Efficiency of remote monitoring using artificial intelligence in patients with chronic heart failure for 6 months after discharge from hospital
Authors:
Company:
1 I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russian Federation
2 City Clinical Hospital No. 1 named after N.I. Pirogov, Moscow, Russian Federation
For correspondence: Sign in or register.
Type: Original articles
DOI:
For citation: Chomakhidze P.Sh., Mesitskaya D.F., Galimova R.R., Bguasheva Z.A., Podgalo D.D., Kuznetsova N.O., Shchekochikhin D.Yu., Kopylov F.Yu. Efficiency of remote monitoring using artificial intelligence in patients with chronic heart failure for 6 months after discharge from hospital. Creative Cardiology. 2026; 20 (2): 282–292 (in Russ.). DOI: 10.24022/1997-3187-2026-20-2-282-292
Received / Accepted: 10.03.2026 / 08.05.2026
Keywords: heart failure remote monitoring machine learning single-channel electrocardiogram mortality hospitalization observation contractility
Abstract
Objective. To determine the clinical efficacy of remote monitoring using artificial intelligence (AI) methods in patients with chronic heart failure (CHF).
Material and methods. A multicenter, randomized, observational, comparative study was conducted with the sequential inclusion of 300 patients hospitalized with decompensated heart failure (HF) in the cardiology department of the Cardiology Clinic of Sechenov University Clinical Hospital No. 1 and the cardiology department of City Clinical Hospital No. 1 named after N.I. Pirogov. All patients underwent an inpatient examination, including analysis of the following parameters: medical history, physical examination data, standard 12-lead ECG data, blood counts, and echocardiography. Patients were divided into two equal groups: daily remote monitoring group using AI and standard care group. In the remote monitoring group, daily single-channel ECG monitoring was performed, analyzed using AI methods, to identify the dynamics of systolic and diastolic myocardial function, patient body weight, blood pressure, and complaints. The average follow-up period was 5.8 months. The endpoints were: death from cardiovascular causes; nonfatal myocardial infarction; stroke; hospitalization for decompensated CHF; hospitalization for atrial fibrillation; hospitalization for uncontrolled arterial hypertension; death from a non-cardiac cause; hypertensive crisis.
Results. Based on the monitoring results, 138 remote and 44 in-person consultations were conducted, as well as additional examinations for 39 patients with signs of unstable CHF. On average, during the six-month observation period, each physician spent 14.4 minutes per workday. The remote AI monitoring group demonstrated a reduction in the number of hospitalizations for patients with CHF decompensation, atrial fibrillation, and blood pressure instability, as well as a decrease in the incidence of strokes and hypertensive crises. There was also a trend toward a reduction in the incidence of cardiovascular death.
Conclusion. The results of monitoring patients with CHF using an innovative method based on artificial intelligence elements confirmed its potential for reducing the incidence of heart failure complications, including hospitalizations for various cardiac pathologies.
