Establishment of a Nomogram for Predicting Early Death in Viral Myocarditis

Objective. This research aimed to establish a nomogram for predicting early death in viral myocarditis (VMC) patients. Method. A total of 362 consecutive VMC patients in Fujian Medical University Affiliated First Quanzhou Hospital between January 1, 2009, and December 31, 2019, were included. A least absolute shrinkage and selection operator (LASSO) regression model was used to detect the risk factors that most consistently and correctly predicted early death in VMC. The performance of the nomogram was assessed by calibration, discrimination, and clinical utility. Result. 9 factors were screened by LASSO regression analysis for predicting the early death of VMC. Combined with the actual clinical situation, the heart failure (HF) (OR: 2.13, 95% CI: 2.76–5.95), electrocardiogram (ECG) (OR: 6.11, 95% CI: 1.05–8.66), pneumonia (OR: 3.62, 95% CI: 1.43–9.85), brain natriuretic peptide (BNP) (OR: 4.66, 95% CI: 3.07–24.06), and lactate dehydrogenase (LDH) (OR: 1.90, 95% CI: 0.19–9.39) were finally used to construct the nomogram. The nomogram’s C-index was 0.908 in the training cohort and 0.924 in the validation cohort. And the area under the receiver operating characteristic curve of the nomogram was 0.91 in the training cohort and 0.924 in the validating cohort. Decision curve analysis (DCA) also showed that the nomogram was clinically useful. Conclusion. This nomogram achieved an good prediction of the risk of early death in VMC patients.

Download Full-text

Development and Validation of a Nomogram for Predicting Bladder Calculi Risk in Patients With Benign Prostatic Hyperplasia

10.21203/rs.3.rs-934816/v1 ◽

2021 ◽

Author(s):

Euxu Xie ◽

Xuelian Gu ◽

Chen Ma ◽

Li Guo ◽

Man Li ◽

...

Keyword(s):

Risk Factors ◽

Benign Prostatic Hyperplasia ◽

Characteristic Curve ◽

Prostatic Hyperplasia ◽

Calibration Plot ◽

Lasso Regression ◽

Net Benefit ◽

Bladder Calculi ◽

Validation Set ◽

Selection Operator

Abstract Objective To develop and validate a nomogram for predicting bladder calculi risk in patients with benign prostatic hyperplasia (BPH).Methods A total of 368 patients who underwent transurethral resection of the prostate (TURP) and had histologically proven BPH from January 2018 to January 2021 were retrospectively collected. Eligible patients were randomly assigned to the training and validation datasets. Least absolute shrinkage and selection operator (LASSO) regression was used to select the optimal risk factors. A prediction model was established based on the selected characteristics. The performance of the nomogram was assessed by calibration plots and the area under the receiver operating characteristic curve (AUROC). Furthermore, decision curve analysis (DCA) was used to determine the net benefit rate of of the nomogram. Results Among 368 patients who met the inclusion criteria, older age, a history of diabetes and hyperuricemia, longer intravesical prostatic protrusion (IPP)and larger prostatic urethral angulation (PUA) were independent risk factors for bladder calculi in patients with BPH. These factors were used to develop a nomogram, which had a good identification ability in predicting the risk of bladder calculi in patients, with AUROCs of 0.911 (95% CI: 0.876–0.945) in the training set and 0.884 (95% CI: 0.820–0.948) in the validation set. The calibration plot showed that the model had good calibration. Moreover, DCA indicated that the model had a goodclinical benefit. Conclusion We developed and internally validated the first nomogram to date to help physicians assess the risk of bladder calculi in patients with BPH, which may help physicians improve individual interventions and make better clinical decisions.

Download Full-text

Predictive nomogram for postoperative pancreatic fistula following pancreaticoduodenectomy: a retrospective study

BMC Cancer ◽

10.1186/s12885-021-08201-z ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Jian Shen ◽

Feng Guo ◽

Yan Sun ◽

Jingyuan Zhao ◽

Jin Hu ◽

...

Keyword(s):

Pancreatic Fistula ◽

Validation Cohort ◽

Characteristic Curve ◽

Postoperative Pancreatic Fistula ◽

Individual Risk ◽

Calibration Plot ◽

Multivariable Logistic Regression Analysis ◽

Lasso Regression ◽

Training Cohort ◽

Significant Difference

Abstract Background Postoperative pancreatic fistula (POPF) represents the most common complication following pancreaticoduodenectomy (PD). Predictive models are needed to select patients with a high risk of POPF. This study was aimed to establish an effective predictive nomogram for POPF following PD. Methods Consecutive patients who had undergone PD between January 2016 and May 2020 at a single institution were analysed retrospectively. A predictive nomogram was established based on a training cohort, and Lasso regression and multivariable logistic regression analysis were used to evaluate predictors. The predictive abilities of the predicting model were assessed for internal validation by the area under the receiver operating characteristic curve (AUC) and calibration plot using bootstrap resampling. The performance of the nomogram was compared with that of the currently used a-FRS model. Results A total of 459 patients were divided into a training cohort (n = 302) and a validation cohort (n = 157). No significant difference was observed between the two groups with respect to clinicopathological characteristics. The POPF rate was 16.56%. The risk factors of POPF POPF were albumin difference, drain amylase value on postoperative day 1, pancreas texture, and BMI, which were all selected into a nomogram. Nomogram application revealed good discrimination (AUC = 0.87, 95% CI: 0.81–0.94, P < 0.001) as well as calibration abilities in the validation cohort. The predictive value of the nomogram was better than that of the a-FRS model (AUC: 0.87 vs 0.62, P < 0.001). Conclusions This predictive nomogram could be used to evaluate the individual risk of POPF in patients following PD, and albumin difference is a new, accessible predictor of POPF after PD. Trial registration This study was registered in the Chinese Clinical Trial Register (ChiCTR2000034435).

Download Full-text

Development and validation of a nomogram for predicting the probability of nontraumatic osteonecrosis of the femoral head

10.21203/rs.2.23333/v1 ◽

2020 ◽

Author(s):

Qiang Xu ◽

Hangjun Chen ◽

Sihai Chen ◽

Jing Shan ◽

Guoming Xia ◽

...

Keyword(s):

Risk Factors ◽

Femoral Head ◽

Demographic Data ◽

Characteristic Curve ◽

Model Development ◽

Lasso Regression ◽

Early Screening ◽

Good Discrimination ◽

Internal Validation ◽

Selection Operator

Abstract Background Although corticosteroids and alcohol are two major risk factors for nontraumatic osteonecrosis of the femoral head (NONFH), the effects of other factors have rarely been studied, thereby making early diagnosis and treatment of NONFH difficult. This study aimed to develop and validate a nomogram to estimate the probability of NONFH using clinical risk factors other than corticosteroids and alcohol consumption. Methods A training cohort of 790 patients (n=434, NONFH; n=356, femoral neck fractures [non-NONFH]) diagnosed in our hospital from January 2011 to December 2016 was used for model development. A least absolute shrinkage and selection operator (lasso) regression model was used for date dimension reduction and optimal predictor selection. A predictive model was developed from univariate and multivariate logistic regression analyses. Performance characterisation of the resulting nomogram included calibration, discriminatory ability, and clinical usefulness. After internal validation, the nomogram was further evaluated in a separate cohort of 300 consecutive patients included between January 2017 and December 2018. Results The simple prediction nomogram included five predictors from univariate and multivariate analyses, including gender, total cholesterol levels, triglyceride levels, white blood cell count, and platelet count. Internal validation showed that the model had good discrimination (area under the receiver operating characteristic curve [AUC]=0.80) and calibration. Good discrimination (AUC=0.81) and calibration were preserved in the validation cohort. Decision curve analysis showed that the predictive nomogram was clinically useful. Conclusions The simple diagnostic nomogram, which combines demographic data and laboratory blood test results, was able to quantify the probability of NONFH in cases of early screening and diagnosis.

Download Full-text

Development and validation of a nomogram for predicting severity in patients with hemorrhagic fever with renal syndrome: A retrospective study

Open Medicine ◽

10.1515/med-2021-0307 ◽

2021 ◽

Vol 16 (1) ◽

pp. 944-954

Author(s):

Zheng Yang ◽

Qinming Hu ◽

Zhipeng Feng ◽

Yi Sun

Keyword(s):

Retrospective Study ◽

Risk Model ◽

Characteristic Curve ◽

Multivariate Logistic Regression Analysis ◽

Public Health Problem ◽

Hemorrhagic Fever ◽

Multiple Organ ◽

Hantavirus Infection ◽

Lasso Regression ◽

Selection Operator

Abstract Background Hemorrhagic fever with renal syndrome (HFRS) is a zoonotic disease caused by hantavirus infection. Patients with severe HFRS may develop multiple organ failure or even death, which makes HFRS a serious public health problem. Methods In this retrospective study, we included a total of 155 consecutive patients who were diagnosed with HFRS, of whom 109 patients served as a training cohort and 46 patients as an independent verification cohort. In the training set, the least absolute shrinkage and selection operator (LASSO) regression was used to screen the characteristic variables of the risk model. Multivariate logistic regression analysis was used to construct a nomogram containing the characteristic variables selected in the LASSO regression model. Results The area under the receiver operating characteristic curve (AUC) of the nomogram indicated that the model had good discrimination. The calibration curve exhibited that the nomogram was in good agreement between the prediction and the actual observation. Decision curve analysis and clinical impact curve suggested that the predictive nomogram had clinical utility. Conclusion In this study, we established a simple and feasible model to predict severity in patients with HFRS, with which HFRS would be better identified and patients can be treated early.

Download Full-text

Development and validation of a nomogram for predicting the probability of nontraumatic osteonecrosis of the femoral head in Chinese population

Scientific Reports ◽

10.1038/s41598-020-77693-9 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Qiang Xu ◽

Hangjun Chen ◽

Sihai Chen ◽

Jing Shan ◽

Guoming Xia ◽

...

Keyword(s):

Femoral Head ◽

Demographic Data ◽

Characteristic Curve ◽

Model Development ◽

Lasso Regression ◽

Early Screening ◽

Good Discrimination ◽

Internal Validation ◽

Selection Operator ◽

Development And Validation

AbstractAlthough corticosteroids and alcohol are two major risk factors for nontraumatic osteonecrosis of the femoral head (NONFH), the effects of other factors have rarely been studied, thereby making early diagnosis and treatment of NONFH difficult. This study aimed to develop and validate a nomogram to NONFH, but patients with alcohol- and steroid-related NONFH are not at all taken into account in this study. A training cohort of 790 patients (n = 434, NONFH; n = 356, femoral neck fractures [non-NONFH]) diagnosed in our hospital from January 2011 to December 2016 was used for model development. A least absolute shrinkage and selection operator (lasso) regression model was used for date dimension reduction and optimal predictor selection. A predictive model was developed from univariate and multivariate logistic regression analyses. Performance characterisation of the resulting nomogram included calibration, discriminatory ability, and clinical usefulness. After internal validation, the nomogram was further evaluated in a separate cohort of 300 consecutive patients included between January 2017 and December 2018. The simple prediction nomogram included five predictors from univariate and multivariate analyses, including gender, total cholesterol levels, triglyceride levels, white blood cell count, and platelet count. Internal validation showed that the model had good discrimination [area under the receiver operating characteristic curve (AUC) = 0.80] and calibration. Good discrimination (AUC = 0.81) and calibration were preserved in the validation cohort. Decision curve analysis showed that the predictive nomogram was clinically useful. The simple diagnostic nomogram, which combines demographic data and laboratory blood test results, was able to quantify the probability of NONFH in cases of early screening and diagnosis.

Download Full-text

Establishment and validation of prognosis model for patients with cerebral contusion

BMC Neurology ◽

10.1186/s12883-021-02482-4 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Yufeng Zhu ◽

Xiaoqing Jin ◽

Lulu Xu ◽

Pei Han ◽

Shengwu Lin ◽

...

Keyword(s):

Prediction Model ◽

Validation Cohort ◽

Characteristic Curve ◽

Third Ventricle ◽

Curve Analysis ◽

Imaging Features ◽

Lasso Regression ◽

Cerebral Contusion ◽

Decision Curve Analysis ◽

Training Cohort

Abstract Background And Objective Cerebral Contusion (CC) is one of the most serious injury types in patients with traumatic brain injury (TBI). In this study, the baseline data, imaging features and laboratory examinations of patients with CC were summarized and analyzed to develop and validate a prediction model of nomogram to evaluate the clinical outcomes of patients. Methods A total of 426 patients with cerebral contusion (CC) admitted to the People’s Hospital of Qinghai Province and Affiliated Hospital of Qingdao University from January 2018 to January 2021 were included in this study, We randomly divided the cohort into a training cohort (n = 284) and a validation cohort (n = 142) with a ratio of 2:1.At Least absolute shrinkage and selection operator (Lasso) regression were used for screening high-risk factors affecting patient prognosis and development of the predictive model. The identification ability and clinical application value of the prediction model were analyzed through the analysis of receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). Results Twelve independent prognostic factors, including age, Glasgow Coma Score (GCS), Basal cistern status, Midline shift (MLS), Third ventricle status, intracranial pressure (ICP) and CT grade of cerebral edema,etc., were selected by Lasso regression analysis and included in the nomogram. The model showed good predictive performance, with a C index of (0.87, 95% CI, 0.026–0.952) in the training cohort and (0.93, 95% CI, 0.032–0.965) in the validation cohort. Clinical decision curve analysis (DCA) also showed that the model brought high clinical benefits to patients. Conclusion This study established a high accuracy of nomogram model to predict the prognosis of patients with CC, its low cost, easy to promote, is especially applicable in the acute environment, at the same time, CSF-glucose/lactate ratio(C-G/L), volume of contusion, and mean CT values of edema zone, which were included for the first time in this study, were independent predictors of poor prognosis in patients with CC. However, this model still has some limitations and deficiencies, which require large sample and multi-center prospective studies to verify and improve our results.

Download Full-text

A Historical Data based Ensemble System for Efficient Stock Price Prediction

Recent Patents on Computer Science ◽

10.2174/2213275912666190730161807 ◽

2019 ◽

Vol 12 ◽

Author(s):

Vijay Kumar Dwivedi ◽

Manoj Madhava Gore

Keyword(s):

Stock Price ◽

Prediction Models ◽

Historical Data ◽

Stock Exchange ◽

Primary Objective ◽

Lasso Regression ◽

Stock Price Prediction ◽

Price Prediction ◽

Consistent Manner ◽

Selection Operator

Background: Stock price prediction is a challenging task. The social, economic, political, and various other factors cause frequent abrupt changes in the stock price. This article proposes a historical data-based ensemble system to predict the closing stock price with higher accuracy and consistency over the existing stock price prediction systems. Objective: The primary objective of this article is to predict the closing price of a stock for the next trading in more accurate and consistent manner over the existing methods employed for the stock price prediction. Method: The proposed system combines various machine learning-based prediction models employing least absolute shrinkage and selection operator (LASSO) regression regularization technique to enhance the accuracy of stock price prediction system as compared to any one of the base prediction models. Results: The analysis of results for all the eleven stocks (listed under Information Technology sector on the Bombay Stock Exchange, India) reveals that the proposed system performs best (on all defined metrics of the proposed system) for training datasets and test datasets comprising of all the stocks considered in the proposed system. Conclusion: The proposed ensemble model consistently predicts stock price with a high degree of accuracy over the existing methods used for the prediction.

Download Full-text

Development of Machine Learning Models to Predict Probabilities and Types of Stroke at Prehospital Stage: the Japan Urgent Stroke Triage Score Using Machine Learning (JUST-ML)

Translational Stroke Research ◽

10.1007/s12975-021-00937-x ◽

2021 ◽

Author(s):

Kazutaka Uchida ◽

Junichi Kouno ◽

Shinichi Yoshimura ◽

Norito Kinjo ◽

Fumihiro Sakakibara ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Random Forests ◽

Prediction Models ◽

Characteristic Curve ◽

Predictive Performance ◽

Vessel Occlusion ◽

Predictive Values ◽

Training Cohort ◽

Sensitivity Specificity

AbstractIn conjunction with recent advancements in machine learning (ML), such technologies have been applied in various fields owing to their high predictive performance. We tried to develop prehospital stroke scale with ML. We conducted multi-center retrospective and prospective cohort study. The training cohort had eight centers in Japan from June 2015 to March 2018, and the test cohort had 13 centers from April 2019 to March 2020. We use the three different ML algorithms (logistic regression, random forests, XGBoost) to develop models. Main outcomes were large vessel occlusion (LVO), intracranial hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral infarction (CI) other than LVO. The predictive abilities were validated in the test cohort with accuracy, positive predictive value, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F score. The training cohort included 3178 patients with 337 LVO, 487 ICH, 131 SAH, and 676 CI cases, and the test cohort included 3127 patients with 183 LVO, 372 ICH, 90 SAH, and 577 CI cases. The overall accuracies were 0.65, and the positive predictive values, sensitivities, specificities, AUCs, and F scores were stable in the test cohort. The classification abilities were also fair for all ML models. The AUCs for LVO of logistic regression, random forests, and XGBoost were 0.89, 0.89, and 0.88, respectively, in the test cohort, and these values were higher than the previously reported prediction models for LVO. The ML models developed to predict the probability and types of stroke at the prehospital stage had superior predictive abilities.

Download Full-text

Predicting drug–target interactions Based on the Ensemble Models of Multiple Feature Pairs

International Journal of Molecular Sciences ◽

10.3390/ijms22126598 ◽

2021 ◽

Vol 22 (12) ◽

pp. 6598

Author(s):

Cheng Wang ◽

Jun Zhang ◽

Peng Chen ◽

Bing Wang

Keyword(s):

Drug Target ◽

Essential Feature ◽

Characteristic Curve ◽

Prediction Method ◽

New Drugs ◽

Good Prediction ◽

Ensemble Model ◽

Test Set ◽

Multiple Feature ◽

Validation Set

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.

Download Full-text

A machine learning-based model for predicting intensive care unit length of stay in patients with cardiac surgery (Preprint)

10.2196/preprints.32887 ◽

2021 ◽

Author(s):

Nianyue Wu ◽

Siru Liu ◽

Haotian Zhang ◽

Xiaomin Hou ◽

Ping Zhang ◽

...

Keyword(s):

Machine Learning ◽

Intensive Care ◽

Length Of Stay ◽

Confidence Interval ◽

Medical Information ◽

Lasso Regression ◽

Icu Length Of Stay ◽

Data Source ◽

The Mean ◽

Selection Operator

BACKGROUND The intensive care unit (ICU) length of stay is significant to evaluate the effect of cardiac surgical treatment inpatient. OBJECTIVE This research aims to accurately predict the ICU length of stay in patients with cardiac surgery. Methods: We used machine learning methods to construct the model, and the medical information mart for intensive care (MIMIC IV) database was used as the data source. A total of 7,567 patients were enrolled and the mean length of stay in the ICU was 3.12 days. A total of 126 predictors were included, and 44 important predictors were screened by least absolute shrinkage and selection operator (Lasso) regression. METHODS We used machine learning methods to construct the model, and the medical information mart for intensive care (MIMIC IV) database was used as the data source. A total of 7,567 patients were enrolled and the mean length of stay in the ICU was 3.12 days. A total of 126 predictors were included, and 44 important predictors were screened by least absolute shrinkage and selection operator (Lasso) regression. RESULTS The mean accuracy are 0.603 (95% confidence interval (CI): [0.602-0.604]), 0.687 (95% confidence interval (CI): [0.687-0.688]) and 0.688 (95% confidence interval (CI): [0.687-0.689]) for the logistic regression (LR) with all variables, the gradient boosted decision tree (GBDT) with important variables and the GBDT with all variables respectively. CONCLUSIONS The GBDT model with important predictors partly overestimated patients whose length of stay was less than 3 days and underestimated patients whose length of stay was longer than 3 days. But the better prediction performance of GBDT facilitates early intervention of ICU patients with a long period of hospitalization.

Download Full-text