Fundraise

Carnegie Mellon spinout Xlue raises $35M seed for cancer-risk AI

What's the deal? XlueDealroom has a profile for this one. Try Dealroom →, a Carnegie Mellon spinout building clinical-intelligence AI, has raised a $35 million seed round led by ConvictionDealroom has a profile for this one. Try Dealroom →, Sarah Guo's AI-focused venture firm. The company uses AI to flag patients at elevated risk of cancer so doctors can test them earlier.

What does it do? Xlue's model trains on large-scale, longitudinal health records from the US, Taiwan, and elsewhere to learn patients' health trajectories, then analyzes electronic records to predict cancer risk. "This is not diagnostic, it is risk stratification," chief executive officer Chenyan Xiong told Forbes. "This is about who the doctors should test early."

Who's behind it? Xiong worked on large language models at Microsoft before becoming a Carnegie Mellon professor. His co-founders include health AI researchers from Georgetown, Stanford, and the NIH.

The evidence: A retrospective study of 80,000 patients at Kaohsiung Medical University in Taiwan tested the model across seven cancer types. It flagged cancer risk 12.6% of the time at least 180 days before diagnosis and 19.5% of the time at least 90 days before, beating a tree-based model and a rule-based system using screening guidelines.

What's the endgame? Xiong plans to extend the model to other diseases and to help drug companies manage development pipelines. "Clinical trials many times are driven by a hunch," he said. The startup is in talks with hospitals and pharmaceutical firms about partnerships.

What could go wrong? Funding does not establish clinical benefit. Xlue's impact will hinge on whether its predictions prove reliable in practice and prompt appropriate testing without triggering excess false alarms.

The signal: At $35 million, the seed sits in the 99th percentile of US health seed rounds, a sign of investor appetite for AI trained on clinical histories rather than tools that merely summarise records. UC Berkeley spinout Knit Health announced a separate $35 million Series A the same week for AI that forecasts patients' care needs, underscoring momentum behind predictive clinical models.

Read more: forbes.com

Image credit: Xlue

More top stories