Predicting Parkinson's disease using gradient boosting decision tree models with electroencephalography signals.

INTRODUCTION: Parkinson's disease (PD) is a neurodegenerative disorder with only symptomatic treatments currently available. Although correct, early diagnoses of PD are important, the existing diagnostic method based on pathologic examinations only has an accuracy of approximately 80.6%. Although electroencephalography (EEG)-based assistive technology has been introduced, it has been difficult to implement in practice due to the high computational complexity and low accuracy of the analysis methods. This study proposed a fast, accurate PD prediction method using the Hjorth parameter and the gradient boosting decision tree (GBDT) algorithm. METHOD: We used an open EEG dataset with 41 PD patients and 41 healthy controls (HCs); EEG signals were recorded from participants at the University of New Mexico (PD: 27 vs. HC: 27) and University of Iowa (PD: 14 vs. HC: 14). We explored the analytic time segment and frequency range in which the Hjorth parameter best represents the EEG characteristics of PD patients. RESULTS: Our best model (CatBoost-based) distinguished PD patients from controls with an accuracy of 89.3%, an area under the receiver operating characteristics curve (AUC) of 0.912, an F-score of 0.903, and an odds ratio of 115.5. These results showed that our models outperformed those of all other previous works and were even superior to previously known pathologic examination-based diagnoses with long-term follow-up (accuracy = 83.9%). CONCLUSION: The proposed methods are expected to be utilized as an effective method for improving the diagnosis of PD.

Assessment of central cartilaginous tumor of the appendicular bone: inter-observer and intermodality agreement and comparison of diagnostic performance of CT and MRI.

BACKGROUND: Diagnostic performance, inter-observer agreement, and intermodality agreement between computed tomography (CT) and magnetic resonance imaging (MRI) in the depiction of the major distinguishing imaging features of central cartilaginous tumors have not been investigated. PURPOSE: To determine the inter-observer and intermodality agreement of CT and MRI in the evaluation of central cartilaginous tumors of the appendicular bones, and to compare their diagnostic performance. MATERIAL AND METHODS: Two independent radiologists retrospectively reviewed preoperative CT and MRI. Inter-observer and intermodality agreement between CT and MRI in the assessment of distinguishing imaging features, including lesion size, deep endosteal scalloping, cortical expansion, cortical disruption, pathologic fracture, soft tissue extension, and peritumoral edema, were evaluated. The agreement with histopathology and the accuracy of the radiologic diagnoses made with CT and MRI were also analyzed. RESULTS: A total of 72 patients were included. CT and MRI showed high inter-observer and intermodality agreements with regard to size, deep endosteal scalloping, cortical expansion, cortical disruption, and soft tissue extension (ICC = 0.96-0.99, k = 0.60-0.90). However, for the evaluation of pathologic fracture, MRI showed only moderate inter-observer agreement (k = 0.47). Peritumoral edema showed only fair intermodality agreement (k = 0.28-0.33) and moderate inter-observer agreement (k = 0.46) on CT. Both CT and MRI showed excellent diagnostic performance, with high agreement with the histopathology (k = 0.89 and 0.87, respectively) and high accuracy (91.7% for both CT and MRI). CONCLUSION: CT and MRI showed high inter-observer and intermodality agreement in the assessment of several distinguishing imaging features of central cartilaginous tumors of the appendicular bones and demonstrated comparable diagnostic performance.