Objective To establish the mode of anterior cervical surgery in outpatient setting, and evaluate its preliminary effectiveness. Methods A clinical data of patients who underwent anterior cervical surgery between January 2022 and September 2022 and met the selection criteria was retrospectively analyzed. The surgeries were performed in outpatient setting (n=35, outpatient setting group) or in inpatient setting (n=35, inpatient setting group). There was no significant difference between the two groups (P>0.05) in age, gender, body mass index, smoking, history of alcohol drinking, disease type, the number of surgical levels, operation mode, as well as preoperative Japanese Orthopaedic Association (JOA) score, visual analogue scale score of neck pain (VAS-neck), and visual analogue scale score of upper limb pain (VAS-arm). The operation time, intraoperative blood loss, total hospital stay, postoperative hospital stay, and hospital expenses of the two groups were recorded; JOA score, VAS-neck score, and VAS-arm score were recorded before and immediately after operation, and the differences of the above indexes between pre- and post-operation were calculated. Before discharge, the patient was asked to score satisfaction with a score of 1-10. Results The total hospital stay, postoperative hospital stay, and hospital expenses were significantly lower in the outpatient setting group than in the inpatient setting group (P<0.05). The satisfaction of patients was significantly higher in the outpatient setting group than in the inpatient setting group (P<0.05). There was no significant difference between the two groups in operation time and intraoperative blood loss (P>0.05). The JOA score, VAS-neck score, and VAS-arm score of the two groups significantly improved at immediate after operation when compared with those before operation (P<0.05). There was no significant difference in the improvement of the above scores between the two groups (P>0.05). The patients were followed up (6.67±1.04) months in the outpatient setting group and (5.95±1.90) months in the inpatient setting group, with no significant difference (t=0.089, P=0.929). No surgical complications, such as delayed hematoma, delayed infection, delayed neurological damage, and esophageal fistula, occurred in the two groups. Conclusion The safety and efficiency of anterior cervical surgery performed in outpatient setting were comparable to that performed in inpatient setting. Outpatient surgery mode can significantly shorten the postoperative hospital stay, reduce hospital expenses, and improve the patients’ medical experience. The key points of the outpatient mode of anterior cervical surgery are minimizing damage, complete hemostasis, no drainage placement, and fine perioperative management.
Objective To develop a deep learning system for CT images to assist in the diagnosis of thoracolumbar fractures and analyze the feasibility of its clinical application. Methods Collected from West China Hospital of Sichuan University from January 2019 to March 2020, a total of 1256 CT images of thoracolumbar fractures were annotated with a unified standard through the Imaging LabelImg system. All CT images were classified according to the AO Spine thoracolumbar spine injury classification. The deep learning system in diagnosing ABC fracture types was optimized using 1039 CT images for training and validation, of which 1004 were used as the training set and 35 as the validation set; the rest 217 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. The deep learning system in subtyping A was optimized using 581 CT images for training and validation, of which 556 were used as the training set and 25 as the validation set; the rest 104 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. Results The accuracy and Kappa coefficient of the deep learning system in diagnosing ABC fracture types were 89.4% and 0.849 (P<0.001), respectively. The accuracy and Kappa coefficient of subtyping A were 87.5% and 0.817 (P<0.001), respectively. Conclusions The classification accuracy of the deep learning system for thoracolumbar fractures is high. This approach can be used to assist in the intelligent diagnosis of CT images of thoracolumbar fractures and improve the current manual and complex diagnostic process.