The gray oximeter sitting on my kitchen table looks like a record player. A product of the 1970s, its alarm for low blood oxygen levels is set by analog dial. I bought it on eBay late last year, after writing a story about the racial bias built into oximetry for the Boston Review. A professor of medicine at Yale, Meir Kryger, reached out afterward with a suggestion: I should also look into the models predating contemporary pulse oximeters, specifically one made by Hewlett-Packard. It's a technological dinosaur, but as I'd soon learn, its inner workings are more advanced than many devices that measure blood oxygen in hospitals today.
Meet Oxehealth, a startup that plans to turn any regular security camera into a health monitor. The British company wants to make it easier to monitor patients in a hospital, police station, psychiatric hospital or an assisted living residence. It's a non-intrusive way to make sure that everybody is doing well. The startup is launching onstage at Disrupt London. Finger pulse oximeters are the easiest way to check your vital signs right now.
Apple is working on a software update that will allow its smartwatches to detect blood oxygen levels, according to reports. The tech giant is working on new features that will send blood oxygen readings to existing versions of its Apple Watch, as well as the new model, expected to be revealed in September. When Apple Watch detects low blood oxygen saturation below a certain threshold, a notification will be sent to the wearer much like the current heart rate notification capability, according to 9to5Mac. The new feature will be enabled by a built-in'pulse oximeter' – a small device that estimate the amount of oxygen carried by red blood cells. The feature was allegedly revealed via a leak of the code from Apple's upcoming iOS 14 for its next generation of smartphones, which would carry the accompanying app.
I want to give you an idea of what it feels like to do something important, dangerous, and entirely stupid--and then to have to do it all again. To do that, I would like you to consider the baby monitor: a 5-inch screen and a camera that can, from rooms away, watch an infant rest or fuss. For months, I have had a bag of baby monitors under the cramped desk in the tiny room that serves as my office at the hospital where I work as a high-risk obstetrician. They are not special baby monitors; they are the same ones you could buy on Amazon or at CVS. They're stacked alongside a plastic bin full of clogs and a box of unused printer paper--the kind of things you can't quite throw out, because you might need them.
We use a deep learning model trained only on a patient's blood oxygenation data (measurable with an inexpensive fingertip sensor) to predict impending hypoxemia (low blood oxygen) more accurately than trained anesthesiologists with access to all the data recorded in a modern operating room. We also provide a simple way to visualize the reason why a patient's risk is low or high by assigning weight to the patient's past blood oxygen values. This work has the potential to provide cutting-edge clinical decision support in low-resource settings, where rates of surgical complication and death are substantially greater than in high-resource areas.