.jpg)
The same devices that are used to take selfies and tweets are being repurposed and commercialized for quick access to information needed for patient monitoring. A heart rate can be measured by pressing a fingertip against a phone's camera lens. The microphone, which is kept by the bed, can detect sleep apnea. The speaker is also being tapped in order to monitor breathing using sonar technology.
In the best-case scenario, data is transmitted remotely to a medical professional for the patient's convenience and comfort or, in some cases, to support a clinician without the need for costly hardware.
According to experts, using smartphones as diagnostic tools is still a work in progress. The majority of the time, this is true.
Smartphones have sensors that can monitor a patient's vital signs. They can help assess people for concussions, monitor for atrial fibrillation, and conduct mental health wellness checks, to name a few emerging applications.
Companies and researchers looking for medical applications for smartphone technology are taking advantage of modern phones' built-in cameras and light sensors, microphones, and accelerometers, which detect body movements, gyroscopes, and even speakers. The apps then employ artificial intelligence software to analyze the images and sounds collected in order to facilitate communication between patients and physicians. According to a Grand View Research report, the more than 350,000 digital health products available in app stores demonstrate earning potential and marketability.
"It's very difficult to put devices in the patient's home or hospital," said Dr. Andrew Gostine, CEO of sensor network company Artist. According to the Pew Research Center, the majority of Americans own a smartphone, including more than 60% of those aged 65 and up, up from 13% a decade ago. As a result of the covid-19 pandemic, people are becoming more comfortable with virtual care.
Some of these items have been applied to the FDA for approval to be marketed as clinical devices. If patients are required to pay to use the product, health insurance plans will almost certainly cover a portion of the cost. Various items are designated as being excluded from this administrative interaction and are clinically grouped as a Bandage. Regardless, the organization's approach to dealing with artificial intelligence and AI-based clinical devices is still being refined to reflect the versatile programming concept.
Obtaining buy-in from healthcare providers requires ensuring accuracy and clinical validation. Many tools still require fine-tuning, according to Dr. Eugene Yang, a medical professor at the University of Washington. Yang is currently testing contactless blood pressure, heart rate, and oxygen saturation measurements obtained remotely via Zoom camera footage of a patient's face.
It is difficult to evaluate these new technologies because they collect data using algorithms created by machine learning and artificial intelligence rather than the physical tools commonly used in hospitals. As a result, researchers cannot "compare apples to apples" with medical industry standards, according to Yang. Failure to incorporate such assurances jeopardizes the technology's ultimate goals of lowering costs and increasing access because results must still be verified by a doctor.
"False positives and false negatives result in more testing and higher costs to the healthcare system," he explained.
Big tech companies like Google have heavily invested in this type of research, catering to clinicians, in-home carers, and consumers. Users can currently check their heart rate in the Google Fit app by placing their finger on the rear-facing camera lens or tracking their breathing rate in the front-facing camera.
"If you took the sensor out of the phone and out of a clinical device, they're probably the same thing," said Shwetak Patel, Google's director of health technologies and a University of Washington professor of electrical and computer engineering.
Google's research makes use of machine learning and computer vision, two branches of artificial intelligence that rely on information from visual inputs such as videos or images. According to Patel, instead of using a blood pressure cuff, the algorithm can interpret minor visual changes in the body as proxies and biosignals for a patient's blood pressure.
According to information published last year by Google, the company is also investigating the effectiveness of the built-in microphone for detecting heartbeats and murmurs, as well as using the camera to preserve eyesight by screening for diabetic eye disease.
Sound Life Sciences, a Seattle startup with an FDA-cleared sonar technology app, was recently purchased by the tech behemoth. It detects movement and monitors breathing by using the speaker of a smart device to bounce inaudible pulses off a patient's body.
Binah.ai, based in Israel, is another company that calculates vital signs using a smartphone camera. Its software examines the area around the eyes, where the skin is thinner, and analyses the light reflected back to the lens by blood vessels. According to company spokesperson Mona Popilian-Yona, the company is wrapping up a clinical trial in the United States and marketing its wellness app directly to insurers and other health companies.
- Canary Speech analyses patients' voices for mental health conditions using the same underlying technology as Amazon's Alexa. According to Henry O'Connell, the company's CEO, the software can integrate with telemedicine appointments and allow clinicians to screen for anxiety and depression using a library of vocal biomarkers and predictive analytics.
- ResApp Health, based in Australia, received FDA approval last year for its iPhone app, which listens to breathing and snoring to detect moderate to severe obstructive sleep apnea. SleepCheckRx, which will require a prescription, is less invasive than current sleep studies used to diagnose sleep apnea. These can cost thousands of dollars and necessitate a battery of tests.
- Brightlamp's Reflex app, among other things, is a clinical decision support tool for managing concussions and vision rehabilitation. The mobile app measures how a person's pupils react to changes in light using the camera on an iPad or iPhone. The imagery provides practitioners with data points for evaluating patients via machine learning analysis. Bright lamp sells directly to medical professionals and is used in over 230 clinics. Clinicians pay a standard annual fee of $400 per account, which is not currently covered by insurance. The Department of Defense is currently conducting a clinical trial with Reflex.
Brightlamp CEO Kurtis Sluss explained that data is processed directly on the phone in some cases, such as with the Reflex app, rather than in the cloud. Because streaming data elsewhere requires patient consent, the app avoids privacy concerns by processing everything on the device.
However, algorithms must be trained and tested by collecting massive amounts of data, which is a continuous process.
For example, researchers discovered that some computer vision applications, such as heart rate or blood pressure monitoring, can be less accurate for people with darker skin. Better solutions are being researched.
Small algorithm flaws can also cause false alarms, scaring patients enough to prevent widespread adoption. For example, Apple's new car-crash detection feature, which is available on both the latest iPhone and the Apple Watch, was triggered when people rode roller coasters and automatically dialled 911.
0 Comments :
Post a Comment