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.
【Abstract】 Objective To explore the effectiveness of bone grafting by intervertebral disc endoscope for postoperativenonunion of fracture of lower limb. Methods Between August 2004 and August 2008, 40 patients (23 males and 17 females) with postoperative nonunion of femoral and tibial fracture, aged 20-63 years (mean, 41.5 years) were treated. Nonunion of fracture occurred at 10-16 months after internal fixation. During the first operation, the internal fixation included interlocking intramedullary nail ing of femoral fracture in 12 cases and plate in 16 cases, and interlocking intramedullary nail ing of tibial fractures in 9 cases and plate in 3 cases. The X-ray films showed hypertrophic nonunion in 24 cases, common nonunion in 3 cases, and atrophic nonunion in 13 cases. Results The average operation time was 61 minutes (range, 40-80 minutes), and the blood loss was 80-130 mL (mean, 100 mL). The hospital ization time were 6-11 days (mean, 8.1 days). Incisions healed by first intention in all patients with no complication of infection or neurovascular injury. Forty patients were followed up 10-16 months (mean, 12.3 months). The X-ray films showed that all patients achieved healing of fracture after 4-10 months (mean, 6.8 months). No pain, disfunction, or internal fixation failure occurred. Conclusion Bone grafting by intervertebral disc endoscope is an effective method for treating postoperative nonunion of femoral and tibial fracture.
Objective To investigate the effectiveness and safety of low molecular weight heparin combined with aspirin for perioperative prophylactic anticoagulation in patients with lower extremity fracture after splenectomy. MethodsThe clinical data of 50 patients with splenic rupture combined with lower extremity fracture between January 2009 and June 2022 were retrospectively analyzed. All patients were given enoxaparin sodium at 48 hours after splenectomy, and stopped at 24 hours before fracture surgery. After fracture surgery, the patients were divided into aspirin group (group A, 15 cases), low molecular weight heparin group (group B, 16 cases), and low molecular weight heparin combined with aspirin group (group C, 19 cases) according to different anticoagulation regimens. The treatment course was 28 days. There was no significant difference in gender, age, body mass index, cause of injury, fracture site, time from injury to operation, complications, and other general data between groups (P>0.05). The occurrence of venous thromboembolism (VTE) was observed; hemoglobin (Hb), platelet (PLT), D-D dimer, and fibrinogen degradation product (FDP) were recorded before operation and at 1, 3, and 7 days after operation, and the effect of anticoagulation regimen on coagulation function was observed. The incidences of wound complications and bleeding related complications were recorded, and the total perioperative blood loss, hidden blood loss, and overt blood loss were calculated. Results The incidences of VTE in groups A, B, and C were 13.33% (2/15), 12.50% (2/16), and 5.26% (1/19), respectively, and there was no significant difference between groups (χ2=0.770, P=0.680). There was no portal vein thrombosis and no VTE-related death in the 3 groups. There was no significant difference in the levels of Hb, PLT, D-D dimer, and FDP between groups before and after operation (P>0.05); and there was no significant difference in total perioperative blood loss, hidden blood loss, and overt blood loss between groups (P>0.05). No local skin necrosis was found in all patients. In group A, 1 case occurred redness and swelling of incision; in group B, 1 case had incision discharge, redness, and swelling, and 1 case had fat liquefaction; in group C, 1 case had repeated incision exudation accompanied by local tissue redness and swelling, and 1 case had local hematoma. The incidences of adverse incision in groups A, B, and C were 6.66% (1/15), 12.50% (2/16), and 11.76% (2/19), respectively, with no significant difference (χ2=0.302, P=0.860). There were 4 cases of bleeding related complications, including 1 case of incision ecchymosis in groups A and B respectively, with the incidence of 6.66% and 6.25%, respectively; there was 1 case of incision hematoma and 1 case of bleeding in group C, with the incidence of 11.76%; showing no significant difference in the incidence of bleeding related complications between groups (χ2=0.268, P=0.875). Conclusion Perioperative combined use of low molecular weight heparin and aspirin for prevention of anticoagulation in patients with splenic rupture and lower extremity fracture can effectively prevent the occurrence of VTE without increasing the incidence of complications, which is an effective and safe treatment method. However, whether the incidence of VTE can be reduced needs to be further studied by expanding the sample size.
目的：探討綜合康復治療體系對54例地震致下肢骨折患者功能恢復的影響。方法：采用綜合康復治療方法治療“5·12”汶川大地震所致54例下肢骨折患者，臨床觀察患者傷口的愈合情況和骨折的復位情況，有無骨折并發癥，分析比較治療前后患者下肢功能恢復情況及日常生活活動能力的改善。結果：康復治療后關節活動度明顯改善，由入院時的平均218.61°增加至出院時的237.5°（P＜0.001）。Barthel指數由入院時的平均55.4增加至出院時的70.8（P＜0.001），日常生活活動能力有較大幅度提高。結論：綜合康復治療體系對于地震傷致下肢骨折患者的功能恢復至關重要，一套完善的體系應包括：①康復治療早期介入，功能鍛煉長期堅持；②發揮大型綜合性醫院的優勢，多學科交叉，多部門合作；③功能康復和心理康復并重；④專業人士與社會團體共同參與。
ObjectiveTo explore the value of recombinant inferior vena cava filter (IVCF) in the prevention of perioperative pulmonary embolism in patients with lower limb or pelvic fracture combined with deep venous thrombosis (DVT).MethodsThe clinical data of 168 patients with lower limb or pelvic fracture combined with DVT were analyzed retrospectively.ResultsThe filters were successfully implanted in 168 patients, and the recoverable filters were removed after (48.3±4.8) d (14–97 d). The filters were removed successfully in 159 cases, and the removal rate was 94.6%. Sixty-one cases were found to have thrombus on the filter after contrast examination or removal of vena cava filter, that is, the thrombus interception rate was 36.3%.ConclusionFor patients with lower limb or pelvic fracture combined with DVT, the rechargeable vena cava filter can effectively stop thrombosis and avoid pulmonary embolism.