💵 AI's 4 Trillion-Dollar Test

Good morning! 

Welcome to Healthcare AI News, your weekly dose of the latest developments and headlines in the world of Healthcare AI.

In this issue, we explore:

✅ Headlines: Mayo Clinic to commercialize AI cancer model

✅ Industry: Procedure allows heart repairs to grow with children

✅ Interesting Reads: Biohacker Bryan Johnson swipes back at Elon Musk’

✅ Tech: What I learned as a product designer at Apple

✅ Feature: 3 ways AI is accelerating CRISPR's impact on health

HEADLINE ROUNDUP

• Mayo Clinic to commercialize AI cancer model (Read More)

• AI predictions for the new year (Read More)

• ChatGPT had a high error rate for pediatric cases (Read More)

• Cyborg computer combining AI and human brain cells really works (Read More)

• Framework to address algorithmic bias in healthcare AI models (Read More)

TOGETHER WITH ARAGON

Get stunning professional headshots without the hassle! Never pay for a photographer again.

Aragon AI’s tech is built by leading AI researchers and delivers the best results within 90-minutes. Just upload some selfies to see for yourself.

INDUSTRY NEWS

• AI’s big test: Making sense of $4 trillion in medical expenses (Read More)

• Groundbreaking procedure allows heart repairs to grow with children (Read More)

• Why weight loss drugs stop working and how to break past the Ozempic plateau (Read More)

• Why Is TikTok parent ByteDance Moving Into Pharma? (Read More)

• Doctors unionize as healthcare services are consolidated into corporate systems (Read More)

• Cigna reportedly nearing $3B - $4B deal to sell Medicare business (Read More)

• FDA approves AnX Robotica’s AI endoscopy tool (Read More)

INTERESTING READS

• Biohacker Bryan Johnson swipes back at Elon Musk’s criticism of his $2-million-a-year youth-chasing regimen (Read More)

• AI-created virtual influencers are stealing business from humans (Read More)

• Humanoid robots are getting to work (Read More)

• Japan earthquakes: the science behind the deadly tremors (Read More)

TECH NEWS

• How IBM sees AI changing the game for companies of all sizes (Read More)

• Understanding De-Identified data, how to use it in healthcare (Read More)

• What I learned as a product designer at Apple (Read More)

• How Grab implemented rate limiting (Read More)

HEALTHCARE AI JOBS

• Healthcare AI Teacher

• Machine Learning Engineer

• Senior AI Scientist - Medical Imaging

THE FEATURE

3 ways AI is accelerating CRISPR's impact on human health

Today, we’re talking about molecular biology darling CRISPR-Cas9.

No need to check your calendar. It’s not 2012.

For anyone who has been under a rock for the past decade, a reminder: CRISPR is a genetic technology that allows researchers to remove, add, or alter sections of DNA with the help of the Cas9 enzyme. 

You may also remember Jennifer Doudna won the 2020 Nobel Prize in Chemistry for her work on the gene-editing tool.

But why are we discussing CRISPR in 2023? 

AI is bringing gene editing applications to the next level. 

Today, we want to tell you about 3 applications we’re especially excited about.

Finessing on- and off-target effects

Some of the most exciting work around gene editing and AI is happening in Big Tech.

Specifically, Microsoft has been collaborating with academic researchers from UCLA and the Broad Institute to improve the precision of the CRISPR-Cas9 system.

The project has resulted in two sets of software:

1. Azimuth: On-target prediction

2. Elevation: Off-target prediction

Azimuth helps researchers predict which part of a gene to target with the CRISPR system to achieve their desired knockout (AKA when a gene is “shut off”). Whereas Elevation uses machine learning to predict effects that researchers are trying to avoid (hence the name “off-target”).

When used in concert, the tools help researchers save time and resources by minimizing the need for experimental iteration.

Predicting gene expression

Recently, scientists have started using another type of CRISPR. This one targets RNA instead of DNA using the Cas13 enzyme. This form of RNA editing can be used to block expression of certain genes.

Why would researchers want to do that? 

RNA manipulation is involved in drug discovery and even the development of new methods to prevent or treat viral infections. (Hint: SARS-CoV-2 and the flu are both RNA viruses.) Other ideal applications involve studying diseases like Down syndrome and schizophrenia— where there are too many copies of a gene.

And with the help of deep learning models, the use of these RNA-targeting CRISPRs is getting more precise. Scientists are using AI to predict how the
“molecular scissors” will impact target RNA and other potential effects. 

In other words, the model is looking for the same kind of on- and off-target effects the Microsoft software identifies in CRISPR-Cas9 work.

The so-called TIGER deep learning model was trained on data from RNA-targeted CRISPR screens in human cells. 

So, why the fuss? This predictive analysis can result in a much more precise gene expression design.

Beyond CRISPR: Speeding up zinc finger editing

When genes help the body make proteins, they’re often not acting alone. Genes use transcription factors to tell cells how much of a protein to produce.

If something goes wrong in that communication process, you can get diseases like diabetes and cancer due to over- or under-active genes.

Now, let’s talk about another gene-editing tool: zinc fingers. Zinc fingers hook onto transcription factors and use them to regulate gene segments like the ones mentioned above. 

Zinc-finger editing matters because it’s a potentially safer alternative to CRISPR. 

Without the need to rely on bacterial proteins as geneticists do with CRISPR-based gene therapy tools, there’s a lower risk of triggering a patient’s immune response. Plus, it could give us more flexible gene therapy techniques with the smaller size of the zinc-finger tools. 

Sounds great, right? 

Well, the challenge is that specifically designing zinc fingers for certain tasks is painstaking work.

Now, AI is being put to the task.

Enter ZFDesign: A system using AI to model and then design these zinc finger-DNA interactions based on data of 50 billion possibilities screened from the researchers’ lab.

The researchers hope to speed zinc finger editing along and even make it possible to modify several genes at once. Talk about a possible path to hyper-personalized gene therapy.

Final thoughts from HAN

We wouldn’t blame you for being hyped up about the possibilities of AI-enabled gene editing. We are, too.

The market forecast for gene editing—and gene therapy—indicates that we’re not alone in believing there’s something really special to this work.

But it’s also important to remember that, as this technology rapidly advances, the risks and ethical questions are growing right along with it. 

The specter of eugenics is always haunting gene editing. And we must always question how the alterations we make to genetic material may be passed on to future generations.

When it comes to gene therapy, we must strive to make life-changing treatments available to all—and now just those who can afford them.

As we eagerly watch the progress happening in genetic innovation, we continue to look to bioethicists and regulators to take the responsibility of these technologies seriously.

TWEET OF THE WEEK

🌟 Advertise With Us 🌟

Boost your brand amongst Healthcare's influential circle! Our diverse subscriber base boasts top executives, key decision makers, and visionary professionals from leading organizations – the ultimate platform for your brand's success. 🔥

Get in touch today