Objective: To explore the clinical significance of key pelvic floor ultrasound indicators in the treatment of pelvic organ prolapse (POP). This study aims to address the limitations of the subjective POP-Q system and the costly static MRI, optimize objective evaluation metrics, and construct an effective POP risk prediction model. Methods: A retrospective analysis was conducted on 110 patients with POP or lower urinary tract symptoms. All participants underwent POP-Q assessment and 3D pelvic floor ultrasonography. Following 1: 1 age-matched propensity score matching (PSM), Lasso regression was employed to screen variables and establish the POP index model. Model efficacy was validated through area under the curve (AUC), sensitivity, specificity, and decision curve analysis. Results: Eighty-four participants were included after matching. In the POP group, the levator hiatus area was significantly larger, and both bladder neck mobility and rectal prolapse rate were higher (both p< 0. 001). Seven core ultrasound indicators were identified. The POP index demonstrated excellent diagnostic efficiency, with an AUC of 0. 94, and both sensitivity and specificity at 0. 88, yielding an ideal clinical net benefit. Conclusion: Pelvic floor ultrasound, combined with PSM and machine learning, enables accurate POP assessment. The prediction model and ultrasound indicators provide an objective basis for clinical diagnosis and risk stratification, facilitating individualized intervention and primary-level POP screening. Keywords: pelvic organ prolapse, pelvic floor ultrasound, risk prediction model, POPIndex, propensity score matching, LASSO regression, pelvic organ prolapse quantification
Wang et al. (Mon,) studied this question.