Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

HeartSciences’ MyoVista Technology Used to Develop AI-ECG Algorithm to Identify Patients

Independent study demonstrates novel AI-ECG algorithm could provide a cost-effective strategy for improving cardiac risk stratification

Heart Test Laboratories,  d/b/a HeartSciences , a medical technology company focused on saving lives by making an ECG (also known as an EKG) a far more valuable screening tool through the use of AI, announced that an independent study utilizing its MyoVista proprietary technology was featured in Advocate Aurora Health’s Journal of Patient-Centered Research and Reviews, an open access, peer-reviewed medical journal devoted to advancing patient centered care practices, health outcomes, and patient experiences.

Latest NaturalAI Insights: InspireXT Announces Acquisition Of NaturalAI – A Conversational Artificial Intelligence Platform To Expand Its Solution Portfolio

The publication concluded that the MyoVista® technology ECG-derived machine learning model “provides a cost-effective strategy for predicting patient subgroups in whom an integrated milieu of systolic and diastolic dysfunction is associated with a high-risk of major adverse cardiovascular events (MACE).”

Key study highlights:

  •  Patients (n=518) from West Virginia University served as the validation set and were followed up over a three-year period (38-months) for clinical outcomes including MACE rehospitalization and cardiac death.
  •  Results demonstrate the potential of AI-ECG algorithms for rapid decision-making in an office-based setting to evaluate and monitor the progress of the patient and justify appropriate downstream referral for additional tests like echocardiography or other interventions.
  •  The Deep Neural Network (DNN) AI-ECG model demonstrated significantly increased probability for identifying patients at high-risk compared to low risk of MACE (21% vs 3%; P<0.001)
  •  The AI-ECG model results were similar to an echo-based model (21% vs 5%; P<0.001), suggesting comparable utility.
  •  Data used to develop the AI-ECG algorithm was collected from a multi-center trial, which included 727 patients from the Icahn School of Medicine at Mount Sinai, The University of California Los Angeles and Windsor Cardiac Center, Windsor Ontario.

“This independent study demonstrates the opportunity that AI-ECG algorithms could bring to improving health outcomes. I believe the solution to unnecessary cardiac deaths will come from low-cost, front-line screening using AI-ECGs. Imagine the day where you can go to your primary care physician and a simple 20-second ECG test shows not only whether you have early-stage heart disease, but also whether you are at high-risk of a major adverse cardiovascular event in the next three years,” stated Andrew Simpson, CEO of HeartSciences. “There are millions of ECGs conducted every week and HeartSciences is at the leading edge of commercialization in the field of adding new clinical indications to the ECG.”

Related Posts
1 of 40,985

AI News: Infobip Creates AI-powered Chatbot for Uber

The study trained the AI-ECG model against an echo-derived model for predicting MACE events combining multiple parameters for identifying patient phenogroups at risk for MACE. Nine echo parameters were included for determining patient risk: ejection fraction; left ventricular mass index; left atrial volume index; early diastolic transmitral flow velocity (E); late diastolic transmitral flow velocity (A); E/A ratio; early diastolic relaxation velocity (e’); E/e’ ratio; and tricuspid regurgitation peak velocity.

The final AI-ECG model included 51 ECG features, of which the majority were MyoVista® CWT frequency features (n=26, 51%), followed by traditional ECG features derived from the MyoVista® (n=23, 45%) and clinical features were age and past medical history of coronary artery disease (n=2, 4%).

“The extracted frequency parameters provided via MyoVista®’s CWT technology represented the majority of the statistically significant data variables used to develop the algorithm using AI-based variable reduction techniques,” stated Mark Hilz, COO of HeartSciences. “We believe this clearly demonstrates the value of our signal processing technology and its ability to identify additional meaningful information from the electrical signal of the heart.”

The deep neural network (DNN) model showed robust classification of patients with areas under the receiver operating characteristic curves (AUC) of 0.84 (95% CI: 0.80–0.87). The ECG-predicted model demonstrated an increased probability for MACE in high-risk compared to low-risk patients (21% vs 3%; P<0.001).  The results were similar to the echo-trained model (21% vs 5%; P<0.001), suggesting a comparable utility of the MyoVista® technology compared to echo to identify patients at risk of MACE events.

As reported in the publication, cardiovascular disease is the leading cause of morbidity and mortality globally, resulting in estimated health care costs of more than $200 billion in the United States annually. Effective, economical, and personalized prevention and risk-stratification strategies are imperative to mitigate this burden.

Latest Aithority Insights : NVIDIA Raises the Standard of Low Code DevOps with the NVIDIA AI Enterprise 2.1

 [To share your insights with us, please write to sghosh@martechseries.com] 

Comments are closed.