ETRI Journal

  • 제45권1호
  • /
  • Pages.105-118
  • /
  • 2023
  • /
  • 1225-6463(pISSN)
  • /
  • 2233-7326(eISSN)
한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

Automated detection of panic disorder based on multimodal physiological signals using machine learning

  • Eun Hye Jang (Welfare and Medical ICT Research Department, Electronics and Telecommunications Research Institute) ;
  • Kwan Woo Choi (Department of Psychiatry, Korea University) ;
  • Ah Young Kim (Welfare and Medical ICT Research Department, Electronics and Telecommunications Research Institute) ;
  • Han Young Yu (Industry and IoT Intelligence Research Department, Electronics and Telecommunications Research Institute) ;
  • Hong Jin Jeon (Department of Psychiatry in the Samsung Medical Center, Sungkyunkwan University School of Medicine) ;
  • Sangwon Byun (Department of Electronics Engineering, Incheon National University)
  • 투고 : 2021.08.30
  • 심사 : 2022.05.02
  • 발행 : 2023.02.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

We tested the feasibility of automated discrimination of patients with panic disorder (PD) from healthy controls (HCs) based on multimodal physiological responses using machine learning. Electrocardiogram (ECG), electrodermal activity (EDA), respiration (RESP), and peripheral temperature (PT) of the participants were measured during three experimental phases: rest, stress, and recovery. Eleven physiological features were extracted from each phase and used as input data. Logistic regression (LoR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) algorithms were implemented with nested cross-validation. Linear regression analysis showed that ECG and PT features obtained in the stress and recovery phases were significant predictors of PD. We achieved the highest accuracy (75.61%) with MLP using all 33 features. With the exception of MLP, applying the significant predictors led to a higher accuracy than using 24 ECG features. These results suggest that combining multimodal physiological signals measured during various states of autonomic arousal has the potential to differentiate patients with PD from HCs.

키워드

과제정보

This work was supported by the Electronics and Telecommunications Research Institute (ETRI)'s internal funds, Development of Digital Biopsy Core Technology for high-precision Diagnosis and Therapy of Senile Disease (21YR2500), Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. 2015-0-00062), and National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1F1A1049236).

참고문헌

  1. A. Y. Kim, E. H. Jang, S. Kim, K. W. Choi, H. J. Jeon, H. Y. Yu, and S. Byun, Automatic detection of major depressive disorder using electrodermal activity, Sci. Rep. 8 (2018), 17030. 
  2. S. Byun, A. Y. Kim, E. H. Jang, S. Kim, K. W. Choi, H. Y. Yu, and H. J. Jeon, Detection of major depressive disorder from linear and nonlinear heart rate variability features during mental task protocol, Comput. Biol. Med. 112 (2019), 103381. 
  3. S. Byun, A. Y. Kim, E. H. Jang, S. Kim, K. W. Choi, H. Y. Yu, and H. J. Jeon, Entropy analysis of heart rate variability and its application to recognize major depressive disorder: A pilot study, Technol. Health Care 27 (2019), 407-424.  https://doi.org/10.3233/THC-199037
  4. G. Valenza, L. Citi, C. Gentili, A. Lanata, E. P. Scilingo, and R. Barbieri, Point-process nonlinear autonomic assessment of depressive states in bipolar patients, Methods Inf. Med. 53 (2014), 296-302.  https://doi.org/10.3414/ME13-02-0036
  5. P. de Jonge, A. M. Roest, C. C. Lim, S. E. Florescu, E. J. Bromet, D. J. Stein, M. Harris, V. Nakov, J. M. Caldas-deAlmeida, D. Levinson, A. O. al-Hamzawi, J. M. Haro, M. C. Viana, G. Borges, S. O'Neill, G. de Girolamo, K. Demyttenaere, O. Gureje, N. Iwata, S. Lee, C. Hu, A. Karam, J. Moskalewicz, V. Kovess-Masfety, F. Navarro-Mateu, M. O. Browne, M. Piazza, J. Posada-Villa, Y. Torres, M. ten Have, R. C. Kessler, and K. M. Scott, Cross-national epidemiology of panic disorder and panic attacks in the world mental health surveys, Depress. Anxiety 33 (2016), 1155-1177.  https://doi.org/10.1002/da.22572
  6. J. C. Ballenger, Toward an integrated model of panic disorder, Am. J. Orthopsychiatry 59 (1989), 284-293.  https://doi.org/10.1111/j.1939-0025.1989.tb01661.x
  7. D. F. Klein and M. Fink, Psychiatric reaction patterns to imipramine, Am. J. Psychiatry 119 (1962), 432-438.  https://doi.org/10.1176/ajp.119.5.432
  8. S. Freud, The aetiology of hysteria, In The standard edition of the complete psychological works of Sigmund Freud, J. Strachey (ed.), Hogarth Press, London, 1986, 162-222. 
  9. American Psychiatric Association, Diagnostic and statistical manual for mental disorders, 4th ed. DSM-IV, American Psychiatric Press, Washington DC, USA, 1994. 
  10. F. N. Busch, B. L. Milrod, and M. B. Singer, Theory and technique in psychodynamic treatment of panic disorder, J. Psychother. Pract. Res. 8 (1999), 234-242. 
  11. M. K. Hasan and R. P. Mooney, Panic disorder: A review, Compr. Ther. 12 (1986), 3-7. 
  12. R. R. Freedman, P. Ianni, E. Ettedgui, and N. Puthezhath, Ambulatory monitoring of panic disorder, Arch. Gen. Psychiatry 42 (1985), 244-248.  https://doi.org/10.1001/archpsyc.1985.01790260038004
  13. M. R. Liebowitz, J. M. Gorman, A. J. Fyer, M. Levitt, D. Dillon, G. Levy, I. L. Appleby, S. Anderson, M. Palij, S. O. Davies, and D. F. Klein, Lactate provocation of panic attacks. II. Biochemical and physiological findings, Arch. Gen. Psychiatry 42 (1985), 709-719.  https://doi.org/10.1001/archpsyc.1985.01790300077010
  14. J. A. Chalmers, D. S. Quintana, M. J. A. Abbott, and A. H. Kemp, Anxiety disorders are associated with reduced heart rate variability: A meta-analysis, Front. Psych. 5 (2014), 80. 
  15. P. J. Tully, S. M. Cosh, and B. T. Baune, A review of the affects of worry and generalized anxiety disorder upon cardiovascular health and coronary heart disease, Psychol. Health Med. 18 (2013), 627-644.  https://doi.org/10.1080/13548506.2012.749355
  16. A. Pittig, J. J. Arch, C. W. R. Lam, and M. G. Craske, Heart rate and heart rate variability in panic, social anxiety, obsessivecompulsive, and generalized anxiety disorders at baseline and in response to relaxation and hyperventilation, Int. J. Psychophysiol. 87 (2013), 19-27.  https://doi.org/10.1016/j.ijpsycho.2012.10.012
  17. H. Cohen, J. Benjamin, A. B. Geva, M. A. Matar, Z. Kaplan, and M. Kotler, Autonomic dysregulation in panic disorder and in post-traumatic stress disorder: Application of power spectrum analysis of heart rate variability at rest and in response to recollection of trauma or panic attacks, Psychiatry Res. 96 (2000), 1-13.  https://doi.org/10.1016/S0165-1781(00)00195-5
  18. A. Garakani, J. M. Martinez, C. J. Aaronson, A. Voustianiouk, H. Kaufmann, and J. M. Gorman, Effect of medication and psychotherapy on heart rate variability in panic disorder, Depress. Anxiety 26 (2009), 251-258.  https://doi.org/10.1002/da.20533
  19. S. J. Petruzzello, D. M. Landers, B. D. Hatfield, K. A. Kubitz, and W. Salazar, A meta-analysis on the anxiety-reducing effects of acute and chronic exercise. Outcomes and mechanisms, Sports Med. 11 (1991), 143-182.  https://doi.org/10.2165/00007256-199111030-00002
  20. D. J. McEntee and R. P. Halgin, Cognitive group therapy and aerobic exercise in the treatment of anxiety, J. Coll. Stud. Psychother. 13 (1999), 37-55.  https://doi.org/10.1300/J035v13n03_04
  21. K. L. Rennie, H. Hemingway, M. Kumari, E. Brunner, M. Malik, and M. Marmot, Effects of moderate and vigorous physical activity on heart rate variability in a British study of civil servants, Am. J. Epidemiol. 158 (2003), 135-143.  https://doi.org/10.1093/aje/kwg120
  22. M. E. Alvarenga, J. C. Richards, G. Lambert, and M. D. Esler, Psychophysiological mechanisms in panic disorder: A correlative analysis of noradrenaline spillover, neuronal noradrenaline reuptake, power spectral analysis of heart rate variability, and psychological variables, Psychosom. Med. 68 (2006), 8-16.  https://doi.org/10.1097/01.psy.0000195872.00987.db
  23. A. Kotianova, M. Kotian, M. Slepecky, M. Chupacova, J. Prasko, and I. Tonhajzerova, The differences between patients with panic disorder and healthy controls in psychophysiological stress profile, Neuropsychiatr. Dis. Treat. 14 (2018), 435-441.  https://doi.org/10.2147/NDT.S153005
  24. R. Vetrugno, R. Liguori, P. Cortelli, and P. Montagna, Sympathetic skin response: Basic mechanisms and clinical applications, Clin. Auton. Res. 13 (2003), 256-270.  https://doi.org/10.1007/s10286-003-0107-5
  25. R. R. Freedman, P. Ianni, E. Ettedgui, R. Pohl, and J. M. Rainey, Psychophysiological factors in panic disorder, Psychopathology 17 (1984), 66-73.  https://doi.org/10.1159/000284079
  26. D. McDuff, S. Gontarek, and R. Picard, Remote measurement of cognitive stress via heart rate variability, (Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, USA), Aug. 2014, pp. 2957-2960. 
  27. G. Giannakakis, D. Grigoriadis, K. Giannakaki, O. Simantiraki, A. Roniotis, and M. Tsiknakis, Review on psychological stress detection using biosignals, IEEE Trans. Affect. Comput. 13 (2019), 440-460.  https://doi.org/10.1109/TAFFC.2019.2927337
  28. P. Grossman, Respiration, stress, and cardiovascular function, Psychophysiology 20 (1983), 284-300.  https://doi.org/10.1111/j.1469-8986.1983.tb02156.x
  29. C. Pruneti, C. Cosentino, M. Sgromo, and A. Innocenti, Skin conductance response as a decisive variable in individuals with a DSM-IV TR axis I diagnosis, JMED Res. 2014 (2014), 565009. 
  30. C. Pruneti, M. Sacco, C. Cosentino, and D. Sgromo, Relevance of autonomic arousal in the stress response in psychopathology, J. Basic Appl. Sci. 12 (2016), 176-184.  https://doi.org/10.6000/1927-5129.2016.12.26
  31. K. S. Na, S. E. Cho, and S. J. Cho, Machine learning-based discrimination of panic disorder from other anxiety disorders, J. Affect. Disord. 278 (2021), 1-4.  https://doi.org/10.1016/j.jad.2020.09.027
  32. U. Lueken, B. Straube, Y. Yang, T. Hahn, K. Beesdo-Baum, H. U. Wittchen, C. Konrad, A. Strohle, A. Wittmann, A. L. Gerlach, B. Pfleiderer, V. Arolt, and T. Kircher, Separating depressive comorbidity from panic disorder: A combined functional magnetic resonance imaging and machine learning approach, J. Affect. Disord. 184 (2015), 182-192.  https://doi.org/10.1016/j.jad.2015.05.052
  33. B. Sundermann, J. Bode, U. Lueken, D. Westphal, A. L. Gerlach, B. Straube, H. U. Wittchen, A. Strohle, A. Wittmann, C. Konrad, T. Kircher, V. Arolt, and B. Pfleiderer, Support vector machine analysis of functional magnetic resonance imaging of interoception does not reliably predict individual outcomes of cognitive behavioral therapy in panic disorder with agoraphobia, Front. Psych. 8 (2017), 1-11. 
  34. G. D. Fuller, Biofeedback methods and procedures in clinical practice, Biofeedback Press, San Francisco, USA, 1979. 
  35. T. Hoehn, S. Braune, G. Scheibe, and M. Albus, Physiological, biochemical and subjective parameters in anxiety patients with panic disorder during stress exposure as compared with healthy controls, Eur. Arch. Psychiatry Clin. Neurosci. 247 (1997), 264-274.  https://doi.org/10.1007/BF02900305
  36. M. Lehofer, M. Moser, R. Hoehn-Saric, D. McLeod, P. Liebmann, B. Drnovsek, S. Egner, G. Hildebrandt, and H. G. Zapotoczky, Major depression and cardiac autonomic control, Biol. Psychiatry 42 (1997), 914-919.  https://doi.org/10.1016/S0006-3223(96)00494-5
  37. P. Zarjam, J. Epps, F. Chen, and N. H. Lovell, Estimating cognitive workload using wavelet entropy-based features during an arithmetic task, Comput. Biol. Med. 43 (2013), 2186-2195.  https://doi.org/10.1016/j.compbiomed.2013.08.021
  38. M. K. Shear, T. A. Brown, D. H. Barlow, R. Money, D. E. Sholomskas, S. W. Woods, J. M. Gorman, and L. A. Papp, Multicenter collaborative panic disorder severity scale, Am. J. Psychiatry 154 (1997), 1571-1575.  https://doi.org/10.1176/ajp.154.11.1571
  39. M. Hamilton, The assessment of anxiety states by rating, Br. J. Med. Psychol. 32 (1959), 50-55.  https://doi.org/10.1111/j.2044-8341.1959.tb00467.x
  40. J. F. Thayer, S. S. Yamamoto, and J. F. Brosschot, The relationship of autonomic imbalance, heart rate variability and cardiovascular disease risk factors, Int. J. Cardiol. 141 (2010), 122-131.  https://doi.org/10.1016/j.ijcard.2009.09.543
  41. M. Liu, M. Wang, J. Wang, and D. Li, Comparison of random forest, support vector machine and back propagation neural network for electronic tongue data classification: Application to the recognition of orange beverage and Chinese vinegar, Sens. Actuators B 177 (2013), 970-980.  https://doi.org/10.1016/j.snb.2012.11.071
  42. G. Sun, T. Shinba, T. Kirimoto, and T. Matsui, An objective screening method for major depressive disorder using logistic regression analysis of heart rate variability data obtained in a mental task paradigm, Front. Psych. 7 (2016), 180. 
  43. G. C. Cawley and N. L. C. Talbot, On over-fitting in model selection and subsequent selection bias in performance evaluation, J. Mach. Learn. Res. 11 (2010), 2079-2107. 
  44. S. Saeb, L. Lonini, A. Jayaraman, D. C. Mohr, and K. P. Kording, The need to approximate the use-case in clinical machine learning, GigaScience 6 (2017), 1-9.  https://doi.org/10.1093/gigascience/gix019
  45. A. M. Molinaro, R. Simon, and R. M. Pfeiffer, Prediction error estimation: A comparison of resampling methods, Bioinformatics 21 (2005), 3301-3307.  https://doi.org/10.1093/bioinformatics/bti499
  46. G. Chandrashekar and F. Sahin, A survey on feature selection methods, Comput. Electr. Eng. 40 (2014), 16-28.  https://doi.org/10.1016/j.compeleceng.2013.11.024
  47. A. Kraskov, H. Stogbauer, and P. Grassberger, Estimating mutual information, Phys. Rev. E - Stat. Phys. Plasmas Fluids Relat. Interdiscip. Top. 69 (2004), 066138. 
  48. B. C. Ross, Mutual information between discrete and continuous data sets, PLoS ONE 9 (2014), e87357. 
  49. K. W. Choi, E. H. Jang, A. Y. Kim, M. Fava, D. Mischoulon, G. I. Papakostas, D. J. Kim, K. Kim, H. Y. Yu, and H. J. Jeon, Heart rate variability for treatment response between patients with major depressive disorder versus panic disorder: A 12-week followup study, J. Affect. Disord. 246 (2019), 157-165.  https://doi.org/10.1016/j.jad.2018.12.048
  50. J. M. Martinez, A. Garakani, H. Kaufmann, C. J. Aaronson, and J. M. Gorman, Heart rate and blood pressure changes during autonomic nervous system challenge in panic disorder patients, Psychosom. Med. 72 (2010), 442-449.  https://doi.org/10.1097/PSY.0b013e3181d972c2
  51. G. G. Berntson, J. Thomas Bigger JR., D. L. Eckberg, P. Grossman, P. G. Kaufmann, M. Malik, H. N. Nagaraja, S. W. Porges, J. P. Saul, P. H. Stone, and M. W. van der Molen, Heart rate variability: Origins, methods, and interpretive caveats, Psychophysiology 34 (1997), 623-648.  https://doi.org/10.1111/j.1469-8986.1997.tb02140.x
  52. M. Malik, J. T. Bigger, A. J. Camm, R. E. Kleiger, A. Malliani, A. J. Moss, and P. J. Schwartz, Heart rate variability: Standards of measurement, physiological interpretation, and clinical use, Eur. Heart J. 17 (1996), 354-381.  https://doi.org/10.1093/oxfordjournals.eurheartj.a014868
  53. E.-H. Kang, I. S. Lee, J. E. Park, K. J. Kim, and B. H. Yu, Platelet serotonin transporter function and heart rate variability in patients with panic disorder, J. Korean Med. Sci. 25 (2010), 613-618.  https://doi.org/10.3346/jkms.2010.25.4.613
  54. J. M. Gorman and R. P. Sloan, Heart rate variability in depressive and anxiety disorders, Am. Heart J. 140 (2000), 77-83.  https://doi.org/10.1067/mhj.2000.109981
  55. J. F. Brosschot, B. Verkuil, and J. F. Thayer, Exposed to events that never happen: Generalized unsafety, the default stress response, and prolonged autonomic activity, Neurosci. Biobehav. Rev. 74 (2017), 287-296.  https://doi.org/10.1016/j.neubiorev.2016.07.019
  56. J. F. Brosschot, Markers of chronic stress: Prolonged physiological activation and (un)conscious perseverative cognition, Neurosci. Biobehav. Rev. 35 (2010), 46-50.  https://doi.org/10.1016/j.neubiorev.2010.01.004
  57. E.-H. Jang, B. J. Park, M. S. Park, S. H. Kim, and J. H. Sohn, Analysis of physiological signals for recognition of boredom, pain, and surprise emotions, J. Physiol. Anthropol. 34 (2015), 25. 
  58. U. Miura, The effect of variations in relative humidity upon skin temperature and sense of comfort, Am. J. Epidemiol. 13 (1931), 432-459.  https://doi.org/10.1093/oxfordjournals.aje.a117129
  59. F. B. Talbot, V. Bates, E. Bates, and A. J. Dalrymple, Skin temperatures of children, Am. J. dis. Child. 42 (1931), 965-967. 
  60. H. Helson and L. Quantius, Changes in skin temperature following intense stimulation, J. Exp. Psychol. 17 (1934), 20-35.  https://doi.org/10.1037/h0074670
  61. J. A. Gray, The neuropsychology of anxiety, Br. J. Psychol. 69 (1978), 417-434.  https://doi.org/10.1111/j.2044-8295.1978.tb02118.x
  62. D. C. Fowles, The three arousal model: Implications of Gray's two-factor learning theory for heart rate, electrodermal activity, and psychopathy, Psychophysiology 17 (1980), 87-104.  https://doi.org/10.1111/j.1469-8986.1980.tb00117.x
  63. D. C. Fowles, Psychophysiology and psychopathology: A motivational approach, Psychophysiology 25 (1988), 373-391.  https://doi.org/10.1111/j.1469-8986.1988.tb01873.x
  64. M. Grassi, D. Caldirola, G. Vanni, G. Guerriero, M. Piccinni, A. Valchera, and G. Perna, Baseline respiratory parameters in panic disorder: A meta-analysis, J. Affect. Disord. 146 (2013), 158-173.  https://doi.org/10.1016/j.jad.2012.08.034
  65. R. Hoehn-Saric and D. R. McLeod, Somatic manifestations of normal and pathological anxiety, In Biology of anxiety disorders, R. Hoehn-Saric, D. R. McLeod (eds.), American Psychiatric Association, Arlington, VA, USA, 1993, 177-222. 
  66. M. B. Stein and G. J. C. Asmundson, Autonomic function in panic disorder: Cardiorespiratory and plasma catecholamine responsivity to multiple challenges of the autonomic nervous system, Biol. Psychiatry 36 (1994), 548-558.  https://doi.org/10.1016/0006-3223(94)90619-X
  67. W. T. Roth, M. J. Telch, C. B. Taylor, J. A. Sachitano, C. C. Gallen, M. L. Kopell, K. L. McClenahan, W. S. Agras, and A. Pfefferbaum, Autonomic characteristics of agoraphobia with panic attacks, Biol. Psychiatry 21 (1986), 1133-1154.  https://doi.org/10.1016/0006-3223(86)90221-0
  68. W. T. Roth, A. Ehlers, C. B. Taylor, J. Margraf, and W. S. Agras, Skin conductance habituation in panic disorder patients, Biol. Psychiatry 27 (1990), 1231-1243.  https://doi.org/10.1016/0006-3223(90)90421-W
  69. L. Dratcu and A. Bond, Panic patients in the non-panic state: Physiological and cognitive dysfunction, Eur. Psychiatry 13 (1998), 18-25.  https://doi.org/10.1016/S0924-9338(97)86747-8
  70. A. C. B. V. Parente, C. Garcia-Leal, C. M. del-Ben, F. S. Guimaraes, and F. G. Graeff, ˜ Subjective and neurovegetative changes in healthy volunteers and panic patients performing simulated public speaking, Eur. Neuropsychopharmacol. 15 (2005), 663-671.  https://doi.org/10.1016/j.euroneuro.2005.05.002
  71. C. Pruneti, F. Fontana, and C. Fante, Autonomic changes and stress response in psychopathology, Int. J. Psychophysiol. 69 (2008), 224-225.  https://doi.org/10.1016/j.ijpsycho.2008.05.069
  72. R. Hoehn-Saric, D. R. McLeod, and W. D. Zimmerli, Psychophysiological response patterns in panic disorder, Acta Psychiatr. Scand. 83 (1991), 4-11.  https://doi.org/10.1111/j.1600-0447.1991.tb05503.x
  73. W. Boucsein, Electrodermal activity, Springer, NY, USA, 2012. 
  74. H. F. Posada-Quintero and K. H. Chon, Innovations in electrodermal activity data collection and signal processing: A systematic review, Sensors. 20 (2020), 479. 
  75. S. Uddin, A. Khan, M. E. Hossain, and M. A. Moni, Comparing different supervised machine learning algorithms for disease prediction, BMC Med. Inform. Decis. Mak. 19 (2019), 1-16.  https://doi.org/10.1186/s12911-018-0723-6
  76. A. Onan and M. A. Tocoglu, A term weighted neural language model and stacked bidirectional LSTM based framework for sarcasm identification, IEEE Access 9 (2021), 7701-7722.  https://doi.org/10.1109/ACCESS.2021.3049734
  77. A. Onan, Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks, Concurr. Comput. Pract. Exp. 33 (2021), 1-12. https://doi.org/10.1002/cpe.5909