In the News

In the United States, rare disease affects 1 in 10 people. The average time to diagnosis is about 4 to 5 years, though it can take as long as 30 years depending on the condition. Besides medical suffering, patients with rare diseases cost health systems an excess of about $28,000 in additional direct medical cost per year compared to patients without rare disease. We can’t expect healthcare providers, even specialists, to be experts in managing and diagnosing all 10,000 currently known rare diseases.

Artificial intelligence tools are increasingly bridging the gap in rare disease research by working with limited datasets to improve detection and diagnosis. The article highlights several AI solutions—including ThinkRare, DxGPT, ZebraMD, and STARVar—that help clinicians identify rare genetic conditions earlier, potentially reducing diagnostic delays that typically span ten to fifteen years.

Doctors at the University of California, Los Angeles’ David Geffen School of Medicine and the UC Health Network have devised a predictive algorithm that uses artificial intelligence to scour electronic health records to identify patients who may be at risk of having the condition and should undergo testing.

In her first year at the David Geffen School of Medicine at UCLA, Katharina “Kat” Schmolly, MD, heard an old saying: “When you hear hoofbeats, think of horses, not zebras.”