Singapore develops AI for predicting diabetes amputation riskSingapore General Hospital, SingHealth, and the Ministry of Health Office for Healthcare Transformation have developed an AI model intended to predict lower extremity amputation risk in patients with diabetes three to five years before foot ulcers and infections develop.The LEA-Neural Network Model (LEA-Net) uses anonymised data from more than 830,000 SingHealth patient records, including demographics, clinical conditions, and medical test results, to classify patients into low- and high-risk groups and support earlier referral or intervention.A media release noted that the model recorded nearly 80% sensitivity and close to 90% specificity in a validation study using 250,000 patient records.The research team is looking to further validate the AI model through a pilot study involving patients from SingHealth's Diabetes Registry.NHG Health, Fourier expand rehab robotics partnershipNHG Health and Fourier Rehab have signed a five-year memorandum of understanding to expand collaboration on rehabilitation robotics and AI-enabled technologies following an earlier partnership on clinical rehabilitation initiatives.According to a press statement, the new agreement involves establishing a joint rehabilitation innovation hub, called RehabHub, and co-developing and validating rehabilitation and assistive robotic technologies for inpatient, outpatient, and transitional care settings.The expanded collaboration builds on an initial MOU in 2021 and a Master Research Collaboration agreement a year later, under which selected Fourier rehabilitation technologies were deployed and evaluated for rehabilitation services at Tan Tock Seng Hospital.ICMR ties up with IndiaAI The Indian Council of Medical Research (ICMR) has signed an MOU with the IndiaAI Mission under the Ministry of Electronics and Information Technology to advance responsible AI in healthcare in India.Based on a LinkedIn post, the collaboration will support the development and operationalisation of the health datasets vertical on AIKosh using the MIDAS framework, including the use of the MIDAS Rubric to assess dataset quality, and the provision of anonymised datasets, metadata, documentation, and annotation guidelines by ICMR/the Indian Institute of Science and supported investigators.It also covers high-performance CPU/GPU compute, storage, and secure sandboxed environments for authorised users, alongside workshops, hackathons, and policy roundtables.