Yonsei University Health System

A new deep learning-based model developed in South Korea has shown potential to reduce the time it takes to identify causes and predict risk factors of brain and spinal infections. Researchers from the Yonsei University Health System (YUHS) teamed up on a Hyundai Motor foundation-backed project to develop and test an AI model for diagnosing and prognosing central nervous system (CNS) diseases, such as encephalitis and meningitis. FINDINGS They trained their AI model on nearly 1,500 3D images of cerebrospinal fluid (CSF) immune cells collected from 14 patients who presented with CNS infections at Severance Hospital. The team claimed to be the first to utilise 3D cell images and analyse cell morphology in the diagnosis and prognosis prediction of brain and spinal infections. In a study evaluating the AI model, the researchers found that its predictive performance increased in accuracy as more cell images were run through it. Initially, running one cell image showed 89% accuracy in identifying the cause of infection and 79% accuracy in predicting the disease's likely course. Feeding five cell images, the accuracy of causal pathogen identification and prognosis prediction reached 99% and 94%, respectively. A 100% accuracy in both tasks was achieved with less than 10 cell images. Additionally, the authors also identified cell mass, volume, and protein density as important factors for predicting prognosis. The study findings have been published in Wiley's Advanced Intelligent Systems journal. WHY IT MATTERS The diagnosis and prognosis of central nervous system diseases may vary depending on the cause. Bacterial or tuberculous causes have the highest mortality rate, which, according to the YUHS researchers, critically requires early, rapid diagnosis and treatment. Meanwhile, there are different diagnostic tests for each causal pathogen, and certain tests may take weeks or more to produce reports. The CSF test, for instance, would require further manual confirmation of cell shape and count. The Yonsei University researchers sought to cut this entire process – from CSF collection to evaluation – down to an hour. "The method we propose is faster than the current diagnostic techniques, such as brain imaging, and the frequently employed clinical biomarkers such as blood levels of procalcitonin and C-reactive protein," they said. They also emphasised the potential of cell morphology, analysed through 3D holotomography, as a "highly accurate and effective" biomarker for brain and spinal infections. This cost-effective imaging technique produces real-time, label-free 3D cell images. ON THE RECORD "This study is the first case of using three-dimensional images of immune cells in cerebrospinal fluid to predict the cause and prognosis of patients with central nervous system infections. We expect that the deep learning model presented in the study will be helpful in shortening the time required for patient diagnosis and prognosis prediction," said Park Yu-rang, one of the researchers and an associate professor at the Department of Biomedical Systems Informatics of Yonsei University College of Medicine.

A new study from South Korea has demonstrated the use of AI models to possibly diagnose and stratify attention deficit hyperactivity disorder by analysing eye images. FINDINGS Researchers from Yonsei University Health System have used four machine learning models and the AutoMorph deep learning pipeline to analyse approximately 1,108 retinal fundus photographs from over 600 children with ADHD and children with typical development. Based on findings published in npj Digital Medicine, all four models showed high accuracy, reaching up to 96.9%. These AI models also showed high performance of up to 87.3% in predicting the degree of impairment in visual selective attention, an ability that ADHD patients are usually challenged with. The study also identified representative symptoms of ADHD by deriving key retinal features via a Shapley Additive Explanations analysis. These include increased vascular density, decreased arterial vessel width, and changes in the optic disc structure. WHY IT MATTERS ADHD is a neurodevelopmental disorder that is difficult to diagnose quickly, says the Yonsei University researchers. Challenges in diagnosis include patients' high subjectivity, the variability of symptoms among individuals, and overlapping symptoms with other existing conditions. Considering the established role of dopamine in retinal function and ADHD symptoms, the researchers looked at retinal images as a potential ADHD screening biomarker in their study. Eventually, they proved the potential of retinal images as an ADHD biomarker and rapid screening tool. "Fundus examinations are very simple, taking less than five minutes. It seems these can be used as a rapid test to monitor the effectiveness of ADHD treatments," said Keun-ah Cheon, professor of Paediatrics at Severance Hospital and co-research lead. THE LARGER TREND Most digital innovations that came out over the past years have only complemented ADHD management, like a mobile application developed at Flinders University in Australia and a digital therapeutics-based program by Singapore's Institute of Mental Health and local startup Neeuro. Meanwhile, eye and eye image-based screening technologies, augmented by AI, have also been applied to diagnose or predict other neurodevelopmental conditions, particularly autism spectrum disorder. Recently, a researcher from Waseda University in Japan demonstrated the use of eye-tracking technology to test children's responses to predictable movement stimuli, which was found to have potential as a behavioural marker for early autism diagnosis.

Qure.ai nets $65M for foundational AI Qure.ai has raised $65 million in a Series D funding round led by Lightspeed and 360 ONE Asset. The company said it will use its fresh funds to invest more in foundational AI models, as well as acquire complementary startups in medical technology. It will also be used to accelerate its expansion in the United States and other markets. Early this year, the Mumbai-based company obtained two major clearances from the United States Food and Drug Administration: a breakthrough device designation for its tuberculosis screening AI solution, qSpot-TB, and a 510(k) clearance for the lung nodule on the qXR AI-powered chest X-ray software. Mediwhale bags $12M to seek US FDA approval South Korean health diagnostics firm Mediwhale has scored $12 million in a Series A2 funding round led by the Korea Development Bank. The company claims to offer the world's first retina-based solution – called Reti-CVD – that uses AI to assess cardiovascular disease risk. It plans to use its new funds to pursue a US FDA approval for Reti-CVD. The software was reportedly rolled out across the Yonsei University Health System early this year. "We are determined to secure FDA De Novo approval by 2025, with plans to launch our product in the United States shortly thereafter," CEO Kevin Choi said in a statement. Besides securing a regulatory clearance, Mediwhale also seeks to improve its AI further and develop new solutions to predict chronic kidney disease risk. Mediwhale last raised $2 million in a pre-Series A funding round in 2021 and $9 million in a Series A round in 2023. Huawei launches medical imaging AI Huawei recently unveiled a new AI-powered solution for analysing medical images. Called "Medical Technology Digitalization 2.0," the technology enables smart segmentation, detection, and quantitative analysis of medical images using AI with up to 98% accuracy. Huawei claims the solution can shorten disease diagnosis time by 40%, although it has not specified which disease. Additionally, the AI solution can also be applied to ultrasound devices running on the OpenHarmony operating system. The Chinese tech giant worked with several local medical technology companies, including MED Imaging AI, Wanxiang, Beijing DeepWise, and KFBIO, to develop the solution, which has been implemented in such major projects as the Fourth People's Hospital in Shenyang, capital of China’s northeast Liaoning Province. Korean pharma turns to AI for new drug discovery Korean pharmaceutical company GI Innovation is pursuing the application of AI for new drug development. It recently signed a memorandum of understanding with local company i-Divine to develop its core cancer drug pipelines and utilise the latter's AI solution to discover new cancer therapy targets. i-Divine's AI is based on a large language model trained on over a billion patents, papers, and real-time biological data sourced globally. It was previously utilised to analyse the success potential of 16,000 new drug substances, including one of GI Innovation's anti-cancer drug pipelines. MediBuddy adopts Philips' predictive heart AI MediBuddy in India is integrating Philips' heart health monitoring platform into its mobile health application. The AI-based longitudinal triaging solution called HeartPrint tracks and assesses key biomarkers from a person's finger when scanned through their smartphone's camera. These include cardiovascular age, diabetes risk, OSA risk, cardio-respiratory fitness index, heart rate analysis, cardiac index, blood pressure variability, and stress disorder prediction. The AI solution also analyses patterns indicating a person's risk of developing heart disease, overall health deterioration, heart resilience, and short and long-term changes in cardiac function.