scholarly journals A Machine Learning Model to Predict Intravenous Immunoglobulin-Resistant Kawasaki Disease Patients: A Retrospective Study Based on the Chongqing Population

2021 ◽  
Vol 9 ◽  
Author(s):  
Jie Liu ◽  
Jian Zhang ◽  
Haodong Huang ◽  
Yunting Wang ◽  
Zuyue Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Retrospective Study ◽  
Kawasaki Disease ◽  
Prediction Model ◽  
Prediction Models ◽  
Ivig Resistance ◽  
Independent Risk Factors

Objective: We explored the risk factors for intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD) and constructed a prediction model based on machine learning algorithms.Methods: A retrospective study including 1,398 KD patients hospitalized in 7 affiliated hospitals of Chongqing Medical University from January 2015 to August 2020 was conducted. All patients were divided into IVIG-responsive and IVIG-resistant groups, which were randomly divided into training and validation sets. The independent risk factors were determined using logistic regression analysis. Logistic regression nomograms, support vector machine (SVM), XGBoost and LightGBM prediction models were constructed and compared with the previous models.Results: In total, 1,240 out of 1,398 patients were IVIG responders, while 158 were resistant to IVIG. According to the results of logistic regression analysis of the training set, four independent risk factors were identified, including total bilirubin (TBIL) (OR = 1.115, 95% CI 1.067–1.165), procalcitonin (PCT) (OR = 1.511, 95% CI 1.270–1.798), alanine aminotransferase (ALT) (OR = 1.013, 95% CI 1.008–1.018) and platelet count (PLT) (OR = 0.998, 95% CI 0.996–1). Logistic regression nomogram, SVM, XGBoost, and LightGBM prediction models were constructed based on the above independent risk factors. The sensitivity was 0.617, 0.681, 0.638, and 0.702, the specificity was 0.712, 0.841, 0.967, and 0.903, and the area under curve (AUC) was 0.731, 0.814, 0.804, and 0.874, respectively. Among the prediction models, the LightGBM model displayed the best ability for comprehensive prediction, with an AUC of 0.874, which surpassed the previous classic models of Egami (AUC = 0.581), Kobayashi (AUC = 0.524), Sano (AUC = 0.519), Fu (AUC = 0.578), and Formosa (AUC = 0.575).Conclusion: The machine learning LightGBM prediction model for IVIG-resistant KD patients was superior to previous models. Our findings may help to accomplish early identification of the risk of IVIG resistance and improve their outcomes.

scholarly journals Development of a Risk Prediction Model for Central-Line–Associated Bloodstream Infection (CLABSI) in Patients With Continuous Renal Replacement Therapy

2020 ◽  
Vol 41 (S1) ◽  
pp. s515-s515
Author(s):  
Hui Zhang
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Renal Replacement Therapy ◽  
Prediction Model ◽  
Prediction Models ◽  
Total Bilirubin ◽  
Cutoff Point ◽  
Dialysis Catheter ◽  
Spss Software

Background: The number of patients with end-stage renal disease and acute kidney injury in China is large and increasing year by year. Continuous renal replacement therapy (CRRT) is one of the important treatment methods. However, long-time CRRT would inevitably lead to CLABSI, which would seriously affect the treatment and prognosis of the patient. Although CLABSIs can be prevented and controlled, the rate of CLABSI in China is still higher than in other countries. Therefore, it is urgent to find new intervention methods on the basis of existing methods. Surveillance is the prerequisite of infection prevention and control. We sought to develop a risk prediction model for CLABSI in patients with CRRT according to uncontrollable risk factors, which could be used for early assessment and screening of high-risk infection groups. Such a tool would bring the supervision and infection control to the forefront in addressing these issues. Methods: We selected 3,103 CRRT patients in the West China Hospital of Sichuan University from January 2013 to December 2018 using the hospital infection and infectious disease monitoring module of electronic medical records (EMR) system with the integration and elimination criteria. Data mining and feature selection were performed using Weka software. Separately, prediction models developed by Weka software and SPSS software were compared with each other using the area under the curve (AUC) method to assess the performance of the forecasting models. Result: The incidence of CLABSI in CRRT patients was 8.01 per 1,000 catheter days (238 of 29,711). According to the multifactor regression analysis by SPSS software, the retaining time of dialysis catheter, C-reactive protein levels, total bilirubin, acute pancreatitis, and systemic inflammation reaction syndrome were the risk factors. According to the Youden’s index, the cutoff point of the retaining time of dialysis catheter was 5.5 days; the cutoff point of CRP was 112.5mg/L; and the cutoff point of total bilirubin was 14.15 μmol/L. The prediction models of CLABSI for CRRT patients were developed: The AUC of the prediction model developed by SPSS software was 0.763 (95% CI, 0.717–0.809). The receiver operating characteristic (ROC) curve analysis showed that the AUCs of the prediction models developed separately by Weka software using Bayes, logistic regression analysis, multiple layer Perceptron and J48, and SPSS software through logistic regression analysis were between 0.6 and 0.8. Using the down-sampling technique, the AUC ranged between 0.7 and 0.9, and the sensitivity, precision, and κ value increased. Thus, these models had definite clinical significance. Conclusion: The prediction models of CLABSI for CRRT patients, developed based on the big healthcare data, not only had good judgment ability, but also had good application value for individual evaluations and the target population.Funding: This study was supported by the Health Commission of Sichuan Province.Disclosures: None

scholarly journals Nomogram for Predicting the Postoperative Venous Thromboembolism in Spinal Metastasis Tumor: A Multicenter Retrospective Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Hao-ran Zhang ◽  
Ming-you Xu ◽  
Xiong-gang Yang ◽  
Feng Wang ◽  
Hao Zhang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Venous Thromboembolism ◽  
Prediction Model ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Independent Risk Factors

IntroductionVenous thromboembolism can be divided into deep vein thrombosis and pulmonary embolism. These diseases are a major factor affecting the clinical prognosis of patients and can lead to the death of these patients. Unfortunately, the literature on the risk factors of venous thromboembolism after surgery for spine metastatic bone lesions are rare, and no predictive model has been established.MethodsWe retrospectively analyzed 411 cancer patients who underwent metastatic spinal tumor surgery at our institution between 2009 and 2019. The outcome variable of the current study is venous thromboembolism that occurred within 90 days of surgery. In order to identify the risk factors for venous thromboembolism, a univariate logistic regression analysis was performed first, and then variables significant at the P value less than 0.2 were included in a multivariate logistic regression analysis. Finally, a nomogram model was established using the independent risk factors.ResultsIn the multivariate logistic regression model, four independent risk factors for venous thromboembolism were further screened out, including preoperative Frankel score (OR=2.68, 95% CI 1.78-4.04, P=0.001), blood transfusion (OR=3.11, 95% CI 1.61-6.02, P=0.041), Charlson comorbidity index (OR=2.01, 95% CI 1.27-3.17, P=0.013; OR=2.29, 95% CI 1.25-4.20, P=0.017), and operative time (OR=1.36, 95% CI 1.14-1.63, P=0.001). On the basis of the four independent influencing factors screened out by multivariate logistic regression model, a nomogram prediction model was established. Both training sample and validation sample showed that the predicted probability of the nomogram had a strong correlation with the actual situation.ConclusionThe prediction model for postoperative VTE developed by our team provides clinicians with a simple method that can be used to calculate the VTE risk of patients at the bedside, and can help clinicians make evidence-based judgments on when to use intervention measures. In clinical practice, the simplicity of this predictive model has great practical value.

scholarly journals Monocytes as an Early Predictor for Patients with Acute Paraquat Poisoning: A Retrospective Analysis

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Yong Zhao ◽  
Ya Qi Song ◽  
Jie Gao ◽  
Shun Yi Feng ◽  
Yong Li
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Receiver Operator Characteristic ◽  
Monocyte Count ◽  
Central Hospital ◽  
Predictive Values ◽  
Kaplan Meier ◽  
Independent Risk Factors ◽  
Early Predictor

Background. The predictive values of monocytes in the prognosis of patients with acute paraquat (PQ) poisoning are unclear. This retrospective study investigated the predictive values of monocytes in the prognosis of patients with acute PQ poisoning. Methods. Adult patients who suffered from acute PQ poisoning in the emergency care unit of Cangzhou Central Hospital from May 2012 to December 2018 were enrolled. The patients were divided into groups, namely, survival and nonsurvival, according to a 90-day prognosis. Moreover, correlation, logistic regression, receiver-operator characteristic (ROC), and Kaplan–Meier curve analyses were applied to evaluate the monocyte values used to predict the prognosis of patients with acute PQ poisoning. Result. Among the 109 patients, 45 survived within 90 days after the poisoning, resulting in a 41.28% survival rate. The monocyte count of the nonsurvivors was significantly higher than that of the survivors (P< 0.001). Correlation analysis showed that monocyte count positively correlated with plasma PQ concentration (r= 0.413; P< 0.001) and negatively correlated with survival time (r= 0.512; P< 0.001) and 90-day survival (r= 0.503; P< 0.001). Logistic regression analysis showed that elevated monocytes were the independent risk factors for the 90-day survival. The area under the ROC curve of the monocyte count used to predict the 90-day survival was 0.826 (95% CI: 0.751–0.904), the optimal cut-off was 0.51×109/L, sensitivity was 73.4%, and specificity was 86.7%. Conclusion. This study demonstrated that elevated monocyte count is a useful early predictor of 90-day survival in patients with acute PQ poisoning. However, further studies are warranted to draw firm conclusions.

scholarly journals Effect of Positive Hepatitis B Surface Antigen on The Risk of Synchronous Liver Metastasis: A Retrospective Study of 868 Consecutive Patients of Newly Diagnosed Gastric Cancer

2020 ◽  
Author(s):  
Tingya Wang ◽  
Haijun Zhang
Keyword(s):  
Risk Factors ◽  
Gastric Cancer ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Retrospective Study ◽  
Liver Metastasis ◽  
Hepatitis B ◽  
Surface Antigen ◽  
Hepatitis B Surface Antigen ◽  
Newly Diagnosed

Abstract Background. The study aimed to explore the influence of hepatitis B virus (HBV) infection on the risk of synchronous gastric cancer liver metastasis (synGCLM).Methods. This was a retrospective study which enrolled 868 patients with newly diagnosed gastric cancer (GC). The study compared the prevalence of synGCLM between hepatitis B surface antigen (HBsAg)-positive (HBsAg+) and -negative (HBsAg-) patients. Logistic regression analysis was utilized to analyze the risk factors for synGCLM. Among patients with and without synGCLM, aspartate aminotransferase to platelet ratio index (APRI), liver fibrosis-4 index (FIB-4) and hepatitis B e antigen (HBeAg) status were further analyzed. Results. The prevalence of synGCLM in the HBsAg+ patients was higher than that in the HBsAg- patients, which was statistically significant (P = 0.025). Multivariate logistic regression analysis demonstrated that HBsAg, the elevated level of carcinoembryonic antigen (CEA), alpha-fetoprotein (AFP), γ-glutamyltransferase (GGT) and alkaline phosphatase (ALP) were risk factors for synGCLM. Among the HBsAg+ patients, both ARPI and FIB-4 were significantly higher in the patients with synGCLM (synGCLM+) than those without synGCLM (synGCLM-) (ARPI: P = 0.045; FIB-4: P = 0.047); HBeAg positivity was detected in 20.0% of synGCLM+ patients compared to 6.0% of synGCLM- patients, but the difference was of no significance (P = 0.190). Conclusions. HBV infection significantly increases the risk of synGCLM, and elevated ARPI and FIB-4 may be pro-metastatic especially among the HBsAg+ GC patients.

scholarly journals Development of Predictive Nomograms for Clinical Use to Quantify the Risk of Amputation in Patients with Diabetic Foot Ulcer

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Bocheng Peng ◽  
Rui Min ◽  
Yiqin Liao ◽  
Aixi Yu
Keyword(s):  
Risk Factors ◽  
Regression Analysis ◽  
Prediction Model ◽  
Predictive Factors ◽  
Diabetic Foot ◽  
Univariate Analysis ◽  
Foot Ulcer ◽  
Diabetic Foot Ulcer ◽  
Single Factor ◽  
Independent Risk Factors

Objective. To determine the novel proposed nomogram model accuracy in the prediction of the lower-extremity amputations (LEA) risk in diabetic foot ulcer (DFU). Methods and Materials. In this retrospective study, data of 125 patients with diabetic foot ulcer who met the research criteria in Zhongnan Hospital of Wuhan University from January 2015 to December 2019 were collected by filling in the clinical investigation case report form. Firstly, univariate analysis was used to find the primary predictive factors of amputation in patients with diabetic foot ulcer. Secondly, single factor and multiple factor logistic regression analysis were employed to screen the independent influencing factors of amputation introducing the primary predictive factors selected from the univariate analysis. Thirdly, the independent influencing factors were applied to build a prediction model of amputation risk in patients with diabetic foot ulcer by using R4.3; then, the nomogram was established according to the selected variables visually. Finally, the performance of the prediction model was evaluated and verified by receiver working characteristic (ROC) curve, corrected calibration curve, and clinical decision curve. Results. 7 primary predictive factors were selected by univariate analysis from 21 variables, including the course of diabetes, peripheral angiopathy of diabetic (PAD), glycosylated hemoglobin A1c (HbA1c), white blood cells (WBC), albumin (ALB), blood uric acid (BUA), and fibrinogen (FIB); single factor logistic regression analysis showed that albumin was a protective factor for amputation in patients with diabetic foot ulcer, and the other six factors were risk factors. Multivariate logical regression analysis illustrated that only five factors (the course of diabetes, PAD, HbA1c, WBC, and FIB) were independent risk factors for amputation in patients with diabetic foot ulcer. According to the area under curve (AUC) of ROC was 0.876 and corrected calibration curve of the nomogram displayed good fitting ability, the model established by these 5 independent risk factors exhibited good ability to predict the risk of amputation. The decision analysis curve (DCA) indicated that the nomogram model was more practical and accurate when the risk threshold was between 6% and 91%. Conclusion. Our novel proposed nomogram showed that the course of diabetes, PAD, HbA1c, WBC, and FIB are the independent risk factors of amputation in patients with DFU. This prediction model was well developed and behaved a great accurate value for LEA so as to provide a useful tool for screening LEA risk and preventing DFU from developing into amputation.

scholarly journals Risk Factors of Atrial Arrhythmia in Patients With Liver Cirrhosis: A Retrospective Study

2021 ◽  
Vol 8 ◽  
Author(s):  
Xiya Lu ◽  
Zhijing Wang ◽  
Liu Yang ◽  
Changqing Yang ◽  
Meiyi Song
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Liver Cirrhosis ◽  
Retrospective Study ◽  
Logistic Regression Analysis ◽  
Multiple Logistic Regression Analysis ◽  
Multivariate Logistic Regression Analysis ◽  
Clinical Information ◽  
Atrial Arrhythmia

Background and Objectives: Liver cirrhosis is known to be associated with atrial arrhythmia. However, the risk factors for atrial arrhythmia in patients with liver cirrhosis remain unclear. This retrospective study aimed to investigate the risk factors for atrial arrhythmia in patients with liver cirrhosis.Methods: In the present study, we collected data from 135 patients with liver cirrhosis who were admitted to the Department of Gastroenterology at Shanghai Tongji Hospital. We examined the clinical information recorded, with the aim of identifying the risk factors for atrial arrhythmia in patients with liver cirrhosis. Multiple logistic regression analysis was used to screen for significant factors differentiating liver cirrhosis patients with atrial arrhythmia from those without atrial arrhythmia.Results: The data showed that there were seven significantly different factors that distinguished the group with atrial arrhythmia from the group without atrial arrhythmia. The seven factors were age, white blood cell count (WBC), albumin (ALB), serum Na+, B-type natriuretic peptide (BNP), ascites, and Child-Pugh score. The results of multivariate logistic regression analysis suggested that age (β = 0.094, OR = 1.098, 95% CI 1.039–1.161, P = 0.001) and ascites (β =1.354, OR = 3.874, 95% CI 1.202–12.483, P = 0.023) were significantly associated with atrial arrhythmia.Conclusion: In the present study, age and ascites were confirmed to be risk factors associated with atrial arrhythmia in patients with liver cirrhosis.

Abstract O.07: The Clinical Risk Factors of Intravenous Immunoglobulin Resistance and Coronary Artery Lesion of Kawasaki Disease: Retrospective Analysis of 602 Cases

Circulation ◽  
2015 ◽  
Vol 131 (suppl_2) ◽  
Author(s):  
lijian xie ◽  
Cuizhen Zhou ◽  
Renjian Wang ◽  
Tingting Xiao ◽  
Jie Shen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Coronary Artery ◽  
Kawasaki Disease ◽  
Intravenous Immunoglobulin ◽  
Clinical Evidence ◽  
Clinical Risk Factors ◽  
Ivig Treatment ◽  
Ivig Resistance ◽  
Sensitive Group

Introduction: The incidence of Kawasaki disease (KD) in China is increasing for years. The current coronary artery lesion (CAL) incidence is 5-10% in KD with intravenous immunoglobulin (IVIG) treatment. And the 10-20% KD patients still exhibit IVIG resistance. However, little clinical evidence on the occurrence of either CAL or IVIG resistance for big KD sample study in China during the past decade. Objective: In order to find clinical risk factors of CAL and IVIG resistance of KD in China. Methods: We retrospectively analyzed the clinical manifestations, laboratory results, treatment and complications of cardiac vascular of 602 KD cases from 2007 to 2012 admitted at Shanghai Children’s Hospital. The SAS 9.2 edition was used for statistical analysis. The mean ± standard deviation or the median were used for measurements. Case numbers and percentages were used for the count number. The t-test and the Mann-Whitney test were both used for mean comparisons. Single factor and multi-factor logistic regression analyses were used to analyze the risk factors. Results: 1. The KD gender male to female ratio was 1.85: 1. The KD median age was 2.0 years old (one month to 11.7 years old). 20.1% cases (121 of 602) exhibited CAL. There was no difference of CAL incidence between the gender (p=0.09). 2. The incidence of bright red cracked lips (p=0.001), peeling of the skin of the toes (p=0.021) and perianal skin peeling (p=0.031) are less in group with CAL. 3. Among the 602 cases, there were 525 cases that were sensitive to IVIG therapy. 100 of those cases had CAL with an incidence of 19.1%. Among the 26 IVIG resistance cases, there were 9 cases with CAL with an incidence of 34.6%, which was higher than the IVIG sensitive group (p=0.05). 4. ESR (p=0.014), CRP (p=0.017), PLT (p=0.003) and Hb (p=0.032) were much higher in the IVIG resistance group than the IVIG sensitive group, even though the IVIG resistance group started the IVIG treatment earlier (p=0.003). 5. Logistic regression analysis was conducted to show that GPT≥80IU/L was the independent risk factor of IVIG resistance, risk ratio was 2.945 (p=0.012) . Conclusion: This research suggests that risk factors of clinical evidence for IVIG resistance and CAL in KD.

scholarly journals Identification of Metabolic Syndrome Based on Anthropometric, Blood and Spirometric Risk Factors Using Machine Learning

2020 ◽  
Vol 10 (21) ◽  
pp. 7741
Author(s):  
Sang Yeob Kim ◽  
Gyeong Hee Nam ◽  
Byeong Mun Heo
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Logistic Regression ◽  
Prediction Model ◽  
Prediction Models ◽  
Strong Association ◽  
Forced Expiratory Volume ◽  
Binary Logistic Regression Analysis ◽  
Cross Sectional Survey ◽  
Cross Sectional

Metabolic syndrome (MS) is an aggregation of coexisting conditions that can indicate an individual’s high risk of major diseases, including cardiovascular disease, stroke, cancer, and type 2 diabetes. We conducted a cross-sectional survey to evaluate potential risk factor indicators by identifying relationships between MS and anthropometric and spirometric factors along with blood parameters among Korean adults. A total of 13,978 subjects were enrolled from the Korea National Health and Nutrition Examination Survey. Statistical analysis was performed using a complex sampling design to represent the entire Korean population. We conducted binary logistic regression analysis to evaluate and compare potential associations of all included factors. We constructed prediction models based on Naïve Bayes and logistic regression algorithms. The performance evaluation of the prediction model improved the accuracy with area under the curve (AUC) and calibration curve. Among all factors, triglyceride exhibited a strong association with MS in both men (odds ratio (OR) = 2.711, 95% confidence interval (CI) [2.328–3.158]) and women (OR = 3.515 [3.042–4.062]). Regarding anthropometric factors, the waist-to-height ratio demonstrated a strong association in men (OR = 1.511 [1.311–1.742]), whereas waist circumference was the strongest indicator in women (OR = 2.847 [2.447–3.313]). Forced expiratory volume in 6s and forced expiratory flow 25–75% strongly associated with MS in both men (OR = 0.822 [0.749–0.903]) and women (OR = 1.150 [1.060–1.246]). Wrapper-based logistic regression prediction model showed the highest predictive power in both men and women (AUC = 0.868 and 0.932, respectively). Our findings revealed that several factors were associated with MS and suggested the potential of employing machine learning models to support the diagnosis of MS.

scholarly journals Predictive value of serum procalcitonin for both initial and repeated immunoglobulin resistance in Kawasaki disease: a prospective cohort study

2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Shuran Shao ◽  
Chunyan Luo ◽  
Kaiyu Zhou ◽  
Yimin Hua ◽  
Mei Wu ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Kawasaki Disease ◽  
Logistic Regression Analysis ◽  
Predictive Value ◽  
Laboratory Data ◽  
Multivariate Logistic Regression Analysis ◽  
Multivariate Logistic Regression ◽  
Ivig Resistance ◽  
Resistance Prediction

Abstract Background Intravenous immunoglobulin (IVIG) resistance prediction is one pivotal topic of interests in Kawasaki disease (KD) since those patients with KD resistant to IVIG might improve of an early-intensified therapy. Data regarding predictive value of procalcitonin (PCT) for IVIG resistance, particularly for repeated IVIG resistance in KD was limited. This study aimed to testify the predictive validity of PCT for both initial and repeated IVIG resistance in KD. Methods A total of 530 KD patients were prospectively recruited between January 2015 and March 2019. The clinical and laboratory data were compared between IVIG-responsive and IVIG-resistant groups. Multivariate logistic regression analysis was applied to determine the association between PCT and IVIG resistance. Receiver operating characteristic (ROC) curves analysis was further performed to assess the validity of PCT in predicting both initial and repeated IVIG resistance. Results The serum PCT level was significantly higher in initial IVIG-resistance group compared with IVIG-response group (p = 0.009), as well as between repeated IVIG responders and nonresponders (p = 0.017). The best PCT cutoff value for initial and repeated IVIG resistance prediction was 1.48 ng/ml and 2.88 ng/ml, respectively. The corresponding sensitivity was 53.9 and 51.4%, while the specificity were 71.8 and 73.2%, respectively. Multivariate logistic regression analysis failed to identify serum PCT level as an independent predictive factor for both initial and repeated IVIG resistance in KD. Conclusions Serum PCT levels were significantly higher in IVIG nonresponders, but PCT may not be suitable as a single marker to accurately predict both initial and repeated IVIG resistance in KD.

Sign in / Sign up

Export Citation Format

Share Document