Loading
Dxcover shone infrared light through blood serum from 2,092 people and used machine learning to tell eight cancer types from no cancer.
Cameron and colleagues applied the Dxcover Cancer Liquid Biopsy, Fourier transform infrared spectroscopy with machine learning, to 2,092 patients across eight cancers. Areas under the curve against symptomatic non-cancer controls were brain 0.90, breast 0.76, colorectal 0.91, kidney 0.91, lung 0.91, ovarian 0.86, pancreatic 0.84 and prostate 0.86. Pooling all eight against asymptomatic non-cancer controls, the model detected 64% of stage I cancers at 99% specificity (overall sensitivity 57%); tuned for sensitivity it found 99% of stage I cancers at 59% specificity.
A cheap, fast signal with promising discovery-stage figures; it has not been tested in a screening population.
Every source this page cites, grouped by who published it. Grouping is read from the web address, not assigned by hand.
A source that has moved or gone is reported by the weekly link check. /audit/