Early identification and referral of inflammatory breast cancer remains challenging within large health-care systems, limiting access to specialized care. We developed and evaluated an artificial intelligence-driven platform integrating natural language processing (NLP) with electronic health records to systematically identify potential inflammatory breast cancer patients across 5 campuses. Our platform analyzed 8 623 494 clinical notes, implementing a sequential review process: NLP screening followed by human validation and multidisciplinary confirmation. Initial NLP screening achieved 55.4% positive predictive value, improving to 78.4% with human-in-the-loop review. Notably, among 255 confirmed patients with inflammatory breast cancer, our system demonstrated 92.2% sensitivity, identifying 57 patients (22.4%) that traditional surveillance methods missed. Documentation patterns influenced system performance, with combined inflammatory breast cancer and T4d staging mentions showing the highest predictive value (98.2%). This proof-of-concept study demonstrates that lightweight NLP systems with targeted human review can identify rare cancer cases that may otherwise remain siloed within complex health-care networks, ultimately improving access to specialized care resources.
© The Author(s) 2025. Published by Oxford University Press.