Artificial intelligence can lower healthcare costs and push treatment toward precision medicine

what: Can you elaborate on the predictability of Artificial Intelligence (AI) and why it is important for individualized care?

John Edwards: Predictive models have to be trained on a data set. And if the data is very limited, it’s very hard to know if the prediction it came from and if the AI ​​model makes sense. You know, only about 3% of the population participated in clinical trials. And so, by their nature, clinical trials have a small group of people that drugs have been tested on.

And yet, when we put the drugs on the market, everybody treats them right there, everybody starts using the drug. But only 3% of that group had characteristics that led them to allow themselves to be part of the clinical trial. The real-world evidence that can come from examining this data, and building AI models based on the data, allows us to use more data from a broader set of people, perhaps more representative of all of us. By offering more comprehensive data sets in larger investigations [and] With daily evidence that can be collected, we can better understand what is driving variations in outcomes and the results of the drugs we give our patients or the treatments we choose to pursue.

Q: How do doctors and pharmacists authorize our data and how is it used?

john edwards: When we go in, we will be asked to authorize almost every visit (or we will be asked to sign some things that say we are giving that provider the right to our information). In Europe, you also have the right to withdraw your information, you know, through privacy techniques, that doesn’t exist as easily in the United States. Once you have signed that this treating physician had rights to your information, they may use it within their institution. If the information is shared with a paying health insurance company, they have a right to the information so they can manage payments. So, in some weird way, my insurance company has more rights to my data collection than each of my doctors, because my doctors only have rights to the data they collected while treating them rather than my entire data collection.

john edwards: It should lower the cost. Anything we can do to get people to make proper use of vendors, pharmaceuticals, or diagnostics that have been proven to work is the belief: it’s the best way, or the cost is the most effective.

If we’re off that path and doing things that aren’t effective, we’re getting detrimental results. We increase the total costs because we are not giving people the best care for them in their conditions. So it could mean that some people’s utilization increases because they need more medication or need to see more doctors, while other people will be comfortable following a protocol that may not require them to see them as often.

Because their risk factors aren’t there, that should cause them to see as many doctors for preventative medicine, or potentially take medications that aren’t going to work for someone like them based on biomarkers that were discovered and then associated with them. people’s results (and you have the same biomarkers).

It takes us one step towards precision medicine. it begins to bridge the gap between the knowledge that is being produced about drugs and the practice of drugs with doctors, so that they can understand better.

Q: How does AI individualize the treatment of diseases like breast cancer?

john edwards: Radiation is not measured throughout life. And if you have more and more radiation through X-rays, through various things that you have from a diet, you’re taking on greater risks and the side effects of radiation. After having cancer, you know, understanding the breast [and] where the tumor is, how dense your breast is, and where the location is, then makes a decision about how to apply radiation to the person’s breast.

And yet those decisions aren’t run through an AI model that learns from the evidence set of all the breast cancer we’re treating. It is done individually by the oncologist and the radiation therapist. So, we can do better. We can provide richer data for decision sciences that then apply the capability. The tools are available to deal with. We just have to be willing to build those kinds of solutions. and lean on the problem in a different way than we have done [before].

Leave a Reply

Your email address will not be published. Required fields are marked *