Early prediction of clinical scores for left ventricular reverse remodeling using extreme gradient random forest, boosting, and logistic regression algorithm representations

Liu, Lu; Qiao, Cen; Zha, Jun-Ren; Qin, Huan; Wang, Xiaorui; Zhang, Xinyu; Wang, Yiou; Yang, Xiao; Zhang, Shu-Long; Qin, Jing

doi:10.3389/fcvm.2022.864312

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alongside CNNs, this study examines four established ML algorithms: XGBoost, Random Forest, Logistic Regression, and Naive Bayes. Each algorithm is selected for its proven strengths: XGBoost for its performance and flexibility [ 8 ]; Random Forest for its accuracy with complex datasets [ 9 ]; Logistic Regression for its interpretability in binary classification tasks [ 10 ]; and Naive Bayes for its efficiency in high-dimensional spaces [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Ku,

Min

2024

Healthcare

View full text Add to dashboard Cite

Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) pose significant burdens on individuals and society, necessitating accurate prediction methods. Machine learning (ML) algorithms utilizing electronic health records and survey data offer promising tools for forecasting these conditions. However, potential bias and inaccuracies inherent in subjective survey responses can undermine the precision of such predictions. This research investigates the reliability of five prominent ML algorithms—a Convolutional Neural Network (CNN), Random Forest, XGBoost, Logistic Regression, and Naive Bayes—in predicting MDD and GAD. A dataset rich in biomedical, demographic, and self-reported survey information is used to assess the algorithms’ performance under different levels of subjective response inaccuracies. These inaccuracies simulate scenarios with potential memory recall bias and subjective interpretations. While all algorithms demonstrate commendable accuracy with high-quality survey data, their performance diverges significantly when encountering erroneous or biased responses. Notably, the CNN exhibits superior resilience in this context, maintaining performance and even achieving enhanced accuracy, Cohen’s kappa score, and positive precision for both MDD and GAD. This highlights the CNN’s superior ability to handle data unreliability, making it a potentially advantageous choice for predicting mental health conditions based on self-reported data. These findings underscore the critical importance of algorithmic resilience in mental health prediction, particularly when relying on subjective data. They emphasize the need for careful algorithm selection in such contexts, with the CNN emerging as a promising candidate due to its robustness and improved performance under data uncertainties.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Ku,

Min

2024

Healthcare

View full text Add to dashboard Cite

show abstract

“…MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions, or products referred to in the content. 2 [4]; Random Forest, an ensemble method known for its accuracy and ability to manage large, highdimensional datasets [5]; Logistic Regression, a statistical method offering a probabilistic framework apt for binary classification tasks like predicting MDD and GAD [6]; and the Naïve Bayesian classifier, grounded in Bayes' theorem, celebrated for its simplicity and efficiency, especially in highdimensional datasets [7].…”

Section: Introductionmentioning

confidence: 99%

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Ku,

Min

2023

Preprint

View full text Add to dashboard Cite

Major depressive disorder (MDD) and generalized anxiety disorder (GAD) exert significant burdens on individuals and society, underscoring the importance of accurate predictions using advanced machine learning (ML) algorithms. Leveraging electronic health records (EHRs) and survey data, these algorithms offer potential in forecasting such mental health conditions. Yet, the precision of these predictions can be compromised by biases or inaccuracies inherent in subjective survey responses. In this research, we assess the reliability of four prominent ML algorithms—Random Forest, XGBoost, Logistic Regression, and Naïve Bayesian—in predicting MDD and GAD. Our dataset encompasses a rich array of information, from biomedical metrics and demographic details to self-reported survey insights. A focal point of our investigation is the algorithms' performance under scenarios with varying degrees of subjective response inaccuracies, such as memory recall biases or subjective interpretation. Our findings reveal that while all algorithms exhibit commendable accuracy with pristine survey data, their performance diverges when faced with erroneous or biased responses. Notably, XGBoost remains stable and excels in identifying true positive cases, even in the presence of such noise. These observations underscore the criticality of algorithmic resilience in mental health prediction, especially when relying on subjective data. The robustness of certain algorithms to noisy inputs positions them as more reliable choices for predicting mental health conditions based on self-reported data, emphasizing the need for careful algorithm selection in such contexts.

show abstract

The Role of Global Longitudinal Strain in Predicting Left Ventricular Reverse Remodeling After Mitral Valve Replacement Surgery in Patients With Primary Mitral Regurgitation

Natalino,

Marsam,

Dinarti

et al. 2024

Echocardiography

View full text Add to dashboard Cite

ObjectivesThis study aimed to identify the utility of global longitudinal strain (GLS) as a reliable parameter that can accurately forecast left ventricle reverse remodeling (LVRR) in patients undergoing valve replacement surgery for severe chronic primary mitral regurgitation (MR), thereby aiding in assessing mortality and morbidity risk.MethodsThis retrospective observational study involved severe primary MR patients who underwent valve replacement surgery between 2018 and 2023. Pre‐ and postsurgery echocardiography data were collected, with GLS measurements utilized to assess left ventricular function. Various echocardiography parameters, including MR severity and LV dimensions, were analyzed. Bivariate and multivariate analyses were performed to explore relationships between GLS and LVRR.ResultsThis study enrolled 103 patients (54.4% male; mean age 45.4 ± 13.6 years). Statistical analyses revealed GLS to be an independent predictor of LVRR, with a threshold of −16.25% showing 89% sensitivity and 50% specificity. Each 1% increase in GLS corresponded to a 1.14‐fold (odds ratio [OR]: 1.14; 95% confidence interval [CI]: 1.01–1.31; p < 0.05) increased likelihood of LVRR.ConclusionThese findings highlight GLS's potential as a prognostic marker for postsurgical outcomes in severe MR patients.

show abstract

Early prediction of clinical scores for left ventricular reverse remodeling using extreme gradient random forest, boosting, and logistic regression algorithm representations

Cited by 3 publications

References 29 publications

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

The Role of Global Longitudinal Strain in Predicting Left Ventricular Reverse Remodeling After Mitral Valve Replacement Surgery in Patients With Primary Mitral Regurgitation

Contact Info

Product

Resources

About