A multi-layer monitoring system for clinical management of Congestive Heart Failure

Gabriele Guidi, Luca Pollonini, Clifford C Dacso, Ernesto Iadanza, Gabriele Guidi, Luca Pollonini, Clifford C Dacso, Ernesto Iadanza

Abstract

Background: Congestive Heart Failure (CHF) is a serious cardiac condition that brings high risks of urgent hospitalization and death. Remote monitoring systems are well-suited to managing patients suffering from CHF, and can reduce deaths and re-hospitalizations, as shown by the literature, including multiple systematic reviews.

Methods: The monitoring system proposed in this paper aims at helping CHF stakeholders make appropriate decisions in managing the disease and preventing cardiac events, such as decompensation, which can lead to hospitalization or death. Monitoring activities are stratified into three layers: scheduled visits to a hospital following up on a cardiac event, home monitoring visits by nurses, and patient's self-monitoring performed at home using specialized equipment. Appropriate hardware, desktop and mobile software applications were developed to enable a patient's monitoring by all stakeholders. For the first two layers, we designed and implemented a Decision Support System (DSS) using machine learning (Random Forest algorithm) to predict the number of decompensations per year and to assess the heart failure severity based on a variety of clinical data. For the third layer, custom-designed sensors (the Blue Scale system) for electrocardiogram (EKG), pulse transit times, bio-impedance and weight allowed frequent collection of CHF-related data in the comfort of the patient's home. We also performed a short-term Heart Rate Variability (HRV) analysis on electrocardiograms self-acquired by 15 healthy volunteers and compared the obtained parameters with those of 15 CHF patients from PhysioNet's PhysioBank archives.

Results: We report numerical performances of the DSS, calculated as multiclass accuracy, sensitivity and specificity in a 10-fold cross-validation. The obtained average accuracies are: 71.9% in predicting the number of decompensations and 81.3% in severity assessment. The most serious class in severity assessment is detected with good sensitivity and specificity (0.87 / 0.95), while, in predicting decompensation, high specificity combined with good sensitivity prevents false alarms. The HRV parameters extracted from the self-measured EKG using the Blue Scale system of sensors are comparable with those reported in the literature about healthy people.

Conclusions: The performance of DSSs trained with new patients confirmed the results of previous work, and emphasizes the strong correlation between some CHF markers, such as brain natriuretic peptide (BNP) and ejection fraction (EF), with the outputs of interest. Comparing HRV parameters from healthy volunteers with HRV parameters obtained from PhysioBank archives, we confirm the literature that considers the HRV a promising method for distinguishing healthy from CHF patients.

Figures

Figure 1
Figure 1
Monitoring Schema and respective stakeholders.
Figure 2
Figure 2
The layers of monitoring: compromise between the follow-up frequency and the prognostic strength of the measured parameters.
Figure 3
Figure 3
Android app to enable nurses to acquire the parameters in the patient's home.
Figure 4
Figure 4
Blue Box Device.
Figure 5
Figure 5
Blue Scale Device.
Figure 6
Figure 6
Cardiologist Dashboard - main.
Figure 7
Figure 7
Cardiologist Dashboard - Patient self-monitoring view.
Figure 8
Figure 8
Strong correlation between BNP (feature 5) and prediction of decompensation.
Figure 9
Figure 9
Strong correlation between BNP (feature 5, capillary measurement) and EF (feature 6) with severity assessment.

References

    1. Takeda A, Sjc T, Rs T, Khan F, Krum H, Underwood M. Clinical service organisation for heart failure ( Review ) 2012.
    1. Wagner EH, Glasgow RE, Davis C, Bonomi AE, Provost L, McCulloch D, Carver P, Sixta C. Quality improvement in chronic illness care: a collaborative approach. The Joint Commission journal on quality improvement. 2001;27(2):63–80. Feb.
    1. Desai AS, Stevenson LW. Rehospitalization for heart failure: predict or prevent? Circulation. 2012;126(4):501–6. doi: 10.1161/CIRCULATIONAHA.112.125435. Jul.
    1. Inglis S, Ra C, Fa M, Ball J, Lewinter C, Cullington D, Stewart S, Jgf C. Structured telephone support or telemonitoring programmes for patients with chronic heart failure ( Review ) The Cochrane Collaboration. 2011;6
    1. Yancy CW, Jessup M, Bozkurt B, Butler J, Casey DE, Drazner MH, Fonarow GC, a Geraci S, Horwich T, Januzzi JL, Johnson MR, Kasper EK, Levy WC, a Masoudi F, McBride PE, McMurray JJV, Mitchell JE, Peterson PN, Riegel B, Sam F, Stevenson LW, Tang WHW, Tsai EJ, Wilkoff BL. 2013 ACCF/AHA guideline for the management of heart failure: a report of the American College of Cardiology Foundation/American Heart Association Task Force on practice guidelines. Circulation. 2013;128(16):e240–327. Oct.
    1. Krumholz HM, Merrill AR, EM S, Al E. Patterns of hospital performance in acute myocardial infarction and heart failure 30-day mortality and readmission. Circ Cardiovasc Qual Outcomes. 2009;2:407–413. doi: 10.1161/CIRCOUTCOMES.109.883256.
    1. Bernheim SM, Grady JN, Lin Z. et al.National patterns of risk-standardized mortality and readmission for acute myocardial infarction and heart failure: update on publicly reported outcomes measures based on the 2010 release. Circ Cardiovasc Qual Outcomes. 2010;3:459–467. doi: 10.1161/CIRCOUTCOMES.110.957613.
    1. Guidi G, Pettenati MC, Melillo P, Iadanza E. A Machine Learning System to Improve Heart Failure Patient Assistance. IEEE Journal of Biomedical and Health Informatics. 2014;18(6):1750–1756.
    1. Guidi G, Melillo P, Pettenati MC, Milli M, Iadanza E. In: The International Conference on Health Informatics SE - 40. Y.-T. Zhang, editor. Vol. 42. Springer International Publishing; 2014. A System to Improve Continuity of Care in Heart Failure Patients; pp. 155–158.
    1. Guidi G, Pettenati MC, Milli M, Iadanza E. A Tool For. Patient Data Recovering Aimed To Machine Learning Supervised Training. IFMBE Proceedings. 2014;41:1899–1902. doi: 10.1007/978-3-319-00846-2_468.
    1. Dolgin M. The Criteria Committee of the New York Heart Association. 9. Boston: Little, Brown & Co; 1994. Nomenclature and Criteria for Diagnosis of Diseases of the Heart and Great Vessels; pp. 253–256.
    1. Guidi G, Melillo P, Pettenati M, Milli M, Iadanza E. Performance Assessment of a Clinical Decision Support System for analysis of Heart Failure. IFMBE Proceedings. 2014;41:1354–1357. doi: 10.1007/978-3-319-00846-2_335.
    1. Pollonini L, Rajan NO, Xu S, Madala S, Dacso CC. A novel handheld device for use in remote patient monitoring of heart failure patients--design and preliminary validation on healthy subjects. Journal of medical systems. 2012;36(2):653–9. doi: 10.1007/s10916-010-9531-y. Apr.
    1. Zhang YL, Zheng YY, Ma ZC, Sun YN. Radial pulse transit time is an index of arterial stiffness. Hypertens Res. 2011;34:884–7. doi: 10.1038/hr.2011.41.
    1. Pollonini L, Padhye N, Re R, Howell P, Simpson RJ, Dacso CC. Pulse transit time measured by photoplethysmography improves the accuracy of heart rate as a surrogate measure of cardiac output, stroke volume and oxygen uptake in response to grade exercise. Physiol Meas. 2015;9;36(5):911–924. Apr.
    1. Pollonini L, Member E, Quadri S, Member N, Chen J, Student I, Ding J, Zheng Z, Naribole S, Mcarthur KK, Knightly EW, Fellow I, Embs CCD. Blue Scale: a multi-sensing device for remote management of congestive heart failure. Annual Meeting of the IEEE Engineering in Medicine and Biology Society (EMBC 2014) September 2010. 2014. p. 2010.
    1. Chen J, Quadri S, Pollonini L, Naribole S, Ding J, Zheng Z, Knightly EW, Dacso CC. Blue Scale: Early Detection of Impending Congestive Heart Failure Events via Wireless Daily Self-Monitoring. IEEE Healthcare Innovation and Point of Care Confer.
    1. Ramshur JT. Design, evaluation, and applicaion of heart rate variability analysis software (HRVAS) 2010.
    1. Melillo P, Fusco R, Sansone M, Bracale M, Pecchia L. Discrimination power of long-term heart rate variability measures for chronic heart failure detection. Medical & biological engineering & computing. 2011;49(1):67–74. doi: 10.1007/s11517-010-0728-5. Jan.
    1. Pecchia L, Melillo P, Sansone M, Bracale M. Discrimination power of short-term heart rate variability measures for CHF assessment. IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society. 2011;15(1):40–6. Jan.
    1. Breiman L. Random Forests. Machine Learning. 2001;45(1):5–32. doi: 10.1023/A:1010933404324.
    1. Guidi G, Pettenati MC, Miniati R, Iadanza E. Random Forest For Automatic Assessment Of Heart Failure Severity In A Telemonitoring Scenario. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. pp. 3230–3233.
    1. Melillo P, De Luca N, Bracale M, Pecchia L. Classification tree for risk assessment in patients suffering from Congestive Heart Failure via long-term Heart Rate Variability. IEEE Journal of Biomedical and Health Informatics. 2013;17(3):727–733.
    1. Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation. pp. e215–e220.
    1. Corrales MM, De B, Torres C, Esquivel AG, Antonio M, Salazar G, Orellana JN. Normal values of heart rate variability at rest in a young healthy and active Mexican population. Health. 2012;4(7):377–385. doi: 10.4236/health.2012.47060.
    1. Nunan D, Sandercock GRH, a Brodie D. A quantitative systematic review of normal values for short-term heart rate variability in healthy adults. Pacing and clinical electrophysiology: PACE. 2010;33(11):1407–17. doi: 10.1111/j.1540-8159.2010.02841.x. Nov.
    1. Liu G, Wang L, Wang Q, Zhou G, Wang Y, Jiang Q. A New Approach to Detect Congestive Heart Failure Using Short-Term Heart Rate Variability Measures. PLoS ONE. 2014;9.4:e93399. Apr.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe