The machine learning is used increasingly and widely in acupuncture prescription optimization, intelligent treatment and precision medicine, and has obtained a certain achievement. But, there are still some problems remained to be solved such as the poor interpretability of the model, the inconsistency of data quality of acupuncture research, and the clinical application of constructed models. Researches in future should focus on the acquisition of high-quality clinical and experimental data sets, take various machine learning algorithms as the basis, and construct professional models to solve various problems, so as to drive the high-quality development of acupuncture research.
Acupuncture Therapy/trends* ; Machine Learning ; Humans ; Algorithms

BACKGROUND:Total knee arthroplasty is the main therapeutic regimen for end-stage osteoarthritis.However,diabetes mellitus can affect the treatment effect and prognosis. OBJECTIVE:To explore the effect of diabetes mellitus on perioperative blood loss and postoperative pain in patients undergoing primary total knee arthroplasty. METHODS:A retrospective study was conducted on 154 patients who underwent primary total knee arthroplasty and met the inclusion criteria in the Osteonecrosis and Joint Reconstruction Ward of Xi'an Honghui Hospital Affiliated to Xi'an Jiaotong University from January to April 2021.Patients were divided into a non-diabetic group and a diabetic group according to their diagnosis,with 32 cases in the diabetic group,9 males and 23 females,aged 55 to 80(66.58±7.16)years and 122 cases in the non-diabetic group,34 males and 88 females,aged 44 to 83(66.69±6.63)years.Perioperative blood loss(including total blood loss,hidden blood loss,the falling value of hemoglobin and hematocrit)was calculated for both groups.Visual analog scale scores,hospital for special surgery knee score,and Caprini scores were recorded preoperatively and postoperatively. RESULTS AND CONCLUSION:(1)Total blood loss was significantly lower in the non-diabetic group(729.93±233.83 mL)than that in the diabetic group(853.69±184.91 mL)(P<0.05).Latent hidden blood loss was also significantly lower in the non-diabetic group(624.40±233.19 mL)than that in the diabetic group(749.08±179.49 mL)(P<0.05).(2)In the non-diabetic group,the visual analog scale scores preoperatively and 1 month postoperatively were significantly lower than those in the diabetic group(P<0.05).The differences in visual analog scale scores at 3 days and 3 months postoperatively between the non-diabetic group and the diabetic group were not statistically significant(P>0.05).(3)The hospital for special surgery knee score at 1 month postoperatively was significantly higher in the non-diabetic group than that in the diabetic group(P<0.05).There was no significant difference in hospital for special surgery knee score between the two groups at 3 months postoperatively(P>0.05).(4)There was no statistically significant difference in preoperative and postoperative Caprini scores between the two groups(P>0.05).(5)It is concluded that having diabetes increases total and occult hidden blood loss in primary total knee arthroplasty.In the short term after total knee arthroplasty,diabetes increases the patient's pain and affects the recovery of joint function,but the negative effects fade with time.

BACKGROUND:Osteonecrosis of the femoral head is one of the refractory diseases in orthopedic diseases.The natural collapse course of osteonecrosis of the femoral head under different stages and types affects the progression and prognosis of the disease. OBJECTIVE:To explore the progression of natural collapse within 5 years in patients under the different classifications of China-Japan Friendship Hospital(CJFH)with stage Ⅱ osteonecrosis of the International Association for Research Circulation Osseous(ARCO),and to analyze the collapse rate and collapse risk of the femoral head under the different classifications of CJFH. METHODS:A retrospective study was performed to select patients diagnosed with ARCO Ⅱ stage osteonecrosis of the femoral head without collapse in the Honghui Hospital Affiliated to Xi'an Jiaotong University from October 2016 to October 2017.According to whether it collapsed,the number of hips was divided into the collapse group(n=82)and the non-collapsed group(n=70).The collapse risk of patients with osteonecrosis of the femoral head under different CJFH classifications,as well as the collapse time,number of collapses,and collapse rate within 5 years were counted,and then the Kaplan-Meier survival curve of the femoral head under different classification of CJFH was plotted. RESULTS AND CONCLUSION:(1)A total of 97 patients with 152 hips were enrolled,and 82 hips collapsed during the follow-up period,with a total collapse rate of 53.9%,of which the collapse rates of M type,C type,L1 type,L2 type,and L3 type were 0.0%,36.7%,51.4%,72.2%,and 77.8%,respectively,and the comparison between the groups was statistically significant(P<0.05).(2)In terms of collapse risk,the collapse risk of L1 type was 1.704 times that of C-type(P>0.05),while the collapse risks of L2 type and L3 type were 3.866 times and 6.423 times that of C type(P<0.05),respectively.(3)In terms of the Kaplan-Meier survival curve,the median survival time of the femoral head of ARCO Ⅱ stage patients was 3 years,with a 95%confidence interval of 2.885-3.471 years,and the survival rates of the femoral head at the first,third and fifth years were 65.1%(99/152),50.7%(77/152),and 46.1%(70/152),respectively.(4)These findings conclude that different CJFH classifications affect the collapse rate of ARCO Ⅱ stage osteonecrosis of the femoral head patients,among which L3 type patients have the highest collapse rate,followed by L2 type and L1 type patients;C type patients have a lower collapse rate,and M type patients do not collapse,which indicates that the preservation of the lateral column of the femoral head is of great significance for the natural collapse course of osteonecrosis of the femoral head.

Objective To evaluate the acute exacerbation of chronic obstructive pulmonary disease(COPD)(AECOPD)status via combining clinical data,lung function parameters with CT radiomic features based on machine learning method.Methods A total of 343 COPD patients,including 158 AECOPD patients and 185 non-AECOPD patients were retrospectively selected and randomly divided into training and testing sets at a ratio of 7∶3.The radiomics features were calculated after automatically delineating the whole lung volume of interest(VOI).Five machine learning methods were used to construct the AECOPD diagnostic model,then the corresponding Radiomics score(Rad-score)was calculated in the training set and was validated in the testing set.The logistic-combined model was established after integrating age,Global Initiative for Chronic Obstructive Lung Disease(GOLD)classification,vital capacity(VC),forced vital capacity(FVC),forced expiratory volume in one second(FEV1),FEV1％pred,FEV1/FVC％,peak expiratory flow(PEF),maximum ventilatory volume(MVV),and Rad-score value.The area under the curve(AUC)of receiver operating characteristic(ROC)curve was calculated to evaluate the evaluated performance of all models.Results The logistic regression model had the best diagnostic performance,with AUC of 0.724 and 0.758 in the training and testing sets,respectively.The performance of the logistic-combined model to diagnose AECOPD was superior to that of the single logistic regression model,with the AUC of 0.777 and 0.760 in the training and testing sets,respectively.Conclusion A combination strategy including clinical data,lung function parameters,and CT radiomics may be helpful to diagnose AECOPD status,with moderate diagnostic performance.

Primary adrenal small cell neuroendocrine carcinoma is clinically rare. This article reported a patient, who was diagnosed as primary adrenal small cell neuroendocrine carcinoma complicated with renal vein cancer thrombus, and underwent laparoscopic left adrenal + left kidney + left renal vein tumor embolectomy.The carcinoma relapsed after 19 months of follow-up after surgery. The patient and his family refused further treatment.

Ambystoma mexicanum/immunology* ; Amputation ; Animals ; Biomarkers/metabolism* ; Blastomeres/immunology* ; Cell Lineage/immunology* ; Connective Tissue Cells/immunology* ; Epithelial Cells/immunology* ; Forelimb ; Gene Expression ; High-Throughput Nucleotide Sequencing ; Humans ; Immunity ; Peroxiredoxins/immunology* ; Regeneration/immunology* ; Regenerative Medicine/methods* ; Single-Cell Analysis/methods*

Objective To explore the correlation between thyroid function and cognitive ability in patients with subcortical arteriosclerotic encephalopathy.Methods Montreal cognitive assessment scale (Montreal Cognitive Assessment,MoCA) was used to evaluate the cognitive function of SAE patients with normal thyroid function and hypothyroidism.And the difference in the risk factors of SAE cognitive ability in patients with different thyroid functions was analyzed.Results There were no significant differences in gender,age,risk factors of hypertension,cerebral infarction,diabetes and smoking between the two groups (P＞0.05).The levels of FT3,FT4,TSH,MoCA and ADL in patients with hypothyroidism were (2.92±0.35) pmol/L,(15.61±2.76) pmol/L,(13.05± 1.64) mU/L,(12.73±5.75) points,(45.64±25.77) points,respectively.The levels of FT3,FT4 and TSH in normal thyroid function group and MoCA,ADL scores were (4.27±0.55)pmol/L,(16.74 ± 2.35) pmol/L,(2.73 ± 0.38) mU/L,(18.15 ± 5.35) points,(62.17 ± 26.72) points,respectively.The data of the hypothyroidism group was significantly lower than thst in the normal thyroid function group,and the difference was statistically significant (t =3.591,3.012,12.753,8.967,15.442,P＜0.05).FT3 levels in SAE patients were positively correlated with MoCA score and ADL score (r=0.518,0.617,P=0.026,0.018),while there was no significant correlation between FT4 level and MoCA and ADL score (r =0.015,0.007,P =0.852,0.074).MoCA score and ADL score were negatively correlated with TSH level (r=-0.651,-0.582,P=0.016,0.005).Conclusion Thyroid function is significantly correlated with cognitive ability of SAE patients.Thyroid function may be a clinical index for patients with subcortical arteriosclerosis,and provide a basis for rational drug use in patients with subcortical arteriosclerosis.

Purpose To explore the independent predictors of malignant solitary pulmonary nodule (SPN) manifesting as ground-glass nodule (GGN),and to establish a prediction model.Materials and Methods The clinical data and CT images of 362 patients (group A) with pathological-confirmed SPN appearing as GGN in Shanghai Chest Hospital Shanghai Jiaotong University from January 2014 to December 2015 were retrospectively analyzed.The independent predictors of malignant SPN were identified,and the clinical prediction model was established.Another 119 SPN patients in Affiliated Zhoushan Hospital of Wenzhou Medical University were selected as group B to verify the diagnostic efficiency of the prediction model.Results Using multivariate Logistic regression analysis,clear border (OR=6.274,P＜0.01),smooth edge (OR=0.391,P＜0.01),lobulation (OR=3.387,P＜0.01),pleural retraction sign (OR=2.430,P＜0.01),and vocule sign (OR=3.076,P＜0.01)were identified as independent predictors of malignant SPN.The area of the model under the ROC curve was 0.859 with 95％ CI (0.804-0.903).The diagnostic accuracy rate,sensitivity,specificity,positive predictive value and negative predictive value were 85.92％,91.03％,81.97％,92.03％ and 73.53％,respectively.Conclusion In this study,the independent predictors of malignant SPN appearing as GGN were identified,and the prediction model was established.The model can accurately identify SPN and provide effective help for early diagnosis of SPN.

Background and objective hTe solitary pulmonary nodule (SPN) is a common and challenging clini-cal problem, especially solid SPN. hTe object of this study was to explore the predictive factors of SPN appearing as pure solid with malignance and to establish a clinical prediction model of solid SPNs.Methods We had a retrospective review of 317 sol-id SPNs (group A) having a ifnal diagnosis in the department of thoracic surgery, Shanghai Chest Hospital from January 2015 to December 2015, and analyzed their clinical data and computed tomography (CT) images, including age, gender, smoking history, family history of cancer, previous cancer history, diameter of nodule, nodule location (upper lobe or non-upper lobe, letf or right), clear border, smooth margin, lobulation, spiculation, vascular convergence, pleural retraction sign, air broncho-gram sign, vocule sign, cavity and calciifcation. By using univariate and multivariate analysis, we found the independent predic-tors of malignancy of solid SPNs and subsequently established a clinical prediction model. hTen, another 139 solid SPNs with a final diagnosis were chosen in department of Cardiothoracic Surgery, Affiliated Zhoushan Hospital of Wenzhou Medical University as group B, and used to verify the accuracy of the prediction model. Receiver-operating characteristic (ROC) curves were constructed using the prediction model.Results MultivariateLogistic regression analysis was used to identify eight clini-cal characteristics (age, family history of cancer, previous cancer history, clear border, lobulation, spiculation, air bronchogram sign, calciifcation) as independent predictors of malignancy of in solid SPNs. hTe area under the ROC curve for our model (0.922; 95%CI: 0.865-0.961). In our model, diagnosis accuration rate was 84.89%. Sensitivity was 90.41%, and speciifcity was 78.79%, and positive predictive value was 80.50%, and negative predictive value was 88.14%.Conclusion Our prediction model could accurately identify malignancy in patients with solid SPNs, thereby it can provide help for diagnosis of solid SPNs.

Objective To assess the impact of miR-429 on lung adenocarcinoma cell SPC-A1 growth inhibition.Methods Pre-miRTM miR-429 precursor was synthesized and transfected to the SPC-A1 cells by liposome; qRT-PCR assay was used to quantify the miR-429 expression levels; The proliferation of SPC-A1 cells was evaluated by Cell Counting Kit-8 (CCK8).The cell apoptosis was evaluated by Annexin V Assay; The cell cycles of each group were assayed by flow cytometry;Western-blot was used to analyze the expression of cylines.Results The expression level of miR-429 was highly induced after transfection (P ＜ 0.001) ;CCK-8 assay showed the cell proliferation activity of pre-miR-429 group was lower than that of blank and control group 48h and 72 h after transfection(P =0.0167,0.0383,P =0.0320,0.0465),whereas the apoptosis rate had no significant difference between pre-miR-429 and control 24h after transfection by Annexin V Assay(P ＞ 0.05) ; The flow cytometry at 48h after transfection showed that miR-429 decreased the percentage of cells in G1 phase,but increased in S phase,indicating the cell cycle arrest at S phase(P =0.0010,0.0010 ; P =0.0068,0.0133) ; however,the expression level of Cyclin E in pre-miR-429 group had no difference compared with control.Conclusion miR-429 could inhibit cell proliferation and promote cell cycle arrest of lung adenocarcinoma cell SPC-A1.miR-429 may play a potential tumor suppressor role in lung adenocarcinoma cell SPC-A1.