This year, be thankful for AI in medicineThe technology is making health care more accurate and less expensive.
https://www.washingtonpost.com/opinions/2024/11/27/ai-medicine-health-care-thanksgiving/
If you’re struggling to come up with something you’re grateful for this Thanksgiving, here’s something all feast-goers can celebrate regardless of their political leanings: Artificial intelligence is revolutionizing medicine, making health care more accurate and less expensive for everyone.
AI is still in its infancy, yet it is already promising to transform how physicians do their jobs. Take, for example, cancer screenings. One controlled trial from 2022 found that software trained to scan images from colonoscopies was able to cut in half the miss rate for potentially cancerous lesions. A 2024 review of studies similarly found that screenings for skin cancer aided by AI were more accurate than those without the technology. Another review found similar results for breast cancer screenings, while also showing that AI reduced the workload of radiologists by 68 percent.
The benefit here is twofold: The technology can help detect cancer at earlier stages, making it easier to treat. It is also better at determining which tumors are benign, limiting the number of unnecessary and expensive biopsies that patients must endure (not to mention the anxiety that comes with the procedures). The purpose is not to eliminate humans in medicine; it is to give them better tools to help their patients. Then again, as AI models improve, it’s possible to imagine a future in which physicians are required to use them in screenings, and doctors devote more and more of their time to doing things AI is less suited to do, such as interacting with patients, explaining the medicine, and thinking through unusual or unexpected circumstances.
And that’s just the start. In 2022, the Department of Health and Human Services reported that about 6 percent of the more than 130 million people who go to emergency rooms every year are misdiagnosed. Of those, 2.6 million people are unnecessarily harmed because of their misdiagnosis. Roughly 400,000 are permanently disabled or die.
Artificial intelligence has the potential to significantly reduce those tragedies. A recent study out of Boston comparing the performance of chatbot-assisted physicians in diagnosing patients to just chatbots themselves found that the bots performed considerably better. Given a patient’s case history and symptoms, the chatbot alone scored an average of 90 percent in correctly diagnosing their condition. Physicians using the technology scored only 76 percent on average — just marginally better than the 74 percent average for humans with no AI help at all.
AI can also speed up care in emergency settings. One study found that hospitals that used AI to detect strokes from a patient’s brain scans were able to shave off almost 40 minutes before a surgeon could intervene. That’s precious time that can save lives.
Incorporating this technology into medicine will no doubt run into bumps. Many people are likely to be skeptical of it, and some might fear it will make visits to the doctor even less personal than they already are. But it could free up physicians’ time dedicated to mundane tasks and cut seemingly interminable wait times at medical practices.
Arguably, AI’s greatest promise is the one that’s hardest to see: its potential to turbocharge medical research. For instance, AlphaFold2, the artificial intelligence program developed by Google DeepMind, has started to crack the code on how proteins take their specific shapes, a question that has confounded scientists for decades. This is important because the shape of proteins governs virtually every task carried out in the body, from delivering oxygen through the blood to controlling a person’s appetite. In the past century, understanding these complex molecules took years of painstaking work. Machine learning is reducing that time frame to a tiny fraction. Such research power could uncover clues to therapies for an enormous variety of diseases.
The challenge with all these exciting developments, of course, is that AI technology can be expensive to adopt. It also requires a lot of energy, which will put pressure on the electrical grid and might accelerate climate change if powered by carbon-intensive sources. The federal government can help address these problems by, for example, offsetting new demand for electricity by expanding the grid with cleaner energy, including nuclear power.
The emergence of AI has provoked great alarm in recent years, and for good reason. The technology could disrupt the economy, upending industries in unpredictable ways. Its awesome power deserves caution, but not fear. Americans can take comfort in the fact that, when it comes to medicine, this bit of human ingenuity has been a force for good — and will probably continue to be.
New AI technology 'can detect over 1,000 diseases before diagnosis' say researchers
How AI is making it easier to diagnose disease | Pratik Shah
AI in Medical Diagnostics | Rob T. Lee and James Lyne
NIH SciBites: Using AI to Diagnose Rare Diseases
Diagnosing AI/LLM Workloads with Dynatrace
Revolutionizing Diagnostics, Treatment and Patient Care
Curing Disease With Genetics And AI
Artificial Intelligence in Healthcare Diagnoses
Better Diagnoses? AI Vs. Doctors!
Total Posts: 10261