PAT I ENT DET E RIORATION
Identifying deterioration using AI technology
The pandemic is accelerating adoption of AI-technology capable of automating the capture of vital signs and proactively identifying patients at risk of deterioration. As the technology gains increasing acceptance, healthcare providers could transform patient care from being ‘re-active’ to a more predictive approach – enabling earlier intervention and better outcomes.
Ten years ago, when Isansys was first set up by Keith Errey and his cofounder Rebecca Weir, driving innovation into healthcare wasn’t easy. Healthcare providers were understandably cautious when it came to the adoption of new technology. However, all this has changed with COVID-19. In the wake of the pandemic, there has been a surge in demand for intelligent technologies capable of monitoring the patient’s status – enabling early detection of deterioration and rapid intervention. The increased numbers of very ill and infectious patients have meant that healthcare providers have had to rapidly find new ways of working.
The company has had to quickly upscale production of its Patient Status Engine (PSE) clinical learning platform as hospitals have sought to rapidly deploy the intelligent monitoring systems to increase capacity and numbers of higher dependency beds and isolation wards.
The PSE is a Class IIa CE-Marked and
FDA approved medical device combining wearable sensors, wireless connectivity, predictive AI analytics, dashboards and alerting for hospital, home and community settings. The PSE replaces wired bedside monitors, integrates with electronic medical records (EMRs), and automates the most basic process of healthcare, knowing the patient’s physiological status at all times – past, present and future. “The PSE obtains the same physiological data collected by an expensive bedside monitoring unit but performs this wirelessly,” Errey explained. “A key advantage is that it allows the patient to be more mobile. Technical alarms are often triggered with wired systems – cables fall off and electrodes become unstuck. The wireless system reduces the time wasted by nurses having to reattach cables and electrodes, as well as
SEPTEMBER 2020
having to respond to these ‘technical’ alarms.” The high quality of the data is ensured since the false alarms, associated with misplaced leads, are eliminated and the data is uninterrupted. Whereas vital signs are normally recorded every 1-4 hours onto paper charts, the PSE collects precise, high resolution and continuous patient data in real-time. “The system enables hospitals to quickly build up a complete data set about an individual’s personal health status. Once you have this, you can start to look at a range of AI or deep learning algorithms, which can proactively predict what is going to happen to the patient in the future,” Errey commented.
The predictive algorithm at the heart of the system is based on the NEWS2 early warning score, which is designed to standardise the assessment and response to
acute illness. The guidance from the Royal College of Physicians states that ‘NEWS2 should be used when managing patients with COVID-19’.
Early warning scoring systems, such as NEWS2, are clinically well validated and have had a significant impact in reducing the number of adverse events and avoidable deaths in those hospitals that have adopted them. However, outstanding challenges remain for such early warning score systems: the data is sparse and tends to be backward looking, and they are time consuming for nurses, even when the scores are electronically calculated from the input observational data. The PSE overcomes these challenges by automating the entire early warning score process including data capture and calculation.
The richer data provides real-time trend information and highly accurate early
WWW.CLINICALSERVICESJOURNAL.COM l 77
▲
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92
