A novel method for diabetes classification and prediction with Pycaret

Whig, Pawan; Gupta, Ketan; Jiwani, Nasmin; Jupalle, Hruthika; Kouser, Shama; Alam, Naved

doi:10.1007/s00542-023-05473-2

Cited by 21 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the final verification stage, a portion of the data, ranging from 20 to 25%, is used for testing. This approach enabled us to validate the predictive accuracy of our models on an independent dataset, thereby confirming their generalizability and effectiveness in predicting asthma diagnoses within the given population ( 12 , 13 ).…”

Section: Methodsmentioning

confidence: 61%

Association between household income levels and nutritional intake of allergic children under 6 years of age in Korea: 2019 Korea National Health and Nutrition Examination Survey and application of machine learning

Jeong,

Choi

2024

Front. Public Health

View full text Add to dashboard Cite

IntroductionThis study investigated the prevalence of allergic diseases in Korean children aged 6 and below, focusing on the interplay between nutritional status, household income levels, and allergic disease occurrence.MethodsThis study used data from the 2019 National Health and Nutrition Examination Survey, a nationwide comprehensive survey, and included a representative sample of 30,382 children under the age of 6 to investigate in detail the relationship between allergic diseases, nutritional intake, and socioeconomic factors. Logistic regression analysis was performed to identify factors associated with allergic diseases, including gender, BMI, eating habits, dietary supplement intake, and nutrient consumption. To predict childhood asthma, 14 machine learning models were compared using the ‘pycaret’ package in Python.ResultsWe discerned that 24.7% were diagnosed with allergic conditions like atopic dermatitis, asthma, and allergic rhinitis. Notably, household income exhibited a significant influence, with the lowest income quartile exhibiting higher prevalence rates of asthma, allergic rhinitis, and multiple allergic diseases. In contrast, the highest income quartile displayed lower rates of allergic rhinitis. Children diagnosed with allergic diseases demonstrated compromised intake of essential nutrients such as energy, dietary fiber, vitamin B1, sodium, potassium, and iron. Particularly noteworthy were the deficits in dietary fiber, vitamin A, niacin, and potassium intake among children aged 3–5 with allergies. Logistic regression analysis further elucidated that within low-income families, female children with higher BMIs, frequent dining out, dietary supplement usage, and altered consumption of vitamin B1 and iron faced an elevated risk of allergic disease diagnosis. Additionally, machine learning analysis pinpointed influential predictors for childhood asthma, encompassing BMI, household income, subjective health perception, height, and dietary habits.DiscussionOur findings underscore the pronounced impact of income levels on the intricate nexus between allergic diseases and nutritional status. Furthermore, our machine learning insights illuminate the multifaceted determinants of childhood asthma, where physiological traits, socioeconomic circumstances, environmental factors, and dietary choices intertwine to shape disease prevalence. This study emphasizes the urgency of tailored nutritional interventions, particularly in socioeconomically disadvantaged populations, while also underscoring the necessity for comprehensive longitudinal investigations to unravel the intricate relationship between allergic diseases, nutritional factors, and socioeconomic strata.

show abstract

Section: Methodsmentioning

confidence: 61%

Association between household income levels and nutritional intake of allergic children under 6 years of age in Korea: 2019 Korea National Health and Nutrition Examination Survey and application of machine learning

Jeong,

Choi

2024

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Table I summarizes the selected representative research papers, grouping them by the chronic diseases under investigation and highlighting the ML methods employed. Breast cancer DT, NB, k-NN, and SVM [29] Breast cancer ANN [30] Breast cancer Deep Learning and Light Boosting Classifier [31] Diabetes PyCaret classifiers [32] Diabetes CNN [33] Diabetes RF, NB, and J48 DT [34] Diabetes XGBoost [35] Heart disease RF, SVM, k-NN, and DT [36] Heart disease ANN [37] Heart disease SVM, DT, RF, Gradient Boosting [38] Heart disease RF, k-NN, and AdaBoost [39] Kidney disease DT, k-NN and NB [40] Kidney disease AdaBoost on SVM [41] Kidney disease CNN [42] Kidney disease Stratified Logistic Regression [43] Kidney disease eXplainable AI…”

Section: Ai-based Prediction In Chronic Diseasesmentioning

confidence: 99%

Synergistic Feature Engineering and Ensemble Learning for Early Chronic Disease Prediction

Al-Jamimi

2024

IEEE Access

View full text Add to dashboard Cite

Chronic diseases, a global public health challenge, necessitate the deployment of cutting-edge predictive models for early diagnosis and personalized interventions. This study presents an advanced methodology for early prediction of chronic diseases, including heart attack, diabetes, breast cancer, and kidney disease, leveraging a synergistic combination of cutting-edge techniques. Recognizing the challenge posed by extensive medical datasets with numerous features, we introduce a novel approach that begins with Feature Engineering using Recursive Feature Elimination (RFE) in conjunction with a Support Vector Machine (SVM). The presented methodology identifies and removes irrelevant features to simplify data complexity. The refined dataset is then input into the robust eXtreme Gradient Boosting (XGBoost) classifier, known for its efficiency and adeptness in predicting complex relationships within the data. The chosen ensemble learning algorithm demonstrates significant prowess in inducing intricate patterns crucial for chronic disease prediction. To enhance model performance, an essential phase of optimization is introduced through hyperparameter tuning using Bayesian optimization. This strategically navigates the hyperparameter space, maximizing the efficiency of the search process and fine-tuning the model for optimal predictive accuracy. The proposed approach showcases a substantial improvement in the early prediction of chronic diseases, demonstrating the effectiveness of the proposed approach.

show abstract

“…During our research, we observed several issues in previous studies. In [12] and [13], the datasets contained missing values, which the authors addressed by dropping the missing entries. However, this approach can lead to information loss.…”

Section: Problem Statementmentioning

confidence: 99%

A Deep Learning Approach for Prediction of Heart Disease using Ensemble Learning Techniques

Hayat,

Javaid,

Nazir

et al. 2024

Preprint

View full text Add to dashboard Cite

Heart Disease (HD) stands as a significant contributor to escalating mortality rates worldwide, impacting communities on a vast scale. While numerous Deep Learning (DL) methodologies have been proposed for HD detection and diagnosis, prior studies have encountered limitations, notably small dataset sizes leading to overfitting. To address these challenges, we present novel ensemble learning approaches aimed at enhancing the authenticity and accuracy of HD prediction. Our work introduces two ensemble techniques, blending and voting, leveraging a combination of Multi-Layer Perceptron, AlexNet, and Deep Belief Network models. Utilizing the heart-disease-health-indicators-BRFSS2015 dataset, characterized by significant imbalances, we employ Adaptive Synthetic oversampling technique to balance the data. Results demonstrate the superior performance of our ensemble models over individual models. The blending model achieves an accuracy of 90.0%, precision of 90.1%, recall of 90.0%, and an F1-score of 90.0%. The voting model attains an accuracy score of 89.3%, precision of 92.2%, recall of 85.9%, and an F1-score of 88.9%. The blending model exhibits superior classification ability compared to the voting model. To assess the generalizability and validate results, K-Fold Cross Validation is employed. For model interpretability and explainability, we utilize an eXplainable Artificial Intelligence technique, Shapley Additive Explanations.

show abstract

A novel method for diabetes classification and prediction with Pycaret

Cited by 21 publications

References 27 publications

Association between household income levels and nutritional intake of allergic children under 6 years of age in Korea: 2019 Korea National Health and Nutrition Examination Survey and application of machine learning

Association between household income levels and nutritional intake of allergic children under 6 years of age in Korea: 2019 Korea National Health and Nutrition Examination Survey and application of machine learning

Synergistic Feature Engineering and Ensemble Learning for Early Chronic Disease Prediction

A Deep Learning Approach for Prediction of Heart Disease using Ensemble Learning Techniques

Contact Info

Product

Resources

About