Researchers at Baylor College of Medicine’s Human Genome Sequencing Center have trained an AI assistant to explain genetic test results to patients. Photo via Getty Images

Artificial intelligence in the health care setting has a lot of potential, and one Houston institution is looking into one particular use.

Researchers at Baylor College of Medicine’s Human Genome Sequencing Center have trained an AI assistant to explain genetic test results to patients. According to findings published in the Journal of the American Medical Informatics Association (JAMIA), the team has developed generative AI to understand and interpret genetic tests. They have also tested its accuracy against Open AI’s ChatGPT 3.5.

“We created a chatbot that can provide guidance on general pharmacogenomic testing, dosage implications, and the side effects of therapeutics, and address patient concerns,” explains first author Mullai Murugan in a press release. Murugan is director of software engineering and programming at the Human Genome Sequencing Center. “We see this tool as a superpowered assistant that can increase accessibility and help both physicians and patients answer questions about genetic test results.”

The initial chatbot training specifically targeted pharmacogenomic testing for statins, meaning a patient’s potential response to cholesterol-lowering drugs, as dictated by genetics.

Murugan explains why they decided to create their own chatbot in the key publication on statin pharmacogenomics was published in May 2022, four months after the training cutoff date for ChatGPT 3.5 in January 2022. Alternatively, her team’s technology uses Retrieval Augmented Generation (RAG) and was trained on the most recent guidelines.

How did the two AI assistants compare? Four experts on cardiology and pharmacogenomics rated both chatbots based on accuracy, relevancy, risk management, and language clarity, among other factors. Though the AI scored similarly on language clarity, Baylor’s chatbot scored 85 percent in accuracy and 81 percent in relevancy compared to ChatGPT’s 58 percent in accuracy and 62 percent in relevancy when asked questions from healthcare providers.

“We are working to fine-tune the chatbot to better respond to certain questions, and we want to get feedback from real patients,” Murugan says. “Based on this study, it is very clear that there is a lot of potential here.” Nonetheless, Murugan emphasized that there is much work still to be done before the program is ready for clinical applications. That includes training the chatbot to explain results in the language used by genetic counselors. Funds from the NIH’s All of Us Research Program helped to make the research possible.

Houston-based alive5 has over 800 customers using their chatbox services — and has found a special niche in sports team's websites. Photo via alive5.com

Houston startup hopes to revolutionize the chatbot business

chatterboxes

It seems like every other webpage nowadays has a virtual assistant that pops up via a chat box. A Houston startups is hoping to ride the wave of this digital marketing initiative.

Houston-based alive5 has created a platform that allows small-to-medium-sized businesses to engage customers using Chatbot Technology, from their websites, apps, SMS text-message, and social media pages.

"What we do at alive5 is really simple," says Glenn Gutierrez, COO and co-founder of alive5. "We help your business make more conversations."

Gutierrez and his co-founder Dustin Yu started out in 2017 as Alive Chat System and they were one of the first chat systems in Texas.

"Our chat system was kind of a common system that you might see on a website that says, 'Hey, how can I help you today?" says Gutierrez. "And when you press that button, somebody on the other end sends a message and says, 'Hey, how are you doing today? How can I help you?"

After exploring how to take the company, which was initially a lifestyle product, to scale, they added new products and found new ways for their clients to have more conversations with their customers.

"We had to create as many channels as possible outside of web chat," says Gutierrez. "We talked about the live chat system, moving into SMS text message, moving into social media and interestingly enough, we started moving into business cards with QR codes where people can actually scan a QR code or text a phone number and we can automatically build a relationship with a customer at an event, in person or from a billboard.

"And that activates pretty much all the rest of the system for businesses to be able to engage a customer. So we think about ourselves as the best way to help you create more conversations, not just on your website, but pretty much anywhere you would engage a customer."

The platform enjoyed a meteoric rise in the chat space due to its participation in Capital Factory's accelerator program. From there, they were placed in another accelerator program in Philadelphia, the Comcast NBCUniversal LIFT Labs Accelerator, powered by Techstars.

"Because of the boost from the accelerator programs, we developed relationships with a lot of great organizations," says Gutierrez. "Today, we service over 800 customers, including 200 of the top college sports teams and pro teams like the NBA, NFL and NHL."

The platform's collaboration helps teams sell more tickets, especially premium seat tickets, by facilitating conversations with VIP clients and allowing fans the opportunity to go to the team's website to use the automated chat solution.

"A good example of one of those is the Jacksonville Jaguars website," says Gutierrez. "You can go there and see one of our chat boxes available to assist with inquiries or questions that you may have before, during or after a game. And our solution is built for organizations with a high volume of customer interactions to automate some of those tier one questions."

Alive5 also services customers like Royal Caribbean Cruise Line, major hotel brands and other companies in the hospitality space. They are also now collaborating with Spectra Venue Management, which manages hundreds of venues throughout North America, to pilot alive5's messaging and concierge services.

Outside of their inroads in the chat space, the platform is creating AI-powered strategies to help companies maximize their communication opportunities at personal touchpoint events such as conferences and trade shows.

"With our A.I. powered business cards, we're able to take an engagement that happens at a conference, an event or at a networking session and turn that into a prospect that's now part of a company's digital lead funnel," says Gutierrez. "What we're proposing is to give them a laser-etched metal business card with the QR code. That is better than just giving them a paper business card that they will take and may or may not call you and that's it, that's the end of the interaction.

"With the QR code, a potential contact can scan it and it will send them a demo of our product to their phone and it will give them all of a client's contact details so they can reach out to that client anytime they're ready to buy. The best part about that is that now you have something that no other system can do and you have that customer's phone number available to you at any point in time."

Moving forward, the Houston-based platform wants to do everything within its power to be one of the most successful chat companies nationwide.

"I like to think about our product like a Lego set," says Gutierrez. "It's up to you to choose what package you want. I've been in the startup space for a long time and to finally see that ecosystem starting to mature to the point that businesses are more open to digitally transforming their organizations, where they're understanding the need to take risks, to try new things, that's great for us.

"When you think about a company that can help you with your communication, I want alive5 to be the first company on their minds."

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Houston researcher builds radar to make self-driving cars safer

eyes on the road

A Rice University researcher is giving autonomous vehicles an “extra set of eyes.”

Current autonomous vehicles (AVs) can have an incomplete view of their surroundings, and challenges like pedestrian movement, low-light conditions and adverse weather only compound these visibility limitations.

Kun Woo Cho, a postdoctoral researcher in the lab of Rice professor of electrical and computer engineering Ashutosh Sabharwal, has developed EyeDAR to help address such issues and enhance the vehicles’ sensing accuracy. Her research was supported in part by the National Science Foundation.

The EyeDAR is an orange-sized, low-power, millimeter-wave radar that could be placed at streetlights and intersections. Its design was inspired by that of the human eye. Researchers envision that the low-cost sensors could help ensure that AVs always pick up on emergent obstacles, even when the vehicles are not within proper range for their onboard sensors and when visibility is limited.

“Current automotive sensor systems like cameras and lidar struggle with poor visibility such as you would encounter due to rain or fog or in low-lighting conditions,” Cho said in a news release. “Radar, on the other hand, operates reliably in all weather and lighting conditions and can even see through obstacles.”

Signals from a typical radar system scatter when they encounter an obstacle. Some of the signal is reflected back to the source, but most of it is often lost. In the case of AVs, this means that "pedestrians emerging from behind large vehicles, cars creeping forward at intersections or cyclists approaching at odd angles can easily go unnoticed," according to Rice.

EyeDAR, however, works to capture lost radar reflections, determine their direction and report them back to the AV in a sequence of 0s and 1s.

“Like blinking Morse code,” Cho added. “EyeDAR is a talking sensor⎯it is a first instance of integrating radar sensing and communication functionality in a single design.”

After testing, EyeDAR was able to resolve target directions 200 times faster than conventional radar designs.

While EyeDAR currently targets risks associated with AVs, particularly in high-traffic urban areas, researchers also believe the technology behind it could complement artificial intelligence efforts and be integrated into robots, drones and wearable platforms.

“EyeDAR is an example of what I like to call ‘analog computing,’” Cho added in the release. “Over the past two decades, people have been focusing on the digital and software side of computation, and the analog, hardware side has been lagging behind. I want to explore this overlooked analog design space.”

12 winners named at CERAWeek clean tech pitch competition in Houston

top teams

Twelve teams from around the country, including several from Houston, took home top honors at this year's Energy Venture Day and Pitch Competition at CERAWeek.

The fast-paced event, held March 25, put on by Rice Alliance, Houston Energy Transition Initiative and TEX-E, invited 36 industry startups and five Texas-based student teams focused on driving efficiency and advancements in the energy transition to present 3.5-minute pitches before investors and industry partners during CERAWeek's Agora program.

The competition is a qualifying event for the Startup World Cup, where teams compete for a $1 million investment prize.

PolyJoule won in the Track C competition and was named the overall winner of the pitch event. The Boston-based company will go on to compete in the Startup World Cup held this fall in San Francisco.

PolyJoule was spun out of MIT and is developing conductive polymer battery technology for energy storage.

Rice University's Resonant Thermal Systems won the second-place prize and $15,000 in the student track, known as TEX-E. The team's STREED solution converts high-salinity water into fresh water while recovering valuable minerals.

Teams from the University of Texas won first and second place in the TEX-E competition, bringing home $25,000 and $10,000, respectively. The student winners were:

Companies that pitched in the three industry tracts competed for non-monetary awards. Here are the companies named "most-promising" by the judges:

Track A | Industrial Efficiency & Decarbonization

Track B | Advanced Manufacturing, Materials, & Other Advanced Technologies

  • First: Licube, based in Houston
  • Second: ZettaJoule, based in Houston and Maryland
  • Third: Oleo

Track C | Innovations for Traditional Energy, Electricity, & the Grid

The teams at this year's Energy Venture Day have collectively raised $707 million in funding, according to Rice. They represent six countries and 12 states. See the full list of companies and investor groups that participated here.

---

This article originally appeared on our sister site, EnergyCapitalHTX.com.