Machine learning algorithm performance evaluation in structural magnetic resonance imaging-based classification of pediatric bipolar disorders type I patients

Abstract

The diagnosis based on clinical assessment of pediatric bipolar disorder (PBD) may sometimes lead to misdiagnosis in clinical practice. For the past several years, machine learning (ML) methods were introduced for the classification of bipolar disorder (BD), which were helpful in the diagnosis of BD. In this study, brain cortical thickness and subcortical volume of 33 PBD-I patients and 19 age-sex matched healthy controls (HCs) were extracted from the magnetic resonance imaging (MRI) data and set as features for classification. The dimensionality reduced feature subset, which was filtered by Lasso or f_classif, was sent to the six classifiers (logistic regression (LR), support vector machine (SVM), random forest classifier, naïve Bayes, k-nearest neighbor, and AdaBoost algorithm), and the classifiers were trained and tested. Among all the classifiers, the top two classifiers with the highest accuracy were LR (84.19%) and SVM (82.80%). Feature selection was performed in the six algorithms to obtain the most important variables including the right middle temporal gyrus and bilateral pallidum, which is consistent with structural and functional anomalous changes in these brain regions in PBD patients. These findings take the computer-aided diagnosis of BD a step forward.

Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection and Diagnosis in Pediatric Radiology: A Systematic Review

“…Twenty-three articles met the selection criteria and were included in this review [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 ]. Table 1 shows their AI-based CAD application areas in the pediatric radiology and the diagnostic performances.…”

“…Table 1 shows their AI-based CAD application areas in the pediatric radiology and the diagnostic performances. These studies covered brain ( n = 9) [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ], respiratory ( n = 9) [ 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 ], musculoskeletal ( n = 2) [ 40 , 41 ], urologic ( n = 2) [ 51 , 52 ] and cardiac imaging ( n = 1) [ 39 ]. The commonest AI-based CAD application area (30.4%, 7/23) was pediatric pneumonia [ 43 , 45 , 46 , 47 , 48 , 49 , 50 ].…”

“…The commonest AI-based CAD application area (30.4%, 7/23) was pediatric pneumonia [ 43 , 45 , 46 , 47 , 48 , 49 , 50 ]. No study reported all seven diagnostic accuracy measures [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 ]. Most commonly, the papers (30.4%, 7/23) reported four metrics [ 30 , 32 , 35 , 42 , 44 , 45 , 52 ].…”

“…No study reported all seven diagnostic accuracy measures [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 ]. Most commonly, the papers (30.4%, 7/23) reported four metrics [ 30 , 32 , 35 , 42 , 44 , 45 , 52 ]. Accuracy ( n = 19) and sensitivity ( n = 18) were the two most frequently used evaluation metrics [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 ].…”

“…Most commonly, the papers (30.4%, 7/23) reported four metrics [ 30 , 32 , 35 , 42 , 44 , 45 , 52 ]. Accuracy ( n = 19) and sensitivity ( n = 18) were the two most frequently used evaluation metrics [ 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 ]. One study only used one measure, AUC [ 40 ].…”