nach oben

Neurological Sciences

Erschienen in:

11.09.2024 | Original Article

Cognitive activity analysis of Parkinson’s patients using artificial intelligence techniques

verfasst von: Bahar Demir, Sinem Ayna Altuntaş, İlke Kurt, Sezer Ulukaya, Oğuzhan Erdem, Sibel Güler, Cem Uzun

Erschienen in: Neurological Sciences | Ausgabe 1/2025

Einloggen, um Zugang zu erhalten

Abstract

Purpose

The development of modern Artificial Intelligence (AI) based models for the early diagnosis of Parkinson’s disease (PD) has been gaining deep attention by researchers recently. In particular, the use of different types of datasets (voice, hand movements, gait, etc.) increases the variety of up-to-date models. Movement disorders and tremors are also among the most prominent symptoms of PD. The usage of drawings in the detection of PD can be a crucial decision-support approach that doctors can benefit from.

Methods

A dataset was created by asking 40 PD and 40 Healthy Controls (HC) to draw spirals with and without templates using a special tablet. The patient-healthy distinction was achieved by classifying drawings of individuals using Support Vector Machine (SVM), Random Forest (RF), and Naive Bayes (NB) algorithms. Prior to classification, the data were normalized by applying the min-max normalization method. Moreover, Leave-One-Subject-Out (LOSO) Cross-Validation (CV) approach was utilized to eliminate possible overfitting scenarios. To further improve the performances of classifiers, Principal Component Analysis (PCA) dimension reduction technique were also applied to the raw data and the results were compared accordingly.

Results

The highest accuracy among machine learning based classifiers was obtained as 90% with SVM classifier using non-template drawings with PCA application.

Conclusion

The model can be used as a pre-evaluation system in the clinic as a non-invasive method that also minimizes environmental and educational level differences by using simple hand gestures such as hand drawing, writing numbers, words, and syllables. As a result of our study, preliminary preparation has been made so that hand drawing analysis can be used as an auxiliary system that can save time for health professionals. We plan to work on more comprehensive data in the future.

Jankovic J (2008) Parkinson’s disease: clinical features and diagnosis. J Neurol Neurosurg Psychiatry 79(4):368–376. https://doi.org/10.1136/jnnp.2007.131045CrossRefPubMed

Postuma RB, Berg D, Stern M et al (2015) MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disorders: Official J Mov Disorder Soc 30(12):1591–1601. https://doi.org/10.1002/mds.26424CrossRef

Chaudhuri KR, Healy DG, Schapira AH (2006) Non-motor symptoms of Parkinson’s disease: diagnosis and management. Lancet Neurol 5(3):235–245. https://doi.org/10.1016/S1474-4422(06)70373-8CrossRefPubMed

Pfeiffer RF (2016) Non-motor symptoms in Parkinson’s disease. Parkinsonism Relat Disord 22. https://doi.org/10.1016/j.parkreldis.2015.09.004. S119-S122

Giannakopoulou K, Roussaki I, Demestichas K (2022) Internet of things technologies and machine learning methods for Parkinson’s disease diagnosis, monitoring and management: a systematic review. Sensors 22(5):1799. https://doi.org/10.3390/s22051799CrossRefPubMedPubMedCentral

Kaegi G, Bhatia KP, Tolosa E (2010) The role of dat-spect in movement disorders. J Neurol Neurosurg Psychiatry 81(1):5–12. https://doi.org/10.1136/jnnp.2008.157370CrossRef

Montaser-Kouhsari L, Young CB, Poston KL (2022) Neuroimaging approaches to cognition in Parkinson’s disease. Prog Brain Res 269(1):257–286. https://doi.org/10.1016/bs.pbr.2022.01.008CrossRefPubMed

Kawa J, Bednorz A, Stępień P, Derejczyk J, Bugdol M (2017) Spatial and dynamical handwriting analysis in mild cognitive impairment. Comput Biol Med 82:21–28. https://doi.org/10.1016/j.compbiomed.2017.01.004CrossRefPubMed

De Stefano C, Fontanella F, Impedovo D, Pirlo G, di Freca AS (2019) Handwriting analysis to support neurodegenerative diseases diagnosis: a review. Pattern Recognit Lett 121:37–45. https://doi.org/10.1016/j.patrec.2018.05.013CrossRef

10.

Yan JH, Rountree S, Massman P, Doody RS, Li H (2008) Alzheimer’s disease and mild cognitive impairment deteriorate fine movement control. J Psychiatr Res 42(14):1203–1212. https://doi.org/10.1016/j.jpsychires.2008.01.006CrossRefPubMed

11.

Yu NY, Chang SH (2016) Kinematic analyses of graphomotor functions in individuals with Alzheimer’s disease and amnestic mild cognitive impairment. J Med Biol Eng 36:334–343. https://doi.org/10.1007/s40846-016-0143-yCrossRef

12.

Chai J, Wu R, Li A, Xue C, Qiang Y, Zhao J, Zhao Q, Yang Q (2023) Classification of mild cognitive impairment based on handwriting dynamics and qEEG. Comput Biol Med 152:106418. https://doi.org/10.1016/j.compbiomed.2022.106418CrossRefPubMed

13.

Kim EJ, Lee BH, Park KC, Lee WY, Na DL (2005) Micrographia on free writing versus copying tasks in idiopathic Parkinson’s disease. Parkinsonism Relat Disord 11(1):57–63. https://doi.org/10.1016/j.parkreldis.2004.08.005CrossRefPubMed

14.

Zham P, Poosapadi SA, Kempster P, Raghav S, Nagao KJ, Wong K, Kumar D (2021) Differences in levodopa response for progressive and non-progressive micrographia in Parkinson’s disease. Front Neurol 12:665112. https://doi.org/10.3389/fneur.2021.665112CrossRefPubMedPubMedCentral

15.

Onder H, Comoglu S (2023) The significance of micrographia as a clinical feature of Parkinson’s disease and underlying pathophysiology. Neurol Sci 1–3. https://doi.org/10.1007/s10072-022-06590-y

16.

Dror B, Yanai E, Frid A et al (2014) Automatic assessment of Parkinson’s disease from natural hands movements using 3d depth sensor. In: 2014 IEEE 28th Convention of Electrical & Electronics Engineers in Israel (IEEEI), IEEE, pp 1–5. https://doi.org/10.1109/EEEI.2014.7005763

17.

Sahyoun A, Chehab K, Al-Madani O, Aloul F, Sagahyroon A (2016) Parknosis: Diagnosing Parkinson’s disease using mobile phones. In: 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), IEEE, pp 1–6. https://doi.org/10.1109/HealthCom.2016.7749491

18.

Bernardo LS, Quezada A, Munoz R, Maia FM, Pereira CR, Wu W, de Albuquerque, V H C (2019) Handwritten pattern recognition for early Parkinson’s disease diagnosis. Pattern Recognit Lett 125:78–84. https://doi.org/10.1016/j.patrec.2019.04.003CrossRef

19.

Yu NY, Chang SH (2019) Characterization of the fine motor problems in patients with cognitive dysfunction–A computerized handwriting analysis. Hum Mov Sci 65:71–79. https://doi.org/10.1016/j.humov.2018.06.006CrossRef

20.

Impedovo D, Pirlo G, Vessio G (2018) Dynamic handwriting analysis for supporting earlier Parkinson’s Disease diagnosis. Information 9(10):247. https://doi.org/10.3390/info9100247CrossRef

21.

Aouraghe I, Khaissidi G, Mrabti M (2023) A literature review of online handwriting analysis to detect Parkinson’s disease at an early stage. Multimedia Tools Appl 82(8):11923–11948. https://doi.org/10.1007/s11042-022-13759-2CrossRef

22.

Ali L, Zhu C, Golilarz NA, Javeed A, Zhou M, Liu Y (2019) Reliable Parkinson’s disease detection by analyzing handwritten drawings: construction of an unbiased cascaded learning system based on feature selection and adaptive boosting model. IEEE Access 7:116480–116116. https://doi.org/10.1109/ACCESS.2019.2932037CrossRef

23.

Deharab ED, Ghaderyan P (2022) Graphical representation and variability quantification of handwriting signals: New tools for Parkinson’s disease detection. Biocybernetics Biomedical Eng 42(1):158–172. https://doi.org/10.1016/j.bbe.2021.12.007CrossRef

24.

de Souza JW, Alves SS, Rebouças E D S, Almeida JS, Rebouças Filho PP (2018) A new approach to diagnose Parkinson’s disease using a structural cooccurrence matrix for a similarity analysis. Comput Intell Neurosci. https://doi.org/10.1155/2018/7613282CrossRefPubMedPubMedCentral

25.

Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2014) Decision support framework for Parkinson’s disease based on novel handwriting markers. IEEE Trans Neural Syst Rehabil Eng 23(3):508–516. https://doi.org/10.1109/TNSRE.2014.2359997CrossRefPubMed

26.

Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2016) Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson’s disease. Artif Intell Med 67:39–46. https://doi.org/10.1016/j.artmed.2016.01.004CrossRefPubMed

27.

Kamble M, Shrivastava P, Jain M (2021) Digitized spiral drawing classification for Parkinson’s disease diagnosis. Measurement: Sens 16:100047. https://doi.org/10.1016/j.measen.2021.100047CrossRef

28.

Kotsavasiloglou C, Kostikis N, Hristu-Varsakelis D, Arnaoutoglou M (2017) Machine learning-based classification of simple drawing movements in Parkinson’s disease. Biomed Signal Process Control 31:174–180. https://doi.org/10.1016/j.bspc.2016.08.003CrossRef

29.

Kurt İ, Ulukaya S, Erdem O (2019) Classification of Parkinson’s disease using dynamic time warping. In: 2019 27th Telecommunications Forum (TELFOR), IEEE, pp 1–4. https://doi.org/10.1109/TELFOR48224.2019.8971180

30.

Mucha J, Mekyska J, Faundez-Zanuy M et al (2018) Advanced Parkinson’s disease dysgraphia analysis based on fractional derivatives of online handwriting. In: 2018 10th International Congress on Ultra-Modern Telecommunications and Control Systems and Workshops (ICUMT), IEEE, pp 1–6. https://doi.org/10.1109/ICUMT.2018.8631265

31.

Nõmm S, Bardõš K, Toomela A, Medijainen K, Taba P (2018) Detailed analysis of the luria’s alternating series tests for Parkinson’s disease diagnostics. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, pp 1347–1352. https://doi.org/10.1109/ICMLA.2018.00219

32.

Rios-Urrego CD, Vásquez-Correa JC, Vargas-Bonilla JF, Nöth E, Lopera F, Orozco-Arroyave JR (2019) Analysis and evaluation of handwriting in patients with Parkinson’s disease using kinematic, geometrical, and non-linear features. Comput Methods Programs Biomed 173:43–52. https://doi.org/10.1016/j.cmpb.2019.03.005CrossRefPubMed

33.

Zham P, Arjunan SP, Raghav S, Kumar DK (2017) Efficacy of guided spiral drawing in the classification of Parkinson’s disease. IEEE J Biomedical Health Inf 22(5):1648–1652. https://doi.org/10.1109/JBHI.2017.2762008CrossRef

34.

Pereira CR, Pereira DR, Silva FA, Masieiro JP, Weber SA, Hook C, Papa JP (2016) A new computer vision-based approach to aid the diagnosis of Parkinson’s disease. Comput Methods Programs Biomed 136:79–88. https://doi.org/10.1016/j.cmpb.2016.08.005CrossRefPubMed

35.

Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2014) Analysis of in-air movement in handwriting: a novel marker for Parkinson’s disease. Comput Methods Programs Biomed 117:405–411. https://doi.org/10.1016/j.cmpb.2014.08.007CrossRefPubMed

36.

Isenkul M, Sakar B, Kursun O (2014) Improved spiral test using digitized graphics tablet for monitoring Parkinson’s disease. In The 2nd international conference on e-health and telemedicine (ICEHTM), 5, 171–175. https://doi.org/10.13140/RG.2.1.1898.6005

37.

Mittal V, Sharma R (2021) Machine learning approach for classification of Parkinson disease using acoustic features. J Reliable Intell Environ 7(3):233–239. https://doi.org/10.1007/s40860-021-00141-6CrossRef

38.

Kherif F, Latypova A (2020) Principal component analysis. In: Mechelli A, Vieira S (eds) Machine learning. Elsevier, pp 209–225. https://doi.org/10.1016/B978-0-12-815739-8.00012-2

Titel: Cognitive activity analysis of Parkinson’s patients using artificial intelligence techniques
verfasst von: Bahar Demir
Sinem Ayna Altuntaş
İlke Kurt
Sezer Ulukaya
Oğuzhan Erdem
Sibel Güler
Cem Uzun
Publikationsdatum: 11.09.2024
Verlag: Springer International Publishing
Erschienen in: Neurological Sciences / Ausgabe 1/2025
Print ISSN: 1590-1874
Elektronische ISSN: 1590-3478
DOI: https://doi.org/10.1007/s10072-024-07734-y

Weight gain after Subthalamic Nucleus Deep Brain Stimulation in Parkinson’s Disease: is there a role for GLP-1 agonists?

Letter to the Editor

A cluster-randomised controlled feasibility trial evaluating the Cognitive Occupation-Based programme for people with Multiple Sclerosis (COB-MS)

Open Access
Clinical Trial article

Multi-phase CT-Angiography outperforms angiographic careggi collateral score and predicts functional outcome in acute ischemic stroke

Original Article

Fatigue and depression influence the prevalence of anxiety in patients with multiple sclerosis

Original Article

Phenotypic and mutational spectrum of 17 Chinese patients with Menkes Disease

Original Article

Correction to: Fasciculation score: a sensitive biomarker in amyotrophic lateral sclerosis

Correction

Kompaktes Leitlinien-Wissen Neurologie (Link öffnet in neuem Fenster)

Mit medbee Pocketcards schnell und sicher entscheiden.
Leitlinien-Wissen kostenlos und immer griffbereit auf ihrem Desktop, Handy oder Tablet.

Kostenlos registrieren

Neu im Fachgebiet Neurologie

„Wir wollen die Bedeutung von Gen- und Umwelteinflüssen besser verstehen“

Bipolare Störung
Interview

Eine Mutation in einem einzelnen Gen kann bei Mäusen eine Art Bipolarstörung auslösen. PD Dr. Jan Deussing vom Max-Planck-Institut für Psychiatrie in München sieht in solchen Tiermodellen eine Möglichkeit, den Ursachen der Erkrankung auf den Grund zu gehen.

Suizidassistenz erhöht Suizidzahlen: Aktuelle Ergebnisse der geplanten S3-Leitlinie

DGPPN 2024
Kongressbericht

Erstmals wird in Deutschland eine S3-Leitlinie zum Thema Suizidalität erarbeitet. Ziel ist es, die Versorgung in suizidalen Krisen durch einheitliche Standards zu verbessern. Erste Ergebnisse der bisherigen Leitlinienarbeit wurden auf dem DGPPN-Kongress vorgestellt.

Kaum Vorteile durch intraarterielle Lyse während Thrombektomie

17.01.2025
Ischämischer Schlaganfall
Nachrichten

Nach der Thrombektomie kleinere Fragmente über eine intraarterielle Lyse auflösen – dies könnte die Schlaganfalltherapie verbessern. Zwei aktuelle Studien ergeben für die periprozedurale Lyse jedoch keine großen Vorteile. Die Frage, wie viel sie nützt, bleibt weiter offen.

Nasenstimulation lindert chronische Migräne

16.01.2025
Chronische Migräne
Nachrichten

Wird die Naseninnenseite durch Vibrationen stimuliert, kann dies offenbar die Zahl der Migränetage von Menschen mit chronischer Migräne deutlich senken. Darauf deuten die Resultate einer randomisiert-kontrollierten deutsch-finnischen Untersuchung.

Update Neurologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

Cognitive activity analysis of Parkinson’s patients using artificial intelligence techniques