Abstract： Diseases prognosis is often influenced by multiple factors, and some intricate non-linear relationships exist among those factors. Artificial neural network （ANN）, an artificial intelligence model, simulates the work mode of biological neurons and has a b capability to analyze multi-factor non-linear relationships. In recent years, ANN is increasingly applied in clinical medical fields, especially for the prediction of disease prognosis. This article focuses on the basic principles of ANN and its application in disease prognosis research.
A mechanical study on the bones of 29 rabbits following implantation of carbontendon was carried out. The rabbits were divided into seven groups according to the observation time (2,4,6,8,12,20 and 30 weeks after operation). A bundle of artificial tendon composed of 7,000 carbon fibers was passedthrough a tunnel in the tibia, and both ends of the artificial tendon were ligated to the muscle fibers. The mechanical strength and histological structure of the carbonbone junction and their relationship were studied in each group. Carbon fiberwas split and degradated in six to eight weeks after operation. The tensile strength of carbontendon in the soft tissue was decreased from 82±4.6N in the second week to 27±5.31N and6.3±1.81N in the sixth and eighth week respectively. The tensile strength of carbontendon increased from 3.01±1.2N to 6.1±2.01N at the carbon -tendon-bone junction in the bone. The tensile strength of carbon-tendon was unsatisfactory for implantation into bone. The carbon-tendon was split and degradated and the tensile strength was not b enough to cope with the early functional exercises.
Objective To analyze the hot spot and future application trend of artificial intelligence technology in the field of intensive care medicine. Methods The CNKI, WanFang Data, VIP and Web of Science core collection databases were electronically searched to collect the related literature about the application of artificial intelligence in the field of critical medicine from January 1, 2013 to December 31, 2022. Bibliometrics was used to visually analyze the author, country, research institution, co-cited literature and key words. Results A total of 986 Chinese articles and 4 016 English articles were included. The number of articles published had increased year by year in the past decade, and the top three countries in English literature were China, the United States and Germany. The predictive model and machine learning were the most frequent key words in Chinese and English literature, respectively. Predicting disease progression, mortality and prognosis were the research focus of artificial intelligence in the field of critical medicine. ConclusionThe application of artificial intelligence in the field of critical medicine is on the rise, and the research hotspots are mainly related to monitoring, predicting disease progression, mortality, disease prognosis and the classification of disease phenotypes or subtypes.
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 summarize our operative experiences of cardiac reoperation after mechanical valve prosthesis replacement and investigate the causes of reoperation and the perioperative techniques and operation methods. Methods From January 2001 to December 2008, we performed reoperation on 105 patients (59 males and 46 females, aged 50.2±10.6 years old) who had undergone mechanical valve prosthesis replacement. Among the patients, there were 31 cases of mitral valvular replacement (+ tricuspid valvular plasticity), 38 cases of aortic valvular replacement (+ tricuspid valvular plasticity), 11 cases of Bentall procedure, 7 cases of mitral and aortic bivalvular replacement (+tricuspid valvular plasticity), 8 cases of tricuspid valvular replacement, 6 cases of repairing of prosthetic leakage, and 4 others cases. The time interval between two operations was 3 months to 18 years (46.3 ±31.9 months). Before reoperation, the cardiac function (NYHA) of the patients was class Ⅱ in 27 patients, class Ⅲ in 53 patients, and class Ⅳ in 25 patients. Results There were 6 hospital deaths with a mortality of 5.71%(6/105). All others recovered to NYHA class ⅠⅡ. The causes of mortality included 1 case of multiple organ failure, 1 case of low cardiac output after operation, 1 case of aortic pseudoaneurysm rupture, 1 case of severe infection due to brain complication and 2 cases of prosthetic valve endocarditis (PVE). The causes for cardiac reoperation after mechanical valve prosthesis replacement were 67 cases of prosthetic leakage (63.80%), 16 cases of PVE (15.23%), 14 cases of prosthetic thrombosis (13.33%) and 8 cases of other valvular anomalies. Followup was done for 11 to 107 months, which showed two cases late deaths of cardiac arrest and cerebral hemorrhage. Conclusion Patients who have received mechanical valve prosthesis replacement may undergo cardiac reoperation due to paravalvular prosthetic leakage, paravalvular endocarditis, and prosthetic thrombosis. The keys to a successful cardiac reoperation include appropriate preoperative preparations, operational timing, and suitable choosing of cardiopulmonary bypass and operational skills.
Objective
To summarize the surgical technique and the effectiveness of Becker V-shaped lateral rotation osteotomy in total hip arthroplasty (THA) for Crowe type IV development dislocation of the hip (DDH).
Methods
Between January 2000 and December 2009, 18 patients (22 hips) with Crowe type IV DDH underwent THA. There were 3 males and 15 females with an average age of 54 years (range, 41-75 years). The unilateral hip was involved in 14 cases and bilateral hips in 4 cases. All patients had over anteversion of the femoral neck, with the acetabular anteversion angle of (21.28 ± 4.87)°, the femoral neck anteversion angle of (59.06 ± 1.44)°, and combined anteversion angle of (80.33 ± 1.55)°. All the patients had limb-length discrepancy, ranged from 1.0 to 3.5 cm (mean, 2.5 cm). Before operation, gluteus medius muscle strength was grade 2 in 17 hips and grade 3 in 5 hips; severe or moderate claudication was observed in 13 and 5 patients, respectively. Trendelenburg sign was positive in all patients. Preoperative Harris score was 30.00 ± 6.32. Cementless prosthesis was used. Becker V-shaped lateral rotation osteotomy and subtrochanteric shortening with overlapping femoral resection were performed, and proximal femoral shaft splitting was performed on 21 hips having narrow bone marrow cavity.
Results
All the cases achieved primary healing of incision. No complication of anterior dislocation, deep infection, nerve traction injury, or femoral uncontrolled fracture occurred. All the cases were followed up 3-12 years (mean, 8 years). Postoperative X-ray films showed that the initial fixation result of femoral prosthesis was excellent in 18 hips and good in 4 hips. Bone healing of osteotomy stump was obtained at 3-6 months (mean, 5 months) after operation. Affected limb prolonged for 2.5-3.5 cm (mean, 3.0 cm ) at 1 year after operation; limb-length discrepancy was 0.5-1.5 cm (mean, 1.0 cm). The gluteus medius muscle strength was restored to grade 4 in 5 hips and grade 5 in 17 hips. At last follow-up, 13 patients had no claudication, and 5 patients had mild claudication; Trendelenburg sign was negative in 15 cases and was positive in 3 cases; the Harris score was significantly improved to 91.89 ± 3.22; all showing significant difference when compared with preoperative ones (P lt; 0.05). At last follow-up, the acetabular anteversion angle, the femoral neck anteversion angle, and combined anteversion angle were (19.33 ± 4.49), (13.33 ± 5.70), and (32.67 ± 5.35)°, respectively, all showing significant differences when compared with preoperative ones (P lt; 0.05). No aseptic loosening, osteolysis, or rediolucent line was found around the femoral component. No implant subsidence, stem varus, or revision occurred.
Conclusion
Becker V-shaped lateral rotation osteotomy is a safe and predictable method to treat type Crowe type IV DDH.
