Periodic Reporting for period 1 - AHM (Acorai Heart Monitor - Non-invasive multi-sensor device for heart failure monitoring)
Berichtszeitraum: 2023-10-01 bis 2024-07-31
Heart Failure (HF) is a progressive clinical syndrome with multiple etiologies. It is associated with nearly three million hospitalizations in the EU annually, representing 30% of all readmissions, and accounts for up to 5% of the entire healthcare expenditure. Despite modern medical treatment, HF is a life-threatening and debilitating condition with a poor prognosis.
By delivering Intracardiac pressures (ICPs), the specific blood pressures inside the heart's chambers, to healthcare professionals (HCPs), they can efficiently guide the treatment of patients with HF. This leads to improved quality of life in patients and reduced frequency of hospital admissions. Unfortunately, all current tools for monitoring the ICPs require invasive procedures, limiting the widespread accessibility of these pressures, and just a few percent of patients actually receiving optimal care.
Acorai is developing the Acorai Heart Monitor (AHM), a monitoring device designed to detect and estimate hemodynamic parameters non-invasively. It is a handheld electronic device that collects data from 4 sensor types based upon the patented SAVE Sensor System. The sensor data are processed within the medical device with machine learning (ML) methods, after which the results, the ICPs, are displayed to be read by a qualified healthcare professional (HCP).
AHM is a multi-patient non-invasive device that would dramatically disrupt the paradigm of HF treatment and lead to significant cost saving in the EU whilst improving the overall prognosis of patients who suffers from HF. With the growing prevalence of HF globally, it is a tool with applicability in multiple workflows and represents a first-of-its-kind device to revolutionise HF management.
AHM has already been validated in 300 patients in a Swedish proof of concept study, and the EIC support enables further product development and data collection via a large multi-national study to prove its effectiveness. It also supports the development and execution on the regulatory pathways, to ensure market access after a finalized project.
By delivering Intracardiac pressures (ICPs), the specific blood pressures inside the heart's chambers, to healthcare professionals (HCPs), they can efficiently guide the treatment of patients with HF. This leads to improved quality of life in patients and reduced frequency of hospital admissions. Unfortunately, all current tools for monitoring the ICPs require invasive procedures, limiting the widespread accessibility of these pressures, and just a few percent of patients actually receiving optimal care.
Acorai is developing the Acorai Heart Monitor (AHM), a monitoring device designed to detect and estimate hemodynamic parameters non-invasively. It is a handheld electronic device that collects data from 4 sensor types based upon the patented SAVE Sensor System. The sensor data are processed within the medical device with machine learning (ML) methods, after which the results, the ICPs, are displayed to be read by a qualified healthcare professional (HCP).
AHM is a multi-patient non-invasive device that would dramatically disrupt the paradigm of HF treatment and lead to significant cost saving in the EU whilst improving the overall prognosis of patients who suffers from HF. With the growing prevalence of HF globally, it is a tool with applicability in multiple workflows and represents a first-of-its-kind device to revolutionise HF management.
AHM has already been validated in 300 patients in a Swedish proof of concept study, and the EIC support enables further product development and data collection via a large multi-national study to prove its effectiveness. It also supports the development and execution on the regulatory pathways, to ensure market access after a finalized project.
In this project Acorai is executing on
1. A global Machine Learning Generalization Study (data collection study to enable training of final machine learning models): ~1250 patients across ~14 sites, allows for a diverse and generalizable population. This study also provides insights into further product development, e.g. by exploring potential device deficiencies and useability improvements.
2. Product Development: Based on study learnings and product team insights, the device is improved and prepared for large scale manufacturing.
3. Regulatory Strategy and Execution: A regulatory strategy has been developed and executed on, ensuring all foundational activities are in place for regulatory submission (both US and EU).
4. Pivotal Study: In the pivotal study (~300 patients), the accuracy performance of the developed machine learning models is tested, and will guide documentation for regulatory submissions.
1. A global Machine Learning Generalization Study (data collection study to enable training of final machine learning models): ~1250 patients across ~14 sites, allows for a diverse and generalizable population. This study also provides insights into further product development, e.g. by exploring potential device deficiencies and useability improvements.
2. Product Development: Based on study learnings and product team insights, the device is improved and prepared for large scale manufacturing.
3. Regulatory Strategy and Execution: A regulatory strategy has been developed and executed on, ensuring all foundational activities are in place for regulatory submission (both US and EU).
4. Pivotal Study: In the pivotal study (~300 patients), the accuracy performance of the developed machine learning models is tested, and will guide documentation for regulatory submissions.
The Acorai Heart Monitor's SAVE Sensor System is the most complex sensor combination on the market, providing a richness of data needed for estimating intracardiac parameters.
The ML Generalization and Pivotal studies become the largest studies of their kind, providing large enough datasets for the machine learning models to generate clinically useful accuracies. These datasets provide additional protectionability above existing IPR.
The ML Generalization and Pivotal studies become the largest studies of their kind, providing large enough datasets for the machine learning models to generate clinically useful accuracies. These datasets provide additional protectionability above existing IPR.