Objective To compare the effectiveness of TiRobot-assisted and C-arm X-ray fluoroscopy assisted percutaneous kyphoplasty (PKP) via pedicle of vertebra in the treatment of osteoporotic vertebral compression fracture (OVCF) of thoracic vertebrae. Methods The clinical data of 85 patients with OVCF of thoracic vertebrae who were admitted between January 2020 and March 2023 and met the selection criteria was retrospectively analyzed including 40 patients (50 vertebrae) undergoing PKP assisted by TiRobot (group A) and 45 patients (50 vertebrae) undergoing PKP assisted by C-arm X-ray fluoroscopy (group B). There was no significant difference in the comparison of baseline data such as gender, age, body mass index, bone mineral density T-value, fracture segment, trauma history, and preoperative numerical rating scale (NRS) score, Oswestry disability index (ODI), and Cobb angle of injured vertebra between the two groups (P>0.05). The effectiveness evaluation indexes of the two groups, including the operation time, the volume of injected cement, the times of fluoroscopies, the length of hospital stay, and the occurrence of postoperative complications were collected and compared. Anteroposterior and lateral X-ray films and CT of the injured vertebra were reviewed at 1 day after operation to observe whether there was cement leakage and to evaluate the distribution of cement in the injured vertebra. Before and after operation, pain was assessed using the NRS score, dysfunction was assessed using the ODI, and vertebral height recovery was assessed by measuring the Cobb angle of the injured vertebrae by X-ray films. Results Both groups of patients successfully completed the operation, the operation time, the volume of injected cement, the times of fluoroscopies, and the length of hospital stay in group A were significantly less than those in group B (P<0.05). The patients in two groups were followed up 4-12 months (mean, 9.6 months). Bone cement leakage occurred in 5 vertebrae in group A and 15 vertebrae in group B after operation, all of which leaked to the intervertebral space and around the vertebral body, and the patients had no obvious clinical symptoms. The difference of bone cement leakage between the two groups was significant (P<0.05). No severe complication such as intraspinal leakage, infection, or vascular embolism was found in the two groups. At 1 day after operation, the distribution index of bone cement in group A was mostly grade Ⅴ, which was well dispersed; while in group B, it was mostly grade Ⅱ and grade Ⅴ; the difference of bone cement distribution index between the two groups was significant (P<0.05). The NRS score, ODI, and Cobb angle of injured vertebra in both groups were significantly improved at 1 day after operation when compared with preoperative ones (P<0.05). There was no significant difference in the difference of the above indexes between the two groups before and after operation (P>0.05). Conclusion TiRobot-assisted unilateral PKP in the treatment of OVCF of thoracic vertebrae is safe and effective, which can reduce the X-ray transmission times during operation, shorten the operation time, reduce the volume of bone cement injection, and thus decrease incidence of bone cement leakage.
Objective To explore the efficiency of artificial intelligence algorithm model using preoperative blood indexes on the prediction of deep vein thrombosis (DVT) in patients with lower limb fracture before operation. Methods Patients with lower limb fracture treated in the Department of Orthopedics of Deyang People’s Hospital between January 2018 and December 2022 were retrospectively selected. Their basic and clinical data such as age, gender, height and weight, and laboratory examination indicators at admission were collected, then the neutrophi to lymphocyte ratio (NLR), monocyte to lymphocyte ratio (MLR), and platelet to lymphocyte ratio (PLR) were calculated. According to color Doppler ultrasound indication of DVT in lower extremities at admission, the patients were divided into DVT group and non-DVT group. After data preprocessing, grey relational analysis (GRA) was used to screen the combination model of important predictive features of DVT, and BP neural network prediction model was established using the selected features. Finally, the accuracy of BP neural network prediction model was evaluated, and was compared with those of different models in clinical prediction of DVT. Results A total of 4033 patients with lower limb fracture were enrolled, including 3127 cases in the DVT group and 906 cases in the non-DVT group. GRA selected seven important predictive features: absolute lymphocyte value, NLR, MLR, PLR, plasma D-dimer, direct bilirubin, and total bilirubin. The accuracies of logistic regression analysis, random forest, decision tree, BP neural network and GRA-BP neural network combination model were 74%, 76%, 75%, 84% and 87%, respectively. The GRA-BP neural network combination model had the highest accuracy. Conclusion The GRA-BP neural network selected in this paper has the highest accuracy in preoperative DVT risk prediction in patients with lower limb fracture, which can provide a reference for the formulation of DVT prevention strategies.