Preterm Birth (PTB) can negatively affect the health of mothers as well as infants. Prediction of this gynecological complication remains difficult especially in Middle and Low-Income countries because of limited access to specific tests and data collection scarcity. Machine learning methods have been used to predict PTB but the low prevalence of this pregnancy complication led to rather low prediction values. The objective of this study was to produce a nomogram based on improved prediction for low prevalence PTB using up sampling and lasso penalized regression. We used data from a cohort study in Northern Lebanon of 922 multiparous presenting a PTB prevalence of 8%. We analyzed the personal, demographic, and health indicators available for this group of women. The improved Positive Predictive Value for PTB reached around 88%. The regression coefficients of the 6 selected variables (Pre-hemorrhage, Social status, Residence, Age, BMI, and Weight gain) were used to create a nomogram to screen multiparous women for PTB risk. The nomogram based on readily available indicators for multiparous women reasonably predicted most of the at PTB risk women. The physicians can use this tool to screen for women at high risk for spontaneous preterm birth to improve medical surveillance that can reduce PTB incidence.