Design, development, and evaluation of a local sensor-based gait phase recognition system using a logistic model decision tree for orthosis-control.

BACKGROUND: Functionality and versatility of microprocessor-controlled stance-control knee-ankle-foot orthoses (M-SCKAFO) are dictated by their embedded control systems. Proper gait phase recognition (GPR) is required to enable these devices to provide sufficient knee-control at the appropriate time, thereby reducing the incidence of knee-collapse and fall events. Ideally, the M-SCKAFO sensor system would be local to the thigh and knee, to facilitate innovative orthosis designs that allow more flexibility for ankle joint selection and other orthosis components. We hypothesized that machine learning with local sensor signals from the thigh and knee could effectively distinguish gait phases across different walking conditions (i.e., surface levels, walking speeds) and that performance would improve with gait phase transition criteria (i.e., current states depend on previous states). METHODS: A logistic model decision tree (LMT) classifier was trained and tested (five-fold cross-validation) on gait data that included knee flexion angle, thigh-segment angular velocity, and thigh-segment acceleration. Twenty features were extracted from 0.1 s sliding windows for 30 able-bodied participants that walked on different surfaces (level, down-slope, up-slope, right cross-slope, left cross-slope) at a various walking speeds (self-paced (1.33 m/s, SD = 0.04 m/s), 0.8, 0.6, 0.4 m/s). The LMT-based GPR model was also tested with another validation set containing similar features and surfaces from 12 able-bodied volunteers at self-paced walking speeds (1.41 m/s, SD = 0.34 m/s). A "Transition Sequence Verification and Correction" (TSVC) algorithm was applied to correct for continuous class prediction and to improve GPR performance. RESULTS: The LMT had a tree size of 1643 with 822 leaf nodes, with a logistic regression model at each leaf node. The local sensor LMT-based GPR model identified loading response, push-off, swing, and terminal swing phases with overall classification accuracy of 98.38 for the initial training set (five-fold cross-validation) and 90.60% for the validation set. Applying TSVC increased classification accuracy to 98.72% for the initial training set and 98.61% for the validation set. Sensitivity, specificity, precision, F-score, and Matthew's correlation coefficient results suggest strong evidence for the feasibility of an LMT-based GPR system for real-time orthosis control. CONCLUSIONS: The novel machine learning GPR model that used sensor features local to the thigh and knee was viable for dynamic knee-ankle-foot orthosis-control. This highly accurate GPR model was generalizable when combined with TSVC. Our approach could reduce sensor system complexity as compared with other M-SCKAFO approaches, thereby enabling customizable advantages for end-users through modular unit orthosis designs.

Performance optimization of capacitive motion sensing (CMS) system for intra-fraction motion detection during stereotactic radiosurgery.

The purpose of this investigation is to improve intra-fractional motion detection during cranial stereotactic radiosurgery with a novel capacitive motion sensing (CMS) system. Previous work showed that a capacitive detection system, based on a MPR121 capacitance-to-digital converter, provided a number of advantages over existing patient imaging systems used in the clinic, by uniquely offering ionizing-radiation-free and continuous monitoring without modification to the immobilization mask or treatment room. However, in order to provide submillimeter detection accuracy, the MPR121-based CMS system required relatively large sensors in close proximity to the patient. Therefore, the aim of this investigation was to improve sensitivity of the system, allowing reduction in sensor size and preserving its stable operation in the linear accelerator environment. For this, we developed, characterized and compared motion detection capabilities of four CMS systems based on different capacitance-to-digital converters: MPR121, CPT212B, FDC1004 and FDC2214. Among all candidates, the FDC2214-based system was found to uniquely combine accurate 3D motion detection in real time, with stable performance under ionizing radiation. It exhibited an order of magnitude improvement in sensitivity in comparison with the proof-of-study system, allowing a spatial precision as low as 0.3 mm, and its overall performance was found to satisfy the AAPM practice guidelines of positioning tolerance within 1 mm. Furthermore, the high sensitivity of the system allows both reduction of the sensor area and location more distant from the patient surface, which are key improvements with regard to development of a clinical device.