Ultrasound assessment of cervical status compared to the Bishop score - predicting the success of labor induction using a machine learning-based model.

OBJECTIVE

The main aim of this study was to develop a machine-learning-based model for predicting the success of labor induction (IOL). To that end, the clinical and ultrasound parameters that affect the successfulness of labor induction were assessed. Then, a new ultrasound scoring system (USS) was developed and assessed.

PATIENTS AND

METHODS

This prospective observational study included 192 term women who underwent induction of labor. First, a wide range of clinical and ultrasound pre-induction parameters were recorded. The induction was initiated by endocervical administration of dinoprostone gel (for Bishop score ≤5) or intravenous oxytocin (for Bishop score ≥6). After evaluating ultrasound parameters, we created an ultrasound scoring system and compared it with the Bishop score and clinical parameters. Finally, a comprehensive model using machine learning algorithms for predicting the success of the induction of labor was developed.

RESULTS

In terms of clinical parameters, this study found that IOL correlates with parity, body mass index (BMI) (both at p<0.05), and the Bishop score (p<0.001). All ultrasound parameters were statistically significant (p<0.05) apart from the posterior cervical angle. However, compared to the Bishop score, the new USS showed a slightly lower sensitivity (0.55 compared to 0.64) but much higher specificity (0.75 compared to 0.44) at a cut-off of 1.66. The proposed model, which can predict 83% of the events correctly, encompasses the Bishop score, USS, and clinical parameters.

CONCLUSIONS

The findings imply that the model developed in this study, which takes into account clinical parameters (parity, BMI), the ultrasound parameters and the Bishop score and uses machine learning algorithms, yields better results than models using other parameters.