Detection of evoked resonant neural activity in Parkinson's disease.

Objective. This study investigated a machine-learning approach to detect the presence of evoked resonant neural activity (ERNA) recorded during deep brain stimulation (DBS) of the subthalamic nucleus (STN) in people with Parkinson's disease.Approach. Seven binary classifiers were trained to distinguish ERNA from the background neural activity using eight different time-domain signal features.Main results. Nested cross-validation revealed a strong classification performance of 99.1% accuracy, with 99.6% specificity and 98.7% sensitivity to detect ERNA. Using a semi-simulated ERNA dataset, the results show that a signal-to-noise ratio of 15 dB is required to maintain a 90% classifier sensitivity. ERNA detection is feasible with an appropriate combination of signal processing, feature extraction and classifier. Future work should consider reducing the computational complexity for use in real-time applications.Significance. The presence of ERNA can be used to indicate the location of a DBS electrode array during implantation surgery. The confidence score of the detector could be useful for assisting clinicians to adjust the position of the DBS electrode array inside/outside the STN.

Development of an instrumented thoracoscopic surgical trainer for objective evaluation of esophageal atresia/tracheoesophageal fistula repair.

Operative repair of complex conditions such as esophageal atresia and tracheoesophageal fistula (EA/TEF) is technically demanding, but few training opportunities exist outside the operating theater for surgeons to attain these skills. Learning them during surgery on actual neonates where the stakes are high, margins for error narrow, and where outcomes are influenced by technical expertise, is problematic. There is an increasing demand for high-fidelity simulation that can objectively measure performance. We developed such a simulator to measure force and motion reliably, allowing quantitative feedback of technical skill. A 3D-printed simulator for thoracoscopic repair of EA/TEF was instrumented with motion and force tracking components. A 3D mouse, inertial measurement unit (IMU), and optical sensor that captured force and motion data in four degrees of freedom (DOF) were calibrated and verified for accuracy. The 3D mouse had low average relative errors of 2.81%, 3.15%, and 6.15% for 0 mm, 10 mm offset in Y, and 10 mm offset in X, respectively. This increased to - 23.5% at an offset of 42 mm. The optical sensors and IMU displayed high precision and accuracy with low SDs and average relative errors, respectively. These parameters can be a useful measurement of performance for thoracoscopic EA/TEF simulation prior to surgery. Graphical abstract Inclusion of sensors into a high-fidelity simulator design can produce quantitative feedback which can be used to objectively asses performance of a technically difficult procedure. As a result, more surgical training can be done prior to operating on actual patients in the operating theater.