The solution alerts caregivers in the event of unstable gait, allowing rapid intervention.
Trials at local health facilities are described as promising.
SINGAPORE, January 3, 2024 /PRNewswire/ — Applying AI technology to one of the biggest concerns in patient safety, Nanyang Polytechnic (NYP) and local medical technology company Longway AI Technologies have developed a system capable of analyzing human steps and make recommendations to health professionals so that they can provide assistance before a fall occurs.
In Singapore, data indicates that a third of people aged 65 and older have experienced a fall at least once, with 40 percent of these falls responsible for injury-related deaths. 30 percent of these people will experience recurrent falls. Older adults are more likely to fall for physical or medical reasons, and a change in gait is a critical early sign of a potential fall.
In the United States, an article published last year by the Centers for Disease Control and Prevention (CDC) notes that mortality increases among older people (over 65 years) in the event of a fall.[1]. A study from the Ministry of Health here at Singapore showed that patients suffering from a hip fracture also have adverse consequences: one year after the fracture, mortality is between 20 and 27 percent. Among survivors, 20 percent become semi or fully dependent, and 39 percent report having reduced mobility.[2].
Explains Dr. Phua Chee Teakdirector of the NYP School of Engineering: “We are essentially teaching the system to recognize unstable gaits. The AI then takes over monitoring and must autonomously decide whether the instability has reached a trigger point, such that someone should be alerted.”
During the development phase, the AI system was trained with over 200 hours of videos divided into two phases. The pre-training phase saw the system analyze over 200,000 open source videos covering training, testing and validation. In the second phase, the AI model was refined with more than 300 videos for every type of human activity – including basic activities like getting up, sitting down and taking short walks – to enable the system to understand the biomechanical movements associated with unstable gaits. .
This was achieved by leveraging the 3D Convolutional Neural Network (3DCNN) – an AI method that teaches the computer to process data in a way modeled by the human brain and nervous system. Using deep learning, a machine learning process that uses interconnected nodes or neurons in a layered structure that resembles the human brain, the AI system was programmed to respond based on the movement of different joints at based on a human skeleton model. And when the system detects specific movements with higher probabilities of leading to a fall, it sends the relevant signals to the nearby healthcare team.
Dr Phua adds: “The secret sauce is getting the training right – making sure you don’t cause unnecessary alarm with false cases and being able to actually trigger healthcare professionals if the event is predicted with high certainty. »
Since the system was developed at the school’s Center for Innovation for Electronics and Internet of Things (COI-EIoT) in 2020, various pilot trials have been conducted with partners including the General Hospital of Singapore (SGH) and St. Luke’s ElderCare Rivervale Center:
I. The AI system was able to help healthcare staff prioritize specific patients for immediate acute care in the A&E.
ii. The system allowed St. Luke’s to monitor approximately 40 seniors within the facility, helping to optimize workforce deployment.
Currently, an improved system has been deployed and tested at SASCO Nursing Home on the West Coast. NYP is also in discussions with St. Andrew’s Nursing Home (Queenstown), to deploy the system at their premises and explore how it can assist in other areas of their residential care. Derrick NgSenior Director of Operations at St. Andrew’s Nursing Home (Queenstown), said: “We are excited to explore the system using real-time data and predictive insights so we can further improve our residential care in different areas .
Damien Ooi, Head of Center Management at SASCO Senior Citizens’ Home, said: “We believe NYP’s AI solution will be instrumental in improving our care for older people. Their innovative approach will not only contribute to immediate assistance, but will also contribute significantly to our overall health. Through this pilot project, we hope to better understand and anticipate the needs of our seniors and provide rapid assistance to prevent falls.
NYP is also exploring collaborations with geriatric departments at several hospitals, with the aim of broadening the impact of this technology in the healthcare sector.
About Nanyang Polytechnic
Established as a higher education institution in 1992, Nanyang Polytechnic (NYP) academic schools provide quality education and training through 40 full-time diploma courses and common entry programs. NYP also offers a full range of Continuing Education (CET) options for lifelong learning, from specialist and advanced diplomas to modules and courses supported by SkillsFuture. The Asian Culinary Institute of New York and the Singapore Institute of Retail Studies are CET institutes established in partnership with SkillsFuture Singapore (SSG) to champion and transform that of Singapore F&B and retail sectors, respectively. A third NYP CET institute – the National Center of Excellence for Workplace Learning – also established in collaboration with SSG, will spearhead the development of progressive workplace learning strategies and programs for businesses across the country.
Show original content:https://www.prnewswire.com/apac/news-releases/artificial-intelligence-helps-predict-falls-creating-safety-system-for-patients-302025174.html
SOURCE Nanyang Polytechnic
