Current remote monitoring devices for heart failure have been shown to reduce hospitalizations but are invasive and costly; accurate non-invasive options remain limited. The EuleriAn Video Magnification ApPLications In Heart Failure StudY (AMPLIFY) pilot aimed to evaluate the accuracy of a novel noninvasive method that uses Eulerian video magnification. Video recordings were performed on the neck veins of 50 patients who were scheduled for right heart catheterization at the Palo Alto VA Medical Center. The recorded jugular venous pulsations were then enhanced by applying Eulerian phase-based motion magnification. Assessment of jugular venous pressure was compared across three categories: (1) physicians who performed bedside exams, (2) physicians who reviewed both the amplified and unamplified videos, and (3) direct invasive measurement of right atrial pressure from right heart catheterization. Motion magnification reduced inaccuracy of the clinician assessment of central venous pressure compared to the gold standard of right heart catheterization (mean discrepancy of −0.80 cm H2O; 95% CI −2.189 to 0.612, p = 0.27) when compared to both unamplified video (−1.84 cm H2O; 95% CI −3.22 to −0.46, p = 0.0096) and the bedside exam (−2.90 cm H2O; 95% CI −4.33 to 1.40, p = 0.0002). Major categorical disagreements with right heart catheterization were significantly reduced with motion magnification (12%) when compared to unamplified video (25%) or the bedside exam (27%). This novel method of assessing jugular venous pressure improves the accuracy of the clinical exam and may enable accurate remote monitoring of heart failure patients with minimal patient risk.
Đang xem: Eulerian video magnification app
Heart failure is a tremendously morbid, deadly, and costly disease that affects 6.5 million Americans today.1 It is now implicated in one in nine deaths in the United States and at least 20% of all hospitalizations among persons older than 65.1 It costs the United States $30.7 billion annually, a figure forecasted to increase to $70 billion by 2030.2
Much of this economic burden is generated by hospitalizations for heart failure, which represent up to 80% of direct costs, making heart failure readmissions a key target for cost reduction.2 Preventing readmissions requires early provider intervention in the ambulatory setting, but the ideal timing and methods to achieve such interventions remain elusive. A critical step to reducing heart failure hospitalizations is identifying which patients will imminently decompensate by evaluating their volume status. While physicians have traditionally relied on the bedside exam of the jugular venous pressure (JVP) to assess volume status, this can be impractical as a primary method for monitoring outpatients. With the recent explosion of telemedicine, the majority of healthcare institutions in the United States employ some form of virtual interaction, paving the way for monitoring tools that can tap this potential.
Invasive ambulatory hemodynamic monitors have shown promise as early-warning systems in heart failure. A variety of devices have been developed and studied, including right ventricular (COMPASS-HF and REDUCE HF), left atrial (HOMEOSTASIS and LAPTOP-HF), and pulmonary artery (CHAMPION) pressure measurement systems.3,4,5,6,7 While devices such as the CardioMEMS monitor have been demonstrated to reduce heart failure readmissions, they may not be scalable: they are invasively implanted, costly upfront (approximately $17,000 for a CardioMEMS device), and demand additional personnel and resources to handle the datastream.8 Furthermore, their cost-effectiveness remains debatable.8,9,10,11,12
In this study, we propose a noninvasive and easily scalable alternative to current invasive remote pressure monitoring systems by combining the bedside examination with modern image processing techniques. Eulerian video magnification is an image processing method by which visually imperceptible periodic motions can be deconstructed and amplified into movements discernible to the naked eye.13 We describe the application of Eulerian video magnification to the jugular venous pulse examination and demonstrate its potential as a novel method of noninvasive monitoring of right-sided filling pressures.
Participant characteristics are presented in Table 1. Among the 59 participants enrolled, 48 (81%) completed the study. The most common reason for study noncompletion was due to cancellation of the right heart catheterization (RHC) procedure (6 patients, 10.2%). The average age of patients who completed the study was 70 years (SD: 8.04 years); 85% of participants were over 65 years old. The average BMI was 30 (SD: 4.87) with 83% of participants qualifying as overweight or obese. Most participants had never smoked (77%), while 15% were former smokers and 8% were current smokers. Mean chest circumference among this sample was 120 cm (SD: 12 cm).
Invasive vs. non-invasive measurements
A summary of invasive and noninvasive data are reported in Table 2. On average, participant cardiac output and index were normal at 4.94 L/min and 2.36 L/min/m2, respectively. The average right atrial pressure (RAP) by right heart catheterization was 8.56 cm H2O (IQR 5–10). Similarly, average JVP was 7.11 cm H2O (IQR 5–8) when measured at bedside, 7.8 cm H2O (IQR 6.2–8.4) when measured from unamplified video, and 8.8 cm H2O (IQR 7.2–10) when measured from motion-amplified video.
Table 2 JVP and RHC measurements. Cardiologist mean pressure measurements are reported in cm H2O except as otherwise noted
All noninvasive modalities yielded JVPs lower than the corresponding invasive right atrial pressures, though the magnitude varied depending on the modality (Table 3). When measured at the bedside, JVP was on average 2.90 cm H2O lower than corresponding right heart catheterization measurements (95% CI −4.33 to 1.40, p = 0.0002). This discrepancy narrowed when measured via unamplified video (−1.84 cm H2O; 95% CI −3.22 to −0.46, p = 0.0096). After motion magnification, this discrepancy was no longer significant (−0.80 cm H2O; 95% CI −2.189 to 0.612, p = 0.27).
To better understand the practical clinical utility of the video magnification, we compared the noninvasive to the invasive measurements by characterizing them qualitatively. Each invasive and noninvasive measurement was designated “normal” if it was less than or equal to 7 cm H2O, “borderline” if greater than 7 but less than or equal to 10 cm H2O, or “elevated” if greater than 10 cm H2O. “Agreement” with right heart catheterization was achieved if both categories were the same (e.g., both were “elevated”); partial disagreement was noted if there was a one-category discrepancy (e.g., one was “normal” and the other was “borderline”); and complete disagreement was noted if there was a two-category discrepancy (e.g., one was “normal” and the other was “elevated”). These pooled data are presented in Fig. 1. Complete disagreement was found in 27% of bedside assessments, 25% of unamplified video assessments, and only 12% of amplified video assessments. Neither bedside exam nor unamplified video assessments skewed in a statistically significant fashion towards “agreement” or “disagreement” with right heart catheterization (p = 0.44 and p = 0.10, respectively; Table 4). In contrast, assessments made with amplified video more often agreed or partially disagreed (p = 0.0034) than the other noninvasive modalities.
Agreement with right heart catheterization by assessment type. “Agreement” with right heart catheterization was achieved if clinicians characterized the JVP similarly (e.g., both were “elevated”); “disagree by 1” was noted where a one-category discrepancy existed (e.g., one was “normal” and the other was “borderline”); and “disagree by 2” was noted if there was a two-category discrepancy (e.g., one was “normal” and the other was “elevated”)