Since the knee joint bears the full weight load of the human body and the highest pressure loads while providing flexible movement, it is the body part most vulnerable and susceptible to osteoarthritis. In exercise therapy, the early rehabilitation stages last for approximately six weeks, during which the patient works with the physical therapist several times each week. The patient is afterwards given instructions for continuing rehabilitation exercise by him/herself at home. This study develops a rehabilitation exercise assessment mechanism using three wearable sensors mounted on the chest, thigh and shank of the working leg in order to enable the patients with knee osteoarthritis to manage their own rehabilitation progress. In this work, time-domain, frequency-domain features and angle information of the motion sensor signals are used to classify the exercise type and identify whether their postures are proper or not. Three types of rehabilitation exercise commonly prescribed to knee osteoarthritis patients are: Short-Arc Exercise, Straight Leg Raise, and Quadriceps Strengthening Mini-squats. After ten subjects performed the three kinds of rehabilitation activities, three validation techniques including 10-fold cross-validation, within subject cross validation, and leave-one-subject cross validation are utilized to confirm the proposed mechanism. The overall recognition accuracy for exercise type classification is 97.29% and for exercise posture identification it is 88.26%. The experimental results demonstrate the feasibility of the proposed mechanism which can help patients perform rehabilitation movements and progress effectively. Moreover, the proposed mechanism is able to detect multiple errors at once, fulfilling the requirements for rehabilitation assessment.

Reasons for dissatisfaction with total knee arthroplasty (TKA) include unequal flexion or extension gap, soft tissue imbalance, and patella maltracking, which often occur with mismatch between femoral and tibial coronal bony alignment in the knee joint or extremely varus or valgus alignment. However, lower limb coronal alignment classification is based only on hip–knee–ankle angle (HKAA), leading to oversight regarding a mismatch between femoral and tibial coronal alignment. We aimed to classify alignment of the lower limbs according to the mechanical alignment of the femur and tibia in a healthy population. All 214 normal triple films were reviewed retrospectively. HKAA, mechanical lateral distal femoral angle (mLDFA), mechanical medial proximal tibial angle (mMPTA), angle between the femoral anatomical axis and the mechanical axis (AA-MA), and knee alignment angle (KAA) were measured. Subjects were categorized into one of five types based on the mechanical alignment of femur and tibia. Mean HKAA, mLDFA, and mMPTA of all subjects were 1.2°, 87.3°, and 85.8°, respectively. All subjects were classified into one of five types with significant differences (p < 0.001). About 61% of subjects showed neutral alignment, of which nearly 40% were type 2 (valgus of the femur and varus of the tibia with oblique joint line: mLDFA 85.0° ± 1.4°, mMPTA 85.1° ± 1.2°, TJLA 2.7° ± 2.4°) and 60% exhibited neutral alignment with a neutral femur and tibia (type 1). In varus and valgus types, mismatch between the mechanical angle of the femur and tibia was common. Varus alignment, including types 3 (varus of the tibia: mLDFA 88.0° ± 1.4°, mMPTA 83.5° ± 1.6°) and 4 (varus of both the tibia and femur: mLDFA 91.4° ± 1.4°, mMTPA 85.2° ± 2.0°), was found in 30% of subjects. Valgus alignment (type 5 valgus of femur: mLDFA 84.6° ± 1.6°, mMPTA 88.8° ± 2.0°) accounted for 8.9% of all subjects. Mismatch between mechanical alignment of the femur and tibia was common in varus and valgus alignment types. Joint line obliquity was also observed in 40% of the neutral alignment population. This classification provides a quick, simple interpretation of femoral and tibial coronal alignment, and more detailed guidance for preoperative planning for TKA than the traditional varus–neutral–valgus classification.

Total knee arthroplasty (TKA) is the most common treatment for degenerative osteoarthritis of that articulation. However, either in rehabilitation clinics or in hospital wards, the knee range of motion (ROM) can currently only be assessed using a goniometer. In order to provide continuous and objective measurements of knee ROM, we propose the use of wearable inertial sensors to record the knee ROM during the recovery progress. Digitalized and objective data can assist the surgeons to control the recovery status and flexibly adjust rehabilitation programs during the early acute inpatient stage. The more knee flexion ROM regained during the early inpatient period, the better the long-term knee recovery will be and the sooner early discharge can be achieved. The results of this work show that the proposed wearable sensor approach can provide an alternative for continuous monitoring and objective assessment of knee ROM recovery progress for TKA patients compared to the traditional goniometer measurements.

Total knee arthroplasty (TKA) is one of the most common treatments for people with severe knee osteoarthritis (OA). The accuracy of outcome measurements and quantitative assessments for perioperative TKA is an important issue in clinical practice. Timed up and go (TUG) tests have been validated to measure basic mobility and balance capabilities. A TUG test contains a series of subtasks, including sit-to-stand, walking-out, turning, walking-in, turning around, and stand-to-sit tasks. Detailed information about subtasks is essential to aid clinical professionals and physiotherapists in making assessment decisions. The main objective of this study is to design and develop a subtask segmentation approach using machine-learning models and knowledge-based postprocessing during the TUG test for perioperative TKA. The experiment recruited 26 patients with severe knee OA (11 patients with bilateral TKA planned and 15 patients with unilateral TKA planned). A series of signal-processing mechanisms and pattern recognition approaches involving machine learning-based multi-classifiers, fragmentation modification and subtask inference are designed and developed to tackle technical challenges in typical classification algorithms, including motion variability, fragmentation and ambiguity. The experimental results reveal that the accuracy of the proposed subtask segmentation approach using the AdaBoost technique with a window size of 128 samples is 92%, which is an improvement of at least 15% compared to that of the typical subtask segmentation approach using machine-learning models only.

For compression fracture, vertebral body height loss (VBHL) and kyphotic angle (KA) are two important imaging parameters for determining the prognosis and appropriate treatment. This study used previous measurement methods to assess the degree of VBHL and KA, compare and examine differences between various measurement methods, and examine the correlation between relevant measurement parameters and intravertebral cleft (IVC) in the vertebral body. The radiographic images (lateral view of the T-L spine) of 18 patients with a single-level vertebral compression fracture were reviewed. We measured 9 characteristic lengths and angles on plain radiographs, including anterior vertebral height (AVH) and AVH of the adjacent upper and lower levels, middle vertebral height (MVH) and MVH of the adjacent upper and lower levels, posterior vertebral height (PVH), and vertebral body width, and assessed 6 parameters, including vertebral compression ratio (VBCR), percentage of anterior height compression (PAHC), percentage of middle height compression (PMHC), kyphotic angle (KA), calculated kyphotic angle (CKA), and IVC. The results showed that VBCR is a simple and rapid method of VBHL assessment, but it may result in an underestimation of the degree of VBHL compared to PAHC. WhenPMHC<40%orkyphoticangle>15°, the probability of IVC occurring on the vertebral body was higher which means the higher risk of vertebral body instability. The results of this study could provide a reference for surgeons when using imaging modalities to assess the degree of vertebral body collapse.

Robot-assisted pedicle screw placement for spine surgery has become popular in recent years. This study compares clinical, radiographic outcomes and the screw loosening rate between robot-assisted and fluoroscopy-guided pedicle screw placement in patients who underwent transforaminal lumbar interbody fusion (TLIF). We retrospectively examined 108 patients with the degenerative lumbar disease who underwent TLIF. According to whether the robotic system was used, patients were assigned to either the robot-assisted (Ro TLIF, n = 29) or fluoroscopy-guided TLIF (FG TLIF, n = 79) group. Radiographic parameters and patient-reported outcomes, including leg and back pain visual analog scale (VAS) and Oswestry Disability Index (ODI), were assessed. Loosening signs were noted in 48 out of 552 pedicle screws. The screw loosening rate was higher in the FG TLIF (10.2%) than Ro TLIF group (4.3%). A significant correlation was found between screw loosening and age, the number of level(s) fused, and the ratio of the average distance from the pedicle screw to the upper endplate to vertebral body height. VAS-leg, VAS-back, and ODI showed significant improvements in both groups postoperatively (all p < 0.05). These results indicated that robot-assisted pedicle screw placement in TLIF had a lower screw loosening rate and similar patient-reported outcomes compared with the fluoroscopy-guided technique.