Using Atrial Fibrillation Burden Trends and Machine Learning to Predict Near-Term Risk of Cardiovascular Hospitalization

Abstract

Background: Atrial fibrillation is associated with an increased risk of cardiovascular hospitalization (CVH), which may be triggered by changes in daily burden. Machine learning of dynamic trends in atrial fibrillation burden, as measured by insertable cardiac monitors (ICMs), may be useful in predicting near-term CVH.

Methods: Using Optum's deidentified Clinformatics Data Mart Database (2007-2019), linked with the Medtronic CareLink ICM database, we identified patients with >1 days of ICM-detected atrial fibrillation. ICM-detected diagnostic parameters were transformed into simple moving averages over different periods for daily follow-up. A diagnostic trend was defined as the comparison of 2 simple moving averages of different periods for each diagnostic parameter. CVH was defined as any hospital, emergency department, or ambulatory surgical center encounter with a cardiovascular diagnosis-related group or diagnosis code. Machine learning was used to determine which diagnostic trends could best predict patient risk 5 days before CVH.

Results: A total of 2616 patients with ICMs met the inclusion criteria (71±11 years; 55% male). Among them, 1998 (76%) had a planned or unplanned CVH over 605 363 days. Machine learning revealed distinct groups: (A) sinus rhythm (reference), (B) below-average burden, (C) above-average burden, and (D) above-average burden with decreasing patient activity. The relative risk was increased in all groups versus the reference (B, 4.49 [95% CI, 3.74-5.40]; C, 8.41 [95% CI, 7.00-10.11]; D, 11.15 [95% CI, 9.10-13.65]), including a 21% increase in CVH detection over prespecified burden thresholds of duration (≥1 hour) and quantity (≥5%). The area under the receiver operating characteristic curve increased from 0.55 when using hourly burden amounts to 0.66 when using burden trends and decreasing patient activity (P<0.001), a 20% increase in predictive power.

Conclusions: Trends in atrial fibrillation were strongly associated with near-term CVH, especially above-average burden coupled with low patient activity. This approach could provide actionable information to guide treatment and reduce CVH.

Keywords: atrial fibrillation; data warehousing; hospitals; humans; risk.

Figure 1.

Definition of the index date. CE indicates continuous enrollment.

Figure 2.

Mapping atrial fibrillation (AF) burden trends to a single patient example. This figure presents AF burden values as bars and AF burden moving averages as lines for each follow-up day between the day after device implantation and the day before cardiovascular hospitalization. First AF detection and moving average cross-over events trigger different windows of risk. Trend A represents a window of sinus rhythm before the patient’s first device-detected AF event (baseline risk). Trend B is triggered when the 21-day moving average of AF burden crosses below its historical average (below average risk). Trend C is triggered when the 21-day moving average of AF burden crosses above its historical average (above average risk). Moving averages are adjusted downward by 5 minutes for display purposes. AT indicates atrial tachycardia; CMA, cumulative moving average; and SMA, simple moving average.

Figure 3.

Venn diagram of cardiovascular hospitalization (CVH) events by atrial fibrillation (AF) burden criteria. This Venn diagram shows the number of CVH events (%) and relative risk for the intersection of AF burden duration (≥1 hour), quantity (≥5%), and Trend D (increasing burden with decreasing patient activity) sets. Trend D captures 137 mutually exclusive CVH events, yielding a 21% (137/644) increase in detection over clinical criteria alone. The size of the Venn diagram circles and their overlay are kept constant for ease of presentation and thus do not represent the relative contribution of each set. RR indicates relative risk.

Figure 4.

Distribution of daily atrial tachycardia (AT)/atrial fibrillation (AF) amount by AF burden criteria. Using validation data, this plot visualizes the differences in daily AT/AF amount by AF burden threshold. Follow-up days are counted when the criteria or trend is met for the respective AF burden threshold and presented as a percent of total follow-ups. Of these days, follow-up days are further counted only for patients with persistent AF.