This review describes the concept of artificial intelligence, introduces the working mechanism and the main structure of medical expert system, as well as the development history of medical expert system at home and abroad and its applications in the medical field. The concept of machine learning, commonly used algorithms and its clinical applications in medical diagnosis are briefly described. It mainly introduces the application of artificial intelligence in neurology. The advantages and disadvantages of artificial intelligence system in medical field are analyzed. Finally, the future of artificial intelligence in the medical field is forecasted.
ObjectiveTo investigate the clinical value of real-time elastosonography in diagnosis of thyroid nodules. MethodsThe clinical date of 168 patients with thyroid nodules, admitted to our hospital from June 2009 to December, were retrospectively analyzed with pathological findings as the reference standard． The findings on elastography were classified into five grades: grade 0 to Ⅳ. The nodules with grade less than Ⅱ were diagnosed as benign, otherwise more than Ⅲ were diagnosed as malignancy. ResultsThere were 208 nodules in 168 patients: nodular goiter was in 125 cases, thyroid adenoma in 36 cases, thyroid malignant tumor in 41 cases including 39 cases for thyroid papillary carcinoma, 1 case for thyroid medullary carcinoma, 1 case for thyroid non-Hodgkin lymphoma. Other nodules were in 6 cases, including diffuse toxic goiter in 1 case, local lymphocytic thyroiditis in 3 cases, and subacute granulomatous thyroiditis in 2 cases. There were 148 thyroid nodules in grade 0-Ⅱ and 60 nodules in grade Ⅲ-Ⅳ. According to the pathological findings, 97.3%(144/148) thyroid nodules of grade 0-Ⅱ were benign, however, 38.3% (23/60) of grade Ⅲ-Ⅳ were benign. Furthermore, 2.7% (4/148) thyroid nodules of grade 0-Ⅱ were malignancy, while 61.7% (37/60) of grade Ⅲ-Ⅳ were malignancy. The sensitivity， specificity, and accuracy of the real-time elastosonography in diagnosis of thyroid nodules was 90.2%(37/41), 86.2%(144/167), and 87.0%(181/208), respectively. ConclusionReal-time elastosonography can reflect the relative hardness of thyroid nodules and provide useful information for diagnosis, which is helpful in differentiating benign and malignant thyroid nodules.
Objective To provide the anatomical basis of contralateral C7 root transfer for the recovery of the forearm flexor function. Methods Thirty sides of adult anti-corrosion specimens were used to measure the length from the end of nerves dominating forearm flexor to the anastomotic stoma of contralateral C7 nerve when contralateral C7 nerve transfer was used for repair of brachial plexus lower trunk and medial cord injuries. The muscle and nerve branches were observed. The length of C7 nerve, C7 anterior division, and C7 posterior division was measured. Results The length of C7 nerve, anterior division, and posterior division was (58.8 ± 4.2), (15.4 ± 6.7), and (8.8 ± 4.4) mm, respectively. The lengths from the anastomotic stoma to the points entering muscle were as follow: (369.4 ± 47.3) mm to palmaris longus, (390.5 ± 38.8) mm (median nerve dominate) and (413.6 ± 47.4) mm (anterior interosseous nerve dominate) to the flexor digitorum superficialis, (346.2 ± 22.3) mm (median nerve dominate) and (408.2 ± 23.9) mm (anterior interosseous nerve dominate) to the flexor digitorum profundus of the index and the middle fingers, (344.2 ± 27.2) mm to the flexor digitorum profundus of the little and the ring fingers, (392.5 ± 29.2) mm (median nerve dominate) and (420.5 ± 37.1) mm (anterior interosseous nerve dominate) to the flexor pollicis longus, and (548.7 ± 30.0) mm to the starting point of the deep branch of ulnar nerve. The branches of the anterior interosseous nerve reached to the flexor hallucis longus, the deep flexor of the index and the middle fingers and the pronator quadratus muscle, but its branches reached to the flexor digitorum superficials in 5 specimens (16.7%). The branches of the median nerve reached to the palmaris longus and the flexor digitorum superficial, but its branches reached to the deep flexor of the index and the middle fingers in 10 specimens (33.3%) and to flexor hallucis longus in 6 specimens (20.0%). Conclusion If sural nerve graft is used, the function of the forearm muscles will can not be restored; shortening of humerus and one nerve anastomosis are good for forearm flexor to recover function in clinical.
Transcatheter aortic valve replacement (TAVR) is the best treatment for severe aortic stenosis with high surgical risk, and low body weight significantly increased the risk of surgery and postoperative all-cause mortality. A case of elderly female diagnosed with severe aortic valve stenosis and extremely low body weight was presented in this article. Additionally, horizocardia and low located coronary orifice were also found in this patient, which markedly increased the risk and complexity of the TAVR procedure. During the operation, circulatory collapse occurred, and prosthetic valve was quickly released under emergency cardiopulmonary resuscitation. The operation was successful and the patient’s vital signs recovered soon. The follow-up showed that the patient was in good condition.
Objective To explore the feasibility and accuracy of ultrasound volume navigation (UVN) combined with X-ray fluoroscopy-guided percutaneous pedicle screw implantation through a prospective randomized controlled study. Methods Patients with thoracic and lumbar vertebral fractures scheduled for percutaneous pedicle screw fixation between January 2022 and January 2023 were enrolled. Among them, 60 patients met the selection criteria and were included in the study. There were 28 males and 32 females, with an average age of 49.5 years (range, 29-60 years). The cause of injury included 20 cases of traffic accidents, 21 cases of falls, 17 cases of slips, and 2 cases of heavy object impact. The interval from injury to hospital admission ranged from 1 to 5 days (mean, 1.57 days). The fracture located at T12 in 15 cases, L1 in 20 cases, L2 in 19 cases, and L3 in 6 cases. The study used each patient as their own control, randomly guiding pedicle screw implantation using UVN combined with X-ray fluoroscopy on one side of the vertebral body and the adjacent segment (trial group), while the other side was implanted under X-ray fluoroscopy (control group). A total of 4 screws and 2 rods were implanted in each patient. The implantation time and fluoroscopy frequency during implantation of each screw, angle deviation and distance deviation between actual and preoperative planned trajectory by imaging examination, and the occurrence of zygapophysial joint invasion were recorded. Results In terms of screw implantation time, fluoroscopy frequency, angle deviation, distance deviation, and incidence of zygapophysial joint invasion, the trial group showed superior results compared to the control group, and the differences were significant (P<0.05). Conclusion UVN combined with X-ray fluoroscopy-guided percutaneous pedicle screw implantation can yreduce screw implantation time, adjust dynamically, reduce operational difficulty, and reduce radiation damage.
Objective To investigate the effectiveness of tissue transplantation combined with bone transmission in treatment of large defects of tibial bone and soft tissue. Methods Between February 2006 and February 2011, 15 cases of traumatic tibia bone and soft tissue defects were treated. There were 12 males and 3 females, aged from 16 to 54 years (mean, 32 years). After internal and external fixations of fracture, 11 patients with open fracture (Gustilo type III) had skin necrosis, bone exposure, and infection; after open reduction and internal fixation, 2 patients with closed fracture had skin necrosis and infection; and after limb replantation, 2 patients had skin necrosis and bone exposure. The area of soft tissue defect ranged from 5 cm × 5 cm to 22 cm × 17 cm. Eight cases had limb shortening with an average of 3.5 cm (range, 2-5 cm) and angular deformity. The lenghth of bone defect ranged from 4 to 18 cm (mean, 8 cm). The flap transplantation and skin graft were used in 9 and 6 cases, respectively; bone transmission and limb lengthening orthomorphia were performed in all cases at 3 months after wound healing; of them, 2 cases received double osteotomy bone transmission, and 14 cases received autologous bone graft and reset after apposition of fracture ends. Results All flaps and skin grafts survived; the wound healed at 3.5 months on average (range, 3 weeks-18 months). The length of bone lengthening was 6-22 cm (mean, 8 cm). The time of bone healing and removal of external fixation was 9.5-39.0 months (mean, 15 months). The healing index was 40-65 days/cm (mean, 55 days/cm). All patients were followed up 1-5 years (mean, 4 years). The wounds of all the cases healed well without infection or ulceration. The functions of weight-bearing and walking were recovered; 6 cases had normal gait and 9 cases had claudication. The knee range of motion was 0° in extention, 120-160° in flexion (mean, 150°). According to the American Orthopaedic Foot and Ankle Society (AOFAS) scoring system for ankle function, the results were excellent in 7 cases, good in 4 cases, and fair in 4 cases, with an excellent and good rate of 73.3%. Conclusion Tissue transplantation combined with bone transmission is an effective method to treat large defects of soft tissue and tibial bone, which can increase strength of bone connection and reduce damage to the donor site.
ObjectiveTo analyze the characteristics and cardiac anatomy of patients with conduction block after transcatheter aortic valve replacement (TAVR) with Venus-A valve.MethodsRetrospective analysis was conducted on the clinical data of patients with severe aortic stenosis who underwent TAVR with Venus-A valve in the Second Affiliated Hospital of Army Military Medical University from October 2017 to May 2020. According to the occurrence of heart conduction block after TAVR, the patients were divided into the blocked group and the unblocked group, and the differences in characteristics and cardiac anatomy between the two groups were compared.ResultsForty-nine patients with severe aortic stenosis were included in the analysis, including 29 in the blocked group and 20 in the unblocked group. The incidence of atrial fibrillation in the blocked group was higher than that in the unblocked group (P=0.015), and there was no statistically significant difference in other preoperative indicators (P>0.05). There was no statistically significant difference in postoperative indicators between the blocked group and the unblocked group (P>0.05). Among bicuspid aortic valve, the ellipticity of left ventricular outflow tract and annulus in the blocked group were higher than those in the unblocked group (P<0.05), and the ratio of the short diameter of the left ventricular outflow tract to the bottom diameter of the implanted valve was smaller than that of the unblocked group (t=2.225, P=0.043). There was no significant difference in other cardiac anatomical indicators (P>0.05). As to tricuspid aortic valve cases, there was no significant difference in cardiac anatomic parameters between the blocked group and the unblocked group (P>0.05).ConclusionsFor bicuspid aortic valve patients with severe aortic stenosis and implanted with Venus-A valve, larger elliptic rate of annulus or left ventricular outflow tract, smaller proportion of left ventricular outflow tract diameter to the bottom diameter of implanted valve are associated with conduction block after TAVR. These anatomical patterns might be used as potential clinical indicators to predict postoperative conduction block.
Objective To compare the effectiveness of O-arm navigation and ultrasound volume navigation (UVN) in guiding screw placement during minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) surgery. Methods Sixty patients who underwent MIS-TLIF surgery for lumbar disc herniation between June 2022 and June 2023 and met the selection criteria were included in the study. They were randomly assigned to group A (screw placement guided by UVN during MIS-TLIF) or group B (screw placement guided by O-arm navigation during MIS-TLIF), with 30 cases in each group. There was no significant difference in baseline data, including gender, age, body mass index, and surgical segment, between the two groups (P>0.05). Intraoperative data, including average single screw placement time, total radiation dose, and average single screw effective radiation dose, were recorded and calculated. Postoperatively, X-ray film and CT scans were performed at 10 days to evaluate screw placement accuracy and assess facet joint violation. Pearson correlation and Spearman correlation analyses were used to observe the relationship between the studied parameters (average single screw placement time and screw placement accuracy grading) and BMI. Results The average single screw placement time in group B was significantly shorter than that in group A, and the total radiation dose of single segment and multi-segment and the average single screw effective radiation dose in group B were significantly higher than those in group A (P<0.05). There was no significant difference in the total radiation dose between single segment and multiple segments in group B (P>0.05), while the total radiation dose of multiple segments was significantly higher than that of single segment in group A (P<0.05). No significant difference was found in the accuracy of screw implantation between the two groups (P>0.05). In both groups, the grade 1 and grade 2 screws broke through the outer wall of the pedicle, and no screw broke through the inner wall of the pedicle. There was no significant difference in the rate of facet joint violation between the two groups (P>0.05). In group A, both the average single screw placement time and screw placement accuracy grading were positively correlated with BMI (r=0.677, P<0.001; r=0.222, P=0.012), while in group B, neither of them was correlated with BMI (r=0.224, P=0.233; r=0.034, P=0.697). Conclusion UVN-guided screw placement in MIS-TLIF surgery demonstrates comparable efficiency, visualization, and accuracy to O-arm navigation, while significantly reducing radiation exposure. However, it may be influenced by factors such as obesity, which poses certain limitations.