This AI app will soon screen for type 2 diabetes using audio clips of just 6-10 seconds.

Diabetes is a disease that occurs because the body is unable to produce or use an important panacea called insulin. Insulin, produced by the pancreas, helps absorb glucose and provides energy for the body to function.

There is two Basic types of diabetes: Type 1. The pancreas is attacked by the body’s own immune system and is unable to produce any insulin. Type 2, which accounts for more than 90% of diabetes cases, prevents the body from using insulin to break down glucose.

Related article: 3 ways AI is revolutionizing how healthcare organizations serve patients

In type 2 diabetes, too much insulin floating around the body wreaks havoc. Diabetics are known to suffer from poor blood circulation and are at serious risk of heart attack, stroke, amputations, blindness, kidney disease, and more. If you are overweight, obese, or have little physical activity, you are at higher risk of developing type 2 diabetes.

But the strange thing about diabetes is that people often don’t realize they have it, which is why the disease is called a silent killer.

Approximately 37 million adult Americans, or 11.7% of the adult population have type 2 diabetes, but only 28 million people in the United States have been diagnosed with the disease. The rest don’t know they have it.

Globally, the situation is even worse, with 462 million people have type 2 diabetesBut at least half of them don’t realize it.

test time

One might think that in our technology-driven age, innovators would have developed a systematic, efficient and affordable way to detect the presence of a common disease like diabetes, which primarily affects the underprivileged. yeah. However, progress has been limited so far.

most common test Today, there are still things that measure blood sugar levels (called fasting blood glucose, or FBG), which require an overnight fast and a trip to the clinic. The same goes for the popular glycated hemoglobin (A1C) test, which does not require fasting.

Unfortunately, for most of the world and underprivileged people in the United States, clinics may not be easily accessible, and testing costs can exceed what people can afford.

But what if you could detect a disease using a device that almost everyone owns today, and at virtually no cost? Instead of waiting days for test results, you could get results right away. It’s out, right?

This is emerging promise This is an app powered by an AI engine that is starting to offer a radical new way to detect disease using your smartphone and just a few seconds of audio samples.

Also: Google’s MedPaLM puts human clinicians at the center of medical AI

click healtha Toronto-based life sciences commercialization company, is one of the companies transforming the detection and treatment process with a pioneering test for diabetes.

of test is breathtakingly easy. Anyone with a smartphone can record his or her voice for just 6 to 10 seconds and find out if he or she may be infected with the disease.

The company told ZDNET it will conduct a final round of replication studies this year before seeking regulatory approval.

AI documentation will always exist

welcome to the world of vocal Biomarkers where AI analyzes speech patterns and features. Instead of needles and blood samples, this algorithm measures the most minute changes in voice and breathing that are unrecognizable to mere humans.

Where the “old world” used human breathing and simulated coughs as indicators to tell doctors that there might be a problem internally, these audio biomarkers can detect tone, pitch, and many other markers. Dig deeper.

Also: Amazon AWS rolls out HealthScribe to transcribe doctors’ conversations

The current frontrunner in this field is Klick, whose voice-based diabetes test could revolutionize the early detection and successful treatment of diabetes.

For AI-based training and testing solutionCrick Institute scientist Jaycee Kaufman and her team recorded audio from 267 people who either didn’t have diabetes or were already diagnosed with type 2 diabetes.

Over a two-week period, participants recorded a short sentence saying, “Hello, how are you doing? What is my blood sugar level right now?” — 6 times daily on your smartphone. This process generated over 18,000 audio samples from which 14 acoustic features were extracted that varied in prevalence and intensity across participants.

Related article: Everything we know about the Samsung Galaxy Ring

The basis of Crick’s diabetes test is changes in the acoustic characteristics of a person’s voice due to the disease.

Kaufman said diabetes tends to erode both men’s nerves and muscles, affecting the robustness of their voices. On the other hand, women who have a high correlation between depression and anxiety and diabetes tend to have a higher pitch.

Using these markers, Klick’s AI-powered model achieved incredible accuracy. The model’s diabetes testing accuracy was 89% for women and 86% for men. Results may further improve over time.

Notes

AI-powered voice-based disease detection is set to become one of the most common ways we test ourselves for various diseases.

It was recently awarded to a group of 10 universities. funding Consider using AI to detect voice changes and discover Alzheimer’s disease and autism with low-cost diagnostic tools.

Also: The best smart rings you can buy: Tested by experts

Machine learning is also deployed for detection. parkinson’s disease The disease relies on a method of screening for the disease based on just one sound, the patient’s “aaaaaaaaaaaaaaaaa” sound. The sounds will be compared to a database of recordings from Parkinson’s disease patients and a control group.

However, CLICK’s voice-based diabetes test, while comparable to a clinical test in terms of accuracy, is intended to be the first step towards a final diabetes diagnosis.

All tests have false positives and other errors. Therefore, it is important for those using this test to corroborate the results with other traditional tests and expert validation.

However, given the harmful role of diabetes in accelerating serious health problems, an early warning system in the form of an audio test could save many lives and encourage others to seek early treatment. Just what the doctor ordered.