沖田 周祐, Ph.D.

Shirley Ryan AbilityLabの博士研究員

GitHubLinkedInORCIDResearchMapGoogle Scholar
Shusuke Okita
スクロールして探索

Experience

Research

学歴

研究論文

ニュース

アルバム

Professional Experience

Research/Employment History

  • Postdoctoral Fellow

    Starting August 2025

    RIKEN Center for Brain Science, Japan

    headed by Dr. Kazuhisa Shibata

  • Postdoctoral Fellow

    2024–Present

    Northwestern University, Illinois, USA

    headed by Dr. Arun Jayaraman

  • Postdoctoral Fellow

    2023–Present

    Shirley Ryan AbilityLab, Illinois, USA

    headed by Dr. Arun Jayaraman

  • Graduate Student Researcher

    2018–2023

    University of California Irvine, California, USA

  • Part-time Intern

    2018

    Cyberdyne inc, Ibaraki, Japan

Fellowships / Awards

  • Scholarship by Japan Student Services Organization (JASSO) (2016)
  • Outstanding Student Award, Seikei University (2012–2015)

Other Activities

Ad-hoc Reviewer for Journals

  • Journal of Biomedical and Health Informatics
  • Journal of NeuroEngineering and Rehabilitation
  • Journal of Medical Internet Research
  • Neurorehabilitation and Neural Repair
  • IEEE Transactions on Neural Systems and Rehabilitation Engineering

Professional Memberships

  • Member of IEEE
  • Member of American Society of NeuroRehabilitation
  • Member of The Japan Neuroscience Society

Research Focus

Wearable Sensing and Feedback Systems for Enhancing Hand Function in Stroke Rehabilitation

Stroke rehabilitation requires a high dosage of movement practice to stimulate optimal recovery. Previously, we developed a wrist-worn sensor with inertial measurement units (IMUs) to capture hand and finger movements during patients' daily activities. In a clinical trial, we provided hand count feedback to encourage movement practice, but the results were only modest.

Hence, we developed novel metrics that evaluates movement quality instead of quantity, using data from a wrist-worn sensor. These metrics offer insights into the diversity and complexity of movements, which could be key to breaking the cycle of non-use and promoting neural recovery in individuals with neurological diseases in community settings.

We plan to conduct a new clinical trial testing the efficacy of providing quality based metrics to people after stroke, laying the foundation for integrating wearable sensing with adaptive feedback into at-home stroke rehabilitation, potentially reducing long-term healthcare costs and substantially improving their motor function.

Continuous Observation and Monitoring for Patient Assessment Using a Sensor-Based System

Stroke rehabilitation demands continuous, objective monitoring to tailor interventions and maximize recovery. Many stroke survivors exhibit a broad spectrum of gait deficits—from reduced walking speed to pronounced asymmetry—that reflect the inherent variability in their impairments and underscore the critical need for precision rehabilitation.

To address this challenge, we have been developing the Stroke Recovery Toolkit (SRT), which integrates advanced wearable sensors and machine-learning algorithms to continuously capture multidimensional data on gait and balance throughout the recovery process in inpatient rehabilitation facilities (IRFs).

By providing quantitative feedback on patient mobility, the SRT empowers clinicians to promptly adjust therapeutic interventions and personalize treatment strategies. A clinical trial is planned to test its usability in IRFs, aiming to optimize its integration into routine stroke care in IRFs. This work lays the foundation for more effective, precision rehabilitation strategies that could enhance patient outcomes in IRFs while reducing long-term healthcare costs.

Education

Ph.D. in Mechanical and Aerospace Engineering

University of California, Irvine (2018-2023)

Advisor: Dr. David J. Reinkensmeyer

Dissertation: Improving Wearable Feedback for Upper Extremity Rehabilitation after Stroke

M.Sc. in Mechanical and Aerospace Engineering

University of California, Irvine (2021)

Advisor: Dr. David J. Reinkensmeyer

Thesis: Smoothness Metrics for Measuring Arm Movement Quality after Stroke with a Wrist Accelerometer

B.E. in Mechanical Engineering

Seikei University (2012-2016)

Advisor: Dr. Takashi Sakai

Thesis: Development of Upright and Hub for Formula SAE Car using Finite Element Method (FEM) analysis

Outstanding Student Award (2012-2015)

出版物

  1. Okita, S., Berry, J., Khazanchi, R., Lanotte, F., O'Brien, M.K., & Jayaraman, A. (2025). "Stride and Step Length Estimation using Machine Learning and Inertial Measurement Units for Individuals after Stroke." Journal of Biomedical and Health Informatics. (執筆中)
  2. Nataletti, S., Okita, S., and 10 other authors. (2025). "Predicting Prosthesis Use and Mobility Needs in Lower Limb Amputees: A Machine Learning Approach Using Clinical and Sensor Data." (執筆中)
  3. Lanotte, F., Okita, S.*, Aalla, S., Chau, A., Srinivasan, A., O'Brien, M.K., & Jayaraman, A. (2025). "Estimating Functional Measures through Wearable Sensors and Machine Learning." npj Digital Medicine. (共同第一著者) (執筆中)
  4. Okita, S., Berry, J., Khazanchi, R., Lanotte, F., O'Brien, M.K., & Jayaraman, A. (2025). "Machine Learning-Based Estimation of Upper Extremity Function in Stroke Rehabilitation Using Body-Worn Inertial Sensors." IEEE International Conference on Rehabilitation Robotics (ICORR) 2025. (最優秀論文賞の6候補の一つ) (印刷中)
  5. Cornella-Barba, G., Zimmer, C.S., Okita, S., & Reinkensmeyer, D.J. (2025). "A Home-Based Suite of Sensors for Monitoring and Improving Upper Extremity Proprioception after Stroke." International Conference on Rehabilitation Robotics (ICORR) 2025. (最優秀学生論文賞の6候補の一つ)
  6. Lanotte, F., Okita, S.*, O'Brien, M.K., & Jayaraman, A. (2024). "Enhanced Gait Tracking Measures for Individuals with Stroke using Leg-Worn Inertial Sensors." Journal of NeuroEngineering and Rehabilitation. (共同第一著者)
  7. Lanotte, F., Okita, S., O'Brien, M.K., & Jayaraman, A. (2024). "A Stroke-Specific Neural Network to Estimate Continuous Gait Speed Using a Single Inertial Measurement Unit." 2024 IEEE 20th International Conference on Body Sensor Networks (BSN).
  8. Okita, S., Lucena, D.S., & Reinkensmeyer, D.J. (2024). "Movement Diversity and Complexity Increase as Arm Impairment Decreases after Stroke: Quality of Movement Experience as a Possible Target for Wearable Feedback." IEEE Transactions on Neural Systems and Rehabilitation Engineering.
  9. Cornella-Barba, G., Okita, S., Li, Z., & Reinkensmeyer, D.J. (2024). "Real-Time Sensing of Upper Extremity Movement Diversity Using Kurtosis Implemented on a Smartwatch." Sensors, 24(16), 5266.
  10. Okita, S., Yakunin, R., Korrapati, J., Ibrahim, M., Lucena, D.S., Chan, V., & Reinkensmeyer, D.J. (2023). "Counting Finger and Wrist Movements Using Only a Wrist-Worn Inertial Measurement Unit." Sensors, 23(12), 5690.
  11. Lucena, D.S., Rowe, J.B., Okita, S., Chan, V., Cramer, S.C., & Reinkensmeyer, D.J. (2022). "Providing Real-Time Wearable Feedback to Increase Hand Use after Stroke: A Randomized, Controlled Trial." Sensors, 22(18).
  12. Okita, S., Lucena, D.S., Chan, V., & Reinkensmeyer, D.J. (2021). "Measuring Movement Quality of the Stroke-Impaired Upper Extremity with a Wearable Sensor: Toward a Smoothness Metric for Home Rehabilitation Exercise Programs." The IEEE Engineering in Medicine and Biology Society.
  13. Sanders, Q., Okita, S., Lobo-Prat, J., Lucena, D.S., Smith, B.W., & Reinkensmeyer, D.J. (2018). "Design and Control of a Novel Grip Amplifier to Support Pinch Grip with a Minimal Soft Hand Exoskeleton." 7th IEEE International Conference on Biomedical Robotics and Biomechatronics.

*: 共同第一著者

Conference Abstracts

  1. Lanotte, F., Okita, S., Campagnini, S., Chau, A., O'Brien, M.K., Jayaraman, A. (2024). "Prediction of Responders to Post-stroke Rehabilitation Therapy Based on Section GG of the Inpatient Rehabilitation Facility-Patient Assessment Instrument." International Conference on NeuroRehabilitation 2025.
  2. Cao, Y., Rogers, J.M., Lanotte, F., Okita, S., O'Brien, M.K., Jayaraman, A. (2025). "Patient Performance Metrics Correlate with Functional Outcomes at Discharge during Early Inpatient Stroke Rehabilitation." 2025 Combined Sections Meeting (CSM).
  3. Samaan, T., Buchler, K., Lanotte, F., Okita, S., Jayaraman, A. (2025). "Effects of Varying Distance Walked per Session in Inpatient Rehabilitation on Gait Outcomes Following Stroke." 2025 Combined Sections Meeting (CSM).

Conferences

Oral Presentations

  • International Conference on Rehabilitation Robotics (ICORR) 2025
    May 2025, Chicago, Illinois, United States
    Planned Podium Presentation – one of six candidates for the best paper award
  • Rocky Mountain Muscle Symposium Pre-Conference Summit
    June 18, 2023, Canmore, Alberta, Canada
    Podium Presentation

Poster Presentations

  • The American Society for Neurorehabilitation (ASNR) Annual Meeting
    March 14, 2023, Charleston, South Carolina, United States

Research Capabilities

Technical Skills

  • Programming Languages: Python, MATLAB, C++, SQL, HTML, CSS, JavaScript, TypeScript
  • Machine Learning Frameworks: TensorFlow, PyTorch, Scikit-learn
  • Data Analysis: Signal Processing, Time Series Analysis, Statistical Analysis
  • Hardware: Microcontrollers (Arduino, Raspberry Pi), IMUs, EMG Sensors, Force Sensors
  • Embedded Systems: Firmware Development, Real-time Systems, Sensor Integration
  • Software Development: Git, Docker, REST APIs, Web Development

Research Methods

  • Clinical Outcome Measures: Fugl-Meyer Assessment, Box and Block Test, 10-Meter Walk Test
  • Motion Capture: Inertial Measurement Units (IMUs), Camera-based Systems
  • Sensor Development: Wearable Technology, Custom Sensor Integration
  • Algorithm Development: Feature Extraction, Classification, Regression, Deep Learning
  • Human Subject Research: IRB Protocol Development, Data Collection, Analysis
  • Study Design: Cross-sectional Studies, Longitudinal Studies, Clinical Trials

Domain Expertise

  • Stroke Rehabilitation: Motor Recovery, Functional Assessment, Therapeutic Interventions
  • Wearable Technology: Design, Development, Validation, Clinical Implementation
  • Machine Learning for Healthcare: Predictive Modeling, Patient Monitoring, Outcome Prediction
  • Human Movement Analysis: Gait Analysis, Upper Extremity Function, Movement Quality
  • Assistive Technology: Soft Robotics, Exoskeletons, Haptic Feedback
  • Digital Health: Remote Monitoring, Telehealth, Patient Engagement Strategies

Patents

U.S. Patent Application 63/566,066 (No. P5160PRO)

"Continuous Observation and Monitoring for Patient Assessment Using a Sensor-Based System"

Filed on March 15, 2024

  • Developed a patient monitoring system using wearable sensors to continuously observe and assess health
  • Enables clinicians to track patient recovery outside of clinical settings with minimal manual intervention
  • Supported by government grants: RERC #90REG E0010 (NIDILRR) and P2CHD101899 (NIH)

Update History

DateVersionChanges
May 11, 20253.0Complete redesign with advanced animations and dark mode
April 15, 20252.0Added Research Capability and Patents sections
December 5, 20241.0Initial portfolio website launch

ニュース

ウェブサイトリニューアル

2025年5月11日

ポートフォリオウェブサイトを完全にリニューアルし、アクセシビリティと新機能を向上させました。

ICORR 2025で論文がベストペーパー賞にノミネート

2025年5月11日

上肢機能の機械学習ベース推定に関する論文が、ICORR 2025でベストペーパー賞の6つの候補の一つにノミネートされました。

フォトアルバム

準備中...