Table 1 Summary of studies using various ML models
From: Machine learning approach for the detection of vitamin D level: a comparative study
Reference no | Authors and Year | Subject | Classification | Method | Metrics | Best model |
|---|---|---|---|---|---|---|
[32] | Garcia et al. (2021) | Vitamin D | B | LR SVM RF NB XGboost | Accuracy Recall Specificity Predictive values | SVM |
[33] | Patino-Alonso et al. (2022) | Vitamin D | B | RF LR NB | Accuracy Error Precision Specificity Recall | LR |
[34] | Sambasivam et al. (2020) | Vitamin D | M | KNN DT RF AB BC ET SGD GB SVM MLP | Precision Recall F1-score Accuracy AUC | RF |
[42] | Abdullah, Hafidz and Khairunizam (2020) | Chronic kidney disease | B | RF SVMLINEAR SVM NB LR | Accuracy Precision Recall F1-Score | RF |
[43] | Xiao et al.(2020) | Alzheimer’s disease | B | LR Proposed LR LR-L1 LR-L2 | Accuracy Recall Specificity | Proposed LR |
[44] | Bekele (2022) | Low birth weight | B | LR DT NB K-NN RF SVM Gboost, XGboost | Accuracy Recall Precision F1-Score AUC-ROC | RF |
[45] | Kırğıl, et al. (2022) | Diabetes | B | DT NB SVM LR MLP KNN LMT RF | Accuracy Recall | RF |
[46] | Ranade (2021) | Inflammatory Bowel Disease from vitamin D | M | DT SVM ET | Accuracy AUC | DT |
[47] | Wainer et al. 2016 | NA | B | BST ELM GBM ENLR KNN LVQ NB NNET RF RKNN KNN SDA SVMLINEAR SVMPOLY SVM | Error Rate Bayesian ANOVA Training and Testing time | RF GBM SVM |
[48] | Deist et al. (2018) | Radiation treatment | B | DT RF ANN SVM ENLR Logit-Boost | Calibration Accuracy Cohen’s kappa AUC Brier score | RF ENLR |
[49] | Abdullah et al. (2022) | Alzheimer’s disease | B | Lasso LR Ridge LR ENLR NB SVM K-NN RF | Recall Precision Accuracy F1-Measure | ENLR RF |