Classification and Automated Interpretation of Spinal Posture Data Using a Pathology-Independent Classifier and Explainable Artificial Intelligence (XAI)
Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations of the classification decisions. Spinal posture data of healthy subjects and various pathologies (back pain, spinal fusion, osteoarthritis), as well as synthetic data, were used for modeling. A one-class support vector machine was used as a pathology-independent classifier. The outputs were transformed into a probability distribution according to Plat…
Biografisch-narrative Intervention bei Aphasie – ein innovativer Ansatz zur Steigerung der Lebensqualität
Menschen mit Aphasie erleben massive Beeintrachtigungen in ihrer Lebensqualitat und ein verandertes Identitatsgefuhl. Soziokulturelle Theorien sehen das Konzept narrativer Identitat als essentiell fur Lebensqualitat. Dies meint, dass mittels narrativer Kompetenzen, welche bei Aphasie eingeschrankt sind, eine Selbstthematisierung im Austausch mit anderen erfolgt, wodurch Identitatsarbeit geschieht. In dem Projekt wird ein interdisziplinarer biografisch-narrativer Ansatz zur Stimulation von Identitatsarbeit in angepasster Form entwickelt und evaluiert. In einem Vorher-Nachher-Design mit einer Follow-up-Untersuchung wurden biografisch-narrative Gesprache in 5 Einzel- und 7 Gruppensitzungen dur…
Direct effects of Facio-Oral Tract Therapy® on swallowing frequency of non-tracheotomised patients with acute neurogenic dysphagia
Objectives: The aim of this study was to investigate the direct effect of Facio-Oral Tract Therapy ® on swallowing frequency of non-tracheotomised patients with acute neurogenic dysphagia. Methods: Within a pre-, post-/during and follow-up study design, 19 non-tracheotomised dysphagic patients were included consecutively and treated according to three specific preselected Facio-Oral Tract Therapy stimulation techniques. Results: The primary outcome was the direct effect of the three different Facio-Oral Tract Therapy stimulation techniques on the number of swallows. We found a significant effect of Facio-Oral Tract Therapy on swallowing frequency as compared to baseline with an increase by …
General method for automated feature extraction and selection and its application for gender classification and biomechanical knowledge discovery of sex differences in spinal posture during stance and gait
Modern technologies enable to capture multiple biomechanical parameters often resulting in relational data. The current work proposes a generally applicable method comprising automated feature extraction, ensemble feature selection and classification to best capture the potentials of the data also for generating new biomechanical knowledge. Its benefits are demonstrated in the concrete biomechanically and medically relevant use case of gender classification based on spinal data for stance and gait. Very good results for accuracy were obtained using gait data. Dynamic movements of the lumbar spine in sagittal and frontal plane and of the pelvis in frontal plane best map gender differences.
Machine learning techniques demonstrating individual movement patterns of the vertebral column: the fingerprint of spinal motion
Surface topography systems enable the capture of spinal dynamic movement; however, it is unclear whether vertebral dynamics are unique enough to identify individuals. Therefore, in this study, we investigated whether the identification of individuals is possible based on dynamic spinal data. Three different data representations were compared (automated extracted features using contrastive loss and triplet loss functions, as well as simple descriptive statistics). High accuracies indicated the possible existence of a personal spinal 'fingerprint', therefore enabling subject recognition. The present work forms the basis for an objective comparison of subjects and the transfer of the method to…