Search

Machine learning is considered a potential aid to support human decision making in disease prediction. In this study, we determined the utility of various machine learning algorithms in classifying peripheral vestibular (PV) and non-PV diseases based on the results of equilibrium function tests. A total of 1009 patients who had undergone our standardized neuro-otological examinations were recruited. We applied five supervised machine learning algorithms (random forest, adaboost, gradient boosting, support vector machine, and logistic regression). After preprocessing the data, optimizing the hyperparameters using GridSearchCV, and performing a final evaluation on the test set using scikit-learn, we evaluated the predictive capability using various performance metrics, namely, accuracy, F1-score, area under the receiver operating characteristic curve, precision, recall, and Matthews correlation coefficient (MCC). All five machine learning algorithms yielded satisfactory results; the accuracy of the algorithms ranged from 76 to 79%, with the support vector machine classifier having the highest accuracy. In cases where the predictions of the five models were consistent, the accuracy of the PV diagnostic results was improved to 83%, whereas it increased to 85% for the non-PV diagnostic results. Future research should increase the number of patients and optimize the classification methods to obtain the highest diagnostic accuracy. [ABSTRACT FROM AUTHOR]

The present study investigated the efficacy and safety of using a lower dose of cisplatin (CDDP) in super-selective intra-arterial concurrent chemoradiotherapy (SSIACRT) to treat maxillary squamous cell carcinoma. 10 patients with maxillary squamous cell carcinoma (T3 n = 6, T4a n = 4) without regional or distant metastasis were treated by SSIACRT. The CDDP dose per course was 100 mg/body, i.e. 50-80 mg/m. 6-9 weeks after SSIACRT, partial maxillectomy was performed on all patients. Clinical and histological responses, survival rates, and adverse events were investigated. 10 (100%) of 10 patients achieved both clinical and pathological complete or partial remission. The 3-year overall and disease-free survival rates were 100 and 90%, respectively. Grade 3 toxicity was experienced by two patients. In conclusion, the SSIACRT regimen with a lower dose of CDDP (100 mg/body) had an equivalent therapeutic outcome and lower toxic outcome compared to a higher dose of CDDP. This regimen could be an effective and safe therapeutic modality for maxillary squamous cell carcinoma except T4b and N1/2 disease. [ABSTRACT FROM AUTHOR]

Intravenous injection of thiamine propyldisulphide (TPD), which induces sensation of a garlic-like odor, has been used as a representative subjective olfactory test in Japan. However, cortical loci activated by TPD still remain unclear. We recorded cerebral hemodynamic responses (changes in Oxy-Hb concentrations) induced by TPD administration using whole-head multi-channel near infrared spectroscopy (NIRS) system based on 3D-MRIs. TPD as an odorant and saline as a control were injected from the cephalic vein in the left forearm in ten male normosmic (five young and five elderly) subjects and five dysosmic elderly patients. The all normosmic, but not dysosmic, subjects felt the garlic-like odor in the all TPD trials. There was no significant difference in hemodynamic responses between the young and elderly normosmic subjects. However, TPD injection induced significantly larger hemodynamic responses in the bilateral operculums, bilateral dorsolateral prefrontal cortices (PFC) and anteromedial PFC in the normosmic subjects, compared with saline injection. Onset latencies of these hemodynamic responses were significantly correlated with onset latencies of subjective odor sensation in the normosmic subjects. Comparison of hemodynamic responses between the normosmic and dysosmic subjects indicated a significant difference in the bilateral operculums. The results demonstrated that Oxy-Hb increases in the bilateral operculums reflected olfactory sensation induced by TPD injection. Consideration of a route for intravenous TPD to reach the olfactory mucosa suggests that these hemodynamic responses might be attributed to food-related retronasal olfactory responses to TPD. [ABSTRACT FROM AUTHOR]