Subclass-based semi-random data partitioning for improving sample representativeness

Liu, Han; Chen, Shyi‐Ming; Cocea, Mihaela

doi:10.1016/j.ins.2018.11.002

Cited by 8 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the Pearson Correlation method was selected as our feature selection method. According to the features selected through the Pearson correlation analysis, the selected machine-learning algorithms were tested based on a semi-random [32,33] partitioning framework. The performance evaluation of these models according to their accuracy showed that Logistic Regression and SVM with equal accuracy of 95.8% demonstrated the highest performance.…”

Section: Results Modelingmentioning

confidence: 99%

“…In addition, the results of the ROC curve investigation as shown in Figure 2 indicate that both SVM and Logistic Regression have almost the same AUC at 0.98. [32,33] partitioning framework. The performance evaluation of these models according to their accuracy showed that Logistic Regression and SVM with equal accuracy of 95.8% demonstrated the highest performance.…”

Section: Results Modelingmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Model for Detection of Coronary Artery Disease Using Noninvasive Clinical Parameters

Sayadi

Varadarajan

Sadoughi

et al. 2022

Life

View full text Add to dashboard Cite

Coronary artery disease (CAD) is one of the most prevalent causes of death worldwide. The early diagnosis and timely medical care of cardiovascular patients can greatly prevent death and reduce the cost of treatments associated with CAD. In this study, we attempt to prepare a new model for early CAD diagnosis. The proposed model can diagnose CAD based on clinical data and without the use of an invasive procedure. Methods: In this paper, machine-learning (ML) techniques were used for the early detection of CAD, which were applied to a CAD dataset known as Z-Alizadeh Sani. Since this dataset has 54 features, the Pearson correlation feature selection method was conducted to identify the most effective features. Then, six machine learning techniques including decision tree, deep learning, logistic regression, random forest, support vector machine (SVM), and Xgboost were employed based on a semi-random-partitioning framework. Result: Applying Pearson feature selection to the dataset demonstrated that only eight features were the most effective for CAD diagnosis. The results of running the six machine-learning models on the selected features showed that logistic regression and SVM had the same performance with 95.45% accuracy, 95.91% sensitivity, 91.66% specificity, and a 96.90% F1 score. In addition, the ROC curve indicates a similar result regarding the AUC (0.98). Conclusions: Prediction is an important component of medical decision support systems. The results of the present study showed that feature selection has a high impact on machine-learning performance and, regardless of the evaluation metrics of the machine-learning models, determining the effective features is very important. However, SVM and Logistic Regression were designated as the best models according to our selected features.

show abstract

Section: Results Modelingmentioning

confidence: 99%

Section: Results Modelingmentioning

confidence: 99%

A Machine Learning Model for Detection of Coronary Artery Disease Using Noninvasive Clinical Parameters

Sayadi

Varadarajan

Sadoughi

et al. 2022

Life

View full text Add to dashboard Cite

show abstract

“…The percentage of data used in each dataset is variable. Some studies suggest that the best model performance is achieved when the training and testing databases account for 70% and 30% of the original dataset, respectively (Liu et al 2019); other authors concluded that the percentage of data corresponding to the training database can be as high as 80% (Gholamy et al 2018) or between 50% and 70% (Xu and Goodacre 2018). In this paper, we considered a ratio of 3 to 1 for the time periods corresponding to the training and test catalogues, respectively, at both national and regional levels.…”

Section: Application To Italymentioning

confidence: 99%

Forecasting strong subsequent events in the Italian territory: a National and Regional application for NESTOREv1.0

Brondi,

Gentili,

Giovambattista

2024

Preprint

View full text Add to dashboard Cite

The Italian territory is one of the most seismically active areas in Europe, where Strong Subsequent Events (SSEs), in combination with the strong mainshock effects, can lead to the collapse of already weakened buildings and to further loss of lives. In the last few years, the machine learning-based algorithm NESTORE (Next STrOng Related Earthquake) [Gentili and Di Giovambattista 2017, 2020, 2022, Gentili et al. 2023, Anyfadi et al. 2023] was proposed and used to forecast clusters in which the mainshock is followed by a SSE of similar magnitude. Recently, a first new version of a MATLAB package based on this algorithm (NESTOREv1.0) has been developed to improve SSE forecasting for research purpose and on-line sharing (Gentili et al. 2023). In our analysis, we considered both a nationwide and a regional approach for Italy, by studying the seismicity recorded over the last 40 years in two areas covering most of the Italian territory and northeastern Italy, respectively. In both approaches, using two dedicated catalogs, we trained NESTOREv1.0 on the clusters occurring approximately in the first 30 years of catalogues and we evaluated its performance on the last 10 years. The results showed that 1 day after the mainshock occurrence the rate of correct SSE forecasting is larger than 85% in both areas, supporting the application of NESTOREv1.0 in the Italian territory. Furthermore, by training the software on the entire period available for the two catalogs, we obtained good results in terms of near-real-time class forecasting for clusters recorded from 2021 onward.

show abstract

“…For this nationwide multicenter cohort study, various levels of care centers with different medical roles were included. Random data partitioning by mixing all the data can omit the characteristics of each center and impair sample representativeness [25]. Therefore, we performed center-based semi-random data partitioning, only considering the balance of the number of clinical events between development and validation sets.…”

Section: Dataset Partitioning For Multicenter Validationmentioning

confidence: 99%

Development and Validation of a Multimodal-Based Prognosis and Intervention Prediction Model for COVID-19 Patients in a Multicenter Cohort

Lee¹,

Ahn²,

Chung

et al. 2022

Sensors

View full text Add to dashboard Cite

The ability to accurately predict the prognosis and intervention requirements for treating highly infectious diseases, such as COVID-19, can greatly support the effective management of patients, especially in resource-limited settings. The aim of the study is to develop and validate a multimodal artificial intelligence (AI) system using clinical findings, laboratory data and AI-interpreted features of chest X-rays (CXRs), and to predict the prognosis and the required interventions for patients diagnosed with COVID-19, using multi-center data. In total, 2282 real-time reverse transcriptase polymerase chain reaction-confirmed COVID-19 patients’ initial clinical findings, laboratory data and CXRs were retrospectively collected from 13 medical centers in South Korea, between January 2020 and June 2021. The prognostic outcomes collected included intensive care unit (ICU) admission and in-hospital mortality. Intervention outcomes included the use of oxygen (O2) supplementation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO). A deep learning algorithm detecting 10 common CXR abnormalities (DLAD-10) was used to infer the initial CXR taken. A random forest model with a quantile classifier was used to predict the prognostic and intervention outcomes, using multimodal data. The area under the receiver operating curve (AUROC) values for the single-modal model, using clinical findings, laboratory data and the outputs from DLAD-10, were 0.742 (95% confidence interval [CI], 0.696–0.788), 0.794 (0.745–0.843) and 0.770 (0.724–0.815), respectively. The AUROC of the combined model, using clinical findings, laboratory data and DLAD-10 outputs, was significantly higher at 0.854 (0.820–0.889) than that of all other models (p < 0.001, using DeLong’s test). In the order of importance, age, dyspnea, consolidation and fever were significant clinical variables for prediction. The most predictive DLAD-10 output was consolidation. We have shown that a multimodal AI model can improve the performance of predicting both the prognosis and intervention in COVID-19 patients, and this could assist in effective treatment and subsequent resource management. Further, image feature extraction using an established AI engine with well-defined clinical outputs, and combining them with different modes of clinical data, could be a useful way of creating an understandable multimodal prediction model.

show abstract

Subclass-based semi-random data partitioning for improving sample representativeness

Cited by 8 publications

References 36 publications

A Machine Learning Model for Detection of Coronary Artery Disease Using Noninvasive Clinical Parameters

A Machine Learning Model for Detection of Coronary Artery Disease Using Noninvasive Clinical Parameters

Forecasting strong subsequent events in the Italian territory: a National and Regional application for NESTOREv1.0

Development and Validation of a Multimodal-Based Prognosis and Intervention Prediction Model for COVID-19 Patients in a Multicenter Cohort

Contact Info

Product

Resources

About