22 June 2026 : Clinical Research
Development and Validation of Machine-Learning-Based Prediction Models for Thyroid Diseases During Pregnancy
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
Figure 6 Univariate partial dependence profileUnivariate partial dependence profiles for thyroid disease during pregnancy, illustrating the effect of each feature variable on the RF model predictions. Each subfigure represents the average predicted response across a range of values for a given feature: (A) height; (B) pre-pregnancy weight; (C) gravidity; (D) age; (E) HDP; (F) PM; (G) scarred uterus; (H) AID; and (I) parity. Abbreviations: AID, autoimmune disease; HDP, hypertensive disorders of pregnancy; PM, primipara or multipara; Preweight, pre-pregnancy weight; RF, random forest.