ObjectiveTo enable early prediction of strong traction force vacuum extraction.DesignObservational cohort.SettingKarolinska University Hospital delivery ward, tertiary unit.Population and sample sizeTerm mid and low metal cup vacuum extraction deliveries June 2012—February 2015, n = 277.MethodsTraction forces during vacuum extraction were collected prospectively using an intelligent handle. Levels of traction force were analysed pairwise by subjective category strong versus non-strong extraction, in order to define an objective predictive value for strong extraction.Statistical analysisA logistic regression model based on the shrinkage and selection method lasso was used to identify the predictive capacity of the different traction force variables.PredictorsTotal (time force integral, Newton minutes) and peak traction (Newton) force in the first to third pull; difference in traction force between the second and first pull, as well as the third and first pull respectively. Accumulated traction force at the second and third pull.OutcomeSubjectively categorized extraction as strong versus non-strong.ResultsThe prevalence of strong extraction was 26%. Prediction including the first and second pull: AUC 0,85 (CI 0,80–0,90); specificity 0,76; sensitivity 0,87; PPV 0,56; NPV 0,94. Prediction including the first to third pull: AUC 0,86 (CI 0,80–0,91); specificity 0,87; sensitivity 0,70; PPV 0,65; NPV 0,89.ConclusionTraction force measurement during vacuum extraction can help exclude strong category extraction from the second pull. From the third pull, two-thirds of strong extractions can be predicted.