AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Traditional Chinese Medical Sciences Article
PDF (1.4 MB)
Cite
EndNote(RIS) BibTeX
Collect
AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Original Article | Open Access

Machine learning models for stroke detection by observing the eye-movement features under five-color visual stimuli in traditional Chinese medicine

Qingya Lua, Jingyuan Dengb, Ying Yua, Yang Lia, Kunni Weia, Xia Hanc, Zefeng Wangd, Xun Zhangc, Xu Wanga, Cong Yana( )
School of Life Sciences, Beijing University of Chinese Medicine, Beijing 102488, China
The First Affiliated Hospital, Xi'an Jiaotong University, Xi'an 710061, China
Laboratory LISITE, ISEP School of Computer Engineers, Paris 75006, France
College of Information Engineering, Huzhou University, Huzhou 313000, China

Peer review under responsibility of Beijing University of Chinese Medicine.

Show Author Information

Abstract

Objective

To develop a novel diagnostic modality to identify and diagnose stroke in daily life scenarios for improving the therapeutic effects and prognoses of patients.

Methods

In this study, 16 stroke patients and 24 age-matched healthy participants as controls were recruited for comparative analysis. Leveraging a portable eye-tracking device and integrating traditional Chinese medicine theory with modern color psychology principles, we recorded the eye movement signals and calculated eye movement features. Meanwhile, the stroke recognition models based on eye movement features were further trained by using random forest (RF), k-nearest neighbors (KNN), decision tree (DT), gradient boosting classifier (GBC), XGBoost, and CatBoost.

Results

The stroke group and the healthy group showed significant differences in some eye movement features (P <.05). The models trained based on eye movement characteristics had good performances in recognizing stroke individuals, with accuracies ranging from 77.40% to 88.45%. Under the red stimulus, the eye movement model trained by RF became the best machine learning model with a recall of 84.65%, a precision of 86.48%, a F1 score of 85.47%. Among the six algorithms, RF and CatBoost performed better in classification.

Conclusion

This study pioneers the application of traditional Chinese medicine's five-color stimuli to visual observation tasks. On the basis of the combined design, the eye-movement models can accurately identify stroke, and the developed high-performance models may be used in daily life scenarios.

Keywords

Five-color stimulationTraditional Chinese medicineStrokeEye-tracking technologyEye-movement modelsAccuracyRandom forestCatBoostDynamic eye diagnosis

References

1

Alkahtani R. Molecular mechanisms underlying some major common risk factors of stroke. Heliyon. 2022;8(8):e10218.
Crossref Google Scholar
2

Lozano R, Naghavi M, Foreman K, et al. Global and regional mortality from 235 causes of death for 20 age groups in 1990 and 2010: a systematic analysis for the global burden of disease study 2010. Lancet. 2012;380(9859):2095-2128.
Crossref Google Scholar
3

Zhou M, Wang H, Zeng X, et al. Mortality, morbidity, and risk factors in China and its provinces, 1990-2017: a systematic analysis for the global burden of disease study 2017. Lancet. 2019;394(10204):1145-1158.
Crossref Google Scholar
4

Zweifler RM. Initial assessment and triage of the stroke patient. Prog Cardiovasc Dis. 2017;59(6):527-533.
Crossref Google Scholar
5

Marques JP, Simonis FFJ, Webb AG. Low-field MRI: an MR physics perspective. J Magn Reson Imaging. 2019;49(6):1528-1542.
Crossref Google Scholar
6

Wahlund LO. Structural brain imaging as a diagnostic tool in dementia, why and how? Psychiatry Res Neuroimaging. 2020;306:111183.
Crossref Google Scholar
7

White OB, Fielding J. Cognition and eye movements: assessment of cerebral dysfunction. J Neuro Ophthalmol. 2012;32(3):266-273.
Crossref Google Scholar
8

Batool S, Zafar H, Gilani SA, Ahmad A, Hanif A. Effects of visual scanning exercises in addition to task specific approach on balance and activities of daily livings in post stroke patients with eye movement disorders: a randomized controlled trial. BMC Neurol. 2022;22(1):312.
Crossref Google Scholar
9

Singh T, Fridriksson J, Perry CM, et al. A novel computational model to probe visual search deficits during motor performance. J Neurophysiol. 2017;117(1):79-92.
Crossref Google Scholar
10

Wijesundera C, Vingrys AJ, Wijeratne T, Crewther SG. Acquired visual deficits independent of lesion site in acute stroke. Front Neurol. 2020;11:705.
Crossref Google Scholar
11

Kolecki R, Dammavalam V, Bin Zahid A, et al. Elevated intracranial pressure and reversible eye-tracking changes detected while viewing a film clip. J Neurosurg. 2018;128(3):811-818.
Crossref Google Scholar
12

Kato I, Okada T, Akao I, Shintani T, Kamo T, Sugihara H. Vertical gaze palsy induced by midbrain lesions and its structural imaging. Auris Nasus Larynx. 1998;25(4):339-347.
Crossref Google Scholar
13

Sharpe JA, Bondar RL, Fletcher WA. Contralateral gaze deviation after frontal lobe haemorrhage. J Neurol Neurosurg Psychiatry. 1985;48(1):86-88.
Crossref Google Scholar
14

Choi KD, Jung DS, Kim JS. Specificity of “peering at the tip of the nose" for a diagnosis of thalamic hemorrhage. Arch Neurol. 2004;61(3):417-422.
Crossref Google Scholar
15

Straube A, Scheuerer W, Eggert T. Unilateral cerebellar lesions affect initiation of ipsilateral smooth pursuit eye movements in humans. Ann Neurol. 1997;42(6):891-898.
Crossref Google Scholar
16

Thurston SE, Leigh RJ, Crawford T, Thompson A, Kennard C. Two distinct deficits of visual tracking caused by unilateral lesions of cerebral cortex in humans. Ann Neurol. 1988;23(3):266-273.
Crossref Google Scholar
17

Dong W, Yan B, Johnson BP, et al. Ischaemic stroke: the ocular motor system as a sensitive marker for motor and cognitive recovery. J Neurol Neurosurg Psychiatry. 2013;84(3):337-341.
Crossref Google Scholar
18

Nelles G, Pscherer A, de Greiff A, et al. Eye-movement training-induced plasticity in patients with post-stroke hemianopia. J Neurol. 2009;256(5):726-733.
Crossref Google Scholar
19

Nelles G, Pscherer A, de Greiff A, et al. Eye-movement training-induced changes of visual field representation in patients with post-stroke hemianopia. J Neurol. 2010;257(11):1832-1840.
Crossref Google Scholar
20

Kerkhoff G, Reinhart S, Ziegler W, et al. Smooth pursuit eye movement training promotes recovery from auditory and visual neglect: a randomized controlled study. Neurorehabilitation Neural Repair. 2013;27(9):789-798.
Crossref Google Scholar
21

Smaakjær P, Tødten ST, Rasmussen RS. Therapist-assisted vision therapy improves outcome for stroke patients with homonymous hemianopia alone or combined with oculomotor dysfunction. Neurol Res. 2018;40(9):752-757.
Crossref Google Scholar
22

Correia A, Pimenta C, Alves M, Virella D. Better balance: a randomized controlled trial of oculomotor and gaze stability exercises to reduce risk of falling after stroke. Clin Rehabil. 2021;35(2):213-221.
Crossref Google Scholar
23

Hansen DW, Ji Q. In the eye of the beholder: a survey of models for eyes and gaze. IEEE Trans Pattern Anal Mach Intell. 2010;32(3):478-500.
Crossref Google Scholar
24

Pleshkov M, Zaitsev V, Starkov D, et al. Comparison of EOG and VOG obtained eye movements during horizontal head impulse testing. Front Neurol. 2022;13:917413.
Crossref Google Scholar
25

Zhu ZW, Ji Q. Eye gaze tracking under natural head movements. CVPR'05. 2005;1:918-923.
Google Scholar
26

Feller CN, Goldenberg M, Asselin PD, et al. Classification of comprehensive neuro-ophthalmologic measures of postacute concussion. JAMA Netw Open. 2021;4(3):e210599-e210599.
Crossref Google Scholar
27

Akram U, Ellis JG, Cau G, et al. Eye tracking and attentional bias for depressive internet memes in depression. Exp Brain Res. 2021;239(2):575-581.
Crossref Google Scholar
28

Walle KM, Nordvik JE, Becker F, et al. Unilateral neglect post stroke: eye movement frequencies indicate directional hypokinesia while fixation distributions suggest compensational mechanism. Brain Behav. 2019;9(1):e01170.
Crossref Google Scholar
29

Ross MJ, Guthrie P, Dumont JC. The impact of modulated, colored light on the autonomic nervous system. Adv Mind Body Med. 2013;27(4):7-16.
Google Scholar
30

Wang YX. Analysis of the thinking mode of five-color diagnosis in traditional Chinese medicine. Chin Med Culture. 2017;12(1):25-28 [Chinese].
Crossref Google Scholar
31

Ts'o DY, Gilbert CD. The organization of chromatic and spatial interactions in the primate striate cortex. J Neurosci. 1988;8(5):1712-1727.
Crossref Google Scholar
32

Engel S, Zhang X, Wandell B. Colour tuning in human visual cortex measured with functional magnetic resonance imaging. Nature. 1997;388(6637):68-71.
Crossref Google Scholar
33

Chinese Society of Neurology, Chinese Stroke Society. Chinese guidelines for diagnosis and treatment of acute ischemic stroke 2018. Chin J Neurol. 2018;51(9):666-682 [Chinese].
Google Scholar
34

Lian LF, Zhu SQ. Interpretation in the update of Chinese guidelines for diagnosis and treatment of acute intracerebral hemorrhage 2019. Chin J Neurol. 2019(12):985-988 [Chinese].
Google Scholar
35

Graupner ST, Pannasch S, Velichkovsky BM. Saccadic context indicates information processing within visual fixations: evidence from event-related potentials and eye-movements analysis of the distractor effect. Int J Psychophysiol. 2011;80(1):54-62.
Crossref Google Scholar
36

Huber-Huber C, Buonocore A, Melcher D. The extrafoveal preview paradigm as a measure of predictive, active sampling in visual perception. J Vis. 2021;21(7):12.
Crossref Google Scholar
37

Costello MG, Zhu D, Salinas E, Stanford TR. Perceptual modulation of motor but not visual, responses in the frontal eye field during an urgent-decision task. J Neurosci. 2013;33(41):16394-16408.
Crossref Google Scholar
38

Rucci M, Poletti M. Control and functions of fixational eye movements. Annu Rev Vis Sci. 2015;1:499-518.
Crossref Google Scholar
39

Hessels RS, Niehorster DC, Kemner C, Hooge ITC. Noise-robust fixation detection in eye movement data: Identification by two-means clustering (I2MC). Behav Res Methods. 2017;49(5):1802-1823.
Crossref Google Scholar
40

Goldberg JH, Kotval XP. Computer interface evaluation using eye movements: methods and constructs. Int J Ind Ergon. 1999;24(6):631-645.
Crossref Google Scholar
41

Li C, Xue J, Quan C, Yue J, Zhang C. Biometric recognition via texture features of eye movement trajectories in a visual searching task. PLoS One. 2018;13(4):e0194475.
Crossref Google Scholar
42

Holland CD, Komogortsev OV. Complex eye movement pattern biometrics: the effects of environment and stimulus. IEEE Trans Inf Forensics Secur. 2013;8(12):2115-2126.
Crossref Google Scholar
43

Sen PC, Hajra M, Ghosh M. Supervised classification algorithms in machine learning: a survey and review. AISC. 2020;937:99-111.
Crossref Google Scholar
44

Prokhorenkova L, Gusev G, Vorobev A, Dorogush, AV, Gulin A. CatBoost: unbiased boosting with categorical features. NeurIPS. 2018;31.
Google Scholar
45

Tian J, Fan X. On eyes and mental diseases in treatise on cold damage diseases. Henan Tradit Chin Med. 2020;40(10):1459-1462 [Chinese].
Google Scholar
46
Kang C. The Study on the Specific Representation of “Soul” Disorder in Traditional Chinese Medicine based on Head and Diagnosis Facial Multivariate [dissertation]. Jinan, China: Shandong University of Traditional Chinese Medicine; 2018 [Chinese].
47

Guo F, Lin Y. Survey of eye state tracking and analysis in the wang diagnosis of traditional Chinese medicine. Mind Comput. 2007;(3):391-395 [Chinese].
Google Scholar
48

Yan HJ, Gao QC, Li XL, Zhang YL. Initial application of eyes dynamic detection system in the nerve localization diagnosis. Chin J Med Phys. 2015;32(2):251-254 [Chinese].
Google Scholar
49

Ling X, Sang W, Shen B, et al. Diagnostic value of eye movement and vestibular function tests in patients with posterior circulation infarction. Acta Otolaryngol. 2019;139(2):135-145.
Crossref Google Scholar
50

Liston DB, Stone LS. Oculometric assessment of dynamic visual processing. J Vis. 2014;14(14):12.
Crossref Google Scholar
51

Singman EL. Automating the assessment of visual dysfunction after traumatic brain Injury. Med Instrum. 2013;1(1):3.
Crossref Google Scholar
52

Rivaud S, Müri RM, Gaymard B, et al. Eye movement disorders after frontal eye field lesions in humans. Exp Brain Res. 1994;102(1):110-120.
Crossref Google Scholar
53

Oyama A, Takeda S, Ito Y, et al. Novel method for rapid assessment of cognitive impairment using high-performance eye-tracking technology. Sci Rep. 2019;9(1):12932.
Crossref Google Scholar
54

Kudo Y, Takahashi K, Sugawara E, et al. Bedside video-oculographic evaluation of eye movements in acute supratentorial stroke patients: a potential biomarker for hemispatial neglect. J Neurol Sci. 2021;425:117442.
Crossref Google Scholar
55

Lu, QY, Wei KN, Yan C. Review of eye diagnosis in traditional Chinese medicine: modernization and future prospects. J Tradit Chin Med Sci. 2022;9(3):217-221.
Crossref Google Scholar
56

Kliegl R, Engbert R. Fixation durations before word skipping in reading. Psychon Bull Rev. 2005;12(1):132-138.
Crossref Google Scholar
57

Teslenko EL, Damyanovich EV, Damjanović I, Gačić Z, Baziyan BK. Saccadic dysfunction in patients with hypoxic-ischemic encephalopathy. J Integr Neurosci. 2018;17(3):331-346.
Crossref Google Scholar
58

Attenhofer KS, Hailey L, Mortin M, et al. The sustained DeyeCOM sign as a predictor of large vessel occlusions and stroke mimics. J Stroke Cerebrovasc Dis. 2018;27(6):1466-1470.
Crossref Google Scholar
59

Girard B, Berthoz A. From brainstem to cortex: computational models of saccade generation circuitry. Prog Neurobiol. 2005;77(4):215-251.
Crossref Google Scholar
60

Kelts EA. Traumatic brain injury and visual dysfunction: a limited overview. NeuroRehabilitation. 2010;27(3):223-229.
Crossref Google Scholar
61

Kremmyda O, Glasauer S, Guerrasio L, Büttner U. Effects of unilateral midbrain lesions on gaze (eye and head) movements. Ann N Y Acad Sci. 2011;1233:71-77.
Crossref Google Scholar
62

Bucci MP. Visual training could be useful for improving reading capabilities in dyslexia. Appl Neuropsychol Child. 2021;10(3):199-208.
Crossref Google Scholar
63

Leandro LDS, Mauro M, Adoracíon A, Thierry B, José JC. Approximation of on-line mental workload index in ATC simulated multitasks. J Air Transport Manag. 2010;16(6):330-333.
Crossref Google Scholar
64

Sweller J. Cognitive load during problem solving: effects on learning. Cognit Sci. 1988;12(2):257-285.
Crossref Google Scholar
65

Colak C, Karaman E, Turtay MG. Application of knowledge discovery process on the prediction of stroke. Comput Methods Progr Biomed. 2015;119(3):181-185.
Crossref Google Scholar
66

Klug J, Dirren E, Preti MG, et al. Integrating regional perfusion CT information to improve prediction of infarction after stroke. J Cerebr Blood Flow Metabol. 2021;41(3):502-510.
Crossref Google Scholar
67

Dong S, Zhou KL, Chen JX. Discussion on Zhang Zhongjing’s academic thought of facial color diagnosis based on Treatise on Febrile and Miscellaneous Disease. China J Tradit Chin Med Pharm. 2022;37(8):4604-4606 [Chinese].
Google Scholar
68

Liu YJ, Zhou YD. The principles and modern values of five-color food in traditional Chinese medicine. J Chifeng Univ. 2018;34(3):117-118 [Chinese].
Crossref Google Scholar
69

Huo L, Zhang HR, Zhan XH, Liang Y. Evolution of the connotation of “liver controlling dispersion”. J Basic Chin Med. 2021;27(10):1533-1535 [Chinese].
Crossref Google Scholar
70

Pi GF, Liu L. The application of Huangdi Neijing in the emotional nursing of stroke patients. Chin Community Doctors. 2020;36(35):92-93 [Chinese].
Google Scholar
71

Wang R, Shi LP. “The five colors and five flavors” in TCM health cultivation. Henan Tradit Chin Med. 2014;34(5):796-797 [Chinese].
Google Scholar
72

Jia M, Lu Y, Zhang YL. Application of spleen and stomach theory in treatment of stroke. Shanghai J Tradit Chin Med. 2021;55(03):45-49 [Chinese].
Google Scholar
73

Yuan SH. Evidence of TCM five-color theory in the modern color psychology and color therapy. J Zhejiang Chin Med Univ. 2007;31(1):34-35 [Chinese].
Google Scholar
74

Zhao HB, Shen CL. Discussion on the pathogenesis of stroke disease from the perspective of lung control qi disorder. Beijing J Tradit Chin Med. 2007;8:489-490 [Chinese].
Google Scholar
75

Wang J, Liu W, Li X. Five methods for treating stroke from the perspective of marro. J Shandong Univ Tradit Chin Med. 2021;45(5):604-607 [Chinese].
Crossref Google Scholar
76

Li LN. Application of five colors theory in traditional Chinese medicine. Lishizhen Med Mater Med Res. 2008;10:2549 [Chinese].
Google Scholar
77

Radeljak S, Zarković-Palijan T, Kovacević D, Kovac M. Chromotherapy in the regulation of neurohormonal balance in human brain, complementary application in modern psychiatric treatment. Coll Antropol. 2008;32(Suppl 2):185-188.
Google Scholar
78

Peng QH, Peng J, Tan HY, Dai ZS, Chen KZ. Basic theory and methods of eye diagnosis of traditional Chinese medicine. Hunan J Tradit Chin Med. 2015;35(10):1-5 [Chinese].
Google Scholar
Journal of Traditional Chinese Medical Sciences
Volume 10 Issue 3,
July 2023
Pages 321-330
DOI: 10.1016/j.jtcms.2023.06.003
Cite this article:
Lu Q, Deng J, Yu Y, et al. Machine learning models for stroke detection by observing the eye-movement features under five-color visual stimuli in traditional Chinese medicine. Journal of Traditional Chinese Medical Sciences, 2023, 10(3): 321-330. https://doi.org/10.1016/j.jtcms.2023.06.003

392

Views

6

Downloads

3

Crossref

3

Scopus

Altmetrics
Received: 17 January 2023
Revised: 05 June 2023
Accepted: 08 June 2023
Published: 13 June 2023
© 2023 Beijing University of Chinese Medicine.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return