Classification of orthostatic intolerance through data analytics.
Classification
Clustering
Machine learning
Orthostatic intolerance
Syncope
Journal
Medical & biological engineering & computing
ISSN: 1741-0444
Titre abrégé: Med Biol Eng Comput
Pays: United States
ID NLM: 7704869
Informations de publication
Date de publication:
Mar 2021
Mar 2021
Historique:
received:
19
03
2020
accepted:
15
01
2021
pubmed:
15
2
2021
medline:
30
9
2021
entrez:
14
2
2021
Statut:
ppublish
Résumé
Imbalance in the autonomic nervous system can lead to orthostatic intolerance manifested by dizziness, lightheadedness, and a sudden loss of consciousness (syncope); these are common conditions, but they are challenging to diagnose correctly. Uncertainties about the triggering mechanisms and the underlying pathophysiology have led to variations in their classification. This study uses machine learning to categorize patients with orthostatic intolerance. We use random forest classification trees to identify a small number of markers in blood pressure, and heart rate time-series data measured during head-up tilt to (a) distinguish patients with a single pathology and (b) examine data from patients with a mixed pathophysiology. Next, we use Kmeans to cluster the markers representing the time-series data. We apply the proposed method analyzing clinical data from 186 subjects identified as control or suffering from one of four conditions: postural orthostatic tachycardia (POTS), cardioinhibition, vasodepression, and mixed cardioinhibition and vasodepression. Classification results confirm the use of supervised machine learning. We were able to categorize more than 95% of patients with a single condition and were able to subgroup all patients with mixed cardioinhibitory and vasodepressor syncope. Clustering results confirm the disease groups and identify two distinct subgroups within the control and mixed groups. The proposed study demonstrates how to use machine learning to discover structure in blood pressure and heart rate time-series data. The methodology is used in classification of patients with orthostatic intolerance. Diagnosing orthostatic intolerance is challenging, and full characterization of the pathophysiological mechanisms remains a topic of ongoing research. This study provides a step toward leveraging machine learning to assist clinicians and researchers in addressing these challenges. Graphical abstract Machine learning tools utilized to analyze heart rate (HR) and blood pressure (BP) time-series data from syncope and control patients. Results show that machine learning can provide accurate classification of disease groups for 98% of patients and we identified two subgroups within the control patients differentiated by their BP response.
Identifiants
pubmed: 33582941
doi: 10.1007/s11517-021-02314-0
pii: 10.1007/s11517-021-02314-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
621-632Subventions
Organisme : Directorate for Mathematical and Physical Sciences
ID : 1557761
Organisme : Directorate for Mathematical and Physical Sciences
ID : 1745654
Organisme : NIGMS NIH HHS
ID : 5P50GM094503-06
Pays : United States
Organisme : NIGMS NIH HHS
ID : 5P50GM094503-06
Pays : United States
Références
Bartoletti A, Alboni P, Ammirati F, Brignole M, Del Rosso A, Manzillo G, Menozzi C, Raviele A, Sutton R (2000) The Italian protocol: a simplified head-up tilt testing potentiated with oral nitroglycerin to assess patients with unexplained syncope. Europace 2(4):339–342
pubmed: 11194602
Breiman L (2001) Random forests. Mach Learn 45:5–32
Brennan M, Palaniswami M, Kamen P (2001) Do existing measures of poincaré plot geometry reflect nonlinear features of heart rate variability? Cureus 48(11):1342–1347
Brignole M (2007) Diagnosis and treatment of syncope. Heart 93(1):130–136
pubmed: 17170354
pmcid: 1861366
Brignole M, Alboni P, Benditt D, Bergfeldt L, Blanc JJ, Thomsen PB, van Dijk J, Fitzpatrick A, Hohnloser S, Janousek J, Kapoor W, Kenny R, Kulakowski P, Masotti G, Moya A, Raviele A, Sutton R, Theodorakis G, Ungar A, Wieling W (2004) Guidelines on management (diagnosis and treatment) of syncope. Eurospace 6(6):467–573
Brignole M, Moya A, de Lange F, Deharoa JC, Elliott M, Fanciulli A, Federowski A, Furlan R, Kenny R, Martin A, Probst V, Reed M, Rice C, Sutton R, Ungar A, van Dijk J (2018) 2018 ESC guidelines for the diagnosis and management of syncope. Eur Heart J 39(21):1883–1948
pubmed: 29562304
Brignole M, Ungar A, Casagranda I, Gulizia M, Lunati M, Ammirati F, Del Rosso A, Sasdelli M, Santini M, Maggi R, Vitale E, Morrione A, Francese G, Vecchi M, Giada F (2010) Syncope Unit (SUP) investigators: prospective multicentre systematic guideline-based management of patients referred to the syncope units of general hospitals. Europace 12(1):109–118
pubmed: 19948566
Cubera K, Stryjewski P, Kuczaj A, Nessler J, Nowalany-Kozielska E, Pytko-Polonzyk J (2017) The impact of gender on the frequency of syncope provoking factors and prodromal signs in patients with vasovagal syncope. Przeglad Lekarski 74(4):147–149
pubmed: 29696951
Ferreira R, da Silva L (2016) The current indication for pacemaker in patients with cardioinhibitory vasovagal syncope. Open Cardiovasc Med J 10:179–187
Fletcher J (2020) What to know about vasovagal syncope. https://www.medicalnewstoday.com/articles/327406
Fu Q, Vangundy T, Galbreath M, Shibata S, Jain M, Hastings J, Bhella P, Levine B (2010) Cardiac origins of the postural orthostatic tachycardia syndrome. J Am Coll Cardiol 55(25):2858–2868
pubmed: 20579544
pmcid: 2914315
Furlan R, Diedrich A, Rimoldi A, Palazzolo L, Porta C, Diedrich L, Harris P, Sleight P, Biagioni I, Robertson D, Bernardi L (2003) Effects of unilateral and bilateral carotid baroreflex stimulation on cardiac and neural sympathetic discharge oscillatory patterns. Circulation 108(6):717–723
pubmed: 12900347
Furlan R, Jacob G, Snell M, Robertson D, Porta A, Parris P, Mosqueda-Garcia R (1998) Chronic orthostatic intolerance: a disorder with discordant cardiac and vascular sympathetic control. Circulation 98(20):2154–2159
pubmed: 9815870
Geddes J, Mehlsen J, Olufsen M (2020) Characterization of blood pressure and heart rate oscillations in pots patients via uniform phase empirical mode decomposition. IEEE Trans Biomed Eng 67(11):3016–3025
pubmed: 32078525
Greve Y, Geier F, Popp S, Bertsch T, Singler K, Meier F, Smolarsky A, Mang H, Müller C, Christ M (2014) The prevalence and prognostic significance of near syncope and syncope: a prospective study of 395 cases in an emergency department (the speed study). Dtsch Arztebl Int 111(12):197–204
pubmed: 24717304
pmcid: 3983697
Guyton A, Hall J (2016) Medical physiology, 13th edn. Elsevier, Philadelphia
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Springer Series in Statistics. Springer, New York
Jacob G, Barbic F, Glago M, Dipaola F, Porta A, Furlan R (2018) Cardiovascular autonomic profile in women with constitutional hypotension. J Hypertens 36(10):2068–2076
pubmed: 29781840
Khodor N (2014) Dynamical analysis of mutivariate time series for the early detection of syncope during head-up tilt test. Ph.D. thesis, Université Rennes 1, Rennes, France
Khodor N, Carrault G, Matelot D, Amoud H, Khalil M, Boullay N, Carré F, Hernandez A (2016) Early syncope detection during head up tilt test by analyzing interactions between cardio-vascular signals. Dig Signal Process 49:86–94
Klemenc M, Strumbelj E (2015) Predicting the outcome of head-up tilt test using heart rate variability and baroreflex sensitivity parameters in patients with vasovagal syncope. Clinical Autonomic Res 25 (6):391–398
Kuran A, Erickson M, Petersen M, Franzen A, Williams T, Sutton R (2000) Respiratory changes in vasovagal syncope. J Cardiovasc Electrophysiol 11(6):607–611
Kurbaan A, Bowker T, Wijesekera N, Heaven D, Itty S, Sutton R (2003) Age and hemodynamic responses to tilt testing in those with syncope of unknown origin. J Am Coll Cardiol 41(6):1004–1007
pubmed: 12651049
Li H, Liao Y, Han Z, Wang Y, Liu P, Zhang C, Tang C, Du J, Jin H (2018) Head-up tilt test provokes dynamic alterations in total peripheral resistance and cardiac output in children with vasovagal syncope. Acta Paediatr 107(10):1786–1791
pubmed: 29603793
Mark A (1983) The bezold-jarisch reflex revisited: clinical implications of inhibitory reflexes originating in the heart. JAJCC 1(1):69–72
Mehlsen J, Kaijer M, Mehlsen AB (2008) Autonomic and electrocardiographic changes in cardioinhibitory syncope. Europace 10(1):91–95
pubmed: 17971422
Moya A, Sutton R, Ammirati F, Blanc JJ, Brignole M, Dahm J, Deharo JC, Gajek J, Gjesdal K, Krahn A, Massin M, Pepi M, Pezawas T, Ruiz Granell R, Sarasin F, Ungar A, van Dijk J, Walma E, Wieling W (2009) Guidelines for the diagnosis and management of syncope (version 2009). Europ Heart J 30:2631–2671
Ocon A, Medow M, Taneja I, Stewart J (2011) Respiration drives phase synchronization between blood pressure and rr interval following loss of cardiovagal baroreflex during vasovagal syncope. Am J Physiol 300(2):H527–H540
Parati G, Bretinieri M, Pomidossi G, Casadei R, Groppeli A, Pedotti A, Zanchetti A, Mancia G (1988) Evaluation of the baroreceptor-heart rate reflex by 24-hour intra-arterial blood pressure monitoring in humans. Hypertension 12(2):214– 222
pubmed: 3410530
Parlow J, Viale J, Annat G, Hughson R, Quintin L (1995) Spontaneous cardiac baroreflex in humans: comparison with drug-induced responses. Hypertension 25(5):1058–1068
pubmed: 7737717
Probst M, Kanzaria H, Gbedemah M, Richardson L, Sun B (2015) National trends in resource utilization associated with ed visits for syncope. American. J Emergency Med 33(8):998–1001
Randall E, Billeschou A, Brinth L, Mehlsen J, Olufsen M (2019) A model-based analysis of autonomic nervous function in response to the valsalva maneuver. J Appl Physiol 127(5):1386– 1402
pubmed: 31369335
Randall E, Randolph N, Olufsen M (2020) Persistent instability in a nonhomogeneous delay differential equation system of the valsalva maneuver. Math Biosci 319:108292
pubmed: 31785229
Remmen J, Aengevaeren W, Verheugt F, van ver Werf T, Luijten H, A Bos RJ (2002) Finapres arterial pulse wave analysis with modelflow is not a reliable non-invasive method for assessment of cardiac output. Clin Sci (Lond) 103(2):143–149
Robertson D, Biaggioni I, Low P (2011) Primer on the autonomic nervous system, 3rd edn. Elsevier, London
Romme J, van Dijk N, Boer K, Dekker L, Stam J, Reitsma J, Wieling W (2008) Influence of age and gender on the occurrence and presentation of reflex syncope. Clin Autonom Res 28(3):127–133
Rousseeuw P (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comp Appl Math 20:53–65
Sander-Jensen K, Mehlsen J, Stadeager C, Christensen N, Fahrenkrug J, Schwartz T, Warberg J, Bie P (1988) Increase in vagal activity during hypotensive lower-body negative pressure in humans. Am J Physiol 255(1 Pt 2):R149–R156
pubmed: 3394838
Sheldon R, Grubb B, Olshansky B (2015) 2015 heart rhythm society expert consensus statement on the diagnosis and treatment of postural tachycardia syndrome, inappropriate sinus tachycardia, and vasovagal syncope. Heart Rhythm 12(6):e41–e63
pubmed: 25980576
pmcid: 5267948
van Dijk J, Thijs R, Benditt D, Wieling W (2009) A guide to disorders causing transient loss of consciousness: focus on syncope. Nat Rev Neurol 5(8):438–448
pubmed: 19597513
Virag N, Sutton R, Vetter R, Markowitz T (2007) Prediction of vasovagal syncope from heart rate and blood pressure trend and variability: experience in 1,155 patients. Heart Rhythm 4(11):1375–1382
pubmed: 17954394
Vlasta B, Marchi A, De Maria B, Rossato G, Nollo G, Faes L, Porta A (2016) Nonlinear effects of respiration on the crosstalk between cardiovascular and cerebrovascular systems. Philos Trans A Math Phys Eng Sci 374(2067):2015079
Williams N, Wind-Willassen O, Wright A, Program R, Mehlsen J, Ottesen J, Olufsen M (2014) Patient-specific modelling of head-up tilt. Math Med Biol 31(4):365–392
pubmed: 23959910