Mammogram AI Risk Model Predicts Subsequent Breast Cancer Within One Year in Women with Prior Cancer History

In a case-control study of 96 women with prior breast cancer and a negative screening mammogram, an AI risk model predicted subsequent breast cancer within 1 year with AUC 0.824 (95% CI 0.728-0.921), sensitivity 81.3%, specificity 76.6%.

• The AI model achieved an AUC of 0.824 (95% CI 0.728-0.921) for predicting any subsequent breast cancer within one year; at an exploratory cutoff, sensitivity was 81.3% and specificity 76.6%.
• Discriminatory performance was higher for contralateral new primary breast cancer (AUC 0.860) than for ipsilateral recurrence (AUC 0.790), though these sub-analyses were exploratory.
• This enriched case-control design means the reported PPV of 63.4% and NPV of 89.1% are specific to this sample; prospective validation in routine surveillance populations is required.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.