Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an IOS Application (TDPT-GT)

Overview

Journal Sensors (Basel)

Publisher MDPI

Specialty Biotechnology

Date 2023 Jul 14

PMID 37448065

Authors

Chifumi Iseki

Tatsuya Hayasaka

Hyota Yanagawa

Yuta Komoriya

Toshiyuki Kondo

Masayuki Hoshi

Tadanori Fukami

Yoshiyuki Kobayashi

Shigeo Ueda

Kaneyuki Kawamae

Masatsune Ishikawa

Shigeki Yamada

Yukihiko Aoyagi

Yasuyuki Ohta

Affiliations

Soon will be listed here.

Abstract

Distinguishing pathological gait is challenging in neurology because of the difficulty of capturing total body movement and its analysis. We aimed to obtain a convenient recording with an iPhone and establish an algorithm based on deep learning. From May 2021 to November 2022 at Yamagata University Hospital, Shiga University, and Takahata Town, patients with idiopathic normal pressure hydrocephalus ( = 48), Parkinson's disease ( = 21), and other neuromuscular diseases ( = 45) comprised the pathological gait group ( = 114), and the control group consisted of 160 healthy volunteers. iPhone application TDPT-GT captured the subjects walking in a circular path of about 1 meter in diameter, a markerless motion capture system, with an iPhone camera, which generated the three-axis 30 frames per second (fps) relative coordinates of 27 body points. A light gradient boosting machine (Light GBM) with stratified k-fold cross-validation (k = 5) was applied for gait collection for about 1 min per person. The median ability model tested 200 frames of each person's data for its distinction capability, which resulted in the area under a curve of 0.719. The pathological gait captured by the iPhone could be distinguished by artificial intelligence.

Citing Articles

Development of a Gait Analysis Application for Assessing Upper and Lower Limb Movements to Detect Pathological Gait.

Taishaku A, Yamada S, Iseki C, Aoyagi Y, Ueda S, Kondo T Sensors (Basel). 2024; 24(19).

PMID: 39409369 PMC: 11479076. DOI: 10.3390/s24196329.

The Role of Deep Learning and Gait Analysis in Parkinson's Disease: A Systematic Review.

Franco A, Russo M, Amboni M, Ponsiglione A, Di Filippo F, Romano M Sensors (Basel). 2024; 24(18).

PMID: 39338702 PMC: 11435660. DOI: 10.3390/s24185957.

Emerging Innovations in Preoperative Planning and Motion Analysis in Orthopedic Surgery.

Berhouet J, Samargandi R Diagnostics (Basel). 2024; 14(13).

PMID: 39001212 PMC: 11240316. DOI: 10.3390/diagnostics14131321.

Fluctuations in Upper and Lower Body Movement during Walking in Normal Pressure Hydrocephalus and Parkinson's Disease Assessed by Motion Capture with a Smartphone Application, TDPT-GT.

Iseki C, Suzuki S, Fukami T, Yamada S, Hayasaka T, Kondo T Sensors (Basel). 2023; 23(22).

PMID: 38005649 PMC: 10674367. DOI: 10.3390/s23229263.

References

Schmidle S, de Crignis A, Sturzer M, Hermsdorfer J, Jahn K, Krewer C . Influence of stance width on standing balance in healthy older adults. J Neurol. 2022; 269(12):6228-6236. PMC: 9618500. DOI: 10.1007/s00415-022-11144-5. View

Djuric-Jovicic M, Belic M, Stankovic I, Radovanovic S, Kostic V . Selection of gait parameters for differential diagnostics of patients with de novo Parkinson's disease. Neurol Res. 2017; 39(10):853-861. DOI: 10.1080/01616412.2017.1348690. View

Eltoukhy M, Oh J, Kuenze C, Signorile J . Improved kinect-based spatiotemporal and kinematic treadmill gait assessment. Gait Posture. 2016; 51:77-83. DOI: 10.1016/j.gaitpost.2016.10.001. View

Wolke R, Kuhtz-Buschbeck J, Deuschl G, Margraf N . Insufficiency of trunk extension and impaired control of muscle force in Parkinson's disease with camptocormia. Clin Neurophysiol. 2020; 131(11):2621-2629. DOI: 10.1016/j.clinph.2020.07.019. View

Noamani A, Nazarahari M, Lewicke J, Vette A, Rouhani H . Validity of using wearable inertial sensors for assessing the dynamics of standing balance. Med Eng Phys. 2020; 77:53-59. DOI: 10.1016/j.medengphy.2019.10.018. View

Beauchet O, Annweiler C, Callisaya M, De Cock A, Helbostad J, Kressig R . Poor Gait Performance and Prediction of Dementia: Results From a Meta-Analysis. J Am Med Dir Assoc. 2016; 17(6):482-90. PMC: 5319598. DOI: 10.1016/j.jamda.2015.12.092. View

di Biase L, Di Santo A, Caminiti M, De Liso A, Shah S, Ricci L . Gait Analysis in Parkinson's Disease: An Overview of the Most Accurate Markers for Diagnosis and Symptoms Monitoring. Sensors (Basel). 2020; 20(12). PMC: 7349580. DOI: 10.3390/s20123529. View

Nishiguchi S, Yorozu A, Adachi D, Takahashi M, Aoyama T . Association between mild cognitive impairment and trajectory-based spatial parameters during timed up and go test using a laser range sensor. J Neuroeng Rehabil. 2017; 14(1):78. PMC: 5549311. DOI: 10.1186/s12984-017-0289-z. View

Tsuchida W, Kobayashi Y, Inoue K, Horie M, Yoshihara K, Ooie T . Kinematic characteristics during gait in frail older women identified by principal component analysis. Sci Rep. 2022; 12(1):1676. PMC: 8803892. DOI: 10.1038/s41598-022-04801-2. View

10.

Kegelmeyer D, Kostyk S, Fritz N, Fiumedora M, Chaudhari A, Palettas M . Quantitative biomechanical assessment of trunk control in Huntington's disease reveals more impairment in static than dynamic tasks. J Neurol Sci. 2017; 376:29-34. DOI: 10.1016/j.jns.2017.02.054. View

11.

Granacher U, Gollhofer A, Hortobagyi T, Kressig R, Muehlbauer T . The importance of trunk muscle strength for balance, functional performance, and fall prevention in seniors: a systematic review. Sports Med. 2013; 43(7):627-41. DOI: 10.1007/s40279-013-0041-1. View

12.

Verghese J, Wang C, Allali G, Holtzer R, Ayers E . Modifiable Risk Factors for New-Onset Slow Gait in Older Adults. J Am Med Dir Assoc. 2016; 17(5):421-5. DOI: 10.1016/j.jamda.2016.01.017. View

13.

Abujaber S, Gillispie G, Marmon A, Zeni Jr J . Validity of the Nintendo Wii Balance Board to assess weight bearing asymmetry during sit-to-stand and return-to-sit task. Gait Posture. 2015; 41(2):676-82. PMC: 4385456. DOI: 10.1016/j.gaitpost.2015.01.023. View

14.

Yamada S, Aoyagi Y, Yamamoto K, Ishikawa M . Quantitative Evaluation of Gait Disturbance on an Instrumented Timed Up-and-go Test. Aging Dis. 2019; 10(1):23-36. PMC: 6345343. DOI: 10.14336/AD.2018.0426. View

15.

Kawai H, Obuchi S, Hirayama R, Watanabe Y, Hirano H, Fujiwara Y . Intra-day variation in daily outdoor walking speed among community-dwelling older adults. BMC Geriatr. 2021; 21(1):417. PMC: 8268528. DOI: 10.1186/s12877-021-02349-w. View

16.

Naqvi S, Tennankore K, Vinson A, Roy P, Abidi S . Predicting Kidney Graft Survival Using Machine Learning Methods: Prediction Model Development and Feature Significance Analysis Study. J Med Internet Res. 2021; 23(8):e26843. PMC: 8433864. DOI: 10.2196/26843. View

17.

Merchant R, Banerji S, Singh G, Chew E, Poh C, Tapawan S . Is Trunk Posture in Walking a Better Marker than Gait Speed in Predicting Decline in Function and Subsequent Frailty?. J Am Med Dir Assoc. 2015; 17(1):65-70. DOI: 10.1016/j.jamda.2015.08.008. View

18.

Thomas J, Odonkor C, Griffith L, Holt N, Percac-Lima S, Leveille S . Reconceptualizing balance: attributes associated with balance performance. Exp Gerontol. 2014; 57:218-23. PMC: 4149932. DOI: 10.1016/j.exger.2014.06.012. View

19.

Barth J, Klucken J, Kugler P, Kammerer T, Steidl R, Winkler J . Biometric and mobile gait analysis for early diagnosis and therapy monitoring in Parkinson's disease. Annu Int Conf IEEE Eng Med Biol Soc. 2012; 2011:868-71. DOI: 10.1109/IEMBS.2011.6090226. View

20.

Yamada S, Aoyagi Y, Iseki C, Kondo T, Kobayashi Y, Ueda S . Quantitative Gait Feature Assessment on Two-Dimensional Body Axis Projection Planes Converted from Three-Dimensional Coordinates Estimated with a Deep Learning Smartphone App. Sensors (Basel). 2023; 23(2). PMC: 9865115. DOI: 10.3390/s23020617. View