Connect with us

Technology

AI Predicts PTSD Risk Based on Stories About What Brought Patients to the Emergency Room

Published

on

NEW YORK, Nov. 9, 2026 /PRNewswire/ — An AI tool can analyze patients’ narratives about injuries that sent them to the emergency room to predict who will later develop post-traumatic stress disorder (PTSD), a new study found.

“PREVIA could open a window for timely care approaches, when preventive intervention is most effective.”

About 43 million patients are admitted to a US emergency department (ED) each year with physical injuries (trauma), and more than a quarter of them develop PTSD, according to past studies. That makes the ED a checkpoint for catching the condition early, but clinicians face time constraints severe enough to rule out the use of standard screening questionnaires.

Led by NYU Langone Health researchers, the new study found that the team’s set of AI models — each analyzing the trauma narratives of 145 ED patients — correctly identified more than 95.4 percent of at-risk patients. In a head-to-head test, the AI tool, called PREVIA, flagged 100 percent of 30 cases from the same patient group that went on to develop PTSD, while an ED clinician specializing in PTSD correctly identified 89 percent of these cases.

“This is the first study to show that a patient’s spontaneous answers to a single, routine care question — ‘What brought you to the ED?’ — carries enough of a psychological signal to forecast their PTSD risk a month later,” said senior study author Katharina Schultebraucks, PhD, associate professor in the departments of psychiatry and population health at NYU Langone. “PREVIA can serve as an AI screener that identifies at-risk patients and explains why, without adding any time to intake in busy emergency rooms.”

Published online November 9 in Nature Communications, the new work examined the capabilities of generative AI, which predicts options for the next word in a sentence based on how billions of people used that word in context. This sensitivity to language lets the models analyze a person’s description of what happened to them to find patterns linked to their risk of developing PTSD, the researchers said. The patients’ answers were recorded and transcribed for analysis.

“The emergency department is often the only point of contact a trauma survivor has with the healthcare system before symptoms become much harder to treat,” added Dr. Schultebraucks, who is also co-director of computational psychiatry at NYU Grossman School of Medicine. “By identifying at-risk patients at that first encounter, PREVIA could open a window for timely care approaches, when preventive intervention is most effective.”

The first month after trauma is a key window for finding those at risk for PTSD because many patients are no longer in contact with the hospital after that, the researchers said. Current questionnaires — such as the Peritraumatic Dissociative Experiences Questionnaire and the Posttraumatic Adjustment Scale — effectively forecast PTSD development, yet only about 28 percent of EDs routinely screen for PTSD at all, and only two-thirds of those use validated tools.

This likely reflects overcrowding and limited clinician time, typically about 15–20 minutes per patient, which forces clinicians to prioritize immediate medical concerns over lengthy mental health assessments, the study authors said.

PREVIA was designed as a pipeline of steps that use different AI tools based on their strengths (e.g., the Llama model tends to emphasize signs of PTSD risk, while Mistral highlights protective and contextual factors that could buffer against it). Specifically, the tool’s first layer scans the language of a patient’s narrative for symptoms that happen during the initial trauma, like loss of control or amnesia, as well as early symptoms that show up while a person is in the ED, such as feeling disconnected from the body. Both types of symptoms have been linked to later PTSD development.

The second layer of the team’s AI tool also weighs risk factors such as pre-existing mental health problems or lower socioeconomic status, alongside protective factors such as coping skills or strong social support. A third AI model synthesizes these assessments into a structured summary, reducing the chance that any single model dominates the results. A final layer combines that summary with demographic information (e.g., age, sex), trauma type, and known PTSD prevalence rates to produce a risk score with a plain-language explanation.

Experiments confirmed that this three-layer design consistently outperformed simpler configurations across most performance metrics. Unlike AI that succeeds or fails for reasons unknown, PREVIA explains its reasoning and grounds predictions in established PTSD risk factors. Results with the tool were also validated by comparing them to diagnoses made for the same cases using Clinician-Administered PTSD Scale for DSM-5 (CAPS-5), the gold standard clinical interview for diagnosing PTSD.

“We built PREVIA on open-source models with no training or fine-tuning required,” said Dr. Schultebraucks. “That means other hospitals can test it independently, without access to proprietary software or our patient data, which is essential for widespread adoption.”

Along with Dr. Schultebraucks, authors of the study from NYU Langone were Victoria Mueller, Jyoti Yadav, Annie Farnsworth, Charlotte Hilberdink, Sapir Gershov, and Arieh Shalev in the Department of Psychiatry, Eric Oermann in the Department of Neurosurgery, and Stephen Wall in the Ronald O. Perelman Department of Emergency Medicine.

The study was funded by the National Institute for Mental Health grant R01 MH129856 (PI Dr. Katharina Schultebraucks).

About NYU Langone Health
NYU Langone Health is a fully integrated health system that consistently achieves the best patient outcomes through a rigorous focus on quality that has resulted in some of the lowest mortality rates in the nation. Vizient Inc. has ranked NYU Langone No. 1 out of 118 comprehensive academic medical centers across the country four years in a row, and “U.S. News & World Report” recently ranked four of its clinical specialties No. 1 in the nation. NYU Langone offers a comprehensive range of medical services with one high standard of care across seven inpatient locations, its Perlmutter Cancer Center, and more than 330 outpatient locations in the New York area and Florida. The system also includes two tuition-free medical schools, in Manhattan and on Long Island, and a vast research enterprise.

Media Inquiries:
Gregory.Williams@NYULangone.org 

View original content to download multimedia:https://www.prnewswire.com/news-releases/ai-predicts-ptsd-risk-based-on-stories-about-what-brought-patients-to-the-emergency-room-302926212.html

SOURCE NYU Grossman School of Medicine and NYU Langone Health

Continue Reading

Technology

WIRobotics and Ottobock Join Forces to Expand Access to Wearable Robots Across North America

Published

on

By

The Distribution agreement covers the United States and Canada, with sales through the partnership to begin in the U.S.WIM S is available to U.S. consumers online through Ottobock’s direct-to-consumer platform and WIRobotics USA’s online store.U.S. consumers will be able to try WIM S at select orthotic and prosthetic clinics.

SEOUL, South Korea, Nov. 16, 2026 /PRNewswire/ — WIRobotics, a global robotics company led by Co-CEOs Younbaek Lee and Yongjae Kim, announced that its U.S. subsidiary, WIRobotics USA Inc., signed a distribution and sales agreement with Otto Bock HealthCare LP on October 15. Under the agreement, WIRobotics USA will supply WIM S, the company’s wearable mobility robot, and Ottobock will serve as a distribution partner in the United States and Canada.

The partnership will begin in the United States, where consumers will be able to purchase WIM S online through Ottobock’s dedicated direct-to-consumer online platform and WIRobotics USA’s online store, and try the robot initially at select orthotic and prosthetic (O&P) clinics. Based on customer feedback, the companies will consider offering hands-on experiences at more U.S. locations and extending sales through the partnership to Canada. 

The partnership brings together WIRobotics’ wearable robotics technology and Ottobock’s more than 100 years of experience in human mobility. Founded in Germany in 1919, Ottobock has established distribution, clinical care and service networks in the United States and Canada. The companies plan to collaborate on market development, brand building, product training and after-sales service, with WIRobotics USA supporting training and service operations locally.

The agreement marks a major step in WIRobotics’ global expansion. Now in its third year of commercialization, WIM has surpassed 4,000 units in cumulative sales, and the company has expanded sales beyond South Korea to markets including Europe, China and Japan. WIRobotics has been accelerating its international business, with the United States and Canada as key strategic markets. To support this growth, the company established WIRobotics USA Inc. under General Manager Jacob Kim to build local operations in North America.

The companies also see significant opportunities to extend their collaboration to WIM Medi, which WIRobotics is developing for medical use. They view WIM Medi as a natural next step for the partnership, with entry into U.S. and Canadian medical and rehabilitation channels to follow applicable regulatory authorization and a separate agreement.

“Our goal is to make wearable mobility technology easier for people to experience and integrate into everyday life,” said Younbaek Lee, co-CEO of WIRobotics. “Working with Ottobock gives us an opportunity to introduce WIM S to more people across North America. We will expand our engagement with customers in the region and strengthen WIM’s global business foundation.”

“At Ottobock, we are committed to helping people maintain mobility and independence through innovative solutions that support an active lifestyle,” said Scott Schneider, Head of Government/Medical Affairs & Future Development at Ottobock. “WIRobotics is an exceptional company whose technology closely aligns with that vision. Through this partnership, we look forward to introducing WIM S to consumers across North America, beginning with a focused U.S. launch, while exploring new ways for people to experience wearable mobility technology firsthand.“

About WIRobotics
WIRobotics is a global robotics company that develops wearable mobility robots designed to help people move more freely in everyday life. Its WIM series is sold in South Korea and international markets.  Through the development of its ALLEX humanoid robot, the company is also expanding into humanoid robotics and Physical AI. In May 2026, the company raised KRW 95 billion (approximately USD 68 million) in Series B funding to accelerate its global expansion and the commercialization of its robotics technologies. Headquartered in South Korea, the company operates in North America through WIRobotics USA Inc. For more information, visit https://usa.wirobotics.com

About Ottobock
Ottobock, a listed global MedTech champion, combines over 100 years of tradition with outstanding innovative strength in the fields of prosthetics, neuro-orthotics and exoskeletons. Ottobock develops innovative fitting solutions for people with limited mobility and is driving the digitalization of the industry. Founded in Berlin in 1919, the company has business activities in 45 countries with nearly 9,300 employees (FTEs) worldwide and operates the largest international patient care network with more than 430 patient care clinics. Ottobock is shaping the future of human bionics with a strong R&D ratio in the products and components business and over 2,600 patents and patent applications. Ottobock’s mission of improving freedom of movement, quality of life and independence is deeply rooted in the company’s DNA, as is its social commitment: Ottobock has been a partner and supporter of the Paralympics since 1988.

 

View original content to download multimedia:https://www.prnewswire.com/news-releases/wirobotics-and-ottobock-join-forces-to-expand-access-to-wearable-robots-across-north-america-302939726.html

SOURCE WIRobotics

Continue Reading

Technology

Ekinops unveils PTM300 compact modular platform for ultra-high-capacity datacenter connectivity

Published

on

By

New 3RU* optical platform delivers up to 32 Tb/s capacity with ultra-low power consumption per bit,  open management and multi-vendor interoperability

PARIS, Nov. 16, 2026 /PRNewswire/ — Ekinops (Euronext Paris – FR0011466069 – EKI), a leading provider of optical networks, connectivity and SASE cybersecurity solutions for telecom service providers and enterprises, today announces the release of PTM300, a new compact modular optical platform designed for high-capacity datacenter interconnect (DCI) and scale-across optical networking applications.

Designed to bring carrier-class optical transport into a datacenter form factor, PTM300 delivers up to 32 Tb/s of client and line capacity in just 3RU, supporting up to 40 x 800 Gb/s coherent pluggable interfaces.

The platform combines ultra-high density and ultra-low 0.08W per Gbps (watts per gigabit per second) power consumption with redundant power and cooling, front-to-back airflow, and Open management interface based on Openconfig and Netconf/Yang for easy integration into open, standards-based environments. It is also compatible with Ekinops’ Celestis NMS for unified network management within an Ekinops optical network further simplifying integration.

With PTM300, Ekinops is extending its optical networking portfolio to address increasing interconnection bandwidth requirements between datacenters with compact modular platforms that seamlessly enable the transition from the telco environment.

High density without compromising openness and performance

PTM300 can be deployed over direct fiber, existing Ekinops optical line systems or third-party infrastructure using alien wavelengths. Beyond DCI, it is designed to address metro, regional and long-haul transport applications as well as service regeneration for router-hosted IPoWDM applications.

*RU = Rack Unit

“The rapid growth of cloud and AI is creating unprecedented bandwidth requirements between data centers, as well a greater demand for service providers to deliver wavelength services to these locations. With PTM300, we are bringing together ultra-high capacity, ultra-low power consumption, operational simplicity and openness in a compact platform designed to help operators scale their optical networks while protecting existing infrastructure investments,” said Philippe Moulin, Chief Operating Officer of Ekinops.

PTM300 will be generally available in December 2026 with first customer deployments expected in Q1 2027.

All press releases are published after Euronext Paris market close.

Ekinops contacts

Lionel Chmilewsky, CEO
contact@ekinops.com

Mathieu Omnes, Investor relation
Tel.: +33 (0)1 53 67 36 92
momnes@actus.fr

Amaury Dugast, Press relation
Tel.: +33 (0)1 53 67 36 74
adugast@actus.fr

For more information, visit https://www.ekinops.com/

View original content to download multimedia:https://www.prnewswire.com/news-releases/ekinops-unveils-ptm300-compact-modular-platform-for-ultra-high-capacity-datacenter-connectivity-302940614.html

SOURCE Ekinops

Continue Reading

Technology

Aviemore Launches Seal-Less Magnetic Coupling Pump Platform for Liquid-Cooled AI Data Centers

Published

on

By

Integrated pump, motor and drive built for 800 VDC power and megawatt-class AI racks

CHICAGO, Nov. 16, 2026 /PRNewswire/ — Aviemore Motion Technologies today introduced its seal-less magnetic coupling pumps for liquid-cooled AI and high performance computing at SC26 in Chicago, the international conference for high performance computing. The patent-pending design eliminates the shaft seal, the most common point of wear in a coolant pump. Aviemore delivers the pump, motor and drive as one complete system under a single part number.

Seal-less magnetic coupling pumps with integrated drive, built in Virginia for 800 VDC AI and data center cooling.

AI racks draw 140 kW today. Racks of 240 kW are close behind and 600 kW to megawatt-class racks are in future planning. Power inside the rack is also moving from 54 VDC to 800 VDC, with the first commercial systems expected to ship in Q2 2027. Cooling units built for these racks need pumps that run nonstop, fit in tight spaces and connect directly to high-voltage DC power. Aviemore built its platform for that paradigm shift.

Nearly every watt an AI processor uses turns into heat. Removing that heat is one of the biggest jobs in a data center. Liquid cooling does it far better than air, and the pump is what keeps the coolant moving. Rack and row cooling loops are closed systems. The same coolant circulates over and over instead of being used up, which helps operators cut the water and energy spent on cooling. With no shaft seal, an Aviemore pump keeps that loop closed.

“Liquid cooling is now critical infrastructure and the pump is the one moving part every rack depends on,” said Moe Barani, CEO of Aviemore. “Most pumps on the market were designed for another era and adapted for the data center. We designed ours for where AI infrastructure is going. There is no seal to leak or wear out, the drive runs natively on 800 VDC and our team can turn a custom change in weeks instead of quarters.”

How it works

Aviemore pumps transmit torque through a magnetic coupling across a non-contact sealed barrier. Nothing passes through the wet end. There is no dynamic seal and no wear item in the fluid path. The pumps can run dry during commissioning or a loss of prime, two common causes of early pump failure. A slotless brushless DC motor and integrated drive complete the assembly. CDU builders source, qualify and service one component instead of three.

The platform covers 0.10 to 5.0 kW of output across a 12 to 800 V DC bus range.

Most pumps in data center cooling today come from legacy manufacturers that adapted designs built for other industries. They still rely on a shaft seal, a bolt-on motor and a third-party drive. Their development cycles are measured in years while AI rack designs change every year.

“The traditional pump industry is full of dinosaurs,” said Matt Carroll, VP of Engineering at Aviemore. “They are still selling the same seal, the same separate motor and the same slow change process. Data center operators are left to design around it. We started from a clean sheet. The seal is gone and the motor and drive are built in. When a customer needs a change, our engineering team turns it in weeks.”

Product lines

Rack CDU Pumps: 0.10 to 2.0 kW, 12 to 800 V DC, AC and DC drive, for in-rack and sidecar CDUsRow and Facility Pumps: 1.0 to 5.0 kW, 12 to 800 V DC, AC and DC drive, for row CDUs, coolant skids, and facility loopsOEM Custom Solutions: co-engineered and built to the customer’s architecture, with AC and DC drive options

Proven motor technology, built in Virginia

The Aviemore team has worked together for more than 25 years and has deep experience in data center thermal hardware. Its proprietary slotless motor design has shipped in more than 15,000 motors with zero motor defects. The team has been designing proprietary, patented pumps for the past 20 years and those products remain in service at hyperscale operators today.

Aviemore designs and builds its pumps in a 156,000 square foot facility in Radford, Virginia. Winding, machining, assembly and test all happen in house, which is how the company turns design changes in weeks. The quality system is built on ISO 9001 and products are UL and Intertek certifiable on request.

Data centers are often criticized for bringing few jobs to the towns that host them. Much of the hiring happens in the supply chain that builds the equipment inside. Every Aviemore pump is designed and built in Radford. That supports skilled engineering and manufacturing jobs in Southwest Virginia, and the team grows as AI demand grows.

Aviemore works with Intertek on testing and certification and with Virginia Tech on research. It also partners with the Virginia Economic Development Partnership and GO Virginia on regional industry growth.

Meet Aviemore at SC26

Supercomputing was one of the first fields to adopt direct liquid cooling. The rack densities HPC pioneered are now reaching AI data centers. The Aviemore team is at SC26 in Chicago this week to meet with HPC system builders, thermal engineers and CDU manufacturers. To schedule time or get a pump sized, contact info@aviemoretech.com.

About Aviemore

Aviemore Motion Technologies LLC designs and manufactures seal-less magnetic coupling pumps for liquid-cooled AI and data center infrastructure. Each pump combines the hydraulics, a slotless BLDC motor and an integrated drive in a single assembly. The range covers 0.10 to 5.0 kW and DC bus voltages up to 800 V. Aviemore is headquartered in Radford, Virginia. Learn more at aviemoretech.com.

Media Contact
Ben Khandan-Barani, COO
Aviemore Motion Technologies
info@aviemoretech.com | 540-922-9631
113 Corporate Drive, Radford, VA

View original content to download multimedia:https://www.prnewswire.com/news-releases/aviemore-launches-seal-less-magnetic-coupling-pump-platform-for-liquid-cooled-ai-data-centers-302939792.html

SOURCE Aviemore Motion Technologies

Continue Reading

Trending