CATCH: The Cardio-relay Model for Cross-sectoral Ambulatory Treatment of Congestive Heart Disease based on Personal Health Technology

Background

Chronic heart related diseases are a major public health issue (prevalence 2% and 8% for >65 yrs) and is the leading cause of hospitalization for people >65 yrs. Compared to hospital-based management of patients, home monitoring embraces a patient-centric self-management alternative system. Early detection of cardiac rhythm disorders allows for timely intervention and prevention of serious conditions such as stroke and repeated falls.

Objectives

The CATCH project seeks to provide clinical evidence and commercial proof-of-concept for cross-sectoral ambulatory treatment using personal health technology. The project has a specific focus on heart failure (HF).

The project will;

1. define and document the cadio-relay model for ambulatory treatment of HF related to atrial fibrillation (AF);
2. develop state-of-the-art personal technology for collecting and analyzing physiological, contextual, and patient-reported data, which is shared across patients and clinicians in a high- performing cloud infrastructure;
3. research the digital biomarkers for early detection of HF and AF;
4. run a randomized clinical trial involving N=300 patients, to provide clinical evidence for the efficacy of the proposed treatment pathway.

The project will prepare for national roll-out of the cardio-relay model and reach the 70% of the roughly 8000 patients with incident HF in Denmark who do not receive adequate HF management. The model has the potential to prevent 3,500 yearly re-admissions in Denmark, and 120,000 in Germany, which is the first target market for export.

CATCH will provide commercial proof-of-concept of the scalability of the technology for national and international customers by launching a new medically CE-marked and reimbursable personal health monitoring system for both HF and AF management.

Approach

In order to accomplish its goals, this project will make use of a new heart rhythm monitor, the C3+, developed by the Danish company Cortrium Aps. The C3+ will allow cardiologists at Bispebjerg Hospital (BH) to monitor patients’ heart rhythm remotely, as opposed to the in-hospital procedures used today. This will allow cardiologists to effectively cooperate with general practitioners to quickly start treatments tailored to the individual patient.

Personal health and the individual’s self-management and reporting of diseases and symptoms, is one of the cornerstones of a cost-effective healthcare system. The project will develop a remote telemonitoring system for patients to use, which leverage the research done in the REAFEL project, including the mCardia personal health technology system [1,2] and the different AI-based heart arrhythmia detection algorithms [3-6]. In close collaboration with  the Technical University of Denmark (DTU) and based on these research findings, Cortrium will develop a personal health technology module extending Cortrium’s platform which is focused on management of ECG recordings and reports for healthcare professionals. The core of the product will be a medically approved system with an app that integrates seamlessly into Cortrium’s existing system and development of monitoring hardware that is optimized for wireless Bluetooth transmission of ECG and contextual data.

This project will further research how advanced AI methods can be used to identify “digital biomarkers” from large datasets, which has a high ‘information gain’ in disease classification and prediction. A particular unique feature of CATCH is, that the availability of the personal health technology allows for the collection of contextual, behavioral, and patient-reported data in addition to ambulatory physiological data. Extraction of digital biomarkers for HF and AF and their use in symptoms identification and disease prediction will be led by DTU in close collaboration with BH and Cortrium, who will provide clinical and technological input, respectively. Research will focus on developing advanced algorithms able to automatically detect heart rhythm disturbances using C3+ data, and on developing a system for quickly notifying patients and physicians of early signs of heart rhythm disturbances. This development will allow better organization and communication between heart physicians, general practitioners and patients, leading to earlier diagnoses and more efficient treatment.

References

1. D. Kumar, R. Maharjan, A. Maxhuni, H. Dominguez, A. Frølich, and J. E. Bardram, “mCardia: A Context-Aware ECG Collection System for Ambulatory Arrhythmia Screening,” ACM Transactions on Computing for Healthcare (HEALTH), vol. 3, iss. 2, p. 1–28, 2022. 
2. J. E. Bardram, “The CARP Mobile Sensing Framework–A Cross-platform, Reactive, Programming Framework and Runtime Environment for Digital Phenotyping,” arXiv preprint arXiv:2006.11904, 2020. 
3. R. S. Andersen, A. Peimankar, and S. Puthusserypady, “A deep learning approach for real-time detection of atrial fibrillation,” Expert Systems with Applications, vol. 115, p. 465–473, 2019.
4. A. Peimankar and S. Puthusserypady, “DENS-ECG: A deep learning approach for ECG signal delineation,” Expert systems with applications, vol. 165, p. 113911, 2021.
5. D. Kumar, S. Puthusserypady, H. Domínguez, K. Sharma, and J. E. Bardram, “An investigation of the contextual distribution of false positives in a deep learning-based atrial fibrillation detection algorithm,” Expert Systems with Applications, vol. In Press, 2022.
6. D. Kumar, A. Peimankar, K. Sharma, H. Domínguez, S. Puthusserypady, and J. E. Bardram, “DeepAware: A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection,” Computer Methods and Programs in Biomedicine, vol. 221, p. 106899, 2022.