High-Accuracy Classification of Attention Deficit Hyperactivity Disorder With l _2,1-Norm Linear Discriminant Analysis and Binary Hypothesis Testing

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) is a high incidence of neurobehavioral disease in school-age children. Its neurobiological diagnosis (or classification) is meaningful for clinicians to give proper treatment for ADHD patients. The existing ADHD classification methods suffer from two problems, i.e., insufficient data and noise disturbance. In this paper, a high-accuracy classification method is proposed by using brain Functional Connectivity (FC) as ADHD features, where an l 2,1-norm Linear Discriminant Analysis (LDA) model and a binary hypothesis testing framework are effectively employed. In detail, we introduce a binary hypothesis testing framework to cope with insufficient data of ADHD database. The FCs of test data (without seeing its label) are used for training and thus affect the subspace learning of training data under binary hypotheses. On other hand, the l 2,1-norm LDA model generates a subspace to represent ADHD features, aiming to overcome noise disturbance. By robustly learning ADHD features, the subspace energy difference between binary hypotheses becomes more discriminative. Thereby, the true hypothesis can be rightly estimated with its larger subspace energy, which provides reliable evidence to predict the label of test data. By the test on ADHD-200 database, it shows that our method outperforms other state-of-the-art methods with the significant average accuracy of 97.6%. Moreover, the corresponding result analysis with ADHD symptom score and the explanation of discriminative FCs between ADHD and healthy control groups are given, which further verifies the validity of our classification method.

ADHD classification with cross-dataset feature selection for biomarker consistency detection

“…We employed several state-of-the-art approaches for comparison, including ML-based methods such as R-Relief [6], L 1 BioSVM [9], and Fusion fMRI [40], as well as DL-based methods consisting of Deep fMRI [18], AAEN ( [21], CDAE [22], DVAE [24], and STAAE [25]. In addition, we introduced some methods under the BHT framework for comparison, namely SP-BH [29] and SP-l 2,1 -BH [28]. These methods utilize subspace learning and l 2,1 -norm subspace learning, respectively, for ADHD classification.…”

“…Notably, a modified AE network (AENet) [26,27] also demonstrated attractive performance. When integrated into an existing binary hypothesis testing (BHT) framework [28,29], AENet achieved an accuracy of 99.7%. However, it is observed that most of the aforementioned methods were evaluated on single datasets, resulting in varying features for ADHD on multiple datasets alongside inconsistencies.…”

Complex predictive analysis for health care: a comprehensive review

“…Several studies have examined the use of decision trees to analyse clinical data [11], [12]. Using the tree and its principles to forecast on a dataset is the heart of this method.…”

Rural Financial Mobile Service Management System Based on Big Data

“…e basic idea of linear discriminant analysis (LDA) is to project high-dimensional data samples into the optimal discriminant vector space, which is used to separate two or more categories of objects or events and find the most appropriate projection space so that the data samples with multiple categories of features can project on this space with the least intersection to have the best separation effect [11].…”