[ad_1]
Diagnostic robotics shows that a stitch in time saves nine — and a blood thinner in time saves a trip to the emergency room for heart failure. The company’s machine-learning-powered preventive care aims to predict and avoid dangerous (and expensive) medical crises, saving everyone money and hopefully keeping them healthier overall—and it’s raised $45 million to raise.
It’s important to first clarify that this particular combination of AI, insurance, hospital bills, and “predictive medicine” is not some kind of technological fantasy. The whole company is based on the fact that it is better and cheaper for you if you improve your heart health than, for example, have a heart attack.
That’s why your doctors tell you to cut back on red meat and maybe take cholesterol-lowering drugs, “Well, if you have a heart attack, go to the ER.” This is common sense, and it saves patients, hospitals and insurance companies money. And don’t worry, a forecast like this can’t be used to raise your premiums or deny you care. They want you to pay monthly fees – they don’t want to charge you for a $25,000 operation if they can help it.
The question is, what about conditions that are less obvious, or where patients don’t have a specific diagnosis? This is where machine learning models come in; They are very good at extracting signal from large noise. And in this case, the AI was trained on 65 million unknown medical records.
“We see how people look before The problems – everything we do is preventive care, “said Kira Radinsky, CEO and co-founder of Diagnostic Robotics. “It’s all about giving the right intervention at the right time to the right patient.”
She explained that providers often focus on high-cost patients to cut costs — such as someone with advanced heart disease. But while acute and maintenance care continues to be important to them, that money is already out the door. On the other hand, if you diagnose someone with early signs of heart failure, you can stop its progression and save money and possibly life. And the technique goes beyond what can be detected in laboratories.
“The challenge is finding patients who are suffering from, say, depression or anxiety but are not taking any medication,” Radinsky says. “How do you identify someone with depression or anxiety based on medical records? We identify the number of visits they’ve had—a lot of referrals, a lot of complaints—that’s a strong indicator. Then you do specific questions, a medical exam, and you get them to see a psychologist or a psychiatrist, and so on. They are not being spoiled.
The company says it can cut ER visits by three-quarters, which is significant beyond the immediate benefits to the person and the provider. ERs and urgent cares are overcrowded in the US, paradoxically due to widespread fear of higher medical costs.
An example of a tablet interface showing patient data arranged by diagnostic robotics models. Image Credits: Diagnostic robotics
In many cases, medical providers or insurers will offer drugs or treatment for free or at nominal cost, knowing that they will save themselves a large bill. Of course, it’s all a matter of personal preference, but that means you can trust them.
Tel Aviv-based Diagnostic Robotics has raised a $45 million B round led by Stageon investors, joining Mayo Clinic, Technion (Israel Institute of Technology) and Bradley Blue. Radinski says this will help the company start working directly with providers, taking on general health goals in addition to specific high-risk areas. (The company currently tracks around 20.)
A pilot test of this broad approach was recently confirmed in a study of a few hundred patients, in which the AI-generated health plan was statistically indistinguishable from that of a medical professional. The company already serves millions of patients in Israel, South Africa and the United States with Blue Cross Rhode Island.
If you expand to your provider, don’t expect some kind of robotic diagnosis, even though the name clearly suggests this.
“You get phone calls from care managers who offer free or additional treatment,” Radinsky said. AI may have already done the work, and maybe your test scores and your position are at risk for something – and you’d better take these tips seriously. AI may still have a lot of room to grow, but it’s good to sniff out statistical correlations.
She added that they are actively working to find, determine and mitigate bias in the algorithm, whether it’s due to misinformation or human error elsewhere in the pipeline. “What the algorithm is trying to do is see who will benefit the most,” Radinsky explained, but as with other forms of AI and machine learning, only careful observation will make the idea of who benefits more relevant to the real world.
[ad_2]
Source link
