ObjectiveTo analyze the predictive value of ensemble classification algorithm of random forest for delirium risk in ICU patients with cardiothoracic surgery. MethodsA total of 360 patients hospitalized in cardiothoracic ICU of our hospital from June 2019 to December 2020 were retrospectively analyzed. There were 193 males and 167 females, aged 18-80 (56.45±9.33) years. The patients were divided into a delirium group and a control group according to whether delirium occurred during hospitalization or not. The clinical data of the two groups were compared, and the related factors affecting the occurrence of delirium in cardiothoracic ICU patients were predicted by the multivariate logistic regression analysis and the ensemble classification algorithm of random forest respectively, and the difference of the prediction efficiency between the two groups was compared.ResultsOf the included patients, 19 patients fell out, 165 patients developed ICU delirium and were enrolled into the delirium group, with an incidence of 48.39% in ICU, and the remaining 176 patients without ICU delirium were enrolled into the control group. There was no statistical significance in gender, educational level, or other general data between the two groups (P>0.05). But compared with the control group, the patients of the delirium group were older, length of hospital stay was longer, and acute physiology and chronic health evaluationⅡ(APACHEⅡ) score, proportion of mechanical assisted ventilation, physical constraints, sedative drug use in the delirium group were higher (P<0.05). Multivariate logistic regression analysis showed that age (OR=1.162), length of hospital stay (OR=1.238), APACHEⅡ score (OR=1.057), mechanical ventilation (OR=1.329), physical constraints (OR=1.345) and sedative drug use (OR=1.630) were independent risk factors for delirium of cardiothoracic ICU patients. The variables in the random forest model for sorting, on top of important predictor variable were: age, length of hospital stay, APACHEⅡ score, mechanical ventilation, physical constraints and sedative drug use. The diagnostic efficiency of ensemble classification algorithm of random forest was obviously higher than that of multivariate logistic regression analysis. The area under receiver operating characteristic curve of ensemble classification algorithm of random forest was 0.87, and the one of multivariate logistic regression analysis model was 0.79.ConclusionThe ensemble classification algorithm of random forest is more effective in predicting the occurrence of delirium in cardiothoracic ICU patients, which can be popularized and applied in clinical practice and contribute to early identification and strengthening nursing of high-risk patients.
ObjectiveTo encourage clinicians to code the major diagnosis of diseases, in order to improve the correct rate of disease major diagnosis coding. MethodsWe analyzed the data of major diagnostic codes by clinicians from January 2012 to June 2013. The group leader of the clinical treatment was designated to be responsible for the disease coding. Disease coders introduced knowledge of international classification of diseases to the clinical department according to the different characteristics of disease in each department and communicated with clinicians on the problems of disease coding. Then, we tried to find out whether this method could improve the correct rate of major diagnosis coding of diseases. ResultsThe rate of disease major coding by clinicians of the whole hospital and pilot departments increased from 94.081% to 98.301%. The correct rate of disease major coding decreased from 75.824% to 67.483% and then reached 81.893%. The correct rate of disease major coding of the Department of Hematology was 83.824% in August 2012 and then decreased with the lowest rate of 68.025%; and the correct rate of disease major coding of the Department of Orthopedics increased rapidly and reached 90% in September 2012. ConclusionsThrough the leader of the clinical treatment being responsible for the disease coding and encouraging clinicians to code the main diagnosis of diseases, the accurate of disease major diagnosis coding has improved. Strengthening the communication between clinical and Medical Record Departments can help our hospital improve the quality of disease major diagnosis coding continuously.
Neutrophils are the most abundant myeloid-derived eukaryotic cells in human blood with increasingly recognized as important regulators of cancer progression. However, the functional importance of tumor-associated neutrophils (TANs) is often overlooked due to their short-lived, terminally differentiated, non-proliferative properties. In recent years, a wealth of evidences obtained from experimental tumor models and cancer patients had indicated that TANs had obvious heterogeneity in morphology and function, and TANs had dual functions of pro- and anti-tumor in cancer patients. This review provides an adequate overview of the heterogeneity and distinct roles of neutrophils.
【Abstract】Objective To look for a feasible way to evaluate hepatic reserve function completely by retention rate of indocyanine green at 15 minutes （ICGR15）and Child-Pugh classification supplemented by hepatic clearance of D-sorbitol (CLh-s). Methods The ICGR15, Child-Pugh classification and CLh-s were examined in 186 patients with liver cirrhosis. Relations between CLh-s and operative complications were further studied when ICGR15 and Child-Pugh classification was superposed. ResultsThe superpositions of ICGR15 (40% being boundary) and Child-Pugh classification was centralized between Child-Pugh B and C. ICGR15 of 17 examples were higher than 40% in 63 examples of Child-Pugh B. Eight examples of them had some complications, CLh-s=(584.52±98.27) ml/min (CLh-s＜700 ml/min), while 9 examples of them had no complications, CLh-s=(801.25±75.04) ml/min (CLh-s＞700 ml/min). Conclusion The CLh-s could be interrelated with operative complication, and it is considered as an effective supplement to ICGR15 and Child-Pugh classification for the evaluation of hepatic reserve function, CLh-s (700 ml/min being boundary) could be used to predict operative complication, to evaluate hepatic reserve function effectively, and to provide the basis for choosing the right time for operation.
ObjectiveTo evaluate the effectiveness of total hip arthroplasty (THA) combined with subtrochanteric osteotomy in the treatment of Crowe type Ⅳdevelopmental dysplasia of the hip (DDH).MethodsBetween April 2008 and June 2016, 71 patients with unilateral Crowe type Ⅳ DDH were treated with THA. Of 71 cases, 44 were performed with subtrochanteric osteotomy (osteotomy group) and 27 were performed without subtrochanteric osteotomy (non-osteotomy group). There was no significant difference in gender, age, body mass, height, body mass index, affected side, and preoperative Harris score between 2 groups (P>0.05). The complications were recorded and the effectiveness was assessed by Harris score. Besides, the femoral dislocation height and the settling depth of sleeve were measured in the pelvic anteroposterior X-ray film pre- and post-operatively.ResultsOsteotomy group was followed up 12-90 months (mean. 34.77 months), and non-osteotomy group was followed up 12-79 months (mean, 34.33 months). There was no significant difference in follow-up time between 2 groups (t=–0.088, P=0.930). There was 11 cases of intraoperative or postoperative complications in osteotomy group, and 3 cases of postoperative complications in non-osteotomy group. Among the osteotomy group, 1 case had nonunion due to infection and received revision after 20 months. No loosening or dislocation of the implant occurred in both 2 groups. Significant differences were found in femoral dislocation height and settling depth of sleeve between 2 groups (t=–8.452, P=0.000; t=6.783, P=0.000). Moreover, the osteotomy length was not correlated with the settling depth of sleeve (r=–0.038, P=0.806). At last follow-up, there was no significant difference in Harris score between 2 groups (t=–1.160, P=0.254).ConclusionTHA combined with subtrochanteric osteotomy can provide a favorable outcome for treating Crowe type Ⅳ DDH. Furthermore, patients with higher femoral dislocation and severely narrow femoral proximal canals are prone to be peformed with subtrochanteric osteotomy.
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.
ObjectiveTo investigate the methods and significances of the breast ultrasonographic breast imaging reporting and data system (BI-RADS) category 4 lesions divided into category 4a, 4b, and 4c, and to assess the risk of malig-nancy of lesions with BI-RADS category 4 in order to improve the accuracy of diagnosis. MethodsTwo hundred and eighty-eight breast lesions with BI-RADS category 4 confirmed by histopathology were collected. The ultrasonographic characteristics of benign and malignant lesions, containing the shape, aspect ration, margin, calcification, changes of the surrounding tissue, boundary, blood flow characteristics, internal echo, rear echo of the lesions, were comparatively anal-yzed, and the lesions with BI-RADS-US category 4 were divided into 4a, 4b, 4c according to these ultrasonographic charac-teristics and analyzed by statistics. ResultsThere were 192 malignant lesions and 96 benign lesions in the 288 breast lesions. There were statistical significances in the benign and malignant lesions with the shape, aspect ratio, margin, calci-fication, change of surrounding tissue, and boundary (P < 0.05), in other words, the proportion of these ultrasonographic characteristics were higher in the malignant lesions as compared with the benign lesions. But there were no significant differences of internal echo, rear echo, and blood flow characteristics between two lesions (P > 0.05). The positive predictive value of malignant tumor with BI-RADS category 4a, 4b, and 4c were 21.74%, 58.90%, and 91.78%, respectively, and there was significant difference (χ2=106.09, P=0.000). ConclusionsThe classification of breast lesions with BI-RADS category 4 is refined, it could more accurately assess the risk of benign and malignant breast masses. At the same time, it has an important clinical significance for diagnosis and treatment of benign and malignant breast masses.
Objective To exploring the effectiveness of perioperative application of new surgical clinical classification and staging for myasthenia gravis (MG) in reducing the incidence of postoperative myasthenic crisis (MC). Methods The clinical data of patients with generalized MG admitted to the Comprehensive Treatment Center for Myasthenia Gravis of Henan Provincial People’s Hospital from January 2018 to June 2022 were retrospectively analyzed, who were scored with myasthenia gravis-activities of daily living (MG-ADL) score and quantification of the myasthenia gravis (QMG) score at the first visit, 1 day before surgery, and 3 days after surgery. The patients were divided into a group A (typeⅡ) and a group B (typeⅢ+Ⅳ+Ⅴ) by the new surgical clinical classification and staging of MG according to the disease progression process, and all patients underwent expanded thoracoscopic thymus (tumor) resection after medication and other interventions to control symptoms in remission or stability. The incidence of MC and the efficiency rate after surgery were analyzed. The normal distribution method and percentile method were used to calculate the unilateral 95% reference range of the QMG score and MG-ADL score. Results Finally 126 patients were enrolled, including 62 males and 64 females, aged 13-71 years, with an average age of 46.00±13.00 years. There were 95 patients in the group A and 31 patients in the group B, and the differences of the preoperative baseline data between the two groups were not statistically significant (P>0.05). The incidence of postoperative MC was 1.05% (1/95) in the group A and 3.23% (1/31) in the group B (P>0.05). The effective one-sided 95% reference range of the QMG score and MG-ADL score 1 day before surgery was 0-7.75 and 0-5.00, and there was no postoperative death in both groups. Conclusion The new surgical clinical classification and staging of MG can guide the timing of surgery, which can benefit patients undergoing surgery for MG and greatly reduce the incidence of postoperative MC.
Objective To explore the effectiveness of maintaining the stability between the fourth and the fifth metacarple base during the treatment in the hamate-metacarpal joint injury. Methods Between September 2015 and June 2017, 13 cases of hamate-metacarpal joint injury were treated, including 12 males and 1 female, aged from 17 to 55 years (mean, 30.8 years). The injury causes included heavy boxing in 10 cases and falling in 3 cases. There were 2 cases of simple fourth metacarpal basal fracture, 1 basal fracture of the fourth metacarpal bone combined with intermetacarpal ligament fracture, 7 fractures of the fourth and fifth metacarpal base, 2 fourth metacarpal basal fractures combined with the fifth metacarpal basal fracture dislocation, and 1 base fracture of fourth and fifth metacarpal bone combined with hamate bone fracture. The time from injury to operation was 5-11 days (mean, 7.2 days). According to different damage degree and stability change between the fourth and the fifth metacarple base, a preliminary classification was made for different degrees of injury: 2 cases of type Ⅰ, 1 case of type Ⅱ, 7 cases of type Ⅲ, 2 cases of type Ⅳ, and 1 case of type Ⅴ. The patients were treated with corresponding internal fixation methods under the principle of stability recovery between the fourth and fifth metacarple base. Results All the incisions healed by first intention without infection or skin necrosis. All the 13 patients were followed up 6-18 months with an average of 9.4 months. All fractures healed clinically, and the healing time was 5.5-8.0 weeks with an average of 6.3 weeks. No complication such as plate breakage, fracture dislocation, fracture malunion, and bone nonunion occurred. Hand function was evaluated according to the total active motion (TAM) functional evaluation standard of hand surgery at 6 months after operation, and the results was excellent in 9 cases, good in 3 cases, and fair in 1 case, with an excellent and good rate of 92.3%. Conclusion Stability between the fourth and fifth metacarple base is of great significance to the classification and the treatment of the hamate-metacarpal joint injury.
Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.