Development and Validation of Machine-Learning-Based Prediction Models for Thyroid Diseases During Pregnancy

22 June 2026 : Clinical Research

Guang Yang^{BCDEF 1}, Yi Gao^{BCEF 1}, Pengfei Liu^{BC 1}, Jingwen Jiang^{BC 1}, Hui Qiao^{ADEG 1*}, Weixuan Sheng

^{ACDE 1}

DOI: 10.12659/MSM.953235

Med Sci Monit 2026; 32:e953235

Authors information Article notes Copyright and License information

Introduction Material and Methods Results Discussion Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Table 3 Benchmark comparison of model performance.

Performance metric	LR model with conventional risk factors		RF model
Performance metric	Training set	Test set	Training set	Test set
AUC-ROC	0.55608314	0.55041310	0.99877170	0.99991140
AUC-PRC	0.53579933	0.12096839	0.99864486	0.99922572
ACC	0.55127631	0.89849246	0.98387819	0.99597990
Brier score	0.24692233	0.09098832	0.02495798	0.01921069
Log loss	0.68693139	0.32699989	0.12670703	0.09442025
MCC	0.09550202	0.00	0.96794139	0.97781292
Abbreviations: ACC, accuracy; AUC-ROC, area under the receiver operating characteristic curve; AUC-PRC, area under the precision-recall curve; LR, logistic regression; MCC, Matthews correlation coefficient; RF, random forest.

Back to the Article