disorder using Machine Learning Techniques. Therefore, we extracted data from articles and research papers were studied and analyzed by using statistical analysis tools and machine learning (ML) techniques. Data is visualized to extract and communicate meaningful information from complex datasets on predicting and optimizing various day to day analyses. The study also includes the various research papers having machine Learning algorithms and different classifiers like Decision Trees, Random Forest, Support Vector Machine, Naïve Bayes, Logistic Regression and K- Nearest Neighbor are studied and analyzed for identifying the mental state in a target group. The purpose of the paper is mainly to explore the challenges, adequacy and limitations in detecting the mental health condition using Machine Learning Techniques</i>

Download Full-text

Review on Machine Learning Techniques to predict Bipolar Disorder

10.36227/techrxiv.14346050.v1 ◽

2021 ◽

Author(s):

Nisha Agnihotri

Keyword(s):

Mental Health ◽

Machine Learning ◽

Bipolar Disorder ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

K Nearest Neighbor ◽

Brain Disorder ◽

Research Papers ◽

Learning Techniques

Download Full-text

Blog Backlinks Malicious Domain Name Detection via Supervised Learning

International Journal on Semantic Web and Information Systems ◽

10.4018/ijswis.2021070101 ◽

2021 ◽

Vol 17 (3) ◽

pp. 1-17

Author(s):

Abdulrahman A. Alshdadi ◽

Ahmed S. Alghamdi ◽

Ali Daud ◽

Saqib Hussain

Keyword(s):

Machine Learning ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Financial Loss ◽

Domain Name ◽

Hybrid Features ◽

Learning Techniques ◽

Web Spam ◽

Social Media Platforms

Web spam is the unwanted request on websites, low-quality backlinks, emails, and reviews which is generated by an automated program. It is the big threat for website owners; because of it, they can lose their top keywords ranking from search engines, which will result in huge financial loss to the business. Over the years, researchers have tried to identify malicious domains based on specific features. However, lighthouse plugin, Ahrefs tool, and social media platforms features are ignored. In this paper, the authors are focused on detection of the spam domain name from a mixture of legit and spam domain name dataset. The dataset is taken from Google webmaster tools. Machine learning models are applied on individual, distributed, and hybrid features, which significantly improved the performance of existing malicious domain machine learning techniques. Better accuracy is achieved for support vector machine (SVM) classifier, as compared to Naïve Bayes, C4.5, AdaBoost, LogitBoost.

Download Full-text

Machine learning techniques applied to prediction of residual strength of clay

Open Geosciences ◽

10.2478/s13533-011-0043-1 ◽

2011 ◽

Vol 3 (4) ◽

Cited By ~ 9

Author(s):

Sarat Das ◽

Pijush Samui ◽

Shakilu Khan ◽

Nagarathnam Sivakugan

Keyword(s):

Machine Learning ◽

Residual Strength ◽

Training Data ◽

Machine Learning Techniques ◽

Sensitivity Analyses ◽

Support Vector ◽

Index Properties ◽

Learning Techniques ◽

Svm Model ◽

Ann Models

AbstractStability with first time or reactivated landslides depends upon the residual shear strength of soil. This paper describes prediction of the residual strength of soil based on index properties using two machine learning techniques. Different Artificial Neural Network (ANN) models and Support Vector Machine (SVM) techniques have been used. SVM aims at minimizing a bound on the generalization error of a model rather than at minimizing the error on the training data only. The ANN models along with their generalizations capabilities are presented here for comparisons. This study also highlights the capability of SVM model over ANN models for the prediction of the residual strength of soil. Based on different statistical parameters, the SVM model is found to be better than the developed ANN models. A model equation has been developed for prediction of the residual strength based on the SVM for practicing geotechnical engineers. Sensitivity analyses have been also performed to investigate the effects of different index properties on the residual strength of soil.

Download Full-text

Prediction of Severity of Non Proliferated Diabetic Retinopathy Using Machine Learning Techniques

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9049 ◽

2020 ◽

Vol 17 (9) ◽

pp. 4219-4222

Author(s):

ManjulaSri Rayudu ◽

Srujana Pendam ◽

Srilaxmi Dasari

Keyword(s):

Machine Learning ◽

Diabetic Retinopathy ◽

Vision Loss ◽

Diversity Index ◽

Research Work ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Linear Discriminant ◽

Learning Techniques

All the patients of Type1 and more than 60% of Type2 Diabetes suffer from Diabetic Retinopathy (DR). Diabetic retinopathy causes damage to retina of eye and slowly leads to complete vision loss. The longer the patients are suffering from diabetes the probability of presence of DR is more. Hence diabetic retinopathy is to be identified in early stage to avoid blindness. The objective of this research work is to predict the severity of diabetic retinopathy (Non Proliferated) using machine learning techniques. Proliferated diabetic retinopathy (later stage) is characterized by neovasculature in the retinal veins and is the final stage. Non proliferated DR (earlier stage) is identified by any of the abnormalities out of microaneurysms, Hard exudates and hemorrhages. Then Machine learning techniques are employed to identify the class of DR. The following Classification and regression techniques are employed for categorizing the DR: Gini Diversity Index method, Linear discriminant analysis, Ensemble method with bagged and boosted trees, K-Nearest Neighbor, and Support Vector Machine classification methods. 89 images from DRIVE database (DiaRet DB1) are classified using the machine learning techniques cited above. It is observed the maximum accuracy is achieved as 88.8% with Linear SVM classifier.

Download Full-text

Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology

International Journal of Genomics ◽

10.1155/2016/7604641 ◽

2016 ◽

Vol 2016 ◽

pp. 1-11 ◽

Cited By ~ 10

Author(s):

Jieru Zhang ◽

Ying Ju ◽

Huijuan Lu ◽

Ping Xuan ◽

Quan Zou

Keyword(s):

Machine Learning ◽

Extraction Methods ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Technology ◽

Accurate Identification ◽

Learning Techniques ◽

Hybrid Machine ◽

Computational Identification ◽

Identification Techniques

Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.

Download Full-text