Healthcare built for you: AI and the personalization of medicine
To celebrate AI right now almost feels dangerous, because of the widespread and increasingly intense backlash against it. I myself have written about the dangers of AI, not least in these pages , so I understand the anti-AI sentiment. But we must be careful not to throw the baby out with the bathwater. When my team and I wrote Transcend in 2024, we talked of two sides to AI—the dangerous side,…
In 2021, the author's 18-year-old son was diagnosed with multiple myeloma, a cancer of the plasma cells in the bone marrow. The disease typically affects older individuals, with the average age of diagnosis being 69 years old. Younger patients, like the author's son, are often underrepresented in research, leading to a lack of specific knowledge about their unique cases.
The author's son's treatment protocols and survival estimates were based on data from older patients, despite his young age. This is a common issue in medicine, where individuals are often treated based on the outcomes of broader population studies. However, as AI technology advances, personalized medicine is becoming a reality.
The current limitation of standard medical treatment is the reliance on average outcomes, which can obscure the distribution of effects within a trial. Additionally, most treatments are designed for the average patient, leading to situations where treatments may not work for everyone and can cause unnecessary suffering or cost.
To treat patients as individuals, three key elements are necessary: understanding the patient biologically, choosing a treatment based on that knowledge, and having the ability to develop a custom treatment if needed. AI can assist in all three areas.
First, AI can help by identifying patterns in scans and tissue that are difficult for humans to discern. This can provide crucial information that was previously hidden. For example, a Mayo Clinic model found signs of pancreatic cancer on scans up to three years before diagnosis, when treatment may still be effective.
Second, AI can aid in selecting personalized treatments. By leveraging individual patient data, doctors can make more informed decisions about which treatments are likely to be most effective. This approach reduces the likelihood of treating a patient with a therapy that is not suitable for their specific condition.
Lastly, AI can help develop new treatments tailored to individual patients when existing options are insufficient. This is particularly important for young patients, like the author's son, whose cases may not be well-represented in existing research.
While AI is not yet capable of providing fully personalized treatments, it is a necessary first step in understanding the patient's condition better. Once more information is available, doctors can make more informed decisions about the most appropriate treatment for each individual. As AI continues to evolve, personalized medicine has the potential to transform healthcare, offering more effective and less invasive treatments for patients across the spectrum of conditions.
Written by urgent.news from Fast Company's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
