Browsing by Author "Dastan, Seda"

Now showing 1 - 2 of 2

Development of Restless Legs Syndrome Severity Prediction Models for People with Multiple Sclerosis Using Machine Learning
(Galenos Publishing House, 2025) Kaya, Ergi; Emec, Murat; Ozdogar, Asiye Tuba; Zengin, Eta Simay; Karakas, Hitat; Dastan, Seda; Ozakbas, Serkan
Objectives: This study aimed to develop an artificial intelligence-supported restless legs syndrome (RLS) severity prediction model for people with multiple sclerosis using machine learning methods. Patients and methods: Twenty-three individuals (14 females, 7 males; mean age: 40.6 +/- 10.9 years; range, 33 to 44 years) with multiple sclerosis with RLS were included in this observational study between March 2022 and March 2023. The International Restless Legs Syndrome Study Group Rating Scale was used to determine the RLS severity of the participants. The age, sex, body mass index, regular exercise habits, disease duration, Expanded Disability Status Scale (EDSS), estimated maximal aerobic capacity (VO2max), Pittsburgh Sleep Quality Index (PSQI), Epworth Sleepiness Scale, Multiple Sclerosis International Quality of Life Questionnaire, Multiple Sclerosis Walking Scale-12 (MSWS-12), and timed 25-foot walk test were determined as predictive variables. A correlation matrix was created. DecisionTree, RandomForest, and XGBoost machine learning methods were used to develop a model for predicting the RLS severity. Results: According to the obtained correlation matrix, PSQI scores strongly correlated with RLS severity (Pearson r=0.76). Meanwhile, EDSS scores (0.49), MSWS-12 scores (0.45), and disease duration (0.45) showed moderate correlations with RLS. Among the three different meachine learning methods, XGBoost demonstrated the best performance in predicting the severity of RLS, with a mean absolute error of 1.94, mean squared error of 4.58, mean absolute percentage error of 0.0735, and a test accuracy of 92.65%. The results showed that the severity of RLS could be estimated with 92.65% accuracy. Conclusion: This study showed a strong correlation between PSQI scores and RLS severity and that RLS severity could be predicted using machine learning methods.
Six-Spot Step Test Under Three Different Task Conditions To Assess Dual-Task Ability in People With Multiple Sclerosis
(Taylor & Francis Ltd, 2025) Ertekin, Ozge; Abasiyanik, Zuhal; Kahraman, Turhan; Dastan, Seda; Ozakbas, Serkan
Background: The Six-Spot Step Test (SSST) is a valid measure to assess the ability of people with multiple sclerosis (pwMS) to maintain balance whilst challenging stability during walking. This study aimed to compare the performance of three different SSST conditions in pwMS and healthy controls (HC) and to explore whether incorporating cognitive tasks into the SSST improves its discriminative capacity by increasing cognitive load. Methods: Fifty-two pwMS (median EDSS = 1.75) and 19 HC were recruited. Participants performed the SSST under three different task conditions: conventional SSST, SSST with word-list generation task (WLG), and SSST with the serial-7 backward task. The dual-task cost (DTC) was calculated for two cognitive task conditions. Results: There was a significant difference across different SSST conditions in both groups. There was also significant condition*group interaction [F (2,132) = 3.69, p = 0.028, eta(2) = 0.053]. PwMS completed all SSST conditions in a longer duration compared to HC. The DTC of SSST with backward and WLG tasks was greater in the MS group than in HC. However, there was no significant differences in the number of correct answers during the dual-task conditions between pwMS and HC. All three conditions showed excellent discriminative ability between pwMS and HC (Area Under Curve value > 0.8). Significance: The SSST had the ability to discriminate between pwMS and HC in both conventional method and with secondary cognitive task. The SSST could be used to evaluate early walking and dual-task deficits even in pwMS with mild disability for future research and clinical practice.