Digital Health Frontier
By John Halamka and Paul Cerrato — At face value, LLMs seem to exhibit the logical, analytical skills of experienced clinicians. But trying to comprehend what’s “under the hood” remains a challenge.
By John Halamka and Paul Cerrato — The U.S. government and the European Union both realize the need for measured control over the latest technology. Implement too many regulations too quickly and you stifle innovation. Move too slowly and you risk harm from irresponsible players in the field.
By John Halamka and Paul Cerrato — This digital tool may help healthcare professionals obtain safer, more reliable replies to their large language model prompts.
By John Halamka and Paul Cerrato — Generative AI and digital tools can do much more than finish a sentence or answer patients’ questions, but we need to point them in the right direction.
Guest post by Sonya Makhni — Despite the growth of AI solutions, it has still not translated into widespread clinical adoption. The four pillars of high-quality AI aim to drive sustainable change.
By John Halamka and Paul Cerrato — Bringing together data network partners, solution developers, and provider organizations produced actionable insights that will reinvent the healthcare ecosystem.
By John Halamka and Paul Cerrato — Innovative solutions to stubborn medical problems can come from the most unlikely sources, including many “unexperts.”
By John Halamka and Paul Cerrato — AI-enabled algorithms are only as good as the data they are built on. Managing that data requires a system that enables users to gain insights but at the same time keeps it private and secure.
By John Halamka and Paul Cerrato — Exercise may be an essential part of a healthy lifestyle, but convincing patients to get moving remains a challenge. Here are a few digital tools worth considering.
By John Halamka and Paul Cerrato — We can reinvent medicine by taking a more active role in fixing these barriers to good patient care, and by developing the digital tools to improve early detection of disease.
By John Halamka and Paul Cerrato — While most thought leaders in digital health believe large language models (LLM) are still too immature to guide clinical decision making, a case can be made for using them for writing medical notes and various administrative functions.
By John Halamka and Paul Cerrato — Machine learning-based algorithms can now be used to help detect atrial fibrillation, asymptomatic left ventricular systolic dysfunction, and cardiac amyloidosis. Even more digital diagnostic tools are on the drawing board.