Artificial intelligence: an attempt to automate remote device follow-up. (24th May 2021)

• Record Type: Journal Article
• Authors: Ferreira, HDS; Ferrer, F; Cabanelas, N; Nelumba, T; Ferreira, AR; Faustino, M; Antunes, S; Vasconcelos, H; Beringuilho, M; Polena, C; Borralho, C; Madeira, F; Morais, C
• Is Part Of: Europace. Volume 23:Supplement 3(2021)
• Publication Date: 2021-05-24
• Subjects: Arrhythmia -- Treatment -- Periodicals; Cardiac pacing -- Periodicals; Catheter ablation -- Periodicals; Heart -- Physiology -- Periodicals; Electrophysiology -- Periodicals; 617.4120645
• DOI: 10.1093/europace/euab116.517
• Languages: English
• ISSNs: 1099-5129

Abstract

Abstract: Funding Acknowledgements: Type of funding sources: None. Introduction: Artificial intelligence (AI) through machine learning (ML) refers to the simulation of human intelligence with the capacity for achieving goals within computers. In electrophysiology, ML has many applications in electrocardiography, intracardiac mapping and cardiac implantable electronic devices (CIEDs). Remote monitoring (RM) of patients equipped with CIEDs associates the analysis of event reports and calendar-based remote follow-ups (FU). ML applications have allowed for risk stratification, improved arrhythmia localisation and streamlined remote monitoring which may significantly reduce the workload faced by electrophysiologists. Aim To develop a system that automates cardiac implantable electronic devices remote follow-up. Methods and Results We created a Java software application, that uses the latest optical character recognition techniques combined with artificial intelligence and natural language processing to extract information from PDF reports of RM of CIEDs from different manufacturers. The current version is HIPAA (Health Insurance Portability and Accountability Act) complaint and runs on local computers only. Using the current system, we were able to run and extract data from 30 remote follow-up PDF reports of Cardiac Implantable Defibrillators (ICDs) and Cardiac Resynchronization Therapy with Defibrillator (CRT-Ds). Time taken from data extraction to conversion of all 30 device PDFs was under 5 minutes. Process and data extracted are presented in the figure below. (Figure 1) Conclusion: This machine learning algorithm proved that it is possible to facilitate and automate remote follow-up of cardiac implantable electronic devices. In a near future this will allow to us to efficiently increase productivity, by speeding and facilitating interpretation of remote device follow-ups, leading to improvements in patientcare and precision cardiovascular medicine. Furthermore, in the current and future pandemics it may help prevent unnecessary in-person medical visits, avoiding additional, unnecessary strain on an already overburdened and overwhelmed healthcare system, and saving costs.