scoring model
Recently Published Documents


TOTAL DOCUMENTS

656
(FIVE YEARS 293)

H-INDEX

29
(FIVE YEARS 6)

2022 ◽  
Author(s):  
Yuto Sunaga ◽  
Atsushi Watanabe ◽  
Nobuyuki Katsumata ◽  
Takako Toda ◽  
Masashi Yoshizawa ◽  
...  

Abstract In Kawasaki disease (KD), accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial to reduce a risk for developing coronary artery lesions. To establish a simple and accurate scoring model predicting IVIG resistance, we conducted a retrospective cohort study of 996 KD patients that were diagnosed at 11 facilities for 10 years, in which 108 cases (23.5%) were resistant to initial IVIG treatment. We performed machine learning with random forest model using 30 clinical variables at diagnosis in 796 and 200 cases for training and test datasets, respectively. Random forest model accurately predicted IVIG resistance (AUC; 0.75, sensitivity; 0.54, specificity; 0.80). Next, using top five influential features (days of illness at initial therapy, serum levels of C-reactive protein, sodium, total bilirubin, and total cholesterol) in the random forest model, we designed a simple scoring system. In spite of its simplicity, the scoring system predicted IVIG resistance (AUC; 0.73, sensitivity; 0.55, specificity; 0.83) as accurately as the random forest model itself. Moreover, accuracy of our scoring system with five clinical features was almost identical to that of Gunma score with seven clinical features (AUC; 0.73, sensitivity; 0.53, specificity; 0.83), a well-known logistic regression scoring model, and superior to that of two widely used scores (Kurume score; 0.67, 0.46 and 0.76, respectively, and Osaka score; 0.69, 0.33 and 0.84, respectively). Conclusions: Our simple scoring system based on the findings in machine learning, as well as machine learning itself, seems to be useful to accurately predict IVIG resistance in KD patients.


2022 ◽  
Author(s):  
Kyohei Yugawa ◽  
Takashi Maeda ◽  
Shigeyuki Nagata ◽  
Jin Shiraishi ◽  
Akihiro Sakai ◽  
...  

Abstract Background: Posthepatectomy liver failure (PHLF) is a life-threatening complication following hepatic resection. The aspartate aminotransferase-to-platelet ratio index (APRI) is a noninvasive model for assessing the liver functional reserve in patients with hepatocellular carcinoma (HCC). This study aimed to establish a scoring model to stratify patients with HCC at risk for PHLF.Methods: This single-center retrospective study included 451 patients who underwent hepatic resection for HCC between 2004 and 2017. Preoperative factors, including noninvasive liver fibrosis markers and intraoperative factors, were evaluated. The predictive impact for PHLF was evaluated using receiver operating characteristic (ROC) curves of these factors.Results: Of 451 patients, 30 (6.7%) developed severe PHLF (grade B/C). Multivariate logistic analysis indicated that APRI, model for end-stage liver disease (MELD) score, operating time, and intraoperative blood loss were significantly associated with severe PHLF. A scoring model (over 0–4 points) was calculated using these optimal cutoff values. The area under the ROC curve of the established score for severe PHLF was 0.88, which greatly improved the predictive accuracy compared with these factors alone (p < 0.05 for all). Conclusions: The scoring model-based APRI, MELD score, operating time, and intraoperative blood loss can predict severe PHLF in patients with HCC.


2022 ◽  
pp. 270-292
Author(s):  
Luca Di Persio ◽  
Alberto Borelli

The chapter developed a tree-based method for credit scoring. It is useful because it helps lenders decide whether to grant or reject credit to their applicants. In particular, it proposes a credit scoring model based on boosted decision trees which is a technique consisting of an ensemble of several decision trees to form a single classifier. The analysis used three different publicly available datasets, and then the prediction accuracy of boosted decision trees is compared with the one of support vector machines method.


Medicine ◽  
2021 ◽  
Vol 100 (51) ◽  
pp. e28219
Author(s):  
Patcharin Khamnuan ◽  
Nipaporn Chuayunan ◽  
Acharaporn Duangjai ◽  
Surasak Saokaew ◽  
Natthaya Chaomuang ◽  
...  

2021 ◽  
Vol 14 (1) ◽  
pp. 130
Author(s):  
Sunghyon Kyeong ◽  
Daehee Kim ◽  
Jinho Shin

The credit scoring model is one of the most important decision-making tools for the sustainability of banking systems. This study is the first to examine whether it can be improved by using system log data that are stoed extensively for system operation. We used the log data recorded by the mobile application system of KakaoBank, a leading internet bank used by more than 14 million people in Korea. After generating candidate variables from KakaoBank’s log data, we created a credit scoring model by utilizing variables with high information values and logistic regression, the most common method for developing credit scoring models in financial institutions. To prove our hypothesis on the improvement of credit scoring model performance, we performed an independent sample t-test using the simulation results of repeated model development and performance measurement based on randomly sampled data. Consequently, the discrimination power of the proposed model using logistic regression (neural network) compared to the credit bureau-based model significantly improved by 1.84 (2.22) percentage points based on the Kolmogorov–Smirnov statistics. The results of this study suggest that a bank can utilize the accumulated log data inside the bank to improve decision-making systems, including credit scoring, at a low cost.


2021 ◽  
Author(s):  
Vincenzo Lisandrelli ◽  
Niccolo' Pozzi

Abstract Zohr field has developed a smart tool for the Process Safety compliance self-assessment. Scope of the tool is to evaluate field Process Safety Management system performance as well as driving a step change in field culture by making Process Safety a transversal target for all departments, not only HSE. To reach this scope, an internal Field multidisciplinary team has been created with the scope to verify the Process Safety pillars compliance through a simplified check list and scoring model. The initial 8 key elements are: ESDs Alarm management Safety Critical Elements Overrides Loss of Primary Containment Management of Change Permit to Work Manuals/Procedures For each elements a weighted scoring model from 0 to 5, composed by multiple questions, has been defined; a detailed guidance is supporting and assisting the team during the assessment. Once completed the scoring model a traffic lights system integrated with a spider diagram will automatically represents the field compliance with the elements. A quick and immediate graphic representation identifies then the main gaps for each elements. Based on those results the multidisciplinary team defines an Action Plan to be addressed to the relevant dpt for improvement and follow-up. The assessment frequency has been set to 6 months and the multidisciplinary team is appointed on rotation basis by Zohr Field General Manager and the relevant Department General Manager. The first PS self-assessment performed in Zohr in September 19 showed the PTW system and SCE management as the main points of strength while the Management of Change implementation and the ESD tracking as the elements to be improved. In particular Zohr has already set a robust system for the PTW management through a dedicated technical process team SIMOPS and developed a robust override and leak management system across the related departments. As all the plant modifications have been managed so far thorough a DCN (Design Change) System with project support, as action plan was foreseen to implement a dedicated system for the electronic management of the MoC. The first assessment highlighted also the need to improve the actions monitoring to keep traced all the findings coming from the RCA of the plant ESD and PSD. Moreover as additional benefit the interactive self-assessment tool effectively contributed to spread across all the departments the Process Safety terminology and culture in order to allow the team to get familiar with the pillars with a smart and user friendly approach.


Author(s):  
SHREEJI GOYAL ◽  
SUJATA SHARMA ◽  
ARVINDER SINGH ◽  
AMARJEET KAUR

Introduction: Patients with placenta previa are at an increased risk of uncontrolled hemorrhage. Various clinical and ultrasound parameters can predict the risk of bleeding in these patients. Hence, the objective of our study is to develop a combined ultrasound and clinical scoring model for the prediction of peripartum complications in pregnancies complicated by placenta previa. Methods: Fifty singleton pregnant women with placenta previa who underwent cesarean delivery in our hospital were included in the study. We collected clinical and ultrasound data prospectively, and the score was given to each parameter, and total score correlated with the occurrence of peripartum complications. Clinical parameters included age, parity, history of dilatation and evacuation, previous cesarean delivery, history of placenta previa, antepartum hemorrhage, and ultrasound parameters included type of previa, no. of lacunae in placenta, uteroplacental hypervascularity. The peripartum complications noted were the need for blood transfusion, uterine artery ligation, and cesarean hysterectomy. Results: According to the composite scoring done, uterine artery ligation was needed in more than 50% of patients at a score of 9–10. It increased to 100% as the score increased to ≥11. At a score of ≥12, hysterectomy was needed in around 75% of patients, and 100% of patients needed a blood transfusion. Univariate analysis using the Pearson Chi-square test was also done to know whether individual parameters and peripartum complications were significantly related that is p<0.05 with one another. Conclusion: The scoring system may serve to predict peripartum complications in pregnancies complicated by placenta previa.


2021 ◽  
pp. 1-16
Author(s):  
Fang He ◽  
Wenyu Zhang ◽  
Zhijia Yan

Credit scoring has become increasingly important for financial institutions. With the advancement of artificial intelligence, machine learning methods, especially ensemble learning methods, have become increasingly popular for credit scoring. However, the problems of imbalanced data distribution and underutilized feature information have not been well addressed sufficiently. To make the credit scoring model more adaptable to imbalanced datasets, the original model-based synthetic sampling method is extended herein to balance the datasets by generating appropriate minority samples to alleviate class overlap. To enable the credit scoring model to extract inherent correlations from features, a new bagging-based feature transformation method is proposed, which transforms features using a tree-based algorithm and selects features using the chi-square statistic. Furthermore, a two-layer ensemble method that combines the advantages of dynamic ensemble selection and stacking is proposed to improve the classification performance of the proposed multi-stage ensemble model. Finally, four standardized datasets are used to evaluate the performance of the proposed ensemble model using six evaluation metrics. The experimental results confirm that the proposed ensemble model is effective in improving classification performance and is superior to other benchmark models.


2021 ◽  
Vol 14 (4) ◽  
pp. 44-49
Author(s):  
E. Yu. Dorokhina

The article substantiates the possibility of using a scoring model to assess the risks of construction projects and real estate agencies. The problems of determining the weights of risk categories, individual risks and their factors are analyzed. Examples of using the model to solve practical problems are shown.


Sign in / Sign up

Export Citation Format

Share Document