While it’s simple in principle, this approach is powerful for two main reasons:
1. It can uncover complex relationships in a way that traditional statistical methods and the human brain cannot achieve.
As we start to be able to gather data from different streams; multimodal data from:
- Electronic Health records (EHRs)
- biometric information
- genetic information
- activity data
- environmental exposure,
- social media
Applying ML on combined data and search history, we can use AI methods to interrogate the complexity of those relationships and understand a little bit better about what drives human health and disease. Essentially what we can do with big data plus AI is enable precision medicine and personalized medicine, as well as foster innovation.
2. AI never gets tired. It performs as reliably and as well for the first task as it does for the one million.
However, AI in its present form and likely for the foreseeable future is merely a tool that can be trained to perform specific tasks, and it’s powerful in some ways that we humans are not. It is not by itself a solution. Building in a purposeful way will determine the ability to impact care.
Reference: Justin Ko, MD. AAD Position Statement on Augmented Intelligence. Fusing technology with human Expertise to enhance Dermatological Care. 8th World Congress of Teledermatology, Skin Imaging and AI in Skin diseases – November 2020