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.

Development of the clinical assessment scale in autoimmune encephalitis.

OBJECTIVE: There is no scale for rating the severity of autoimmune encephalitis (AE). In this study, we aimed to develop a novel scale for rating severity in patients with diverse AE syndromes and to verify the reliability and validity of the developed scale. METHODS: The key items were generated by a panel of experts and selected according to content validity ratios. The developed scale was initially applied to 50 patients with AE (development cohort) to evaluate its acceptability, reproducibility, internal consistency, and construct validity. Then, the scale was applied to another independent cohort (validation cohort, n = 38). RESULTS: A new scale consisting of 9 items (seizure, memory dysfunction, psychiatric symptoms, consciousness, language problems, dyskinesia/dystonia, gait instability and ataxia, brainstem dysfunction, and weakness) was developed. Each item was assigned a value of up to 3 points. The total score could therefore range from 0 to 27. We named the scale the Clinical Assessment Scale in Autoimmune Encephalitis (CASE). The new scale showed excellent interobserver (intraclass correlation coefficient [ICC] = 0.97) and intraobserver (ICC = 0.96) reliability for total scores, was highly correlated with modified Rankin scale (r = 0.86, p < 0.001), and had acceptable internal consistency (Cronbach α = 0.88). Additionally, in the validation cohort, the scale showed high interobserver reliability (ICC = 0.99) and internal consistency (Cronbach α = 0.92). INTERPRETATION: CASE is a novel clinical scale for AE with a high level of clinimetric properties. It would be suitable for application in clinical practice and might help overcome the limitations of current outcome scales for AE. ANN NEUROL 2019;85:352-358.

Quantitative assessment of Azumiobodo hoyamushi distribution in the tunic of soft tunic syndrome-affected ascidian Halocynthia roretzi using real-time polymerase chain reaction.

BACKGROUND: The kinetoplastid parasite, Azumiobodo hoyamushi, is the causative agent of soft tunic syndrome (STS) in ascidians and leads to their mass mortality in Korean waters. This study was conducted to quantify A. hoyamushi density during the development of STS in the tunics of ascidians (Halocynthia roretzi) using real-time polymerase chain reaction (qPCR). FINDINGS: The infection intensity of A. hoyamushi, as measured by qPCR, varied depending on the part of the tunic analyzed, as well as the stage of STS development. The highest infection intensity was recorded in the tunics of the siphons. The infection intensity of A. hoyamushi in the siphons was only 2.9 cell/tunic (area, 0.25 cm(2)) or 106.0 cell/gram tunic (GT) in the early phase of STS, but this value increased dramatically to 16,066 cells/tunic (0.25 cm(2)) or 617,004 cell/GT at the time of death. The number of A. hoyamushi parasites increased gradually and their distribution spread from the siphons to the other parts of the tunics. CONCLUSIONS: qPCR enabled the quantitation of A. hoyamushi and the results revealed that parasite density increased as STS progressed. In addition, our results suggested that the siphons might function as the portal of entry for A. hoyamushi during infection.