Heart-Rate-Based Machine-Learning Algorithms for Screening Orthostatic Hypotension
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Background and Purpose Many elderly patients are unable to actively stand up by themselves and have contraindications to performing the head-up tilt test (HUTT). We aimed to develop screening algorithms for diagnosing orthostatic hypotension (OH) before performing the HUTT. Methods This study recruited 663 patients with orthostatic intolerance (78 with and 585 without OH, as confirmed by the HUTT) and compared their clinical characteristics. Univariate and multivariate analyses were performed to investigate potential predictors of an OH diagnosis. Machine-learning algorithms were applied to determine whether the accuracy of OH prediction could be used for screening OH without performing the HUTT. Results Differences between expiration and inspiration (E-I differences), expiration:inspiration ratios (E:I ratios), and Valsalva ratios were smaller in patients with OH than in those without OH. The univariate analysis showed that increased age and baseline systolic blood pressure (BP) as well as decreased E-I difference, E:I ratio, and Valsalva ratio were correlated with OH. In the multivariate analysis, increased baseline systolic BP and decreased Valsalva ratio were found to be independent predictors of OH. Using those variables as input features, the classification accuracies of the support vector machine, k-nearest neighbors, and random forest methods were 84.4%, 84.4%, and 90.6%, respectively. Conclusions We have identified clinical parameters that are strongly associated with OH. Machine- learning analysis using those parameters was highly accurate in differentiating OH from non-OH patients. These parameters could be useful screening factors for OH in patients who are unable to perform the HUTT.
Abstract
Background and Purpose Many elderly patients are unable to actively stand up by themselves and have contraindications to performing the head-up tilt test (HUTT). We aimed to develop screening algorithms for diagnosing orthostatic hypotension (OH) before performing the HUTT. Methods This study recruited 663 patients with orthostatic intolerance (78 with and 585 without OH, as confirmed by the HUTT) and compared their clinical characteristics. Univariate and multivariate analyses were performed to investigate potential predictors of an OH diagnosis. Machine-learning algorithms were applied to determine whether the accuracy of OH prediction could be used for screening OH without performing the HUTT. Results Differences between expiration and inspiration (E-I differences), expiration:inspiration ratios (E:I ratios), and Valsalva ratios were smaller in patients with OH than in those without OH. The univariate analysis showed that increased age and baseline systolic blood pressure (BP) as well as decreased E-I difference, E:I ratio, and Valsalva ratio were correlated with OH. In the multivariate analysis, increased baseline systolic BP and decreased Valsalva ratio were found to be independent predictors of OH. Using those variables as input features, the classification accuracies of the support vector machine, k-nearest neighbors, and random forest methods were 84.4%, 84.4%, and 90.6%, respectively. Conclusions We have identified clinical parameters that are strongly associated with OH. Machine- learning analysis using those parameters was highly accurate in differentiating OH from non-OH patients. These parameters could be useful screening factors for OH in patients who are unable to perform the HUTT.
참고문헌 (38)
- Freeman R, "Consensus statement on the definition of orthostatic hypotension, neurally mediated syncope and the postural tachycardia syndrome", Clin Auton Res, 21, pp.69~72 (2011)
- Gupta V, "Orthostatic hypotension in the elderly : diagnosis and treatment", Am J Med, 120, pp.841~847 (2007)
- Task Force for the Diagnosis and Management of Syncope, "Guidelines for the diagnosis and management of syncope (version 2009)", Eur Heart J, 30, pp.2631~2671 (2009)
- Veronese N, "Orthostatic changes in blood pressure and mortality in the elderly: the pro.V.A study", Am J Hypertens, 28, pp.1248~1256 (2015)
- Angelousi A, "Association between orthostatic hypotension and cardiovascular risk, cerebrovascular risk, cognitive decline and falls as well as overall mortality : a systematic review and meta-analysis", J Hypertens, 32, pp.1562~1571 (2014)
- Mol A, "Orthostatic hypotension and falls in older adults : a systematic review and meta-analysis", J Am Med Dir Assoc, 20, pp.589~597 (2019)
- Iseli R, "Orthostatic hypotension and cognition in older adults : a systematic review and meta-analysis", Exp Gerontol, 120, pp.40~49 (2019)
- Shaw BH, "Relationships between orthostatic hypotension, frailty, falling and mortality in elderly care home residents", BMC Geriatr, 19, pp.80~ (2019)
- Fleg JL, "Orthostatic Hypotension in the ACCORD (Action to Control Cardiovascular Risk in Diabetes) blood pressure trial: prevalence, incidence, and prognostic significance", Hypertension, 68, pp.888~895 (2016)
- Parry SW, "The Newcastle protocols 2008 : an update on head-up tilt table testing and the management of vasovagal syncope and related disorders", Heart, 95, pp.416~420 (2009)
- Kim JB, "Utility of corrected QT interval in orthostatic intolerance", PLoS One, 9, pp.e106417~ (2014)
- Kim YH, "Prefrontal hemodynamic changes measured using near-infrared spectroscopy during the Valsalva maneuver in patients with orthostatic intolerance", Neurophotonics, 5, pp.015002~ (2018)
- Kim HA, "Detailed relationship between the pattern of blood pressure change during the valsalva maneuver and the degree of orthostatic hypotension during the head-up tilt test in patients with orthostatic intolerance: a retrospective case-control study", Medicine (Baltimore), 95, pp.e3608~ (2016)
- Palamarchuk IS, "The utility of Valsalva maneuver in the diagnoses of orthostatic disorders", Am J Physiol Regul Integr Comp Physiol, 310, pp.R243~R252 (2016)
- Lee SP, "Highly flexible, wearable, and disposable cardiac biosensors for remote and ambulatory monitoring", NPJ Digit Med, 1, pp.2~ (2018)
- 석흥열, "Patterns of Orthostatic Blood Pressure Changes in Patients with Orthostatic Hypotension", Journal of Clinical Neurology, 14(3), pp.283~290 (2018), 대한신경과학회[DOI]
- 구용서, "Pitfalls in Using Electrophysiological Studies to Diagnose Neuromuscular Disorders", Journal of Clinical Neurology, 8(1), pp.1~14 (2012), 대한신경과학회
- Kim JB, "Autonomic dysfunction according to disease progression in Parkinson’s disease", Parkinsonism Relat Disord, 20, pp.303~307 (2014)
- Low PA, "Composite autonomic scoring scale for laboratory quantification of generalized autonomic failure", Mayo Clin Proc, 68, pp.748~752 (1993)
- Low PA, "Autonomic nervous system function", J Clin Neurophysiol, 10, pp.14~27 (1993)
- Low PA, "Effect of age and gender on sudomotor and cardiovagal function and blood pressure response to tilt in normal subjects", Muscle Nerve, 20, pp.1561~1568 (1997)
- Vogel ER, "Blood pressure recovery from Valsalva maneuver in patients with autonomic failure", Neurology, 65, pp.1533~1537 (2005)
- The Consensus Committee of the American Autonomic Society and the American Academy of Neurology, "Consensus statement on the definition of orthostatic hypotension, pure autonomic failure, and multiple system atrophy", Neurology, 46, pp.1470~ (1996)
- Kubat M, "Addressing the curse of imbalanced training sets:one-sided selection", Proceedings of the Fourteenth International Conference on Machine Learning, pp.179~186 (1997)
- Cortes C, "Support-vector networks", Mach Learn, 20, pp.273~297 (1995)
- Weinberger KQ, "Advances in Neural Information Processing Systems 18", pp.1473~1480 (2006), MIT Press
- Liaw A, "Classification and regression by randomForest", R News, 2, pp.18~22 (2002)
- Pedregosa F, "Scikit-learn : machine learning in Python", J Mach Learn Res, 12, pp.2825~2830 (2011)
- Low PA, "Management of neurogenic orthostatic hypotension : an update", Lancet Neurol, 7, pp.451~458 (2008)
- Phillip A. Low, "Autonomic Function Tests: Some Clinical Applications Open Access", Journal of Clinical Neurology, 9(1), pp.1~8 (2013), 대한신경과학회[DOI]
- Shields RW Jr, "Heart rate variability with deep breathing as a clinical test of cardiovagal function", Cleve Clin J Med, 76(Suppl 2), pp.S37~S40 (2009)
- Padilla JM, "Assessment of relationships between blood pressure, pulse wave velocity and digital volume pulse", Proceedings of 2006 Computers in Cardiology, pp.893~896 (2006), IEEE
- Chandrasekaran V, "Cuffless differential blood pressure estimation using smart phones", IEEE Trans Biomed Eng, 60, pp.1080~1089 (2013)
- Jones DW, "Measuring blood pressure accurately : new and persistent challenges", JAMA, 289, pp.1027~1030 (2003)
- Beevers G, "ABC of hypertension: blood pressure measurement. Part II-conventional sphygmomanometry: technique of auscultatory blood pressure measurement", BMJ, 322, pp.1043~1047 (2001)
- Rajendra Acharya U, "Heart rate variability : a review", Med Biol Eng Comput, 44, pp.1031~1051 (2006)
- Grubb BP, "Tilt table testing : concepts and limitations", Pacing Clin Electrophysiol, 20, pp.781~787 (1997)
- Ward C, "Reproducibility of orthostatic hypotension in symptomatic elderly", Am J Med, 100, pp.418~422 (1996)