Remember meForgot password?
    Log in with Twitter

article imageAI that detects cardiac arrests in real-time

By Tim Sandle     Apr 29, 2018 in Health
Corti is an artificial intelligence platform that uses machine learning to provide emergency medical personnel with life-saving diagnostic assistance. A new pilot study has been launched in Europe to assess cardiac arrests.
Corti, the Copenhagen-based company, is to enter into a partnership with the European Emergency Number Association (EENA). Under the initiative four sites across Europe have been selected to pilot the technology. The project could change the way emergency medical calls are handled in the future.
Currently Corti is being deployed by Copenhagen Emergency Medical Services in order to detect cardiac arrests during emergency calls. Data suggests that Corti is 20 percent more accurate at detecting Out of Hospital Cardiac Arrests than medical dispatchers. Moreover, it is also significantly faster (by 31 seconds) at undertaking this assessment. Even completing this assessment by a few seconds faster can mean the difference between a patient surviving or dying.
In order to test out the Corti technology, 161,650 emergency calls (158,330 non- Out of Hospital Cardiac Arrests and 2,157 Out of Hospital Cardiac Arrests calls) were analysed in 2014 using Corti’s machine learning platform. The model showed a detection rate (sensitivity) of 93.1 percent, and a specificity (that is, detection of those without the condition) rate of 98 percent.
In comparison, human dispatchers achieved a sensitivity of 72.9 percent. This meant that the Corti platform is 20.2 percent more accurate in terms of detecting cardiac arrests than human dispatchers.
The following video shows the AI application at work:
Corti is built on a real-time automatic speech recognition technology that can act as a digital assistant for medical dispatchers handling emergency calls, detecting out-of-hospital cardiac arrests. The platform uses deep neural networks process the conversation in real-time, looking for verbal and non-verbal patterns of communication - such as tone of voice and breathing issues - that might not be obvious to a human, and even when there is heavy background noise
By utilizing this data, Corti provides human call-takers with recommendations for how to best triage patients, resulting in significantly reduced error rates, faster critical diagnoses, and lives being saved
Going forwards, the four sites will be chosen by June 2018, and they will begin start running the platform by early September 2018 through to April 2019. Following this an evaluation will take place and this could lead to a greater roll out of the technology.
More about Artificial intelligence, machine learning, Cardiac arrest
More news from
Latest News
Top News