Analysis of Spastic Gait in Patients With Cervical Myelopathy Using the Timed Up and Go Test With a Laser Range Sensor

A screening method for cervical myelopathy using machine learning to analyze a drawing behavior

Early detection of cervical myelopathy (CM) is important for a favorable outcome, as its prognosis is poor when left untreated. We developed a screening method for CM using machine learning-based analysis of the drawing behavior of 38 patients with CM and 66 healthy volunteers. Using a stylus pen, the participants traced three different shapes displayed on a tablet device. During the tasks, writing behaviors, such as the coordinates, velocity, and pressure of the stylus tip, along with the drawing time, were recorded. From these data, features related to the drawing pressure, and time to trace each shape and combination of shapes were used as training data for the support vector machine, a machine learning algorithm. To evaluate the accuracy, a receiver operating characteristic curve was generated, and the area under the curve (AUC) was calculated. Models with triangular waveforms tended to be the most accurate. The best triangular wave model identified patients with and without CM with 76% sensitivity and 76% specificity, yielding an AUC of 0.80. Our model was able to classify CM with high accuracy and could be applied to the development of disease screening systems useful outside the hospital setting.

Development and testing of a new application for measuring motion at the cervical spine

Background

Cervical myelopathy is a progressive disease, and early detection and treatment contribute to prognosis. Evaluation of cervical intervertebral instability by simple X-ray is used in clinical setting and the information about instability is important to understand the cause of myelopathy, but evaluation of the intervertebral instability by X-ray is complicated. To reduce the burden of clinicians, a system that automatically measures the range of motion was developed by comparing the flexed and extended positions in the lateral view of a simple X-ray of the cervical spine. The accuracy of the system was verified by comparison with spine surgeons and residents to determine whether the system could withstand actual use.

Methods

An algorithm was created to recognize the four corners of the vertebral bodies in a lateral cervical spine X-ray image, and a system was constructed to automatically measure the range of motion between each vertebra by comparing X-ray images of the cervical spine in extension and flexion. Two experienced spine surgeons and two residents performed the study on the remaining 23 cases. Cervical spine range of motion was measured manually on X-ray images and compared with automatic measurement by this system.

Results

Of a total of 322 cervical vertebrae in 46 images, 313 (97%) were successfully estimated by our learning model. The mean intersection over union value for all the 46-test data was 0.85. The results of measuring the CRoM angle with the proposed cervical spine motion angle measurement system showed that the mean error from the true value was 3.5° and the standard deviation was 2.8°. The average standard deviations for each measurement by specialist and residents are 2.9° and 3.2°.

Conclusions

A system for measuring cervical spine range of motion on X-ray images was constructed and showed accuracy comparable to that of spine surgeons. This system will be effective in reducing the burden on and saving time of orthopedic surgeons by avoiding manually measuring X-ray images.

Trial registration Retrospectively registered with opt-out agreement.