Surgical Hand Gesture Recognition Utilizing Electroencephalogram as Input to the Machine Learning and Network Neuroscience Algorithms.

Surgical gestures detection can provide targeted, automated surgical skill assessment and feedback during surgical training for robot-assisted surgery (RAS). Several sources including surgical videos, robot tool kinematics, and an electromyogram (EMG) have been proposed to reach this goal. We aimed to extract features from electroencephalogram (EEG) data and use them in machine learning algorithms to classify robot-assisted surgical gestures. EEG was collected from five RAS surgeons with varying experience while performing 34 robot-assisted radical prostatectomies over the course of three years. Eight dominant hand and six non-dominant hand gesture types were extracted and synchronized with associated EEG data. Network neuroscience algorithms were utilized to extract functional brain network and power spectral density features. Sixty extracted features were used as input to machine learning algorithms to classify gesture types. The analysis of variance (ANOVA) F-value statistical method was used for feature selection and 10-fold cross-validation was used to validate the proposed method. The proposed feature set used in the extra trees (ET) algorithm classified eight gesture types performed by the dominant hand of five RAS surgeons with an accuracy of 90%, precision: 90%, sensitivity: 88%, and also classified six gesture types performed by the non-dominant hand with an accuracy of 93%, precision: 94%, sensitivity: 94%.

Living with a left ventricular assist device: Capturing recipients experiences using group concept mapping software.

BACKGROUND: Left ventricular assist device (LVAD) implantation significantly impacts on a recipient's symptoms and quality of life. Capturing their experiences and post implant journey is an important part of clinical practice, research and device design evolution. Patient reported outcome measures (PROMs) are a useful tool for capturing that experience. However, patient reported outcome measures need to reflect recipients' experiences. Discussions with a patient partner group found that none of the frequently used cardiology PROMs captured their unique experiences. AIMS: To capture the experiences and important issues for LVAD recipients. Develop a conceptual map of domains and items that should be reflected in patient reported outcomes. METHODS: Group concept mapping (GCM) web-based software was used to remotely capture and structure recipients' experiences across a wide geographical area. GCM is a semi-quantitative mixed method consisting of 3 stages: item generation, item sorting and rating (importance, relevance and frequency). Patient partners were involved in all aspects of the study design and development. RESULTS: 18 LVAD recipients consented to take part. 101 statements were generated and multi-dimensional scaling, and hierarchical cluster analysis identified 9 clusters. Cluster themes included: Activities, Partner/family support, Travel, Mental wellbeing, Equipment and clothing, Physical and cognitive limitations, LVAD Restrictions, LVAD Challenges and positive impact of the LVAD (LVAD Positives). LVAD Positives were scored highest across all the rating variables, e.g., frequency (2.85), relevance (2.44) and importance (2.21). Other domains rated high for importance included physical and cognitive limitations (2.19), LVAD restrictions (2.11), Partner/family support (2.02), and Equipment and clothing (2.01). CONCLUSION: Online GCM software facilitated the inclusion of geographically dispersed recipients and provided useful insights into the experiences of LVAD recipients. The conceptual framework identifies important domains and items that should be prioritised and included in patient reported outcomes in future research, LVAD design evolution, and clinical practice.