Computer Power Taking Medicine to New Frontiers

Multimodal artificial intelligence (AI) – that is, AI which integrates various data types and algorithms to achieve more complex results – has extraordinary potential for transforming healthcare.

This is especially true for the field of health monitoring, says cardiologist, Dr Eric Topol in this eLetter to Science.

“…the convergence of unprecedented, massive computing power and self-supervised learning of a ginormous body of human-derived data has laid the foundation for medical applications that were not previously within reach,” says Dr Topol.

“The big shift ahead is the ability to transcend narrow, unimodal tasks, confined to images, and broaden machine capabilities to include text and speech, encompassing all input modes, setting the foundation for multimodal AI.”

He points to the latest in large language models (LLMs, or ‘generative AI’) such as ChatGPT-4 as one example of multimodal technology working across text, audio, speech and visuals, which require no specific data input and has broad applicability for the way patients can access healthcare.

“This multimodal AI has the potential for a wide range of data-driven applications… [For example] people at risk for developing chronic medical conditions, a virtual health assistant could provide frequent feedback about their data to achieve prevention or better manage pre-existing conditions,” says Dr Topol.

“Multimodal data for an individual can also make remote monitoring a reality, allowing a ‘hospital-at-home’ with continuous vital-sign capture that is equivalent to an intensive care unit.”

Read the full eLetter via Science.