Artificial Intelligence To Improve Patient Safety

AI in healthcare are mostly focusing on imaging, because the recent wave of AI development actually kind of thanks to a breakthrough in the imaging recognition like CNN, new algorithms like CNN. That’s why most people actually focus their AI effort on medical image processing, but again, I would like to emphasize that if we use AI in quality and patient safety, you know, it might be easier to get benefit for the patient and faster as well. Especially in an environment like Taiwan, we have a National Health Insurance, so every improvement, every tiny little improvement will be amplified by 23 million, that’s how many patients we have. And it’s all one database.

So that’s why I think it’s about time we have a conference on AI QPS, AI in quality and patient safety. Okay, before we have our keynote speaker, I actually would like to show you a few slides of one example that we dedicate the AI effort into patient safety, and this is for improved the medication safety. I would like to just spend a few minutes. So as you know that medical error has been a major problem.

It was in the year 2000, the medical error still ranked number five in the top 5 causes of death in the year 2000, every year medical error kills about, these are deaths, these are not injury, those people are dead okay, so about 100,000 people dead for medical error, due to medical error, and in 2013, after about 13 years, this one is published in 2016, but the numbers are from 2013. So after 13 years of effort, you know, everybody is working on it, and feel likes it’s a big problem, we managed to make medical error, you know, number three in the top five causes of death.

If we work even harder, it will actually, you know, replace cancer and heart disease, and become number one, you know. So that’s really a big problem, and of course, it’s not that we’re not doing enough, well actually, we probably are not doing enough, but uh, but again, the Asian population make people, you know, uh, it make the poly-morbidity issue, you know, there are more diseases in one patient. It’s a doctor I’ve been seeing patient for twenty years, and you know, many of my patients ages with me. Okay so when they started to see me, they were like sixty in their 60s, now they’re in their 80s.

But they’re still kind of relatively healthy, but again, they have diabetes, hypertension, you know, poly-morbidity. So me many patients suffer from multiple diseases. In poly-pharmacy, because of the multiple diseases, they need to take a lot of medicine, you know, the maximum, um, number of drugs that you can prescribe to one person. Do you know there’s a limit for that? In our hospital, you know, in many of our hospital, that number was 21, okay so in a hospital. But there’s no limit if you do it, if you take your drug from several different hospitals, right? So, um, poly-pharmacy, that’s a big problem, and more patient visit means shorter physician time, and there are new drugs, new exams, and new procedures.

Some people estimate that the half-life of medical knowledge is 70 months. Okay, if that’s the case, that means one and a half year after you graduate from medical school, half of your knowledge has already outdated, right? So it’s really a lot of new things that we have to learn, not to mention genomic factors, environmental factors, and other factors are increasing the complexity of these things.