Journal of Mechanics in Medicine and Biology

In this paper, a new auto-scoring algorithm that automatically evaluates the Berg balance scale (BBS) tasks is proposed. The BBS can be used as an indicator for patients to analyze their rehabilitation status by themselves. In the proposed method, the patient must use a wearable inertial measurement unit (IMU) sensor, and the result of the patient’s BBS task execution would be scored automatically by the evaluation algorithm. The proposed evaluation algorithm involves only few computations and has high scoring accuracy. Nonlinear kernel principal component analysis and a small number of linear features were combined to reduce the features from each sensor, and the algorithm model was implemented using a support vector machine (SVM), a machine learning technique with low computational complexity. The effectiveness of the algorithm was evaluated through clinical evaluation of 53 subjects with up to eight IMU sensors. The average accuracy of the proposed algorithm using eight sensors was 93.2%, and that using five sensors was 91.5%. There was a 12.6% and 10.9% increase in accuracy, respectively, compared to a previous study. The training and testing times of the proposed SVM model were over 38 times faster than the multi-layer perceptron model used in a previous study.

The functional near-infrared spectroscopy (fNIRS) technology is an optical imaging technology that applies near-infrared light to measure the oxygenated and deoxygenated hemoglobin concentration alteration in cortical brain structures. It has the ability to directly measure changes in the blood oxygen level of the high temporal resolution associated with neural activation. Thus, it has been utilized in different neurological diseases, such as epilepsy, stroke, and Parkinson. The work of this paper will focus on the application of the fNIRS in the three neurological diseases and the principle of fNIRS. Moreover, the difficulties and challenges that the technology is currently experiencing have been discussed.

The TLD-100H readout system performance under various radioactive I-131 exposure doses was optimized by four key factors via the revised Taguchi dynamic quality loss function. Taguchi dynamic analysis and the orthogonal array reorganizing the essential factors are crucial for the optimization of the thermoluminescent dosimeter (TLD) readout system given strict criteria of multiple irradiated environments and long-term exposure for calibrated TLDs. Accordingly, 96 TLD-100H chips were selected and randomly categorized into three batches with eight groups (four TLD chips in each group). Four factors, namely (1) initial temperature, (2) heating rate, (3) maximal temperature, and (4) TLD preheat time before reading were organized into eight combinations according to Taguchi suggestion, whereas each factor was preset at two levels. All 96 $(3\times 8\times 4=96)$ chips were put in three concentric circles with 30, 60, and 90 cm radii for 48 h, surrounding the radioactive 150mCi ($5.55\times 10^3$MBq) I-131 capsule and exposed to the cumulative doses of 88.2, 18.6, and 8.6mSv for the respective radii, accordingly. The TLD readings obtained from each group were analyzed to derive the sensitivity, coincidence, and reproducibility, then those were reorganized to draw four fish-bone-plots for the optimization. The optimal option for the TLD readout system implied the combination of A1 (a $135^{\circ }$C initial temperature), B1 (a $10^{\circ }$C/s heating rate), C1 (a $240^{\circ }$C maximal temperature), and D2 (a 15s preheat time), which was further verified by the follow-up measurements. The dominant factors were A (initial temperature) and B (heating rate), whereas C (maximal temperature) and D (preheat time) were minor and provided negligible contributions to the system performance optimization.

Pedicle screw placement is a common internal fixation technology used in spine surgery, with preoperative planning and assessment being one of the most important steps. Preoperative planning mainly refers to determining the path and parameters of screws, and preoperative assessment mainly refers to effects during and after operations (i.e., firmness, etc.). Technologies available at present lack effective quantitative assessments on the firmness of screws. Bone mineral density (BMD) is one of the most important influencing factors for firmness. To address the aforementioned problems, this study aimed to put forward quantitative assessments for the firmness of pedicle screws taking bone mass as the basis. In other words, quantitative assessments of the firmness of screw trajectories were made by computing the total mineral content of the bone supporting screws. Meanwhile, the quantitative assessment results of the firmness were used as the optimized objective functions to put forward and realize an automatic planning optimization method for screw trajectories. The findings of this study might provide more complete and simplified planning schemes for doctors, to enhance the postoperative firmness of screws effectively, prevent from issues such as the loosening of screws due to the low value of a patient’s bone mass, and promote the effects of operations.

Hearing loss in people is increasing because of a rise in the usage of wireless audio multimedia devices. Hearing aids are used as representative hearing rehabilitation devices. Bone conduction hearing aids are recommended for problems in the eardrum and middle ear. Bone conduction is classified according to the driving method into two types, electromagnetic and piezoelectric. Electromagnetic bone conduction causes skin disease and aesthetic problems due to transplantation, high power consumption, and external interference. Piezoelectric bone conduction converts electrical energy into mechanical vibrations, and the characteristics change linearly with size. However, the driving force of ear canal insertion of the piezoelectric body is limited because of the ear canal anatomy. In this paper, a piezoelectric actuator with a bridge structure inserted into the ear canal is proposed. The proposed method is that the displacement amplification ratio was derived using the formula of a bridge-type structure, and the displacement and resonance frequency were derived by finite element analysis (FEA) using different variables. The piezoelectric actuator was fabricated on the basis of FEA simulation results and verified through an artificial mastoid for stimulation in the ear canal. It is expected that the proposed piezoelectric actuator can be used in the various fields for sound and precision control.

Understanding the relationship between the changes in the axonal transport of the optic nerve (ON) and lamina cribrosa (LC) deformation will be helpful to estimate the degree of axonal transport block by measuring the LC deformation in vivo. First, the changes in the axonal transport of the ON were studied using an acute high intraocular pressure (IOP) model, which was established by perfusing saline water into the anterior chamber of cats. The IOP of cat was unilaterally elevated to and maintained at 30, 40, and 50mmHg. The axonal transport of the ON was examined by confocal laser scanning microscope. Then the deformations and stress distributions of the LC and ON were calculated using a three-dimensional finite element model of the LC microstructure including ON. The results showed axonal transport changes of ON increased with elevation of the IOPs. While Young’s modulus of the LC and ON were assumed as 0.1MPa and 0.03MPa, the numerical simulation results showed that LC had displacements of 0.02, 0.03, and 0.04mm backward at the IOPs of 30, 40, and 50mmHg, respectively. The calculated compressive strain applied to the ON were 0.0425, 0.0567, and 0.0709 under 30, 40, and 50mmHg IOP, respectively. The results of strain and stress analysis of LC and ON showed that the deformation of LC would compress the ON. The axonal transport abnormalities could be inferred by measuring the LC deformation in vivo.

It is very useful in the human computer interface to quickly and accurately recognize human hand movements in real time. In this paper, we aimed to robustly recognize hand gestures in real time using Convolutional Recurrent Neural Network (CRNN) with pre-processing and overlapping window. The CRNN is a deep learning model that combines Long Short-Term Memory (LSTM) for time-series information classification and Convolutional Neural Network (CNN) for feature extraction. The sensor for hand gesture detection uses Myo-armband, and six hand gestures are recognized and classified, including two grips, three hand signs, and one rest. As the essential pre-processing due to the characteristics of EMG data, the existing Short Time Fourier Transform (STFT), Continuous-time Wavelet Transform (CWT), and newly proposed Scale Average Wavelet Transform (SAWT) are used, and thus, the SAWT showed relatively high accuracy in the stationary environmental test. The CRNN with overlapping window has been proposed that can improve the degradation of real-time prediction accuracy, which is caused by inconsistent start time and hand motion speed when acquiring the EMG signal. In the stationary environmental test, the CRNN model with SAWT and overlapping window showed the highest accuracy of 92.5%. In the real-time environmental test, for all subjects learning, 80% accuracy and 0.99 s time delay were obtained on average, and for individual learning, 91.5% accuracy and 0.32 s time delay were obtained on average. As a result, in both stationary and real-time tests, the CRNN with SAWT and overlapping window showed better performance than the other methods.

Proximal humerus fracture is a common injury and is usually treated using an internal fixation. However, clinical studies have reported that such treatments are associated with problems such as varus deformity and screw penetration. Therefore, to solve these problems, a surgical method using fibular allografts (FAs) is recently reported. Thus, this study is aimed to confirm the effective insertion angle ($0^{\circ }$, $30^{\circ }$, $50^{\circ }$, and $90^{\circ }$) of the FA. We applied axial and shear loads to finite element models used in our study. Finite element simulations using these models were repeated five times for each fibular insertion angle. We evaluated the construct stiffness, stress distribution on the plate and fibula, and fracture micromotion. Results showed that the method using the FA caused less stress on the plate and provided higher structural stability than the method without using the FA. In particular, the axis perpendicular condition yielded significantly greater construct stiffness and caused less von Mises stresses than the other conditions. In conclusion, the finite element analysis results showed that the FA inserted horizontally was effective in the treatment of proximal humerus fracture with an unstable medial support.

Plantar pressure refers to the interfacial contact pressure between the foot and the supporting surface during daily locomotor activities. Information derived from plantar pressure measures is essential in gait and posture research for diagnosing patho-mechanics associated with the musculoskeletal diseases. In particular, it is compulsory to reduce the abnormally high plantar pressure in people with diabetes for the prevention and treatment of foot ulcerations in this population. In this study, a portable biofeedback-based gait training device is developed to advocate able-bodied subjects to adopt different movement patterns in walking to manipulate the plantar pressure distribution under the foot. Through the simultaneous detection of the plantar pressure pattern and the kinematics of the lower extremity joints, it was revealed that the unloading effects for the plantar site in particular to the lateral forefoot subareas were more abundant through biofeedback-assisted gait alterations than the self-awareness control for gait adjustment. In addition, the corresponding relationship between joint coordination and pressure redistribution pattern was obtained, which could potentially be used in gait retraining interventions to correct abnormal plantar pressure patterns in people with diabetes.

More of power wheelchair users’ needs have to be met in the making of power wheelchairs. However, there has been no usability scale for the power wheelchair that is specifically focusing on the users’ needs. The purpose of this study was to test and validate a usability scale for power wheelchairs (USPW). The USPW has been developed through interviews with power wheelchair and consultations with a panel of experts. The USPW consists of four evaluation categories (safety, operation, efficiency, and satisfaction). In order to validate it, its usability and the Quebec User Evaluation of Satisfaction Assistive Technology (QUEST) were also administered to 50 power wheelchair users. The USPW was extracted 12 items from safety, 7 from operation, 5 from efficiency, and 14 from satisfaction, with a total of 38 items. The content validity met the criteria. The total internal consistency (Cronbach’s $\alpha$) of the USPW was 0.75. Users of power wheelchair demanded that the safety of moving on the slopes, the satisfaction of storage space for power wheelchairs, and the repair service process would be improved. The correlation between the USPW and the QUEST was significant ($r=0.342,p<0.05$). The USPW may be very useful to evaluate overall usability of power wheelchair including its safety, operability, efficiency, and satisfaction. The developed usability scale (USPW) may help wheelchair makers become aware of the problems of present power wheelchairs and the users’ needs, allowing them to make better ones.

As the number of wheelchair users increases, safety accidents related to wheelchairs are increasing. Wheelchair training has been emphasized as a way to deal with this problem. Therefore, this study aimed to develop a wheelchair training structure as an adjustable type and verify its usefulness. Methods: In order to develop the wheelchair training structure as an adjustable type, idea meetings were held by related experts. The structure reflecting the ideas generated by the expert meetings was drawn through 3D modeling and it was produced by a commissioned woodwork shop. Then the final products including the adjustable curb and stairs were evaluated to verify their effectiveness and user satisfaction. Ten physical or occupational therapists rated satisfaction using the Korean-Quebec User Evaluation of Satisfaction with Assistive Technology, and four manual wheelchair users rated effectiveness using the wheelchair Skill Test-Questionnaire 5.0. And the evaluations were conducted twice before and after the 10 wheelchair training sessions each with 30 min duration. Results the result of satisfaction evaluation of the adjustable curbs and stairs by the 10 therapists showed that effectiveness was the highest, and the size and weight were the lowest. As for the effectiveness evaluation by the four manual wheelchair users, both the capacity and confidence of all subjects improved. Conclusion: This study confirmed that training using this type of wheelchair training construct will help wheelchair users improve the confidence and skills of using wheelchair which are essential for their safety and independent mobility. Therefore, if the adjustable curbs and stairs are to be used in the rehabilitation process of early manual wheelchair users, it is expected to contribute to the advancing their successful social return.

This study investigated changes in gait symmetry with trunk displacement during phase-shifted auditory paced treadmill walking for effective training with auditory cueing provided in conventional gait training. Eighteen able-bodied participants walked at a comfortable speed on a treadmill and the measured cadence was set at 100% (baseline). The phase-shifted auditory cue was set to both phase advance and delay of 20% at 5% intervals based on the baseline with respect to matching foot contact to the auditory cue. Trunk displacement increased with the phase-shifted auditory cue, and the largest value was found in the 120% condition compared to baseline ($P<0.05$). Step length, step time, and swing phase time symmetry ratio gradually increased with increasing phase delay and gradually decreased with increasing phase advance on the linear model. However, single support time and stance phase time symmetry ratio showed contrasting characteristics compared to above parameters. The results indicate that the phase-shifted auditory cue significantly changes gait symmetry and trunk displacement. Particularly, the 20% phase advance and delay cues yielded about a 5% change in the step length symmetry ratio. These results could be used to induce a symmetric gait pattern when an asymmetric gait appears in hemiplegia.

The overall survival (OS) prediction for nonsmall cell lung carcinoma (NSCLC) patients of clinical IIIA-N2 stage undergone various treatments was investigated through a refined Taylor series expansion algorithm. The model was created according to a population-based study in Taiwan. The proposed prediction algorithm is based on the well-known hit and target model adopted for analyzing the cell death from the microscopic viewpoint. It also implies the application of the Taylor series expansion to the population-based survey dataset. In the proposed algorithm, the basic degradation of a patient’s health is represented via a specific function comprising a single exponential term exp($-\alpha t$). The refined algorithm successfully predicted NSCLC IIIA-N2 patients’ OS rate. A total of 127,301 patients were collected from 2010 to 2017. Then, 2655 patients were recognized as effective events and classified into eight classes according to various medical treatments, namely surgical operation, radiotherapy, and chemotherapy. For each class of patients, the average life was evaluated, according to Taylor’s expansion algorithm, and the average derived life range spread from 3.51 to 7.81 years. An index of life gain with specific treatment was defined according to the Taguchi optimization analysis. The life gains provided by the surgical operation, chemotherapy, and radiotherapy were 2.74, 1.18, and 0.48 years. The surgical operation was the most beneficial treatment, which is in concert with recommendations of European experts. A similar finding was also reflected in four out of eight classes, which included the surgical operation in the treatment plans of most Taiwanese hospitals.

The study was to compare an off-loading cushion, designed for individuals with spinal cord injury, with air cushion to analyze the effect of pressure on skin injury and user satisfaction. The off-loading cushion can reduce the incidence of pressure ulcers by minimizing the pressure of the ischial tuberosity and coccyx. Because anatomical structures of each participant are different, 3D scanning is used in the customized manufacturing of the cushions. In the 3D modeling, the product is designed so that the ischial tuberosity and coccyx have minimal contact with the cushion’s surface area. The X-sensor was used to confirm the pressure dispersion effect. As a result, maximum pressure of the ischial tuberosity and the coccyx were measured and observed to be lower than that of the air cushion. User satisfaction was compared between two cushions using the QUEST 2.0. The off-loading cushion has slightly higher service and product satisfaction than the air cushion. Based on these findings, this study suggests that off-loading cushions reduce the occurrence of pressure injury compared to air cushions.

This study investigated the quantitative scaling properties of the center of pressure (COP) as well as the spatial-temporal properties of the COP to elucidate the postural control behavior of healthy elderly (HE) adults and adults with Parkinson’s disease (PD) during quiet standing. Eighteen adults with PD and eighteen HE adults participated in this study. The COP movements were recorded while participants stood on either a firm surface or on a foam pad with their eyes either opened or closed. The sway ranges in the anterior–posterior (AP) ($R_x)$ and medio-lateral (ML) ($R_y)$ directions, the total length of the trajectory ($L)$, sway area ($A)$, and scaling exponents ($\alpha )$ from detrended fluctuation analysis were computed from the measured COP data. All temporal variables of the COP in all conditions were found to be significantly larger in the PD group than in the HE group. Low scaling exponents obtained for the PD group showed this group possessed diminished postural control ability compared to the HE group. The PD group showed unpredictable open-loop control in both the AP and ML directions. This proprioceptive control became predictable and the time scale relations decreased as the postural challenges increased. The AP and ML closed-loop control of the PD group was more predictable than that of the HE group only when proprioception was distorted using intact visual input, and the visual and proprioceptive inputs were both intact.

Cable-driven parallel robots (CDPR) have been well used in the rehabilitation field. However, the cables can provide the tension in a single direction, there is a pseudo-drag phenomenon of the cables in the CDPR, which will have a great impact on the safety of patients. Therefore, the novelty of this work is that a bionic muscle cable is used to replace the ordinary cable in the CDPR, which can solve the pseudo-drag phenomenon of the cables in the CDPR and improve the safety performance of the rehabilitation robot. The cable-driven lower limb rehabilitation robot with bionic muscle cables is called as the bionic muscle cable-driven lower limb rehabilitation robot (BMCDLR). The motion planning of the rigid branch chain of the BMCDLR is studied, and the dynamics and system stiffness of the BMCDLR are analyzed based on the man–machine model in this paper. The influence of the parameters of the elastic elements in the bionic muscle cables on the mechanical characteristics of the BMCDLR system was analyzed by using simulation experiments. The research results can provide a reference basis for research on the safety evaluation and control methods of the BMCDLR system.

This paper reports the design, fabrication and calibration results of a miniature cross-shaped three-axial piezoresistive force sensor, which can simultaneously detect three force components in orthogonal directions. MEMS technology was used to fabricate the sensor structure and deposit a phosphosilicate layer on the silicon wafer to form piezoresistive resistors. Using the finite element simulation, the developed sensor performance characteristics, such as linearity, repeatability, sensitivity, and hysteresis, are analyzed for different arrangements of eight piezoresistors on the silicon beam surface. The sensor performance was experimentally validated by monitoring the voltage variation of Wheatstone bridge when a load-bearing rigid rod was loaded in three different directions by a set of weights. Calibration results exhibited linear output responses with the maximum linearity of 0.98 and small crosstalk below 7%. The MEMS sensor repeatability was tested with a commercial stepper motor by measuring a step function-varying profile force was applied to the sensor. Further optimization of the sensor design for sensing six degrees of freedom movement is envisaged with its sensitivity enhancement by the silicon substrate reduction.

In this study, a new instance selection method that combines the neural network with weighted fuzzy memberships (NEWFM) and Takagi–Sugeno (T–S) fuzzy model was proposed to improve the classification accuracy of healthy people and Parkinson’s disease (PD) patients. In order to evaluate the proposed instance selection for the classification accuracy of healthy people and PD patients, foot pressure data were collected from healthy people and PD patients as experimental data. This study uses wavelet transforms (WTs) to remove the noise from the foot pressure data in preprocessing step. The proposed instance selection method is an algorithm that selects instances using both weighted mean defuzzification (WMD) in the T–S fuzzy model and the confidence interval of a normal distribution used in statistics. The classification accuracy was compared before and after instance selection was applied to prove the superiority of instance selection. Classification accuracy before and after instance selection was 77.33% and 78.19%, respectively. The classification accuracy after instance selection exhibited a higher classification accuracy than that before instance selection by 0.86%. Further, McNemar’s test, which is used in statistics, was employed to show the difference in classification accuracy before and after instance selection was applied. The results of the McNemar’s test revealed that the probability of significance was smaller than 0.05, which reaffirmed that the classification accuracy was better when instance selection was applied than when instance selection was not applied. NEWFM includes the bounded sum of weighted fuzzy memberships (BSWFMs) that can easily show the differences in the graphically distinct characteristics between healthy people and PD patients. This study proposes new technique that NEWFM can detect PD patients from foot pressure data by the BSWFMs embedded in devices or systems.

The purpose of this study was to design and validate a new bilateral instrumented wheel system (IWS) to measure triaxial handrim forces and torques simultaneously during the wheelchair propulsion. The designed and implemented system measures the force applied to the handrims on both sides of a manual wheelchair using 6-axis force/torque sensors. In addition, a user interface receives the measurements from the left and right IWSs. To verify the accuracy of the wheel system, we evaluate force and torque measurements during the static and dynamic tests. The maximum error in static measurements of force and torque are 4.29% and 1.95%, respectively. Likewise, dynamic tests using planar forces and axle torques provide low errors and measurements that are highly correlated with the expected values ($r>0.98$). The results revealed that the proposed IWS can be used to measure bilateral 3D handrim reaction forces with acceptable accuracy.

This study intends to develop a system for managing the health of the spinal joints of elderly people who mainly live on Korean floor heating (Ondol). The spine health management system consists of a seat cushion-type posture balance device that can measure the sitting posture, an application for smart devices capable of real-time collection of posture balance data, and a database server for analysis and visualized feedback of the data. Each force signal measured with the four load cells installed in posture balance device is wirelessly transmitted to an Arduino-based Android application, and the center of pressure (COP) value of the sitting position is analyzed using the four load cell data. To test the usability of the spinal health management system, the COP values of front, back, left and right torso tilts of healthy adults in a sitting position were measured with the posture balance device and 3D motion analysis program (Visual 3D, USA). After that, the COP values were compared and analyzed. As a result of the analysis, the COP direction data (front, back, left and right) measured with the posture balance device exactly matched the direction analyzed by the 3D motion analysis system.

Although noninvasive ventilation has been increasingly used in clinics and homes to treat respiratory diseases, the problem of air leaks should not be neglected because they may affect the performance of the ventilation and even pose a threat to life. The detection and estimation of the leakage are required to implement auto-compensation, which is important in the development of intelligent ventilation. In this study, the methods of detection and estimation of the leakage were established and validated. Ventilation experiments were performed based on the established experimental platform. The air flow and pressure were detected at different locations of the airway to determine the relationship between the leakage and the other variables. The leakage was estimated using linear predictor models. The curves describing the relationships among pressure, flow and volume changed regularly with the leakage. For pressure-controlled ventilation, the leakage could be estimated by the detected peak flow and by the ventilation volume of one breathing cycle. The methods for the leakage estimation were validated. Volume-controlled ventilation was also studied. Although the leakage could be estimated using the detected peak pressure, the limitation of volume-controlled ventilation was obvious for noninvasive ventilation (NIV). Leaks could be detected and estimated using a linear predictor model via the flow/pressure curve. The use of this model is a potential method for the auto-compensation of noninvasive ventilation.

Proprioception while standing is important for the balance control, but the proprioception has not been investigated in the unconstrained standing conditions. The purpose of this study was to investigate the effects of age and gender on the thresholds of perception and muscle response in response to the support surface rotation. The experiment was designed so that the thresholds depend mainly on the proprioception, i.e., quasistatic condition (0.2^∘/s rotation of the platform) with eyes closed. Fifty-two healthy subjects (half young and half elderly) participated in this study. A platform was developed which can be rotated in four directions. Perception threshold angle was registered from subjects’ pressing a button. Muscle response threshold angle was determined as the earlier onset of EMG in lower limb muscles. Two standing conditions (feet together and natural stance) were tested. Repeated-measures ANOVA showed that both thresholds increased with age. Post hoc tests revealed (1) that the perception threshold was greater for women than men in the elderly and (2) both thresholds of the elderly were greater for the feet-together stance than natural stance. Inferior perception sensitivity of platform rotation in elderly women may be associated with inferior performance in cortical postural control and greater fall ratio compared to elderly men, which suggests the need of proprioception trainings.

In this study, the correlation between triggered timing for head and neck CT angiography (TT CTA) scanning and the average of CT values of both left and right arterial to upper sinuses (LRA/US) reaching a maximal ratio was surveyed and explored using the inverse problem algorithm according to a six-factor semi-quantitative analysis of 251 patients. Six risk factors, namely TT CTA, mean arterial pressure (MAP), heart rate (HR), contrast media solution (CMS), given pressure (Pre), and body surface area (BSA) were used to identify a nonlinear first-order regression correlation between projected and actual LRA/US values. The respective 22 terms were derived via the STATISTICA program. In doing so, a customized loss function ($\mathrm{\Phi }$) was defined according to the total fluctuation between theoretically projected and actual LRA/US values for all 216 patients. Thus, $216\times 22=4752$ individual data points were included in the algorithm to optimize the compromised solution array [$22\times 1=22$] of LRA/US values. The results exhibited a close correlation with loss function $\mathrm{\Phi }=2.0144$, correlation coefficient $r^2=0.9650$, and a 93.13% variance. Another group of 35 patients with similar symptoms was selected to verify the prediction accuracy and exhibited a high coincidence, although the reverse calculation-based correlation between CC CTA and LRA/US was still controversial from a clinical viewpoint. The proposed algorithm is considered quite instrumental in predicting the LRA/US with ischemic stroke symptoms in the CTA examination.