New Neural Network Enables Easy Screening of Sleep Apnoea in Patients with Cerebrovascular Disease

A new neural network developed by researchers at the University of Eastern Finland and Kuopio University Hospital enables an easy and accurate assessment of sleep apnoea severity in patients with cerebrovascular disease. The assessment is automated and based on a simple nocturnal pulse oximetry, making it possible to easily screen for sleep apnoea in stroke units.

Up to 90% of patients experiencing a stroke have sleep apnoea, according to earlier studies conducted at Kuopio University Hospital. If left untreated, sleep apnoea can reduce the quality of life and rehabilitation of patients with stroke and increase the risk for recurrent cerebrovascular events.

"Although screening of sleep apnoea is recommended for patients with cerebrovascular disease, it is rarely done in stroke units due to complicated measurement devices, time-consuming manual analysis, and high costs," Researcher Akseli Leino from the University of Eastern Finland says.

In the new study, researchers developed a neural network to assess the severity of sleep apnoea in patients with acute stroke and transient ischaemic attack (TIA) by using a simple nocturnal oxygen saturation signal. The apnoea-hypopnea index, which represents the number of apnoea and hypopnea events per hour, is commonly used in the diagnostics of sleep apnoea. When the researchers compared the results of manual scoring and those obtained using the new neural network, the median difference was only 1.45 events per hour. The neural network was also 78% accurate in classifying patients into four different categories on the basis of sleep apnoea severity (no sleep apnoea, mild, moderate, severe). The neural network was able to identify moderate and severe sleep apnoea, both of which require treatment, in patients with acute stroke or TIA with a 96% specificity and a 92% sensitivity.

"The neural network developed in the study enables an easy and cost-effective screening of sleep apnoea in patients with cerebrovascular disease in hospital wards and stroke units. The nocturnal oxygen saturation signal can be recorded with a simple finger pulse oximetry measurement, with no time-consuming manual analysis required," Medical Physicist Katja Myllymaa from Kuopio University Hospital points out.

The study was conducted in collaboration between the Department of Clinical Neurophysiology and the Department of Neurology at Kuopio University Hospital, and the Department of Applied Physics at the University of Eastern Finland. The study was funded by the Academy of Finland, Business Finland, Kuopio University Hospital, the Finnish Cultural Foundation, Kuopio Area Respiratory Foundation, the Research Foundation of the Pulmonary Diseases, the Finnish Anti-Tuberculosis Association Foundation, Päivikki & Sakari Sohlberg Foundation, Paulo Foundation, and Tampere Tuberculosis Foundation.

Leino A, Nikkonen S, Kainulainen S, Korkalainen H, Töyräs J, Myllymaa S, Leppänen T, Ylä-Herttuala S, Westeren-Punnonen S, Muraja-Murro A, Jäkälä P, Mervaala E, Myllymaa K.
Neural network analysis of nocturnal SpO2 signal enables easy screening of sleep apnea in patients with acute cerebrovascular disease.
Sleep Med 2020;79. doi: 10.1016/j.sleep.2020.12.032

Most Popular Now

Using Data and AI to Create Better Healt…

Academic medical centers could transform patient care by adopting principles from learning health systems principles, according to researchers from Weill Cornell Medicine and the University of California, San Diego. In...

AI Medical Receptionist Modernizing Doct…

A virtual medical receptionist named "Cassie," developed through research at Texas A&M University, is transforming the way patients interact with health care providers. Cassie is a digital-human assistant created by Humanate...

Northern Ireland Completes Nationwide Ro…

Go-lives at Western and Southern health and social care trusts mean every pathology service is using the same laboratory information management system; improving efficiency and quality. An ambitious technology project to...

AI Tool Set to Transform Characterisatio…

A multinational team of researchers, co-led by the Garvan Institute of Medical Research, has developed and tested a new AI tool to better characterise the diversity of individual cells within...

AI Detects Hidden Heart Disease Using Ex…

Mass General Brigham researchers have developed a new AI tool in collaboration with the United States Department of Veterans Affairs (VA) to probe through previously collected CT scans and identify...

Human-AI Collectives Make the Most Accur…

Diagnostic errors are among the most serious problems in everyday medical practice. AI systems - especially large language models (LLMs) like ChatGPT-4, Gemini, or Claude 3 - offer new ways...

Highland Marketing Announced as Official…

Highland Marketing has been named, for the second year running, the official communications partner for HETT Show 2025, the UK's leading digital health conference and exhibition. Taking place 7-8 October...

MHP-Net: A Revolutionary AI Model for Ac…

Liver cancer is the sixth most common cancer globally and a leading cause of cancer-related deaths. Accurate segmentation of liver tumors is a crucial step for the management of the...

Groundbreaking TACIT Algorithm Offers Ne…

Researchers at VCU Massey Comprehensive Cancer Center have developed a novel algorithm that could provide a revolutionary tool for determining the best options for patients - both in the treatment...

The Many Ways that AI Enters Rheumatolog…

High-resolution computed tomography (HRCT) is the standard to diagnose and assess progression in interstitial lung disease (ILD), a key feature in systemic sclerosis (SSc). But AI-assisted interpretation has the potential...