Key result
Machine learning models using simple anthropometric measurements varied in predicting adolescent hypertension, with LightGBM performing best across most metrics and Decision Tree performing worst.
Why the study?
It was essential to assess the impacts of different machine learning models for predicting adolescent hypertension using only simple anthropometric measurements.
Do different machine learning models perform equally well in predicting hypertension in adolescents using simple anthropometric measurements?
Observational (n=2,461)
Do different machine learning models perform equally well in predicting hypertension in adolescents using simple anthropometric measurements?
The choice of machine learning model significantly impacts the prediction of hypertension in adolescents using simple anthropometric measurements, with LightGBM performing best overall.
Answers are grounded in this paper and cite their sources.
Model performance varies by algorithm; hypothesis-generating for adolescent hypertension screening and requires prospective validation.
The use of anthropometric measurements in machine learning algorithms for hypertension prediction enables the development of simple, non-invasive prediction models. However, different machine learning algorithms were utilized in conjunction with various anthropometric data, either alone or in combination with other biophysical and lifestyle variables. It is essential to assess the impacts of the chosen machine learning models using simple anthropometric measurements. We developed and tested 13 machine learning methods of neural network, ensemble, and classical categories to predict hypertension in adolescents using only simple anthropometric measurements. The imbalanced dataset of 2461 samples with 30.1% hypertension subjects was first partitioned into 90% for training and 10% for validation. The training dataset was reduced to eight simple anthropometric measurements: age, C index, ethnicity, gender, height, location, parental hypertension, and waist circumference using correlation coefficient. The Synthetic Minority Oversampling Technique (SMOTE) combined with random under-sampling was used to balance the dataset. The models with optimal hyperparameters were assessed using accuracy, precision, sensitivity, specificity, F1-score, misclassification rate, and AUC on the testing dataset. Across all seven performance measures, no model consistently outperformed the others. LightGBM was the best model for all six performance metrics, except sensitivity, whereas Decision Tree was the worst. We proposed using Bayes’ Theorem to assess the models’ applicability in the Sarawak adolescent population, resulting in the top four models being LightGBM, Random Forest, XGBoost, and CatBoost, and the bottom four models being Logistic Regression, LogitBoost, SVM, and Decision Tree. This study demonstrates that the choice of machine learning models has an effect on the prediction outcomes.
No takes yet. Share an insight, caveat, or question.
Chai et al. (2022) conducted an observational in Hypertension (n=2,461). Machine learning models (e.g., LightGBM, Random Forest, XGBoost, CatBoost) vs. Other machine learning models (e.g., Logistic Regression, SVM, Decision Tree) was evaluated on Model performance (accuracy, precision, sensitivity, specificity, F1-score, misclassification rate, and AUC). Machine learning models using simple anthropometric measurements varied in predicting adolescent hypertension, with LightGBM performing best across most metrics and Decision Tree performing worst.
Synapse has enriched 10 related papers. Consider them for comparative context: