A cervical abnormality risk prediction model: can we use clinical information to predict which patients with ASCUS/LSIL Pap tests will develop CIN 2/3 or AIS?

Objective: Human papillomavirus (HPV) infections and abnormal Pap test results are common, and most do not progress to cervical cancer. Because it is difficult to predict which mild Pap abnormalities will develop into precancerous lesions, many women undergo painful and costly evaluations and even unnecessary treatment. The objective of this study was to develop a risk prediction model based on clinical and demographic information to identify women most likely to develop significant precancerous lesions (cervical intraepithelial neoplasia grades 2/3 [CIN 2/3] or adenocarcinoma in situ [AIS]) among women with mild Pap abnormalities (atypical squamous cells of undetermined significance/low-grade squamous intraepithelial lesion).

Materials And Methods: The Abnormal Pap Smear Registry includes women who received treatment at the Brigham and Women's Hospital/Dana Farber Cancer Institute Pap Smear Evaluation Center beginning in 2006. It includes 1,072 women with mild cervical dysplasia (atypical squamous cells of undetermined significance or low-grade squamous intraepithelial lesion) on their referral Pap test. We derived a clinical prediction model to predict the probability of developing CIN 2/3 or AIS using multivariate logistic regression with a split-sample approach.

Results: By the end of the follow-up, 93 of the 1,072 women developed CIN 2/3 or AIS (8.7%). There were several differences between women who developed CIN 2/3 or AIS and women who did not. However, once we put these into the regression model, the only variable that was significantly associated with CIN 2/3 or AIS was having a history of an abnormal Pap or biopsy result (odds ratio = 2.44; 95% CI =1.03-5.76). The resulting prediction model had poor discriminative ability and was poorly calibrated.

Conclusions: Despite accounting for known risk factors, we were unable to predict individual patients' probability for progression on the basis of available data.