"Using Voice to Save Lives", Enabling mass prevention of strokes and chronic complications over time in at-risk populations using voice-based markers for telemonitoring & screening. we offer revolutionary affordable, scalable, long-term and age-friendly monitoring solutions. Our technology is applicable for mass at-risk populations including older adults (65+).
Several benefits are associated with the Cardiokol voice-based application and cannot be matched by any other current methods: 1.It eliminates the need to continuously wear a device and get used to handling a new technology - more suitable and adaptable for the older population. 2.It is an affordable solution- wearables are priced at hundreds of dollars while the Cardiokol screening application will be offered for about €1/month/user under the basic plan providing a cost-effective solution 3.It provides a far-reaching solution by being compatible with a wide range of voice interfaces such as voice activated assistants, and any other method that produce a voice signal. This flexibility feature is superior to current market alternatives because it provides an intuitive, age-friendly, and effortless use 4.It is a scalable solution since it offers detection via telecom networks providing remote mass-monitoring to millions of subscribers. Hence, our solution can reach large populations that have no alternative methods with unmatched scalability (application-based, cloud-based, central/remote mass-monitoring) and present a market disruptive solution for screening AF in the over 65 growing population. Our peer-reviewed paper : ”Automated detection of atrial fibrillation based on vocal features analysis” was published in the Journal of Cardiovascular Electrophysiology (JCE), we received CE approval in Europe, AMAR approval (Ministry of Health Israel ) in Israel and launched our first product in Israel, our patent no. 16/485,173 "Verbal Periodic Screening for Heart Disease" approved in the USA.
Atrial Fibrillation (AF), an abnormal heart rhythm (arrhythmia), is associated with five-fold increase risk for stroke and is considered a major cardiovascular challenge in modern society. Although AF is a treatable condition, it is often undetected because AF episodes are frequently silent (asymptomatic) and missed in a single opportunistic AF test, leading to a significant portion of undiagnosed AF patients (30-90%). To better detect AF, populations at risk (age 65+) must be frequently monitored for years. However current approaches either have limited monitoring periods, require invasive procedures, or require active engagement with a monitoring device- a resistant compliance among users age 65+. Cardiokol developed a voice-biomarker based digital telehealth solution that utilizes widespread speech platforms (phones, land-lines, speakers, voice assistant) to support age-friendly, intuitive, long-term, extended monitoring in populations at risk. The Voice Assisted Arrhythmia Monitoring (VAAM) detects AF independent of speech content or language barriers. Furthermore, it works without the need to wear, operate, or charge special devices, therefore providing a device-less, non-invasive and an age-friendly solution to the largest population at risk with unmet need. Our overall objective is to be the first to make long-term cardiac arrhythmia monitoring and screening practical and economical for large populations at risk (the aging population). The main benefit of continuously monitoring AF in the at-risk populations is that AF detection require clinical evaluation that often result in anticoagulant treatment. Indeed, AF is a treatable condition with oral drugs which can prevent 75% of AF-related strokes.
A total of 158 patients were recruited in 2 mdedial center. The final analysis of “Ahh” and “Ohh” syllables was performed on 143 and 142 patients, respectively. The mean age was 71.4 ± 9.3 and 43% of patients were females. The developed AF indicator was reliable. Its numerical value decreased significantly in sinus rhythm (SR) after the cardioversion (“Ahh”: from 13.98 ± 3.10 to 7.49 ± 1.58; “Ohh”: from 11.39 ± 2.99 to 2.99 ± 1.61). The values at SR were significantly more homogenous compared to AF as indicated by a lower standard deviation. The area under the receiver operating characteristic curve was >0.98 and >0.89 (“Ahh” and “Ohh,” respectively, p < .001). The AF indicator sensitivity is 95% with 82% specificity. Conclusion: This study is the first report to demonstrate feasibility and reliability of the identification of AF episodes using voice analysis with acceptable accuracy, within the identified limitations of our study methods. The developed AF indicator has higher accuracy using the “Ahh” syllable versus “Ohh.” KEYWORDS Large-scale community pilot ongoing over 500 patients enrolled in 10 MC.
