This page contains supplementary information accompanying the manuscript entitled: Predicting the outcome of pregnancy of unkown location: Bayesian networks with expert information compared to logistic regression.
Olivier Gevaert, Frank De Smet, Emma Kirk, Ben Van Calster, Tom Bourne, Sabine Van Huffel, Yves Moreau, Dirk Timmerman, Bart De Moor and George Condous.
Abstract:
BACKGROUND: As women present at earlier gestations to early pregnancy units (EPUs), the number of women diagnosed with a pregnancy of unknown location (PUL) increases. Some of these women will have an Ectopic Pregnancy (EP) and it is this group in the PUL population that poses the greatest concern. The aim of this study is to develop Bayesian networks to predict EPs in the PUL population.
METHODS: Data was gathered in a single EPU from all women with a PUL. This data set was divided into a model building (599 women with 44 EPs) and a validation (257 women with 22 EPs) data set and consisted of the following variables: vaginal bleeding, fluid in the pouch of Douglas, midline echo, lower abdominal pain, age, endometrial thickness, gestation days, the ratio of hCG 48 hr and 0 hr, progesterone levels (0 hr and 48 hr) and the clinical outcome of the PUL. We developed Bayesian networks with expert information using this data set to predict EPs.
RESULTS: The best Bayesian network used the gestational age, hCG ratio and the progesterone level at 48 hr and had an area under the receiver operator characteristic curve (AUC) of 0.88 for predicting EPs when tested prospectively.
CONCLUSIONS: Discrete-valued Bayesian networks are more complex to build than, for example, logistic regression. Nevertheless, we have demonstrated that such models can be used to predict EPs in a PUL population. Prospective interventional multi-center studies are needed to validate the use of such models in clinical practice.
A full specification of PPM can be downloaded from here
or you can assess the model by selecting a value for the three variables from the drop-down menu's below and clicking Evaluate.
We chose the operating point on the ROC curves where the sum of the sensitivity and specificity was maximal. The operating point for PPM corresponded to a threshold of 0.13. The probability predicted by PPM is considered an EP above this threshold and a non-EP below this threshold.
