BrainLM is now well-trained enough to use to fine-tune a specific task and to ask questions in other studies. Photo via Getty Images

Houston researchers are part of a team that has created an AI model intended to understand how brain activity relates to behavior and illness.

Scientists from Baylor College of Medicine worked with peers from Yale University, University of Southern California and Idaho State University to make Brain Language Model, or BrainLM. Their research was published as a conference paper at ICLR 2024, a meeting of some of deep learning’s greatest minds.

“For a long time we’ve known that brain activity is related to a person’s behavior and to a lot of illnesses like seizures or Parkinson’s,” Dr. Chadi Abdallah, associate professor in the Menninger Department of Psychiatry and Behavioral Sciences at Baylor and co-corresponding author of the paper, says in a press release. “Functional brain imaging or functional MRIs allow us to look at brain activity throughout the brain, but we previously couldn’t fully capture the dynamic of these activities in time and space using traditional data analytical tools.

"More recently, people started using machine learning to capture the brain complexity and how it relates it to specific illnesses, but that turned out to require enrolling and fully examining thousands of patients with a particular behavior or illness, a very expensive process,” Abdallah continues.

Using 80,000 brain scans, the team was able to train their model to figure out how brain activities related to one another. Over time, this created the BrainLM brain activity foundational model. BrainLM is now well-trained enough to use to fine-tune a specific task and to ask questions in other studies.

Abdallah said that using BrainLM will cut costs significantly for scientists developing treatments for brain disorders. In clinical trials, it can cost “hundreds of millions of dollars,” he said, to enroll numerous patients and treat them over a significant time period. By using BrainLM, researchers can enroll half the subjects because the AI can select the individuals most likely to benefit.

The team found that BrainLM performed successfully in many different samples. That included predicting depression, anxiety and PTSD severity better than other machine learning tools that do not use generative AI.

“We found that BrainLM is performing very well. It is predicting brain activity in a new sample that was hidden from it during the training as well as doing well with data from new scanners and new population,” Abdallah says. “These impressive results were achieved with scans from 40,000 subjects. We are now working on considerably increasing the training dataset. The stronger the model we can build, the more we can do to assist with patient care, such as developing new treatment for mental illnesses or guiding neurosurgery for seizures or DBS.”

For those suffering from neurological and mental health disorders, BrainLM could be a key to unlocking treatments that will make a life-changing difference.

This Houston startup has a game-changing technology for deep learning. Photo via Getty Images

Houston artificial intelligence startup raises $6M in seed funding

money moves

A computer science professor at Rice University has raised seed funding last month in order to grow his company that's focused on democratizing artificial intelligence tools.

ThirdAI, founded by Anshumali Shrivastava in April, raised $6 million in a seed funding round from three California-based VCs — Neotribe Ventures and Cervin Ventures, which co-led the round with support from Firebolt Ventures.

Shrivastava, CEO, co-founded the company with Tharun Medini, a recent Ph.D. who graduated under Shrivastava from Rice's Department of Electrical and Computer Engineering. Medini serves as the CTO of ThirdAI — pronounced "third eye." The startup is building the next generation of scalable and sustainable AI tools and deep learning systems.

"We are democratizing artificial intelligence through software innovations," says Shrivastava in a news release from Rice. "Our innovation would not only benefit current AI training by shifting to lower-cost CPUs, but it should also allow the 'unlocking' of AI training workloads on GPUs that were not previously feasible."

The technology ThirdAI is working with comes from 10 years of deep learning research and innovation. The company's technology has the potential to make computing 15-times faster.

"ThirdAI has developed a breakthrough approach to train deep learning models with a large number of parameters that run efficiently on general purpose CPUs. This technology has the potential to result in a gigantic leap forward in the accuracy of deep learning models," per and announcement from Cervin Ventures. "Our investment in ThirdAI was a no-brainer and we are fortunate to have had the opportunity to invest."

Anshumali Shrivastava is an associate professor of computer science at Rice University. Photo via rice.edu

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

New Houston-born app OpenToBites connects users over meals in 16 cities

Friends and Food

A Houston-born social is connecting foodies and social butterflies for shared meals. OpenToBites launched on Android on June 18 and iOS on June 22, and is available to use for free in Houston and beyond.

Founded and operated by Houston developer Kelvin John, OpenToBites allows users to connect over meals in 16 cosmopolitan cities. That includes Austin and Houston in Texas, plus other American cities like Denver and New York, and even international destinations including Paris, Tokyo, and Sydney.

The app is built on a simple concept, and a press release emphasizes that it's for anyone who wants "friendly company."

“We built OpenToBites in response to several trends, including the rise of solo travel and the demand for social experiences that don’t feel like dating, networking, or large organized events,” said a spokesperson in the release. “We are not a dating app. We are offering shared food and conversation for people who want simple, in-person meal company in a public setting.”

When signing up, users provide their first name, an optional profile photo, and a short bio. They mark themselves as a traveler, a local, or both, and have the option to select their age range or opt out.

Once a profile is created, the user can search for existing meals or create a meal happening within the next 72 hours. To find an existing meal to join as a guest, they select the city, date, and apply filters for the number of seats, type of cuisine, and whether they want to share food with the table or order their own.

Since someone has to get the party started, users can also take the initiative to start a meal as a host. They'll choose the date, time, and restaurant — anything is on the menu, as long as they can link to the restaurant on Google Maps or its own website.

This divides users into "host" and "guest." Guests request to join a table, and a host can decide to accept the request or not. Guests aren't able to see the exact restaurant until their request is accepted, so hosts have a "helpful note" field to fill out with more information about the restaurant.

A similar app called Timeleft launched in Austin in 2024, acting as a friendship matchmaker for small groups of strangers who answer personality questions, meet at a restaurant for dinner, and decide if they wanted to stay in touch.

Though OpenToBites has a similar concept, it seems to work more like Couchsurfing, an app that connects travelers on their own terms. OpenToBites also emphasizes the immediate over the long-term — the meal itself is the social goal.

OpenToBites is available for free on the App Store and Play Store; the app plans to grow each current city's user base before adding new locations.

---

This article originally appeared on CultureMap.com.

Houston mental health nonprofit expands platform statewide to connect more Texans with care

access granted

As mental health conversations evolve, the necessary pivot becomes how organizations across Texas navigate improved ways to help people access the care they need before their challenges become crises.

That’s why Mental Health America of Greater Houston recently announced that it is expanding its Care Connect platform statewide.

The expansion will address perhaps the most persistent barrier to behavioral healthcare—helping people find and navigate services that already exist.

Care Connect’s extended reach comes at a time when more than 3.5 million adults in the state live with some kind of mental health condition and scores of those in need continue to struggle with accessing care despite the growing awareness of mental health needs.

According to President and CEO Renae Vania Tomczak, Care Connect’s main goal was to remove as many obstacles as possible that Texans face when seeking mental health support.

“Care Connect was about a two-year planning process,” Tomczak says. “It really began with asking what challenges people in the Greater Houston Area were facing regarding mental health. It’s not just accessing care, but the difficulty in navigating the mental healthcare system.”

While provider shortages remain a challenge in some communities, Mental Health America of Greater Houston found that many individuals and families struggle simply to determine where to turn, how to identify the right provider and whether services are affordable.

“We wanted to make it easier for people who have questions, who may never have had a mental health challenge before, or they’re a caregiver for somebody who has a mental health issue,” Tomczak says. “We wanted to be the place that people can come to get their questions answered and be connected to care.”

Care Connect combines a vetted network of more than 1,000 providers and services across Texas with personalized navigation support.

Searches generate care results based on insurance coverage, language preferences, ZIP code and clinical specialties.

Additionally, one-on-one guidance and follow-up support are provided by bilingual resource specialists.

The platform also seeks to address affordability, one of the most significant barriers to mental healthcare access. Through participating providers, eligible individuals can receive six to eight counseling sessions at no cost.

“We have several providers who are willing to provide six to eight counseling sessions at no cost for people who do not have the means to pay for services themselves,” Tomczak says.

When provider matches are unavailable, the organization can connect individuals with master’s-level mental health professionals working under the supervision of licensed clinicians.

The statewide rollout builds on the platform’s early success in the Houston region, where it has helped thousands of individuals connect with mental health resources since launching last fall.

According to Tomczak, the decision to expand was driven in part by growing demand from outside the organization’s traditional service area.

“Last month we decided to take this program statewide,” she says. “It’s not just Houston that can use help in connecting to appropriate mental health services, but the whole state.”

The Care Connect program’s promotion through healthcare providers, community organizations and public-sector partners across Texas is now one of Mental Health America of Greater Houston’s top priorities.

Their goal is to create a stronger referral ecosystem that ultimately helps those who need access to mental health care more quickly.

To facilitate that, the organization has also added free mental health screenings to its website so that users will better identify any symptoms related to anxiety, depression and other conditions.

“Once they do that, then where do they go?” Tomczak says. “They’re not sure who to call and who can help them. At that point, we hope they’ll call us and talk to somebody live who can answer their questions and help them get started on the right path to improving their mental health.”

With eyes on the future, Tomczak believes public understanding of mental health has improved in recent years, particularly following the COVID-19 pandemic, which brought new attention to the effects of stress, isolation and uncertainty.

“The more we talk about it and have the opportunity to share that mental health conditions are traceable, the better,” she says.

According to Tomczak, long-term, Care Connect aims to reduce roadblocks that exist between recognizing the need for help and receiving it.

Ultimately, Care Connect hopes to create a robustly connected behavioral health system that gives Texans the ability to access mental health services swiftly and with confidence.

“No one should have to navigate mental health challenges alone,” Tomczak adds. “Care Connect is here to help connect people with resources, services and answers to ensure they get the care they need to take the next step toward better mental health.”