scholarly journals The Value of Predicting Human Epidermal Growth Factor Receptor 2 Status in Adenocarcinoma of the Esophagogastric Junction on CT-Based Radiomics Nomogram

2021 ◽  
Vol 11 ◽  
Author(s):  
Shuxing Wang ◽  
Yiqing Chen ◽  
Han Zhang ◽  
Zhiping Liang ◽  
Jun Bu
Keyword(s):  
Logistic Regression ◽  
Esophagogastric Junction ◽  
Area Under The Curve ◽  
Growth Factor Receptor ◽  
Predictive Performance ◽  
Regression Method ◽  
Training Cohort ◽  
T Stage ◽  
Logistic Regression Method ◽  
Radiomics Signature

PurposeWe developed and validated a CT-based radiomics nomogram to predict HER2 status in patients with adenocarcinoma of esophagogastric junction (AEG).MethodA total of 101 patients with HER2-positive (n=46) and HER2-negative (n=55) esophagogastric junction adenocarcinoma (AEG) were retrospectively analyzed. They were then randomly divided into a training cohort (n=70) and a verification cohort (n=31). The radiomics features were obtained from the portal phase of the CT enhanced scan. We used the least absolute shrinkage and selection operator (LASSO) logistic regression method to select the best radiomics features in the training cohort, combined them linearly, and used the radiomics signature formula to calculate the radiomics score (Rad-score) of each AEG patient. A multivariable logistic regression method was applied to develop a prediction model that incorporated the radiomics signature and independent risk predictors. The prediction performance of the nomogram was evaluated using the training and validation cohorts.ResultIn the training (P<0.001) and verification groups (P<0.001), the radiomics signature combined with seven radiomics features was significantly correlated with HER2 status. The nomogram composed of CT-reported T stage and radiomics signature showed very good predictive performance for HER2 status. The area under the curve (AUC) of the training cohort was 0.946 (95% CI: 0.919–0.973), and that of the validation group was 0.903 (95% CI: 0.847–0.959). The calibration curve of the radiomics nomogram showed a good degree of calibration. Decision-curve analysis revealed that the radiomics nomogram was useful.ConclusionThe nomogram CT-based radiomics signature combined with CT-reported T stage can better predict the HER2 status of AEG before surgery. It can be used as a non-invasive prediction tool for HER2 status and is expected to guide clinical treatment decisions in clinical practice, and it can assist in the formulation of individualized treatment plans.

scholarly journals Preoperative Prediction of Lymphovascular Space Invasion in Cervical Cancer With Radiomics –Based Nomogram

2021 ◽  
Vol 11 ◽  
Author(s):  
Wei Du ◽  
Yu Wang ◽  
Dongdong Li ◽  
Xueming Xia ◽  
Qiaoyue Tan ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Clinical Decision Making ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Clinical Decision ◽  
Tumor Stage ◽  
Support Vector ◽  
Training Cohort ◽  
Clinical Model ◽  
Radiomics Signature

PurposeTo build and evaluate a radiomics-based nomogram that improves the predictive performance of the LVSI in cervical cancer non-invasively before the operation.MethodThis study involved 149 patients who underwent surgery with cervical cancer from February 2017 to October 2019. Radiomics features were extracted from T2 weighted imaging (T2WI). The radiomic features were selected by logistic regression with the least absolute shrinkage and selection operator (LASSO) penalty in the training cohort. Based on the selected features, support vector machine (SVM) algorithm was used to build the radiomics signature on the training cohort. Incorporating radiomics signature and clinical risk factors, the radiomics-based nomogram was developed. The sensitivity, specificity, accuracy, and area under the curve (AUC) and Receiver operating characteristic (ROC) curve were calculated to assess these models.ResultThe radiomics model performed much better than the clinical model in both training (AUCs 0.925 vs. 0.786, accuracies 87.5% vs. 70.5%, sensitivities 83.6% vs. 41.7% and specificities 90.9% vs. 94.7%) and testing (AUCs 0.911 vs. 0.706, accuracies 84.0% vs. 71.3%, sensitivities 81.1% vs. 43.4% and specificities 86.4% vs. 95.0%). The combined model based on the radiomics signature and tumor stage, tumor infiltration depth and tumor pathology yielded the best performance (training cohort, AUC = 0.943, accuracies 89.5%, sensitivities 85.4% and specificities 92.9%; testing cohort, AUC = 0.923, accuracies 84.6%, sensitivities 84.0% and specificities 85.1%).ConclusionRadiomics-based nomogram was a useful tool for predicting LVSI of cervical cancer. This would aid the selection of the optimal therapeutic strategy and clinical decision-making for individuals.

scholarly journals 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)

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.

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

2021 ◽  
pp. 1-10
Author(s):  
I. Krug ◽  
J. Linardon ◽  
C. Greenwood ◽  
G. Youssef ◽  
J. Treasure ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Prediction Rule ◽  
Predictive Performance ◽  
Individual Risk ◽  
European Project ◽  
Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

scholarly journals Prediksi Not Operational Transaction Menggunakan Logistic Regression pada Bank XYZ di Kota Kupang

AITI ◽  
2020 ◽  
Vol 17 (1) ◽  
pp. 42-55
Author(s):  
Radius Tanone ◽  
Arnold B Emmanuel
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Regression Method ◽  
Learning Approach ◽  
Know How ◽  
Independent Variables ◽  
Machine Learning Approach ◽  
Logistic Regression Method ◽  
Python Programming

Bank XYZ is one of the banks in Kupang City, East Nusa Tenggara Province which has several ATM machines and is placed in several merchant locations. The existing ATM machine is one of the goals of customers and non-customers in conducting transactions at the ATM machine. The placement of the ATM machines sometimes makes the machine not used optimally by the customer to transact, causing the disposal of machine resources and a condition called Not Operational Transaction (NOP). With the data consisting of several independent variables with numeric types, it is necessary to know how the classification of the dependent variable is NOP. Machine learning approach with Logistic Regression method is the solution in doing this classification. Some research steps are carried out by collecting data, analyzing using machine learning using python programming and writing reports. The results obtained with this machine learning approach is the resulting prediction value of 0.507 for its classification. This means that in the future XYZ Bank can classify NOP conditions based on the behavior of customers or non-customers in making transactions using Bank XYZ ATM machines.  

scholarly journals Talent Performance Analysis Using People Analytics Approach

2021 ◽  
Vol 4 (1) ◽  
pp. 216-230
Author(s):  
Fahreza Nasril ◽  
Dian Indiyati ◽  
Gadang Ramantoko
Keyword(s):  
Logistic Regression ◽  
Multinomial Logistic Regression ◽  
Research Question ◽  
Development Program ◽  
Individual Performance ◽  
Study Data ◽  
Regression Method ◽  
Process Data ◽  
Logistic Regression Method ◽  
The Right

The purpose of this study was to answer the research question "How is the prediction of Talent Performance in the following year with the application of People Analytics?" and knowing the description of employees who are potential talents, the resulting performance contributions, to the description of the development and retention efforts needed by Talent in order to be able to maintain their future performance and position as Talents compared to the previous People Analytics method using predictive analysis, namely prediction of Talent Performance in the year next. In this study, data analysis using the Multivariate Logistic Regression method is used to get the Prediction of the Performance of Talents who become the object of research in the form of individual performance quickly and precisely in accordance with the patterns drawn by individual Performance score data in previous years. And can provide insight regarding the projected strategies that need to be done to maintain the improvement of individual talent performance in the years of the assessment period. It also helps management in making decisions about the right Talent development program and determining which Talents are priorities. The population in this study were the talents of employees of PT. Angkasa Pura II (Persero) with a managerial level consisting of: Senior Leader, Middle Leader, and First Line Leader who has a Person Grade (PG) range of 13 to 21. The sample used is Middle Leader level talent with specified criteria and through a process data cleansing. The results of this study indicate that the variable that significantly affects the performance of the following year is the performance of the previous 2 years. Then prediction analysis can be done using these independent variables with the Multinomial Logistic Regression method, and to get prediction results with better accuracy can be done by the Random Forest method.

scholarly journals Prognostic algorithms for the progression of chronic heart failure depending on the clinical phenotype

2019 ◽  
Vol 18 (3) ◽  
pp. 41-47
Author(s):  
E. A. Polunina ◽  
L. P. Voronina ◽  
E. A. Popov ◽  
I. S. Belyakova ◽  
O. S. Polunina ◽  
...  
Keyword(s):  
Heart Failure ◽  
Logistic Regression ◽  
Chronic Heart Failure ◽  
Clinical Phenotype ◽  
Left Ventricular ◽  
Regression Method ◽  
Left Ventricular Ejection ◽  
Control Group ◽  
Ventricular Ejection Fraction ◽  
Logistic Regression Method

Aim. To develop a mathematical equation (algorithm) to predict the development of chronic heart failure (CHF) for three years, depending on the clinical phenotype.Material and methods. Three hundred forty five patients with CHF with a different left ventricular ejection fraction (preserved, mean, low) were examined. The control group included somatically healthy individuals (n=60). In all patients, 48 parameters that most widely characterize the pathogenesis of CHF (gender-anamnestic, clinical, instrumental, biochemical) were analyzed. To isolate phenotypes, dispersive and cluster analysis was used: the hierarchical classification method and the k-means method. In the development of algorithms we used binary logistic regression method. We used ROC curve to assess the quality of the obtained algorithms.Results. We identified four phenotypes in patients with CHF: fibro-rigid, fibro-inflammatory, inflammatory-destructive, dilated-maladaptive. For the first three phenotypes, a mathematical logistic regression method was used to develop mathematical models for predicting the progression of CHF for three years, with the release of predictors for each phenotype. Belonging to the dilatedmaladaptive phenotype according to the results of the analysis is already an indicator of an unfavorable prognosis in patients with CHF.Conclusion. The developed algorithms based on the selected phenotypes have high diagnostic sensitivity and specificity and can be recommended for use in clinical practice.

Effects of a Bolster Curvature on an Automobile Seat Fit

2021 ◽  
Vol 65 (1) ◽  
pp. 423-426
Author(s):  
Baekhee Lee ◽  
Byoung-Keon (Daniel) Park ◽  
Kihyo Jung ◽  
Jangwoon Park
Keyword(s):  
Logistic Regression ◽  
Design Process ◽  
Cross Sections ◽  
Classification Accuracy ◽  
Regression Method ◽  
Digital Design ◽  
Cross Sectional ◽  
Development Costs ◽  
Logistic Regression Method ◽  
Vehicle Seat

Vehicle-seat dimensions measured at specific cross-sections have been historically utilized as shape determinants to evaluate a driver’s seat fit. The present study is intended to quantify the relationships between seat fits and the seat dimensions for designing an ergonomic vehicle seat. Eight seat engineers evaluated seat fits for 54 different driver seats based on their expertise. Five seat dimensions were measured at six cross-sectional planes using a custom-built, computerized program. The best-subset-logistic-regression method was employed to model the relationships between the seat fit and the seat dimensions. As a result, significant seat dimensions, such as insert width, bolster height, and/or bolster curvature, on the subjective seat fit (e.g., loose-fit, right-fit, and tight-fit) were quantified. The developed models showed 98% overall classification accuracy throughout the cross-sectional planes. The models promote a digital design process of an automobile seat, which would increase the efficiency of the process and reduce the development costs.

Automated NLP Extraction of Clinical Rationale for Treatment Discontinuation in Breast Cancer

2021 ◽  
pp. 550-560
Author(s):  
Matthew S. Alkaitis ◽  
Monica N. Agrawal ◽  
Gregory J. Riely ◽  
Pedram Razavi ◽  
David Sontag
Keyword(s):  
Breast Cancer ◽  
Epidermal Growth Factor Receptor ◽  
Logistic Regression ◽  
Standard Deviation ◽  
Early Stage ◽  
Area Under The Curve ◽  
Growth Factor Receptor ◽  
Treatment Discontinuation ◽  
High Dimensional ◽  
Epidermal Growth

PURPOSE Key oncology end points are not routinely encoded into electronic medical records (EMRs). We assessed whether natural language processing (NLP) can abstract treatment discontinuation rationale from unstructured EMR notes to estimate toxicity incidence and progression-free survival (PFS). METHODS We constructed a retrospective cohort of 6,115 patients with early-stage and 701 patients with metastatic breast cancer initiating care at Memorial Sloan Kettering Cancer Center from 2008 to 2019. Each cohort was divided into training (70%), validation (15%), and test (15%) subsets. Human abstractors identified the clinical rationale associated with treatment discontinuation events. Concatenated EMR notes were used to train high-dimensional logistic regression and convolutional neural network models. Kaplan-Meier analyses were used to compare toxicity incidence and PFS estimated by our NLP models to estimates generated by manual labeling and time-to-treatment discontinuation (TTD). RESULTS Our best high-dimensional logistic regression models identified toxicity events in early-stage patients with an area under the curve of the receiver-operator characteristic of 0.857 ± 0.014 (standard deviation) and progression events in metastatic patients with an area under the curve of 0.752 ± 0.027 (standard deviation). NLP-extracted toxicity incidence and PFS curves were not significantly different from manually extracted curves ( P = .95 and P = .67, respectively). By contrast, TTD overestimated toxicity in early-stage patients ( P < .001) and underestimated PFS in metastatic patients ( P < .001). Additionally, we tested an extrapolation approach in which 20% of the metastatic cohort were labeled manually, and NLP algorithms were used to abstract the remaining 80%. This extrapolated outcomes approach resolved PFS differences between receptor subtypes ( P < .001 for hormone receptor+/human epidermal growth factor receptor 2− v human epidermal growth factor receptor 2+ v triple-negative) that could not be resolved with TTD. CONCLUSION NLP models are capable of abstracting treatment discontinuation rationale with minimal manual labeling.

Modeling Species Distribution

2011 ◽  
pp. 171-197 ◽  
Author(s):  
Yongyut Trisurat ◽  
Albertus G. Toxopeus
Keyword(s):  
Logistic Regression ◽  
Maximum Entropy ◽  
Habitat Suitability ◽  
Logistic Regression Model ◽  
Entropy Method ◽  
Regression Method ◽  
Logistic Regression Method ◽  
Suitable Habitats ◽  
Suitable Area ◽  
Available Information

The results show that among the three approaches, the potentially suitable habitats derived from cartographic overlay cover the largest area and are likely to overestimate existing occurrence areas. The logistic regression model predicts approximately 56% as suitable area, while maximum entropy results covers approximately 9% of the sanctuary. Although the results show large differences in the suitable areas, it should not be concluded that any one method always proves better than the others. Utilization of any method is dependent on the situation and available information. If species observations are limited, the cartographic overlay or habitat suitability is recommended. The logistic regression method is recommended when adequate presence and absence data are available. If presence-only data is available, a niche-based model or the maximum entropy method (MAXENT) is highly recommended.

Sign in / Sign up

Export Citation Format

Share Document