FAU/Baptist Health AI spine model could transform lower back pain treatment

Florida Atlantic University

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Nearly 3 in 10 adults in the U.S. have experienced lower back pain in any three-month period, making it the most common musculoskeletal pain.

view more 

Credit: Florida Atlantic University

Nearly 3 in 10 adults in the United States have experienced lower back pain in any three-month period, making it the most common musculoskeletal pain. Back pain remains one of the leading causes of disability worldwide, affecting millions and often leading to chronic discomfort, missed work and invasive procedures.

Researchers and clinicians are increasingly turning to lumbar spine modeling, which bridges engineering and medicine, creating a virtual, patient-specific model of the lower back. This technology simulates how the spine moves, where mechanical stress builds up, and what might be causing pain or dysfunction.

These detailed models are used to plan surgeries, evaluate spinal implants and develop personalized treatment strategies tailored to each patient’s anatomy. Despite its promise, current lumbar spine modeling is slow, manual and demands specialized expertise, limiting scalability and personalization. This hinders clinical application and results in inconsistent outcomes.

Researchers from the College of Engineering and Computer Science at Florida Atlantic University and the Marcus Neuroscience Institute at Boca Raton Regional Hospital, part of Baptist Health, have reached a major milestone in lumbar spine modeling by integrating artificial intelligence with biomechanics to transform spine diagnostics and personalized treatment planning.

They are the first to create a fully automated finite element analysis pipeline specifically for lumbar spine modeling. Their breakthrough involves integrating deep learning tools like nnUNet and MONAI with biomechanical simulators such as GIBBON and FEBio.

Results of the study, published in the journal World Neurosurgery, show that this new approach reduced lumbar spine model preparation time by 97.9% – from more than 24 hours to just 30 minutes and 49 seconds – without compromising biomechanical accuracy. The fully automated pipeline enables rapid, patient-specific simulations that support preoperative planning, spinal implant optimization and early detection of degenerative spine conditions.

Tests showed that the virtual spine reacted just like a real one, with realistic disc movement, ligament tension and pressure in the back of the spine during bending and stretching. Because the system runs with very little manual work, it’s much faster and more consistent than traditional methods, making it a valuable tool for doctors and researchers alike.

“What sets our approach apart is its ability to automatically convert standard medical images like CT or MRI scans into highly accurate, patient-specific spine models,” said Maohua Lin, Ph.D., corresponding author and a research assistant professor, FAU Department of Biomedical Engineering. “Traditional manual methods require complex geometry processing, meshing and finite element simulation setup, making them not only time-intensive but also highly dependent on the operator’s expertise. Our automated pipeline significantly reduces the time required, cutting what once took several hours or even days down to just minutes.”

For the study, researchers used advanced AI to automatically identify important parts of the spine – like bones and discs – from medical scans. These were then turned into smooth 3D models that included bones, cartilage and ligaments. They mapped where the ligaments attach and shaped the cartilage based on common patterns. Lastly, researchers ran computer simulations to see how the spine responds to movements like bending and twisting, helping them understand where stress builds up and how the spine moves in real life.

“Beyond advancing research, automated lumbar spine modeling plays a critical role in preoperative planning,” said Frank D. Vrionis, M.D., corresponding author and chief of neurosurgery at Marcus Neuroscience Institute. “This technology quickly generates patient-specific models to predict mechanical complications, optimize implant design and reduce surgical risks. By removing manual steps, it also improves speed and consistency, helping clinicians make more informed decisions.”

This research builds upon previous work by the research team published in leading journals including Artificial Intelligence Review and the North American Spine Society Journal, investigating related AI-driven biomechanical modeling techniques.

“This groundbreaking work exemplifies the game-changing power of uniting engineering and medicine to address complex health care challenges,” said Stella Batalama, Ph.D., dean of the FAU College of Engineering and Computer Science. “FAU and Baptist Health researchers are not only pushing the boundaries of innovation, they are also delivering real-world solutions that can improve patient outcomes and redefine spine care.”

Study co-authors are Mohsen Ahmadi, a Ph.D. student in the FAU Department of Electrical Engineering and Computer Science; Xuanzong Zhang, an American Heritage High School student; Yufei Tang, Ph.D., an associate professor, FAU Department of Electrical Engineering and Computer Science and FAU Sensing Institute fellow; Erik Engeberg, Ph.D., a professor, FAU Department of Biomedical Engineering and Department of Ocean and Mechanical Engineering, a member of the FAU Center for Complex Systems and Brain Sciences within the Charles E. Schmidt College of Science, and a member of the FAU Stiles-Nicholson Brain Institute; and Javad Hashemi, Ph.D., inaugural chair and professor of the Department of Biomedical Engineering and associate dean for research, FAU College of Engineering and Computer Science.  

 This research was supported by Boca Raton Regional Hospital, part of Baptist Health, the Helene and Stephen Weicholz Foundation, the National Science Foundation, pilot grants from the FAU College of Engineering and Computer Science, the FAU Stiles-Nicholson Brain Institute, the FAU Center for Smart Health, and the FAU Sensing Institute.

- FAU -

About FAU’s College of Engineering and Computer Science:

The FAU College of Engineering and Computer Science is internationally recognized for cutting-edge research and education in the areas of computer science and artificial intelligence (AI), computer engineering, electrical engineering, biomedical engineering, civil, environmental and geomatics engineering, mechanical engineering, and ocean engineering. Research conducted by the faculty and their teams expose students to technology innovations that push the current state-of-the art of the disciplines. The College research efforts are supported by the National Science Foundation (NSF), the National Institutes of Health (NIH), the Department of Defense (DOD), the Department of Transportation (DOT), the Department of Education (DOEd), the State of Florida, and industry. The FAU College of Engineering and Computer Science offers degrees with a modern twist that bear specializations in areas of national priority such as AI, cybersecurity, internet-of-things, transportation and supply chain management, and data science. New degree programs include Master of Science in AI (first in Florida), Master of Science and Bachelor in Data Science and Analytics, and the new Professional Master of Science and Ph.D. in computer science for working professionals. For more information about the College, please visit eng.fau.edu. 

 

About Florida Atlantic University:

Florida Atlantic University serves more than 32,000 undergraduate and graduate students across six campuses located along the Southeast Florida coast. It is one of only 21 institutions in the country designated by the Carnegie Classification of Institutions of Higher Education as an “R1: Very High Research Spending and Doctorate Production” university and an “Opportunity College and University” for providing greater access to higher education as well as higher earnings for students after graduation. In 2025, Florida Atlantic was nationally recognized as a Top 25 Best-In-Class College and as “one of the country’s most effective engines of upward mobility” by Washington Monthly magazine. Increasingly a first-choice university for students in both Florida and across the nation, Florida Atlantic welcomed its most academically competitive incoming class in the university’s history in Fall 2025. For more information, visit www.fau.edu.

---

Journal

World Neurosurgery

DOI

10.1016/j.wneu.2025.124236 

Method of Research

Computational simulation/modeling

Subject of Research

People

Article Title

Automated Finite Element Modeling of the Lumbar Spine: A Biomechanical and Clinical Approach to Spinal Load Distribution and Stress Analysis

Article Publication Date

19-Sep-2025

 

Hot flashes can be reliably predicted by an ai-driven algorithm developed by UMass Amherst and Embr Labs

The algorithm will be incorporated into the next generation of Embr Labs’ wearable device to mitigate symptoms and provide meaningful relief

University of Massachusetts Amherst

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Current generation of the Embr Wave device that delivers a cooling sensation clinically proven to manage hot flashes.

view more 

Credit: Embr Labs

AMHERST, Mass. — University of Massachusetts Amherst researchers and scientists at Embr Labs, a Boston-based start-up, have developed an AI-driven algorithm that can accurately predict nearly 70% of hot flashes before they’re perceived. The work, featured in the journal Psychophysiology, will be incorporated into the Embr Wave, a wearable wrist device clinically proven to manage hot flashes.

 

In the U.S. alone, an estimated 1.3 million women transition into menopause annually, and 80% of women experience hot flashes — sudden feelings of intense heat, often radiating in the upper body. Most hot flashes occur during this transition, but half of women experience them for 7 years or more. The physiological response had, for decades, been considered more of a nuisance than a treatable condition by medical professionals. However, recent research has linked hot flash severity and related sleep disturbances to risk of cardiovascular disease.

 

“Hot flashes have been dramatically overlooked,” says Matt Smith, co-founder and CTO of Embr Labs. “Even 50 years ago, hot flashes were still considered to be psychosomatic. To our knowledge, our work is the first attempt to undertake a rigorous effort to achieve the prediction of hot flashes. This breakthrough discovery and the  publication of our findings are the result of incredibly deep data science that answers the question: "Is it possible to accurately predict a hot flash before a woman feels it?”

 

The answer is “yes,” and presents the opportunity to incorporate this science into the next version of the Embr Wave that already provides relief for women in menopause. Adding the predictive feature into its next-generation device means that hot flashes can be mitigated in real time.

 

“This study opens this door for real-time, closed-loop digital therapeutics to exist,” says Mike Busa, clinical professor and director of the Center for Human Health & Performance at the UMass Amherst Institute for Applied Life Sciences, and corresponding author on the paper. “Not every target has to be druggable. If we can detect hot flashes early, Embr has a wearable solution that might be able to mitigate symptoms and provide meaningful relief.”

 

This industry-academic partnership leverages the full breadth of both the university’s and Embr Labs' expertise, talent, and innovation to spur job creation, entrepreneurship and workforce development locally, regionally and across the state.

 

To develop the model, which accurately identified 82% of hot flashes and predicted nearly 70% of them, on average, 17 seconds before they were perceived, Busa’s team collected various physiological data points from peri- or postmenopausal women. They found that skin conductance, the amount of electricity that can be conducted by the surface of the skin, provided the best signal. While hot flashes are notorious for causing profuse sweating, the researchers found that even the initial, imperceptible increase in water and salt on the skin that accompanies the start of a hot flash was sufficient to predict an impending hot flash event.

 

The researchers then evaluated the peaks in skin conductance around a hot flash compared to self-report perception of a hot flash, as well as expert characterization of events that occur without being perceived by the test subject, such as when they are distracted or asleep.

 

“We went through a very rigorous tuning process and a lot of different permutations of different ways that you can examine the data,” says Busa. “The mathematical consequences of any one function really can impact the fidelity of what you’re able to see in that data,” particularly when considering the size of the time window around the peak event.

 

Next, they used a separate data pool that was not used to train the model to see which model had the best predictive capabilities. Their best model was able to identify 82% of hot flashes that occurred from 60 seconds before to 30 seconds after a hot flash was perceived by the study participants. When looking just at its predictive capacity, the model identified 69% of hot flashes 17 seconds, on average, before the onset of perceived symptoms.

 

Busa highlights that this academic-industry partnership keeps a constant eye on the practicality for the end-user. “We’re [creating this model] in a way that it goes beyond having the potential of only a retrospective research tool,” he says. “[Embr’s] wearable sensors have the potential to make real-time meaningful impacts on people’s lives, opposed to just creating a graph or chart that can be analyzed later.”

 

“The end goal of this collaboration, which started in 2019, was always focused on enabling a closed-loop solution that could predict hot flashes and then deliver cooling, using the thermal technology that Embr Labs has developed and the deep expertise of Mike and his team at the Institute for Applied Life Sciences,” Smith adds.

 

This research was supported by grants from the Massachusetts Life Sciences Center Women's Health Initiative, awarded to UMass Amherst, and the U.S. National Science Foundation to Embr Labs.

 

###

 

About the University of Massachusetts Amherst  

The flagship of the commonwealth, the University of Massachusetts Amherst is a nationally ranked public land-grant research university. Through our 10-year Strategic Plan, we seek to expand educational access, fuel innovation and creativity, share and use its knowledge, and steward our resources for the common good. Founded in 1863, UMass Amherst sits on nearly 1,450-acres in scenic Western Massachusetts and boasts state-of-the-art facilities for teaching, research, scholarship, and creative activity. The institution advances a diverse, equitable, and inclusive community where everyone feels connected and valued—and thrives, and offers a full range of undergraduate, graduate and professional degrees across 10 schools and colleges, and 100 undergraduate majors.  

 

About Embr Labs, Inc.

 

Embr Labs is the leading healthtech company addressing health conditions through the use of temperature. The company's technology delivers a new category of natural solutions to manage hot flashes, sleep issues, stress, and thermal discomfort. The company was founded at MIT and is backed by Bose Ventures, DigiTx Partners, Safar Partners, Esplanade Ventures, and Ghost Tree Partners. Embr Labs has won numerous awards, including the AARP Innovation in Aging Award, Time Magazine's Best Inventions, the iF Design Award and was named to CB Insights' Digital Health 150 and Fast Company’s Annual List Next Big Thing in Tech.

---

Journal

Psychophysiology

DOI

10.1111/psyp.70056 

Method of Research

Computational simulation/modeling

Subject of Research

People

Article Title

Hot Flash Prediction for the Delivery of Just-In-Time Interventions

Article Publication Date

18-Jul-2025

COI Statement

Nader Naghavi and Sonja Billes are former employees of Embr Labs. Ryan Turner and Sofiya Shreyer received consulting fees from Embr Labs. Matthew Smith is a current employee of Embr Labs.

 

Adverse event profiles following HPV vaccination in males

FAR Publishing Limited

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Adverse event reports following Gardasil and Gardasil 9 vaccination in male recipients were extracted from the VAERS database. Multiple disproportionality analysis methods identified positive signals and potential adverse events. This represents the first systematic safety assessment in male vaccine recipients, with findings that may inform decision-making and support vaccine confidence.

view more 

Credit: Jingyu Wang

The safety profile among male recipients of human papillomavirus (HPV) vaccination remains a critical evidence gap. Adverse events following immunization (AEFIs) reported by male recipients of either Gardasil 9 or Gardasil were included from the US Vaccine Adverse Event Reporting System database. Four disproportionality algorithms were employed to identify positive signals. The temporal distribution of AEFIs was further examined to support Weibull distribution modelling and to estimate cumulative incidence patterns associated with each vaccine. Furthermore, stratified analyses should be performed by age and outcomes. Disproportionality analysis identified 35 positive signals for Gardasil 9, including 20 previously unreported, and 56 for Gardasil, of which 32 were novel. Most AEFI reports occurred within 30 days post-vaccination. The cumulative incidence of AEFIs was lower with Gardasil 9 than with Gardasil. This study presents the first systematic safety evaluation of Gardasil 9 and Gardasil in male recipients, addressing a key evidence gap. Gardasil 9 showed a potentially more favourable safety profile than Gardasil. These findings may strengthen confidence among the public and providers, inform clinical and policy decisions, and support global immunization efforts. Identified positive AEFIs warrant prospective validation to determine their clinical significance.

---

DOI

10.1002/imm3.70006 

 

Community management effectively protects millions of hectares of Amazonian forest

University of East Anglia

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

A team of local fishermen involved in both annual fish counts and collectively guarding community-managed lakes at the critical time of the year. 

view more 

Credit: Edimar Costa / Instituto Juruá

New research reveals “unprecedented” conservation results of community-based management of protected areas in the Amazon - as many face a future in which they may become increasingly degraded due to low enforcement of regulations, growing external encroachment and competition for resources.

The study describes a powerful new mechanism for increasing the extent of effective area-based protection by piggybacking on community management of natural resources.

Tropical protected areas are typically understaffed, underfunded and underequipped and it remains unclear how existing ones can be feasibly implemented under conditions of scarce financial resources, as well as hostile political climates.

The historical expansion of traditionally designated protected areas is also coming to a halt, just when commitments to global targets to protect 30% of the planet for nature by 2030 - known as ‘30x30’ - are renewed, as agreed at the Kunming-Montreal Global Biodiversity Framework of the Convention on Biological Diversity (CBD) three years ago.

Publishing their findings in Nature Sustainability, a team of researchers from Brazil and the UK says one option would be to boost Other Effective Area-Based Conservation Measures (OECMs), which are defined as areas managed in ways that achieve positive and sustained biodiversity conservation outcomes. 

The team, from the Instituto Juruá (Brazil), University of East Anglia (UK), Universidade Federal de Alagoas (Brazil) and Instituto Nacional de Pesquisas da Amazonia (Brazil), investigated the positive conservation results from community-based management of fisheries along a 1,200-km section of the Juruá River, a major tributary of the Amazon in the state of Amazonas, Brazil.

The study shows that by combining all zones of either direct or incidental protection, each community in fact protects a total area of floodplain and upland forest that is nearly 86 times larger than the total dry-season area of oxbow lakes sustaining local arapaima populations. For the state of Amazonas alone, 15 million hectares of floodplain forest have been protected in this way.

Professor Carlos Peres, from UEA’s School of Environmental Sciences and a senior author on the paper, said: “This study clearly demonstrates the effectiveness of empowering local management action by stakeholders who have the greatest interest and a 24-7, year-round presence where conservation battles are being won or lost.

“The conservation dividends from community-based protection are unprecedented and deployed at a tiny fraction of the financial costs of traditional protection mechanisms. In practice, this makes local land managers true ‘unsung heroes’ in the cacophony of theoretical conservation discourse.”

Through locally coordinated enforcement and active surveillance, local communities in the western Brazilian Amazon mount concerted efforts to protect oxbow lakes, where commercially valuable fisheries are managed, against exploitation by outsiders.

These communities then benefit from an annual windfall in sales of sustainably harvested fish, accrued from the local harvesting of protected populations of key resources, which also boosts populations of several other non-target co-occurring species that have been historically overexploited, such as giant otters, manatees, and giant Amazon River turtles.

The study authors call for more recognition and financial support for these crucial conservation efforts, which play a significant role in protecting the vast Amazon biome. Without adequate support, they warn the long-term sustainability of this model - dependent on unpaid labour and costs borne by communities - may be uncertain.

Dr Ana Carla Rodrigues from Universidade Federal de Alagoas led the study. She said: “We have shown how Amazonian community-based management can protect vast areas across one of the planet's most complex and vital biomes. The community-led systems safeguard biodiversity at an impressive scale, despite bearing a heavy social and economic burden.

“Recognizing the vital role local people play in protecting the Amazon rainforest and supporting local communities are essential for long-term conservation and a crucial matter of social justice."

The team analysed data on the costs and benefits of collective protection efforts by local communities over 96 protected lakes located along the Juruá River, which were on average 47.4 ha in size. These lakes were under the direct jurisdiction and stewardship of 14 rural communities and hosted a population count of approximately 109,000 adult arapaima.

They also surveyed both the extent and cost of protection beyond lakes alone, including the adjacent flooded forests and upland terra firme forest areas that are safeguarded by community patrols. These additional areas, functionally linked to lake ecosystems and key for species’ life cycles, expand the overall conservation footprint dramatically.

Currently, the costs of protecting these areas are borne entirely by community members, covering expenses such as fuel and food for volunteer rangers - without any compensation for their work. However, implementing fair compensation schemes such as Payments for Environmental Services (PES) would remain significantly more cost-effective than conventional protected area enforcement strategies.

Dr João Vitor Campos-Silva, a Co-Director of Instituto Juruá and a co-author on the study, added: “Currently, six million people in the Brazilian Amazon depend directly on wild nature. By explicitly including local dwellers into conservation practices, we can both increase the effectiveness of conservation outcomes and enhance local welfare.”

The team hopes its evidence will help persuade governments that supporting local conservation is both extremely good value for money and critical to successful ecological and conservation programmes.

‘Community-based management expands ecosystem protection footprint in Amazonian forests’ is published in Nature Sustainability on September 19.

A local fisherman paddling a large dugout canoe after a successful fishing trip into one of the community-managed lakes protected by his community. 

Credit

Andre Dib / Instituto Juruá

Local community member engaged in Community-Based Management (CBM) carrying a large wild-caught Arapaima fish. 

Credit

Hugo CM Costa / Instituto Jurua

Journal

Nature Sustainability

DOI

10.1038/s41893-025-01633-6 

Article Title

Community-based management expands ecosystem protection footprint in Amazonian forests

Article Publication Date

19-Sep-2025

Consuming more legumes and less red and processed meat may have a surprisingly positive impact on men’s health

University of Helsinki

Facebook

XLinkedInWeChatBluesky
Email

A University of Helsinki study found that partially replacing red and processed meat with pea- and faba bean–based foods resulted in reduced total and ‘bad’ LDL cholesterol levels in men, along with weight loss.

On average, men consume significantly more red and processed meat than is recommended, and more than women do. The high nutritional value of legumes makes them well suited to replacing meat. However, they do not naturally contain vitamin B12, which is found in animal-derived foods. The BeanMan study investigated how partially replacing red and processed meat with legumes thriving in Finnish conditions affected men’s health and levels of critical micronutrients in the blood.

In the study, 102 working-age men were divided into two groups. For six weeks, one group ate 760 grams of red and processed meat a week, that is, the average amount consumed by Finnish men. This accounted for one-quarter of total protein intake. 

Throughout the study, the other group’s diet included a substantial proportion of foods based on peas and faba beans, constituting 20% of total protein intake. In addition, the group members ate 200 grams of red and processed meat per week, comprising 5% of total protein intake. This corresponds to the recommended upper limit for red meat consumption in the planetary health diet. 

While the participants otherwise continued to follow their own diet, they consumed no red or processed meat or legumes other than the foods supplied as part of the study. Red meat encompassed beef and pork, while processed meat comprised sausages and cold cuts made from the same. 

The men who ate a large amount of pea- and faba bean–based foods alongside meat during the study lost an average of one kilo in weight, whereas those who ate only meat dropped just 300 grams.  The results indicate that eating more legumes and less red and processed meat reduces total and LDL cholesterol levels andthe risk of cardiovascular disease and type 2 diabetes, and may support weight management.

The positive change in blood cholesterol levels was expected for the legume group due to the enhanced quality of fat consumed. However, the researchers were surprised by the weight loss. 

“In a trial setting, participants often monitor their eating more closely, which may contribute to weight loss. But in this study, despite its relatively short duration, the legume group lost significantly more weight than the meat group. We didn’t encourage the participants to lose weight, but asked them to continue eating as before, apart from consuming the foods we provided,” says Professor of Molecular Nutrition Anne-Maria Pajari of the Faculty of Agriculture and Forestry.

Partially replacing meat does not jeopardise critical nutrient intake

While cutting back on red meat reduced vitamin B12 intake in the legume group, the status of this vitamin remained at a safe level by the end of the study. Moreover, dietary iron intake was higher for the legume group, whereas no difference was observed between the groups in iodine intake. 

“In the short term, critical nutrient intake wasn’t jeopardised in the legume group. This was likely because the participants remained on mixed diets, rather than cutting out any foods entirely. However, research is needed on the effects of switching to plant-based diets on the body’s nutritional status, particularly in vulnerable population groups, such as children and older adults,” states Pajari. 

She notes that the legume group participants followed their diet successfully even though it included more legumes and less red meat than typically recommended. 

“The legume food products we provided were quick to cook, making them easy to use. We also handed out recipes to encourage cooking. Based on our findings, I believe a moderate dietary change towards a more sustainable direction, using peas, beans and lentils, is possible for most of us,” she says, delighted.

The BeanMan study was conducted as part of the soon-to-conclude, multidisciplinary Leg4Life (Legumes for Sustainable Food System and Healthy Life) project, funded by the Research Council of Finland’s Strategic Research Council. The study’s previously reported findings demonstrated that eating more legumes and less red and processed meat is safe for both bone health and amino acid intake. Results on intestinal health will be published later.

---

Journal

European Journal of Nutrition

DOI

10.1007/s00394-025-03783-x 

Article Title

Nutritional and health benefits of a partial substitution of red and processed meat with non-soy legumes: a 6-week randomized controlled trial in healthy working-age men