Last week saw the launch of Enlitic, a company that is incorporating deep learning to revolutionize diagnostic healthcare. With the intention of making the enormous trove of medical data that is available today accessible to physicians, Enlitic will provide data in the form of “medical images, doctors’ notes, and structured lab tests,” including X-rays, MRIs, and CT scans.
“Medical diagnostics is, at its heart, a data problem – turning images, lab tests, patient histories, and so forth into a diagnosis and proposed intervention,” explains Enlitic Founder and CEO, Jeremy Howard. “Recent applied machine learning breakthroughs, especially using deep learning, have shown that computers can rapidly turn large amounts of data of this kind into deep insights, and find subtle patterns. This is the biggest opportunity for positive impact using data that I’ve seen in my 20+ years in the field.”
In this case, deep learning essentially involves feeding a brain-like systems called artificial neural networks, with data in the form of images, audios, etc. and then extracting a response that is gleaned from the fed information, by the system. Howard believes that tapping into medical data with a similar approach will give rise to handy tools for health-care professionals.
However, more than writing the algorithms, Howard notes, it remains an uphill task to train the algorithms with information; in this regard Enlitic is working jointly with currently unnamed organisations that will assist in providing anonymised medical data.
Read more here.
(Image credit: CeBIT Australia)