Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI's potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities-particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.
Medicine, Chinese Traditional/methods* ; Artificial Intelligence ; Humans ; Precision Medicine ; Decision Support Systems, Clinical

Mitochondrial dysfunction in chondrocytes is a key pathogenic factor in osteoarthritis (OA), but directly modulating mitochondria in vivo remains a significant challenge. This study is the first to verify a correlation between mitochondrial dysfunction and the downregulation of the FOXO3 gene in the cartilage of OA patients, highlighting the potential for regulating mitophagy via FOXO3 gene modulation to alleviate OA. Consequently, we developed a chondrocyte-targeting CRISPR/Cas9-based FOXO3 gene-editing tool (FoxO3) and integrated it within a nanoengineered 'truck' (NETT, FoxO3-NETT). This was further encapsulated in injectable hydrogel microspheres (FoxO3-NETT@SMs) to harness the antioxidant properties of sodium alginate and the enhanced lubrication of hybrid exosomes. Collectively, these FoxO3-NETT@SMs successfully activate mitophagy and rebalance mitochondrial function in OA chondrocytes through the Foxo3 gene-modulated PINK1/Parkin pathway. As a result, FoxO3-NETT@SMs stimulate chondrocytes proliferation, migration, and ECM production in vitro, and effectively alleviate OA progression in vivo, demonstrating significant potential for clinical applications.

BACKGROUND:Current osteoarthritis modeling methods include anterior cruciate ligament transection(ACLT)and ACLT combined with medial meniscal anterior horn resection.ACLT requires excessive postoperative exercise,which is time and labor-intensive.Complete removal of anterior horn of the medial meniscus can cause collateral damage and increase variability in modeling outcomes,requiring higher surgical skills from the surgeon. OBJECTIVE:To modify and simplify the traditional method to create animal osteoarthritis model and compare osteoarthritis symptoms of different modeling methods under a low-load exercise environment. METHODS:Forty-eight Sprague-Dawley rats were randomly assigned in four groups(n=12 per group):sham operation(complete exposure of the knee cavity of the left hind limb followed by suturing the joint cavity and skin),ACLT,ACLT+anterior horn resection(removal of the anterior horn of the medial meniscus)and ACLT+anterior horn tear(anterior horn tear of the medial meniscus).At 4 weeks after modeling,the rats were euthanized and their knee specimens were collected for gross observation,X-ray and CT scans,pathological observation,and PCR detection. RESULTS AND CONCLUSION:Gross observation:Mild meniscal wear was observed in the ACLT group.In the ACLT+anterior horn tear group,severe wear of the lateral condyle articular surface,mild wear of the medial condyle articular surface,severe meniscal wear,and full wear of the medial meniscus were observed.The ACLT+resection group showed severe wear of the lateral condyle articular surface,mild wear of the medial condyle articular surface,absence of the anterior horn of the medial meniscus,and meniscus wear area＞50%.Imaging examinations showed no significant difference among the four groups.However,the anterior tibial translocation sign was observed in the three operation groups and the anterior horn of the medial meniscus was missing in the ACLT+anterior horn resection group.Histopathological section observation:Hematoxylin-eosin,toluidine blue,and Sirius red staining showed smooth joint surfaces in the sham operation group and ACLT group;cartilage damage and matrix degradation were evident in the ACLT+anterior horn tear and ACLT+anterior horn transection groups,with less cartilage damage and matrix degradation in the ACLT+anterior horn tear group.PCR results showed higher mRNA expressions of interleukin 1β,interleukin 6,interleukin 8,tumor necrosis factor α,matrix metalloproteinase 1 and matrix metalloproteinase 3 and lower mRNA expressions of aggrecan in the ACLT+anterior horn tear group and ACLT+anterior horn resection group than in the sham operation group and ACLT group(P＜0.05).The mRNA expressions of interleukin 6,matrix metalloproteinase 1,and matrix metalloproteinase 3 were higher in the ACLT + anterior horn resection group than in the ACLT +anterior horn tear group(P＜0.05).To conclude,ACLT alone is less likely to induce osteoarthritis with obvious cartilage wear.ACLT combined with anterior horn resection or tear of the medial meniscus can induce obvious symptoms of osteoarthritis and achieve similar modeling effects.

Objective:To investigate the safety and clinical efficacy of the lateral-rectus approach combined with the Pfannenstiel approach in the treatment of pelvic fractures complicated with urethral rupture.Methods:From January 2013 to June 2021, 20 patients with pelvic fracture complicated with urethral rupture were surgically managed through the lateral-rectus approach and the Pfannenstiel approach at Department of Traumatic Surgery, Center for Orthopaedic Surgery, the Third Hospital Affiliated to Southern Medical University. They were 15 males and 5 females, with an average age of 42 years (from 18 to 55 years). By the Tile classification, there were 11 cases of type B and 9 cases of type C. The first-stage urethral realignment was performed via the Pfannenstiel approach in the supine position after general anesthesia in conjunction with an urologist; at the second-stage, the lateral-rectus approach was used to reduce and fixate the acetabular or pelvic fractures. The operation time, intraoperative blood loss, fracture reduction quality, pelvic functional recovery and complications were documented.Results:In this cohort, the operation time ranged from 80 to 240 min, averaging 140.5 min; the time for simple urethral convergence ranged from 20 to 30 min; the intraoperative blood loss ranged from 400 mL to 2,000 mL, averaging 730 mL. According to the Mears andVelyvis evaluation for fracture reduction quality, anatomical reduction was achieved in 13 cases, satisfactory reduction in 6 cases, and unsatisfactory reduction in one. The 20 patients were followed up for 12 to 68 months (mean, 37 months) after surgery. One fracture got nonunited but the other fractures got united after 3.0 to 4.5 months (mean, 3.5 months). According to the Majeed scoring system, the pelvic function at 12 months after surgery was excellent in 12 cases, good in 6 and fair in 2, giving an excellent and good rate of 90% (18/20). Screw loosening was found in one patient, traction injury to the lumbosacral trunk nerve in another patient, varying degrees of dysuria which responded to periodic urethral dilation in 8 patients, urethral stricture in 3 patients and erectile dysfunction in 5 patients. No abdominal hernia or pelvic infection was observed.Conclusions:The lateral-rectus approach combined with the Pfannenstiel approach can be used effectively to reduce and fixate the pelvic and acetabular fractures, and to repair the urethral rupture in one stage as well. They are also safe due to a low incidence of such complications as abdominal wall hernia and pelvic infection.

Objective:To investigate the clinical efficacy of integrated acetabular wing-plate in the management of both column fractures with posterior wall involvement via the lateral-rectus approach.Methods:A retrospective case series analysis was performed on 43 patients with both column fractures involved with posterior wall admitted to Third Affiliated Hospital of Southern Medical University from March 2016 to June 2020. There were 35 males and 8 females, aged 19-78 years [(47.3±13.3)years]. The single lateral-rectus approach was used to expose, reduce and fix the fracture using the integrated acetabular wing-plate. Operation time, incision length, intraoperative blood loss and bone healing time were recorded. Quality of fracture reduction was assessed according to the Matta reduction criteria at postoperative 2 days, and hip function by the modified Merle d′Aubigné-Postel score at postoperative 3 months and 12 months. Postoperative complications were observed.Results:All patients were followed up for 12-48 months [(28.1±13.1)months]. Operation duration was 35-150 minutes [(84.6±26.3)minutes], with incision length of 8-12 cm [(9.4±1.0)cm] and intraoperative blood loss of 100-1 200 ml [(200(300, 500) ml]. Bone healing time was 3-6 months [(3.9±0.9)months]. According to Matta reduction criteria,the results were excellent in 32 patients, good in 7 and poor in 4 at postoperative 2 days, with the excellent and good rate of 91%. The modified Merle d′Aubigné-Postel score was 12-18 points [(16.1±1.5)points] at postoperative 3 months, and 13-18 points [(17.3±1.2)points] at postoperative 12 months ( P<0.01). According to modified Merle d′Aubigné-Postel score, the results were excellent in 3 patients, good in 34 and fair in 6 at postoperative 3 months, with the excellent and good rate of 86%; and the results were excellent in 32 patients, good in 9 and fair in 2 at postoperative 12 months, with the excellent and good rate of 95% ( P<0.01). Postoperative complications were incision fat liquefaction and infection in 1 patient, weakness of hip adduction in 5 and screw loosening with traumatic arthritis in 1. There was no sciatic nerve injury or heterotopic ossification. Conclusion:For both column fractures with posterior wall involvement, single lateral-rectus approach combined with integrated acetabular wing-plate has advantages of short operation time, minor trauma, low rate of bleeding and complications, and good hip function recovery, indicating satisfactory clinical effect.

Objective:To investigate the application of three-dimensional (3D) image fusion technique of pelvic enhanced CT and magnetic resonance neurography (MRN) on the patients of pelvic fractures with lumbosacral plexus injury.Methods:From January 2019 to December 2020, 15 patients (11 males, 4 females, mean age 26.67±11.34 of pelvic fracture (AO classification C1.3 of 11 cases, C2 of 2 cases, C3 of 2 cases) with lumbosacral plexus injury underwent 3D image fusion of pelvic enhanced CT and MRN. All patients exhibited lower limb nerve dysfunction after injury. The preoperative muscle strength were evaluated by British Medical Research Council (BMRC) criteria: grade 0 in 2 cases, grade 1 in 5, grade 2 in 7 and grade 3 in 1. Physical examination and enhanced CT combined with MRN 3D image fusion technology were used to accurately determine the injury site of lumbosacral plexus nerve, fracture displacement, and the direction of blood vessels and ureters, and develop corresponding surgical plans. The neurological functions were measured in post-operation follow-up.Results:All 15 operations were successfully completed and the site of lumbosacral plexus injury during operation was consistent with preoperative fusion image, and inconsistency of injury characteristic in 4 patients (4/15, 27%). Among the 6 cases of laparoscopic surgery, 2 cases were changed to open surgery because of the difficulty of nerve decompression. The average time of 4 cases of laparoscopic surgery was 116.27±26.46 min and intraoperative blood loss was 102.50±79.32 ml. The average time of 11 cases of open operation was 123.64±38.28 min, and intraoperative blood loss was 713.64±393.12 ml. For the opening operations, 9 cases were successfully decompressed, and nerve disruption was observed in 2 patients. All 15 patients were followed up. The average follow-up time was 9.33±2.19 months. The radial bony healing was observed in each case at the end of follow-up, mean healing time was 5.03±1.04 months (range, 3-6 months). In addition, patients' muscle strength recovered, 8 cases of grade 5, 3 cases of grade 4, 1 case of grade 3, 1 case of grade 2, and 2 cases of grade 0 after surgery. The difference was statistically significant ( Z=3.27, P<0.001). On the other hand, in sensory function assessment, there were 8 cases of grade S5, 1 case of grade S4, 3 cases of grade S3, 1 case of grade S2 and 2 cases of grade S0 after surgery. Conclusion:3D image fusion of enhanced CT and MRN can accurately locate and characterize pelvic fractures combined with lumbosacral plexus injury before surgery, accurately guide the formulation of surgical plan, and reduce surgical trauma and related complications.

Objective:To investigate the clinical effect assistant with pelvic unlocking reduction frame for the treatment of old Denis I or II sacral fractures combined with sacral plexus nerve injury.Methods:From January 2013 to October 2020, 37 patients diagnosed with old sacral fractures with sacral plexus nerve injury which Gibbons classification was grade III were divided into the use group and the non-use group according to whether assisted with pelvic unlocking reduction frame. Eighteen patients (11 males, 7 females, mean age 38±6.4, range from 13-56) were selected into the use group and nineteen patients (14 males, 5 females, mean age 42±10.7, range 19-59) were selected into the non-use group. The three-dimensional (3D) pelvic model (1∶1) was printed before operation. The operation time, intraoperative bleeding, Matta score, visual analogue scale (VAS), Majeed score and gibbons sacral nerve injury grade of the two groups were compared. The healing time and complications of each group was recorded.Results:The average operation time of the use group and the non-use group was 121.0±16.2 min and 182.6±16.2 min, respectively, with significant difference ( t=11.54, P<0.001). The mean operative bleeding was 686±382 ml of the use group and 963±348 ml of the non-use group ( t=2.38, P=0.003). The quality of fracture reduction was evaluated according to Matta scoring standard: the excellent and good rate of the use group was 94% (17/18), and that of the non-use group was 68% (13/19) ( P=0.039). The curative effect was evaluated according to the Majeed score: the use group was 88.72±7.03 points, and that of the non-use group was 72.00±9.75 points ( t=5.96, P<0.001) at 1 year post-operative. One year after operation, the VAS scale of the use group was 0.83±0.71 points, and that of the non-use group was 1.00±0.82 points ( t=0.66, P=0.512). According to Gibbons classification, 15 patients were grade I, 1 patient was grade II and 2 patients were grade III in the use group and 11 patients were grade I, 3 patients were grade II and 5 patients were grade III in the non-use group one year after operation ( Z=-1.04, P=0.401). One patient in the use group presented rupture of plate without symptoms. In the non-use group, 1 case with internal iliac vein rupture which treated with gelatin sponge and no obvious bleeding after operation. 4 cases with unequal length of lower limbs, walking claudication. The complication rate of the use group was 6% (1/18), and that of the non-use group was 26% (5/19) ( P=0.042) . Conclusion:The lateral rectus abdominis approach combined with pelvic unlocking reduction frame can reduce the operation time and bleeding, improve the fracture reduction in the treatment of old Denis type I and II sacral fractures with sacral plexus injury.

Objective:To explore the efficacyof direct anterior approach (DAA) combined with direct posterior approach (DPA) for the treatment of Pipkin IV fracture.Methods:Data of 18 patients with Pipkin IV fracture treated through DAA combined with DPA from January 2016 to April 2019 was retrospectively analyzed. There were 13 males and 5 females, with an average age of 43.2 years (range,19-56 years). Fractures were caused by traffic accident in 15 and by falling in 3. The fracture lines of 13 cases were located below the fovea of the femoral head and 5 cases were located above the fovea. According to Letournel-Judet classification for acetabular fractures, there were 14 cases of posterior acetabular wall fractures, 2 cases of posterior wall fractures involving posterior column, and 2 transverse plus posterior wall fractures. The operation was performed through DAA approach to treat the femoral head fractures, and DPA approach was used to treat acetabular fractures. Radiographs and CT scans of the pelvis were reexamined after surgery, and fracture reduction, healing, and complications such as femoral head necrosis, sciatic nerve injury, superior gluteal neurovascular injury and heterotopic ossification were evaluated. Quality of acetabular reduction was evaluated according to the criteria proposed by Matta. Thompson-Epstein scoring system was used to evaluate hip function.Results:The average operation time was 133 min (range, 75-205 min). And the average blood loss was 371 ml (range, 240-600 ml). All 18 patients were followed up for 6 to 36 months, with an average period of 15.7 months. All fractures healed 10 to14 weeks after surgery. Three patients had symptoms of sciatic nerve injury after the injury, who recovered 6 to 12 weeks after the operation. All femoral head fractures were reduced. According to Matta criteria of reduction quality, anatomic reduction was gained in 13 cases, and satisfactory reduction was obtained in 3 cases, while unsatisfactory reduction was found in 2 cases, and the overall satisfactory rate was 88.9%(16/18). Two patients had Brooker I level heterotopic ossification. There was no iatrogenic vascular injury, avascular necrosis of femoral head, infection, internal fixation failure or other complications. According to the Thompson-Epstein scoring system at the latest follow-up, the functional results of the affected hip were excellent in 7 cases, good in 8, fair in 2 and poor in 1.Conclusion:Treatment of Pipkin IV fractures through DAA combined with DPA approach reduces surgical invasion. And it can directly reduce and fix the femoral head and posterior acetabular fracture, and protect the important structures such as the arteriae circumflexa femoris medialis, sciatic nerve and lateral femoral cutaneous nerve, and reduce the occurrence of complications such as femoral head necrosis and heterotopic ossification. Therefore, DAA combined with DPA is aneffective method for the treatment of Pipkin IV fractures.

Objective:To explore the surgical method and clinical efficacy of lateral-rectus approach (LRA) in the treatment of fragility fractures of the pelvis (FFP) in the elderly.Methods:A retrospective study was conducted for elderly FFP patients from January 2011 to December 2019. All the pelvic fractures should be exposed and reduced through LRA and fixed with pelvic reconstruction plates and channel screws. Then, a total of 30 elderly patients were included in the study, including 9 males and 21 females, with an average age of 72.5 years (range, 60-87 years). Fractures were caused by car accident in 5 cases, by falling from high places in 8 cases and by tumbling in 17 cases. According to the FFP classification, there were 6 cases of type IIc (6/30, 20%), 22 cases of type III (22/30, 73.33%, of which 13 cases were type IIIa, 7 cases were type IIIb, and 2 cases were type IIIc), 2 cases of type IVa (2/30, 6.67%). Among that, 2 cases suffered ipsilateral acetabular fractures, 17 suffered medical diseases such as hypertension, coronary heart disease, diabetes, etc., and none suffered extremities fractures or other types of injuries. Surgical field was exposed retroperitoneally through LRA, combined with lower limb traction to reduce the anterior and posterior pelvis ring fractures. Then, the reductions were done in direct visions and verified through X-ray fluoroscopy. After that, the posterior ring was fixed with reconstruction plate and/or sacroiliac screws, and the anterior ring was fixed with reconstruction plate or INFIX. The quality of fracture reduction was evaluated by Matta score and the postoperative function was evaluated by Majeed score.Results:All the 30 patients were surgical treated through LRA. The time from injury to operation was 5 to 20 days, with an average of 9.9 days. The operating time ranged from 35 to 150 min (mean, 73.5 min) and the intraoperative bleeding ranged from 220 to 2 400 ml (mean, 586.7 ml). Fractures were successfully reduced under direct vision and the positions of the plates and screws were monitored through X-ray fluoroscopy during the operation. Postoperative X-rays and CT scans showed satisfactory reduction of the pelvic ring. According to Matta criteria, the quality of fracture reduction was evaluated as excellent in 18 cases, good in 6 cases, fair in 4 cases and poor in 2 cases. The overall excellent and good rate was 80% (24/30). All patients were followed up for 6-24 months, the fractures were all healed, and all fractures healed for 2-5 months, with an average of 3.5 months. At the last follow-up, Majeed scores were 86.1±6.11 (range, 66-92), including 21 excellent cases, 7 good cases and 2 fair cases, with an excellent and good rate of 93.3% (28/30). As for complications, 1 patient developed deep venous thrombosis of the affected lower limb, and the thrombosis disappeared after thrombolytic therapy. One patient had fat liquefaction in the incision, and the wound healed after intensive dressing change. After INFIX fixation, 2 patients showed numbness on the lateral thigh of the affected side, and the symptoms were relieved after symptomatic treatment. Four patients were found to have internal fixation screws loosening during follow-up, but still achieved good fracture healing.Conclusion:The entire hemipelvic ring could be exposed through LRA without cutting the peritoneum, so that the sacroiliac joint, ilium wing and anterior ring fractures could be reduced under direct version. In the treatment of pelvis fragility fractures of the elderly, effective reduction and fixation could be achieved using reconstruction plates or channel screws through LRA.

Objective:To investigate the surgical technique and the clinical effects of direct posterior approach (DPA) with the fixation of percutaneous tunnel screw and plate for acetabular posterior comminuted fractures.Methods:Thirty-six cases with acetabular posterior comminuted fractures treated by this technique from January 2016 to July 2020 were retrospectively analyzed in this study. There were 28 males and 8 female, aged 42.0±12.1 (range 19-64) years. According to Letournel-Judet classification, there were 28 cases of transverse associated with posterior wall fractures, 6 cases of posterior column with posterior wall fractures and 2 cases of T shape with posterior wall fractures. DPA was adopted in prone position. The anterior and posterior column fractures of the acetabulum were reduced under direct vision and then fixed with percutaneous tunnel screw. Further, the posterior wall fractures of the acetabulum were reduced and fixed with plate and screws. The operation duration, intraoperative blood loss, incision length, fracture union time, fracture reduction quality, postoperative complications and hip function were recorded.Results:The incision was 9.8±1.2 (range 8-12) cm. The operation duration was 102.9±21.4 (range 65-145) min. Intraoperative bleeding was 214.0±116.9 (range 100-640) ml. Postoperative X-ray and CT examinations showed perfect reduction. All the patients were followed up for 20.9±9.2 (range 10-38) months. The fracture healing time was 4.6±1.0 (range 3-6) months. There was no patient with damaged superior gluteal nerve and blood vessel. There were 2 cases of femoral head cystic changes without pain in walking, 1 case of postoperative infection and bacteremia who was cured at 1 month after debridement and anti-infection treatment, 1 case of sciatic nerve injury but recovered at 3 months after operation, and 1 case of heterotopic ossification at 3 months after surgery without affecting hip motion. According to the Matta's criteria, the reduction quality of the acetabular fracture was rated as excellent in 28 cases, good in 6 cases, fair in 2 cases. According to the modified Merle D'Aubigné and Postel scoring system, hip joint function was excellent in 24 cases, good in 10 cases and fair in 2 cases.Conclusion:DPA approach can directly reduce acetabular posterior comminuted fractures through a minimal incision. Combined with the technique of percutaneous tunnel screw, it displays great advantages of less trauma and with good clinical effects.