Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population

ABSTRACT Introduction: Blood transfusion is a common practice in cardiac surgery, despite its well-known negative effects. To mitigate blood transfusion-associated risks, identifying patients who are at higher risk of needing this procedure is crucial. Widely used risk scores to predict the need for blood transfusions have yielded unsatisfactory results when validated for the Brazilian population. Methods: In this retrospective study, machine learning (ML) algorithms were compared to predict the need for blood transfusions in a cohort of 495 cardiac surgery patients treated at a Brazilian reference service between 2019 and 2021. The performance of the models was evaluated using various metrics, including the area under the curve (AUC), and compared to the commonly used Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST) scoring systems. Results: The study found that the model had the highest performance, achieving an AUC of 0.7350 (confidence interval [CI]: 0.7203 to 0.7497). Importantly, all ML algorithms performed significantly better than the commonly used TRACK and TRUST scoring systems. TRACK had an AUC of 0.6757 (CI: 0.6609 to 0.6906), while TRUST had an AUC of 0.6622 (CI: 0.6473 to 0.6906). Conclusion: The findings of this study suggest that ML algorithms may offer a more accurate prediction of the need for blood transfusions than the traditional scoring systems and could enhance the accuracy of predicting blood transfusion requirements in cardiac surgery patients. Further research could focus on optimizing and refining ML algorithms to improve their accuracy and make them more suitable for clinical use.

Construction of a risk prediction model for bloodstream infection induced by carbapenem-resistant Klebsiella pneumoniae / 中国药房

OBJECTIVE To construct a risk prediction model for bloodstream infection （BSI） induced by carbapenem-resistant Klebsiella pneumoniae （CRKP）. METHODS Retrospective analysis was conducted for clinical data from 253 patients with BSI induced by K. pneumoniae in the First Hospital of Qinhuangdao from January 2019 to June 2022. Patients admitted from January 2019 to December 2021 were selected as the model group （n＝223）， and patients admitted from January 2022 to June 2022 were selected as the validation group （n＝30）. The model group was divided into the CRKP subgroup （n＝56） and the carbapenem- sensitive K. pneumoniae （CSKP） subgroup （n＝167） based on whether CRKP was detected or not. The univariate and multivariate Logistic analyses were performed on basic information such as gender， age and comorbid underlying diseases in two subgroups of patients； independent risk factors were screened for CRKP-induced BSI， and a risk prediction model was constructed. The established model was verified with patients in the validation group as the target. RESULTS Admissioning to intensive care unit （ICU）， use of immunosuppressants， empirical use of carbapenems and empirical use of antibiotics against Gram-positive coccus were independent risk factors of CRKP-induced BSI （ORs were 3.749， 3.074， 2.909， 9.419， 95%CIs were 1.639-8.572， 1.292- 7.312， 1.180-7.717， 2.877-30.840， P＜0.05）. Based on this， a risk prediction model was established with a P value of 0.365. The AUC of the receiver operating characteristic （ROC） curve of the model was 0.848 [95%CI （0.779， 0.916）， P＜0.001]， and the critical score was 6.5. In the validation group， the overall accuracy of the prediction under the model was 86.67%， and the AUC of ROC curve was 0.926 [95%CI （0.809， 1.000]， P＜0.001]. CONCLUSIONS Admission to ICU， use of immunosuppressants， empirical use of carbapenems and empirical use of antibiotics against Gram-positive coccus are independent risk factors of CRKP- induced BSI. The CRKP-induced BSI risk prediction model based on the above factors has good prediction accuracy.

Retinal perfusion density can predict cardiovascular disease risk in patients with retinal vein occlusion

Purpose: To correlate microvascular changes and assess the relationship between microvascular changes and cardiovascular disease (CVD) risk in patients with retinal vein occlusion (RVO). Methods: Patients over 40 years of age with unilateral RVO were included in this prospective study. Those known to have cardiovascular disease were excluded. A detailed medical history was taken and physical exam was done to measure the height, weight, body mass index (BMI), and systolic blood pressure (SBP). A comprehensive eye check?up was followed by optical coherence tomography angiography (OCTA). Microvascular indices such as vessel density (VD) and perfusion density (PD) were noted. A statistical model was developed for prediction of CVD risk and was integrated with the World Health Organization (WHO)’s risk prediction charts. Results: This study included 42 patients with RVO and 22 controls with an age range of 42–82 years. There were 40 males (62.5%) and 24 females (37.5%). Along with age, SBP, and gender, perfusion density was found to have significant impact on CVD risk (P = 0.030). Reduction in PD was associated with increase in CVD risk. PD had a greater influence on CVD in <50 years age than in >70 years group. Using linear regression, a model with accuracy of 72.1% was developed for CVD risk prediction and was converted into color coded charts similar to WHO risk prediction charts. Conclusion: These findings suggest a significant correlation between microvascular parameters and CVD risk in RVO patients. Based on these parameters, an easy?to?use and color?coded risk prediction chart was developed

Construction and Application of Liver Injury Risk Prediction Model of Chinese Medicinals based on Indirect Toxicity / 中医杂志

ObjectiveTo explore and establish the liver injury risk prediction model of indirect toxicity of Chinese medicinals under the condition of compound formulas， and provide new ideas and methods for the study of evaluation of liver injury of Chinese medicinals based on indirect toxicity. MethodsTaking Buguzhi （Fructus Psoraleae） pre-parations as model drug， the combined Chinese medicinals with Buguzhi （Fructus Psoraleae） of high frequency are screened out， and their components and action targets were obtained through TCMSP， TCMIP and PharmMapper databases. The association strength value and risk value of Chinese medicinals that acted on the nuclear factor κB （NF-κB） pathway were analyzed. For those having greater values than the median association strength value and risk value were regarded as indirect Chinese medicinals of liver injury risk. In this way， a prediction model of liver injury risk of Chinese medicinals was constructed based on immune activation-related indirect liver injury process （taking NF-κB pathway as an example）. And verification of the prediction model was performed using Heshouwu （Radix Polygoni Multiflori） preparations. ResultsThe prediction model of liver injury risk based on important immunoactivated pathway （taking NF-κB pathway as an example） found that Yinyanghuo （Herba Epimedii） （association strength value = 0.18， risk value = 0.25） was a Chinese medicinal with potential risk of indirect liver injury within Buguzhi （Fructus Psoraleae） prepartions， which may increase the risk of liver injury by positively regulating Bruton's tyrosine kinase （Btk） and protein kinase C theta （PKCθ） on NF-κB pathway. Further verification of prediction model by Heshouwu （Radix Polygoni Multiflori） preparations showed that Buguzhi （Fructus Psoraleae） （association strength value = 0.25， risk value = 0.33） and Tusizi （Semen Cuscutae） （Semen Cuscutae， association strength value = 0.34， risk value = 0.33） may increase the liver injury risk of Heshouzu. ConclusionThe liver injury risk prediction model of indirect toxicity of Chinese medicinals has been constructed in this study， providing metho-dological reference for the identification of Chinese medicinals of indirect liver injury risk under the condition of compound formulas.

Predictive value of diaphragm thickening fraction and intra-abdominal pressure monitoring-oriented risk prediction model for weaning failure in patients with severe acute pancreatitis / 中华危重病急救医学

Objective:To establish a risk prediction model dominated by diaphragm thickening fraction (DTF) and intra-abdominal pressure (IAP) monitoring, and to explore the predictive value of the model for weaning failure in patients with severe acute pancreatitis (SAP).Methods:A prospective research was conducted. Sixty-three patients undergoing invasive mechanical ventilation treatment who diagnosed with SAP admitted to intensive care unit of the First Affiliated Hospital of Jinzhou Medical University from August 2020 to October 2021 were enrolled. The spontaneous breathing trial (SBT) was carried out when the clinical weaning criteria was met. The stable cardiovascular status, good pulmonary function, no chest and abdominal contradictory movement, and adequate oxygenation were defined as successful weaning. Otherwise, it was defined as failure weaning. The clinical indicators such as SBT 30-minure DTF, IAP, tidal volume (VT), respiratory rate (RR), body mass index (BMI), and blood lactic acid (Lac) were compared between the weaning success group and the weaning failure group. The indicators with statistically significant differences in the single-factor analysis were included in the secondary multivariable Logistic regression analysis to establish a risk prediction model. The correlation between the DTF and IAP at 30 minutes of SBT was analyzed. Receiver operator characteristic curve (ROC curve) was drawn to analyze the predictive value of the risk prediction model for SAP patient withdrawal failure at 30 minutes of SBT.Results:Finally, 63 patients with SAP were enrolled. Among the 63 patients, 42 were successfully weaned and 21 failed. There were no significant differences in age, gender, and oxygenation index (PaO 2/FiO 2), sequential organ failure assessment (SOFA) score, acute physiology and chronic health evaluation Ⅱ (APACHEⅡ) score at admission between the two groups, indicating that the data in the two groups were comparable. Compared with the weaning success group, IAP, RR, BMI and Lac at 30 minutes of SBT in the weaning failure group were significantly increased [IAP (mmHg, 1 mmHg≈0.133 kPa): 14.05±3.79 vs. 12.12±3.36, RR (times/min): 25.43±8.10 vs. 22.02±5.05, BMI (kg/m 2): 23.71±2.80 vs. 21.74±3.79, Lac (mmol/L): 5.27±1.69 vs. 4.55±1.09, all P < 0.05], while DTF and VT were significantly decreased [DTF: (29.76±3.45)% vs. (31.86±3.67)%, VT (mL): 379.00±98.74 vs. 413.60±33.68, both P < 0.05]. Secondary multivariable Logistic regression analysis showed that DTF [odds ratio ( OR) = 0.758, 95% confidence interval (95% CI) was 0.584-0.983, P = 0.037], IAP ( OR = 1.276, 95% CI was 1.025-1.582, P = 0.029), and RR ( OR = 1.145, 95% CI was 1.014-1.294, P = 0.029) were independent risk factors for SBT withdrawal failure in 30 minutes in SAP patients. The above risk factors were used to establish the risk prediction model of aircraft withdrawal failure at 30 minutes of SBT: Logit P = -0.237-0.277×DTF+0.242×IAP+0.136×RR. Pearson correlation analysis showed that SBT 30-minute DTF was significantly correlated with IAP in SAP patients, and showed a significant positive correlation ( r = 0.313, P = 0.012). The ROC curve analysis results showed that area under the ROC curve (AUC) of the risk prediction model for SAP patient withdrawal failure at 30 minutes of SBT was 0.716, 95% CI was 0.559-0.873, P = 0.003, with the sensitivity of 85.7% and the specificity of 78.6%. Conclusions:DTF, IAP and RR were independent risk factors for SBT withdrawal failure in 30 minutes in SAP patients. The DTF and IAP monitoring-oriented risk prediction model based on the above three variables has a good predictive value for weaning failure in patients with SAP.

LASSO regression based risk prediction model establishment for Klebsiella pneumonia infection in patients with severe acute pancreatitis / 中华胰腺病杂志

Objective:To construct a risk prediction model for infection with Klebsiella pneumonia (KP) for patients with severe acute pancreatitis (SAP).Methods:Retrospective analysis was done on the clinical data of 109 SAP patients who were admitted to Shanghai General Hospital, between March 2016 and December 2021. Patients were classified into infection group ( n=25) and non-infection group ( n=84) based on the presence or absence of KP infection, and the clinical characteristics of the two groups were compared. The least absolute shrinkage and selection operator (LASSO) algorithm was used to reduce the dimension of the variables with statistical significance in univariate analysis. A nomogram prediction model was created by incorporating the optimized features from the LASSO regression model into the multivariate logistic regression analysis. Receiver operating characteristic curve (ROC) was drawn and the area under curve (AUC) was calculated; and consistency index (C-index) were used to assess the prediction model's diagnostic ability. Results:A total of 25 strains of KP were isolated from 109 patients with SAP, of which 21(84.0%) had multi-drug resistance. 20 risk factors (SOFA score, APACHEⅡ score, Ranson score, MCTSI score, mechanical ventilation time, fasting time, duration of indwelling of the peritoneal drainage tube, duration of deep vein indwelling, number of invasive procedures, without or with surgical intervention, without or with endoscopic retrograde cholangiopancreatography (ERCP), types of high-level antibiotics used, digestion disorders, abnormalities in blood coagulation, metabolic acidosis, pancreatic necrosis, intra-abdominal hemorrhage, intra-abdominal hypertension, length of ICU stay and total length of hospital stay) were found to be associated with KP infection in SAP patients by univariate analysis. The four variables (APACHEⅡ score, duration of indwelling of the peritoneal drainage tube, types of high-level antibiotics used, and total length of hospital stay) were extracted after reduced by LASSO regression. These four variables were found to be risk factors for KP infection in SAP patients by multiple logistic regression analysis (all P value <0.05). Nomogram prediction model for KP infection in SAP was established based on the four variables above. The verification results of the model showed that the C-index of the model was 0.939, and the AUC was 0.939 (95% CI 0.888-0.991), indicating that the nomogram model had relatively accurate prediction ability. Conclusions:This prediction model establishes integrated the basic clinical data of patients, which could facilitate the risk prediction for KP infection in patients with SAP and thus help to formulate better therapeutic plans for patients.

Epidemiological characteristics and risk prediction of pulmonary infection in elderly patients with chronic obstructive pulmonary disease / 公共卫生与预防医学

Objective To explore the epidemiological characteristics of pulmonary infection in elderly patients with chronic obstructive pulmonary disease (COPD), and to construct a risk prediction model. Methods Among of 125 elderly patients with COPD from May 2020 to June 2022 were selected as the research subjects. The epidemiological characteristics of infected patients were counted, and the risk factors of pulmonary infection in patients were analyzed and a prediction model was constructed. Results A total of the 125 elderly patients with COPD, there were 46 cases of pulmonary infection, with the infection rate of 36.80%. The detection rate of Gram-negative bacteria was higher than that of Gram-positive bacteria or fungi (64.44% vs 33.33% or 2.22%, P2=0.812 and P=0.295. ROC curve analysis revealed that the AUC value of the prediction model on predicting the pulmonary infection in elderly patients with COPD was 0.802. Conclusion The pathogenic bacteria of elderly patients with COPD complicated with pulmonary infection are mainly Gram-negative bacteria. The prediction model constructed according to the risk factors of pulmonary infection in patients has predictive value on pulmonary infection in patients.

Risk predictors of pulmonary tuberculosis in patients with chronic kidney disease / 公共卫生与预防医学

Objective The risk prediction factors of patients with chronic kidney disease (CKD) complicated with pulmonary tuberculosis were analyzed, and the risk prediction model was constructed to provide theoretical basis for the prevention and treatment of pulmonary tuberculosis in patients with CKD. Methods Stratified sampling was used to randomly select 289 patients with CKD admitted to our hospital as the investigation objects. According to whether patients complicated with tuberculosis, they were divided into experimental group (n=65, CKD complicated with tuberculosis) and control group (n=224, CKD). Univariate analysis and logistic regression were used to analyze the influencing factors of pulmonary tuberculosis in PATIENTS with CKD. According to the regression results, the risk prediction model of pulmonary tuberculosis in CKD patients was established, and the ROC curve was used to predict the efficacy of the model. Results Among 289 patients with CKD, 65 cases (22.49%) had pulmonary tuberculosis. Chest X-ray showed 54 cases of infiltrating pulmonary tuberculosis, 5 cases of voiding pulmonary tuberculosis, 4 cases of caseous pneumonia and 2 cases of tuberculous pleurisy. The main clinical manifestations of CKD complicated with pulmonary tuberculosis were low fever, poor appetite and fatigue in 36 cases, cough and expectoration in 18 cases, high fever in 9 cases and pleural effusion in 2 cases. Mycobacterium tuberculosis culture was positive in 23 cases (35.38%). There were no significant differences in age, CKD stage, past tuberculosis history, low immunity, malnutrition, dialysis treatment, anemia and hypoproteinemia between 2 groups (P-(0.496+0.839×(low immunity)+ 0.892×(malnutrition)+ 1.247×(dialysis)]; ROC curve was used to analyze the predictive efficacy of the regression model. The results showed that the AUC of pulmonary tuberculosis predicted by the risk prediction model was 0.779, 95%Cl(0.668-0.889) for CKD patients. Conclusion The risk of tuberculosis in CKD is higher,low immunity, malnutrition, dialysis treatment of CKD patients is high risk for tuberculosis, according to the specific situation of the patients, take targeted measures to prevention, can reduce the risk of tuberculosis in patients with CKD.

Influencing factors of refractory anastomotic stenosis after laparoscopic intersphincteric resec-tion for rectal cancer and construction of nomogram prediction model / 中华消化外科杂志

Objective:To investigate the influencing factors of refractory anastomotic stenosis after laparoscopic intersphincteric resection (Ls-ISR) for rectal cancer and construction of nomogram prediction model.Methods:The retrospective case-control study was conducted. The clinicopatho-logical data of 495 patients who underwent Ls-ISR for rectal cancer in two medical centers, including 448 patients in Peking University First Hospital and 47 patients in Cancer Hospital Chinese Academy of Medical Sciences, from June 2012 to December 2021 were collected. There were 311 males and 184 females, aged 61 (range, 20-84)years. Observation indicators: (1) incidence of anastomotic stenosis; (2) influencing factors of refractory anastomotic stenosis after Ls-ISR; (3) construction and evaluation of nomogram prediction model for refractory anastomotic stenosis after Ls-ISR. Follow-up was conducted using outpatient examination and telephone interview to detect the incidence of postoperative anastomotic leakage and anastomotic stenosis up to August 2022. Measurement data with normal distribution were represented as Mean± SD, and comparison between groups was conducted using the t test. Measurement data with skewed distribution were represented as M(range). Count data were described as absolute numbers, and comparison between groups was conducted using the chi-square test. Univariate and multivariate analyses were conducted using the Logistic regression model. Factors with P<0.10 in univariate analysis were included in multivariate analysis. The R software (3.6.3 version) was used to construct nomogram prediction model. The receiver operating characteristic (ROC) curve was drawn and the area under curve (AUC) was used to evaluate the efficacy of nomogram prediction model. Results:(1) Incidence of anastomotic stenosis. All 495 patients underwent Ls-ISR successfully, without conversion to laparotomy, and all patients were followed up for 47(range, 8-116)months. During the follow-up period, there were 458 patients without anas-tomotic stenosis, and 37 patients with anastomotic stenosis. Of the 37 patients, there were 15 cases with grade A anastomotic stenosis, 3 cases with grade B anastomotic stenosis and 19 cases with grade C anastomotic stenosis, including 22 cases being identified as the refractory anastomotic stenosis. Fifteen patients with grade A anastomotic stenosis were relieved after anal dilation treat-ment. Three patients with grade B anastomotic stenosis were improved after balloon dilation and endoscopic treatment. Nineteen patients with grade C anastomotic stenosis underwent permanent stoma. During the follow-up period, there were 42 cases with anastomotic leakage including 17 cases combined with refractory anastomotic stenosis, and 453 cases without anastomotic leakage including 5 cases with refractory anastomotic stenosis. There was a significant difference in the refractory anastomotic stenosis between patients with and without anastomotic leakage ( χ2=131.181, P<0.05). (2) Influencing factors of refractory anastomotic stenosis after Ls-ISR. Results of multivariate analysis showed that neoadjuvant therapy, distance from tumor to anal margin ≤4 cm, clinic N+ stage were independent risk factors of refractory anastomotic stenosis after Ls-ISR ( hazard ratio=7.297, 3.898, 2.672, 95% confidence interval as 2.870-18.550, 1.050-14.465, 1.064-6.712, P<0.05). (3) Construction and evaluation of nomogram prediction model for refractory anastomotic stenosis after Ls-ISR. Based on the results of multivariate analysis, neoadjuvant therapy, distance from tumor to anal margin and clinic N staging were included to constructed the nomogram prediction model for refractory anastomotic stenosis after Ls-ISR. Results of ROC curve showed the AUC of nomogram prediction model for refractory anastomotic stenosis after Ls-ISR was 0.739 (95% confidence interval as 0.646-0.833). Conclusions:Neoadjuvant therapy, distance from tumor to anal margin ≤4 cm, clinic N+ stage are independent risk factors of refractory anastomotic stenosis after Ls-ISR. Nomogram prediction model based on these factors can predict the incidence of refractory anastomotic stenosis after Ls-ISR.

Application of metabonomics strategy in sepsis / 中国小儿急救医学

Sepsis is a heterogeneous disease with a complex pathogenesis and diverse clinical manifestations.Sepsis leads to disruption of biochemical homeostasis, which strongly promotes changes in metabolites in the body.Initial differences in metabolites may predict the severity of the disease, and changes in metabolites over time may useful in assessing treatment response, predicting progression of disease progression or clinical outcomes.This review focused on the studies related to the application of metabolomics strategy in sepsis, which could help to understand the potential value of sepsis metabolomics in the pathogenesis, diagnosis, prognosis and treatment of sepsis.

Literature analysis of risk prediction models for PICC catheter-related thrombosis / 中国实用护理杂志

Objective:To summarize literature of risk prediction models for catheter-related thrombosis in PICC at home and abroad, in order to provide reference for the development and improvement of risk prediction models for PICC catheter-related thrombosis (PICC-CRT) and the selection and use of medical staff.Methods:All studies on the risk prediction model of PICC-CRT were systematically searched in the Chinese and English literature database from June 2012 to June 2022. Two researchers independently screened the literature and extracted the data. The prediction model risk of bias assessment tool was used to evaluate the bias risk and applicability of the included literature.Results:A total of 13 articles were included, including 1 multicenter study and 12 single-center studies. Eight literatures were retrospective studies and five were prospective studies. Bias risk assessment showed that there was a bias risk in all the 6 studies. In terms of applicability evaluation, the 13 studies had good applicability in all fields and overall.Conclusions:There were various types of PICC catheter-related thrombosis risk assessment models, which had good predictive efficiency, but there was also a high risk of bias in these studies. The important contents of PICC catheter-related thrombosis risk prediction model are patient factors and treatment factors. In the future, the existing models need to be validated and improved, or a prediction model with low risk of bias should be constructed to effectively prevent PICC-CRT.

Development and validation of risk prediction model for new-onset cardiovascular diseases among breast cancer patients: Based on regional medical data of Inner Mongolia / 北京大学学报(医学版)

OBJECTIVE@#To develop and validate a three-year risk prediction model for new-onset cardiovascular diseases (CVD) among female patients with breast cancer.@*METHODS@#Based on the data from Inner Mongolia Regional Healthcare Information Platform, female breast cancer patients over 18 years old who had received anti-tumor treatments were included. The candidate predictors were selected by Lasso regression after being included according to the results of the multivariate Fine & Gray model. Cox proportional hazard model, Logistic regression model, Fine & Gray model, random forest model, and XGBoost model were trained on the training set, and the model performance was evaluated on the testing set. The discrimination was evaluated by the area under the curve (AUC) of the receiver operator characteristic curve (ROC), and the calibration was evaluated by the calibration curve.@*RESULTS@#A total of 19 325 breast cancer patients were identified, with an average age of (52.76±10.44) years. The median follow-up was 1.18 [interquartile range (IQR): 2.71] years. In the study, 7 856 patients (40.65%) developed CVD within 3 years after the diagnosis of breast cancer. The final selected variables included age at diagnosis of breast cancer, gross domestic product (GDP) of residence, tumor stage, history of hypertension, ischemic heart disease, and cerebrovascular disease, type of surgery, type of chemotherapy and radiotherapy. In terms of model discrimination, when not considering survival time, the AUC of the XGBoost model was significantly higher than that of the random forest model [0.660 (95%CI: 0.644-0.675) vs. 0.608 (95%CI: 0.591-0.624), P < 0.001] and Logistic regression model [0.609 (95%CI: 0.593-0.625), P < 0.001]. The Logistic regression model and the XGBoost model showed better calibration. When considering survival time, Cox proportional hazard model and Fine & Gray model showed no significant difference for AUC [0.600 (95%CI: 0.584-0.616) vs. 0.615 (95%CI: 0.599-0.631), P=0.188], but Fine & Gray model showed better calibration.@*CONCLUSION@#It is feasible to develop a risk prediction model for new-onset CVD of breast cancer based on regional medical data in China. When not considering survival time, the XGBoost model and the Logistic regression model both showed better performance; Fine & Gray model showed better performance in consideration of survival time.

A nomograph model for prediction of central lymph node metastasis of papillary thyroid carcinoma / 预防医学

Objective@#To establish a nomograph model for prediction of cervical central lymph node metastasis (CLNM) among patients with thyroid papillary carcinoma (PTC), so as to provide the evidence for designing personalized treatment plans for PTC.@* Methods @#The data of patients that underwent thyroidectomy and were pathologically diagnosed with PTC post-surgery in the Affiliated Traditional Chinese Medicine Hospital of Xinjiang Medical University from 2018 to 2021 were collected. Patients' data captured from 2018 to 2020 and from 2021 were used as the training set and the validation set, respectively. Predictive factors were screened using a multivariable logistic regression model, and the nomograph model for prediction of CLNM risk was established. The predictive value of the model was evaluated using the receiver operating characteristic (ROC) curve and the adjusted curve.@* Results@#Totally 1 820 PTC cases were included in the training set, including 458 cases with CLNM (25.16%), and 797 cases in the validation set, including 207 cases with CLNM (25.98%). The prediction model is p=ey/(1+ey), y=0.761 + 0.525 × sex + (-0.039) ×age + 0.351 × extrathyroid invasion + 0.368 × neck lymph node enlargement + 1.021×maximum tumor diameter + (-0.009) × TT4 + (-0.001) × anti-TPOAb. The area under the ROC curve was 0.732 for the training set and 0.731 for the validation set, and Hosmer-Lemeshow test showed a good fitting effect (P=0.936, 0.722).@*Conclusion@# The nomograph model constructed in this study has a high predictive value for CLNM among patients with PTC.

Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan

BACKGROUND@#Previous cardiovascular risk prediction models in Japan have utilized prospective cohort studies with concise data. As the health information including health check-up records and administrative claims becomes digitalized and publicly available, application of large datasets based on such real-world data can achieve prediction accuracy and support social implementation of cardiovascular disease risk prediction models in preventive and clinical practice. In this study, classical regression and machine learning methods were explored to develop ischemic heart disease (IHD) and stroke prognostic models using real-world data.@*METHODS@#IQVIA Japan Claims Database was searched to include 691,160 individuals (predominantly corporate employees and their families working in secondary and tertiary industries) with at least one annual health check-up record during the identification period (April 2013-December 2018). The primary outcome of the study was the first recorded IHD or stroke event. Predictors were annual health check-up records at the index year-month, comprising demographic characteristics, laboratory tests, and questionnaire features. Four prediction models (Cox, Elnet-Cox, XGBoost, and Ensemble) were assessed in the present study to develop a cardiovascular disease risk prediction model for Japan.@*RESULTS@#The analysis cohort consisted of 572,971 invididuals. All prediction models showed similarly good performance. The Harrell's C-index was close to 0.9 for all IHD models, and above 0.7 for stroke models. In IHD models, age, sex, high-density lipoprotein, low-density lipoprotein, cholesterol, and systolic blood pressure had higher importance, while in stroke models systolic blood pressure and age had higher importance.@*CONCLUSION@#Our study analyzed classical regression and machine learning algorithms to develop cardiovascular disease risk prediction models for IHD and stroke in Japan that can be applied to practical use in a large population with predictive accuracy.

Research progress on genetic control of host susceptibility to tuberculosis / 浙江大学学报·医学版

The "Lübeck disaster", twins studies, adoptees studies, and other epidemiological observational studies have shown that host genetic factors play a significant role in determining the host susceptibility to Mycobacterium tuberculosis infection and pathogenesis of tuberculosis. From linkage analyses to genome-wide association studies, it has been discovered that human leucocyte antigen (HLA) genes as well as non-HLA genes (such as SLC11A1, VDR, ASAP1 as well as genes encoding cytokines and pattern recognition receptors) are associated with tuberculosis susceptibility. To provide ideas for subsequent studies about risk prediction of MTB infection and the diagnosis and treatment of tuberculosis, we review the research progress on tuberculosis susceptibility related genes in recent years, focusing on the correlation of HLA genes and non-HLA genes with the pathogenesis of tuberculosis. We also report the results of an enrichment analysis of the genes mentioned in the article. Most of these genes appear to be involved in the regulation of immune system and inflammation， and are also closely related to autoimmune diseases.

Comparison of the predictive value of anthropometric indicators for the risk of benign prostatic hyperplasia in southern China / 亚洲男科学杂志(英文版)

This study aimed to compare the predictive value of six selected anthropometric indicators for benign prostatic hyperplasia (BPH). Males over 50 years of age who underwent health examinations at the Health Management Center of the Second Xiangya Hospital, Central South University (Changsha, China) from June to December 2020 were enrolled in this study. The characteristic data were collected, including basic anthropometric indices, lipid parameters, six anthropometric indicators, prostate-specific antigen, and total prostate volume. The odds ratios (ORs) with 95% confidence intervals (95% CIs) for all anthropometric parameters and BPH were calculated using binary logistic regression. To assess the diagnostic capability of each indicator for BPH and identify the appropriate cutoff values, receiver operating characteristic (ROC) curves and the related areas under the curves (AUCs) were utilized. All six indicators had diagnostic value for BPH (all P ≤ 0.001). The visceral adiposity index (VAI; AUC: 0.797, 95% CI: 0.759-0.834) had the highest AUC and therefore the highest diagnostic value. This was followed by the cardiometabolic index (CMI; AUC: 0.792, 95% CI: 0.753-0.831), lipid accumulation product (LAP; AUC: 0.766, 95% CI: 0.723-0.809), waist-to-hip ratio (WHR; AUC: 0.660, 95% CI: 0.609-0.712), waist-to-height ratio (WHtR; AUC: 0.639, 95% CI: 0.587-0.691), and body mass index (BMI; AUC: 0.592, 95% CI: 0.540-0.643). The sensitivity of CMI was the highest (92.1%), and WHtR had the highest specificity of 94.1%. CMI consistently showed the highest OR in the binary logistic regression analysis. BMI, WHtR, WHR, VAI, CMI, and LAP all influence the occurrence of BPH in middle-aged and older men (all P ≤ 0.001), and CMI is the best predictor of BPH.

Effects of preoperative lipid metabolism indexes on the prognosis of patients with non-muscular invasive bladder cancer / 现代泌尿外科杂志

【Objective】 To investigate the effects of preoperative lipid metabolism level on the postoperative prognosis of non-muscular invasive bladder cancer (NMIBC). 【Methods】 Clinical data of NMIBC patients who underwent surgical treatment in our hospital during Mar.2014 and May 2021 were retrospectively analyzed. Based on receiver operating characteristic (ROC) curve, the optimal cutoff values of all lipid metabolism indicators were determined and patients were classified accordingly. The independent risk factors for postoperative recurrence were identified with Cox regression model. The survival was analyzed with Kaplan-Meier, and recurrence-free survival (RFS) was compared using log-rank tests. A recurrence risk prediction model was established based on the high-density lipoprotein (HDL) and other clinic pathological factors and the accuracy of prediction was evaluated with the area under the ROC curve (AUC). 【Results】 Cox multivariate analysis showed HDL, tumor number, tumor size and histological grade were independent risk factors for recurrence (P<0.05). Kaplan-Meier analysis showed that RFS was significantly longer in the high-HDL group than in the low-HDL group (P<0.001). Incorporating HDL, tumor number, tumor size, histological grade, and tumor stage into the recurrence risk model, the AUC was 0.706, and internal cross validation showed the AUC was 0.711. 【Conclusion】 Preoperative HDL is an independent risk factor affecting the RFS of patients with NMIBC, and combining it with clinic pathological factors will improve the prediction of tumor recurrence.

Construction of Diagnosis and Treatment System of Traditional Chinese Medicine for Pulmonary Nodules Based on the Whole-Course Management of Disease / 中医杂志

Pulmonary nodule is a key window for moving ahead the diagnosis and treatment of lung cancer. Traditional Chinese medicine （TCM） can delay the transformation of lung nodules into lung cancer， improve the prognosis of patients， effectively fill the treatment gap during the follow-up period of pulmonary nodules， and has been applied it in the whole cycle and multi-dimensional management of pulmonary nodules. This paper discussed the construction ideas and feasible paths of the whole process management diagnosis and treatment system of pulmonary nodules in TCM， proposed the diagnosis and treatment database of TCM for pulmonary nodules based on the social module of “family-community-hospital”. Through artificial intelligence， we can develop， improve and promote the multi-level and multi-modal “disease-symptom combination” risk prediction model and effectiveness evaluation system of pulmonary nodules. At the same time， the biological connotation of the prevention and treatment of pulmonary nodules by TCM is excavated， which provided empirical evidence for the construction of TCM diagnosis and treatment system， in order to further improve the quality and diagnosis and treatment level of the whole course management of pulmonary nodules.

Development of a risk prediction score for acute kidney injury in critically-ill septic Filipino patients admitted in perpetual succour hospital

Introduction@#Acute kidney injury (AKI) is a lethal complication of critical illness characterized by the rapid loss of the kidney's excretory function encountered in 50% of intensive care unit (ICU) admissions. Its impact on the outcome of critically ill patients makes AKI a significant cause of morbidity and mortality.@*Objectives@#To develop and validate an acute kidney injury risk prediction score based on routinely available variables and common laboratories of admitted critically-ill septic Filipino patients.@*Methods@#This is a prospective cohort study conducted in a tertiary hospital in Cebu from February to September 2020. The data of 2545 patients were identified by chart review but only 607 patients with a quick Sepsis Organ Failure Assessment Score (qSOFA) score of >2 were included in the pre-screening. After stratified sampling, a total of 198 septic ICU patients were enrolled. Demographic profile, laboratory results and outcome data were collated. Variables were screened then stepwise forward elimination was done to identify the significant predictors. An AKI risk score model was developed with binomial regression analysis by identifying independent prognostic factors. The diagnostic ability of the model was determined by the Area under the Receiver Operating Characteristics (AuROC).@*Results@#AKI developed in 155 (78%) patients. The significant predictors for Acute Kidney Injury were age, hypertension, atherosclerotic cardiovascular disease, weight, white blood count, creatinine, and BUN. An AKI prediction model with a cut off score of 161.9 was made with a fair diagnostic ability for predicting AKI at 0.79 based on AuROC.@*Conclusion@#The developed risk prediction tool using routinely available variables is found to be fairly accurate to predict the development of AKI among critically ill septic patients.

Establishment and evaluation of the polygenic disease risk prediction model / 上海预防医学

To establish a disease risk prediction model based on genetic susceptibility genes and environmental risk factors， which can target high-risk population as early as possible， and intervene in the environmental risk factors in this population. Moreover， accurate screening of genetically susceptible populations can enhance the efficiency of health system. In recent years， with the maturation and cost reduction of high-throughput gene testing， gene testing has been widely used in individual clinical decision-making and will play a more important role in medical and health decision-making. The correlation between genetic testing and disease risk prediction is increasing， making it a prominent research topic in this field. This review summarizes the approaches for establishing and evaluating risk prediction models and discusses potential future challenges and opportunities.