AI Enables Major Healthcare Advances At JP Morgan Event

How do we create AI in Healthcare? If you are like me, when you see your doctor, the constant probing for data can be somewhat annoying. First, you fill out forms with endless questions about your medical and familial history. Then, your doctor asks about your symptoms, adding more data to a laptop. Afterward, the outcome of any treatment is entered into your file. The reason? All this data will someday be used to provide personalized medicine to cure disease better and improve our lives. Well, that day is nigh, thanks to artificial intelligence.

JP Morgan’s annual Healthcare Conference is almost becoming an AI event as doctors and AI scientists collaborate to turn petabytes of clinical data into generative AI models and actionable insights. The progress made since Chat GPT’s arrival demonstrates that we are on the precipice of a revolution that will produce cures for many common diseases and save countless lives.

Cerebras Systems and Nvidia (both clients of my firm, Cambrian-AI Research) disclosed significant contributions in medicine at the conference that foretell coming advances in healthcare enabled by AI.

Cerebras and Mayo Clinic Apply AI in Healthcare to Predict Efficacy of Drugs

These two institutions have been collaborating for over a year and have produced a new foundation model that can predict the efficacy of drugs to alleviate Rheumatoid Arthritis (RA). Traditionally, RA sufferers resorted to a trial and error approach, with each trial testing a medicine for six months. If it doesn’t help, move on to the next drug and repeat until you hopefully find one that works. Meanwhile, your RA is getting worse.

The genomic model was trained by combining publicly available human reference genome data with Mayo's comprehensive patient exome (protein encoding) data. Feeding this data into the Cerebras Wafer Scale Engine, the companies have now trained the first genomic-data-based LLM to predict which medicine will benefit a particular RA patient most. The human reference genome is a digital DNA sequence representing a composite, "idealized" version of the human genome.

Unlike other models trained exclusively on the human reference genome, Mayo's genomic foundation model is trained on Mayo's Tapestry dataset incorporating 500 unique patient genomes. The combination of reference and patient genome creates the premier dataset for training a genomic foundation model.

Mayo will continue to refine the model with additional genome data to improve accuracy, but it has already achieved an 87% accuracy in drug prediction. Also, the accuracy of predicting the predisposition of cancer and cardiovascular disease is examined in the chart below.

These two companies have only been working together for about a year, and are now turning the expertise and computational power to expanding the foundation model to include support for other areas of medicine.

Nvidia Boosts AI in Healthcare Portfolio

As Nvidia CEO Jensen Huang has forecasted, we are entering the age of physical AI, and healthcare is no exception. Nvidia powers the first digital devices for healthcare from Synchron, Moon Surgical, Neptune Medical, and Virtual Incision.

And just like in automotive, it takes three computers to create physical AI, with DGX creating the model, simulating the physical world with Omniverse, and then running the actual smart device with Holoscan on IGX. Needless to say, Nvidia is providing a comprehensive platform for healthcare solution providers.

Meanwhile, at the Healthcare Conference, Nvidia announced results from several partnerships, including Mayo Clinic. The Mayo Clinic and NVIDIA are accelerating AI-driven digital pathology by developing multi-modal foundation models and working toward a human digital twin for improved disease understanding and treatment strategies.

Nvidia has also partnered with IQVIA to integrate Nvidia AI Foundry and AI Enterprise to accelerate agentic AI solutions for 10,000 healthcare and life science customers.

Illumina and NVIDIA are expanding the genomics market by providing analysis and insight platforms on NVIDIA accelerated computing and integrating state-of- the-art generative AI to unlock new biological understanding.

But what makes Nvidia stand apart aside from their fast GPUs in healthcare is the massive ecosystem they have built across the spectrum of sciences and practices, and of course AI is now the cornerstone upon which this community is built.

Where is AI in Healthcare Heading?

With the fantastic pace set by innovators, providers, and AI hardware vendors, serious diseases will likely be slain by AI, one at a time. Cancer is a disease caused by genetic factors and will practically be eliminated in the next decade thanks to AI.

The next time someone says, “Yeah, AI is cool, but where’s the profit?”, I will point to the life-saving potential AI is opening in healthcare.

Disclosures: This article expresses the author's opinions and should not be taken as advice to purchase from or invest in the companies mentioned. Cambrian-AI Research is fortunate to have many, if not most, semiconductor firms as our clients, including Blaize, BrainChip, Cadence Design, Cerebras, D-Matrix, Eliyan, Esperanto, Flex, GML, Groq, IBM, Intel, Nvidia, Qualcomm Technologies, Si-Five, SiMa.ai, Synopsys, Ventana Microsystems, Tenstorrent and scores of investment clients. We have no investment positions in any of the companies mentioned in this article and do not plan to initiate any in the near future.

For more information, please visit our website at https://cambrian-AI.com.