Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.

You are viewing the site in preview mode

Skip to main content
Fig. 2 | BioPsychoSocial Medicine

Fig. 2

From: Association between maternal overprotection and premenstrual disorder: a machine learning based exploratory study

Fig. 2

Visualization of model performance and contributing features. a Model performance, based on the area under the receiver operating characteristic (ROC) curve. b Features with higher overall Shapley Additive exPlanations (SHAP) scores, indicating higher average contributions to premenstrual disorder (PMD) prediction. c Positive and negative contributions to PMD, characterized by positive and negative SHAP values, respectively. Red and blue represent the magnitude of the values. AUC, area under the receiver operating characteristic curve; PBIm/f, Parental Bonding Instrument (mother/father); MDQ, Menstrual Distress Questionnaire; PSQI, Pittsburgh Sleep Quality Index; BP, blood pressure (s, systolic; d, diastolic; m, mean); SOC, Sense of Coherence; STAI, State–Trait Anxiety Inventory. Items PBIm_23, PBIm_10, and PBIf_23 are scored as follows: very like, 3; moderately like, 2; moderately unlike, 1; and very unlike, 0. Items PBIm_2 and PBIm_15 were reverse scored. The PBIm_care and PBIf_care scores range from to 0–36. The PBIm_overprotection scores range from to 0–39. For information on the other measures, see Additional file 1

Back to article page