SoylentNews is people
SoylentNews
Smartphones May Help Detect Diabetes:
"The ability to detect a condition like diabetes that has so many severe health consequences using a painless, smartphone-based test raises so many possibilities," said co-senior author Geoffrey H. Tison, MD, MPH, assistant professor in cardiology, of the Aug. 17, 2020, study in Nature Medicine. "The vision would be for a tool like this to assist in identifying people at higher risk of having diabetes, ultimately helping to decrease the prevalence of undiagnosed diabetes."
[...] In developing the biomarker, the researchers hypothesized that a smartphone camera could be used to detect vascular damage due to diabetes by measuring signals called photoplethysmography (PPG), which most mobile devices, including smartwatches and fitness trackers, are capable of acquiring. The researchers used the phone flashlight and camera to measure PPGs by capturing color changes in the fingertip corresponding with each heartbeat.
In the Nature Medicine study, UCSF researchers obtained nearly 3 million PPG recordings from 53,870 patients in the Health eHeart Study who used the Azumio Instant Heart Rate app on the iPhone and reported having been diagnosed with diabetes by a health care provider. This data was used to both develop and validate a deep-learning algorithm to detect the presence of diabetes using smartphone-measured PPG signals.
[...] "We demonstrated that the algorithm's performance is comparable to other commonly used tests, such as mammography for breast cancer or cervical cytology for cervical cancer, and its painlessness makes it attractive for repeated testing," said study author Jeffrey Olgin, MD, a UCSF Health cardiologist and professor and chief of the UCSF Division of Cardiology. "A widely accessible smartphone-based tool like this could be used to identify and encourage individuals at higher risk of having prevalent diabetes to seek medical care and obtain a low-cost confirmatory test."
Journal Reference:
Robert Avram, et al. A digital biomarker of diabetes from smartphone-based vascular signals. Nat Med (2020). DOI: https://doi.org/10.1038/s41591-020-1010-5
(Score: 0) by Anonymous Coward on Tuesday August 25 2020, @11:59AM (2 children)
Ummm, just a wild guess? The other 20% of the time it either predicts false positives or false negatives.
(Score: 4, Interesting) by ikanreed on Tuesday August 25 2020, @05:02PM (1 child)
You could actually read the paper and find the 80% here refers to the sensitivity among what they call their "Contemporary cohort" sample, so the 20% error rate here is only false negatives.
The false positive rate is close to 50%, but only 5% among the youngest sample group(younger than 30). At the same time the true positive rate among the under 30 is only 20%. So it seems a lot of what this algorithm detects is age.
The hard numbers seem not really even good enough for a pre-screening tool, to be honest.
(Score: 2) by FatPhil on Tuesday August 25 2020, @07:36PM
Assuming 90% prevalence, it will say "yes" .5*90+.8*10 = 53% of the time, and only be right 8/53 = 15% of the time.
In less blobby countries (the US is king here, save a few pacific islands), the error rate will be even higher.
Great minds discuss ideas; average minds discuss events; small minds discuss people; the smallest discuss themselves