Adaptive Rehabilitation using Mixed-reality at Home: The ARM at Home study RIC Margaret Duff, Meghan Buell, and W. Zev Rymer Emory Steven Wolf and Aimee.

Slides:



Advertisements
Similar presentations
Standardized Scales.
Advertisements

1 Organizational, Time Management, and Planning Treatment for Children with ADHD (OTMP Study) NIMH-funded R01 New York University – Howard Abikoff, PI.
Technological-enhanced treatment of emotional eating in obese subjects: A randomized controlled clinical trial Alessandra Gorini Mauro Manzoni, Francesco.
Addressing Patient Motivation In Virtual Reality Based Neurocognitive Rehabilitation A.S.Panic - M.Sc. Media & Knowledge Engineering Specialization Man.
Steven Browne, O.T. Reg. (N.B.) Brad Holley, O.T.Reg. (N.B.)
Introduction to Therapeutic Exercises
Mary Jo Sariscsany Assessing Health- Related Fitness and Physical Activity 13 chapter.
Games For Upper-limb Stroke Rehabilitation James BurkeMichael McNeill Philip MorrowDarryl Charles School of Computing and Information Engineering Suzanne.
Introduction Semantic Feature Analysis (SFA) is a treatment technique designed to improve the naming abilities by increasing the level of activation within.
Clinical Significance
DARPA Mobile Autonomous Robot SoftwareMay Adaptive Intelligent Mobile Robotics William D. Smart, Presenter Leslie Pack Kaelbling, PI Artificial.
Michael E. Levin, Jacqueline Pistorello, Steven C. Hayes, John Seeley, Crissa Levin, Kristy Dalrymple, Brandon Gaudiano & Jack Haeger USING ADJUNCTIVE.
Online Career Assessment: Matching Profiles and Training Programs Bryan Dik, Ph.D. Kurt Kraiger, Ph.D.
Randomized Controlled Trial of Integrated(Managed)Care Pathway for Stroke Rehabilitation 何雲仙 倪承華 91 年 8 月 30 日.
Multiple Criteria for Evaluating Land Cover Classification Algorithms Summary of a paper by R.S. DeFries and Jonathan Cheung-Wai Chan April, 2000 Remote.
Probabilistic video stabilization using Kalman filtering and mosaicking.
The Sequential Combination of Bilateral and Unilateral Arm Training to Promote Arm and Hand Function in Patients with More Severe Paresis The Sequential.
On Comparing Classifiers: Pitfalls to Avoid and Recommended Approach Published by Steven L. Salzberg Presented by Prakash Tilwani MACS 598 April 25 th.
EFFICACY OF CONSTRAINT-INDUCED MOVEMENT THERAPY INTERVENTION FOR CHILDREN WITH CEREBRAL PALSY Andria Vetsch Mentor: Dr. Jane Case-Smith The Ohio State.
BARRIERS KNR 270. BARRIERS w Intrinsic Barriers w Environmental Barriers w Communication Barriers (Smith, Austin & Kennedy, 1996) w Leisure Provider Actions.
COMPUTER GAMES IN CEREBRAL PALSY (CP) THERAPY RYAN JACKSON, JEN FAITH, TARA SILIANOFF, LAURA MANSON, KATIE EMERY, DIANA AZOSE, ANJALI NIGAM.
A Related Service Part of the Special Education Program.
Parent Tutoring (PT) An Individualized Tier 3 Intervention for Students with Reading Problems Study 1 Duvall, Delquadri, Elliott & Hall (1992) Study 2.
Resource allocation for disability - NDA feasibility study Eithne Fitzgerald Head of Policy and Research National Disability Authority.
Game.reha.lviv.ua International Clinic of Rehabilitation WEB-BASED HOME REHABILITATION GAMING SYSTEM.
A stroke is the leading cause of permanent impairment and disability. Pending a radical cure, patients recovering from a stroke will continue to require.
Loreta Bačenskaitė, Vaida Aleknavičiūtė.  Stroke is the third leading cause of death in Europe;  Aproximetaly 58% of stroke survivors experience hemiparesis,
INTERNATIONAL LABOUR ORGANIZATION Conditions of Work and Employment Programme (TRAVAIL) 2012 Module 15: Capacity development and training on Maternity.
Background to Adaptive Design Nigel Stallard Professor of Medical Statistics Director of Health Sciences Research Institute Warwick Medical School
Movement studies 2011 Slides adapted from 2010 produced by SP University of Hertfordshire MS /12.
Background Participants: Six participants have been recruited to date and placed into bilateral and unilateral task retraining groups using computer randomization.
Miller Function & Participation Scales (M-FUN)
Measuring Complex Achievement
Evaluation of a Closed-Loop BCI-FES System on Recovery of Upper Extremity Function Based on Functionality Post Stroke: A Case Series Angela Gille, OTS.
Optimal Therapy After Stroke: Insights from a Computational Model Cheol Han June 12, 2007.
Training Interventionists to Implement a Brief Experimental Analysis of Reading Protocol to Elementary Students: An Evaluation of Three Training Packages.
Rehabilitation of Finger Extension in Chronic Hemiplegia Derek Kamper 1,5 Tiffany Kline 4 Xun Luo 3 Robert Kenyon 1,3 Heidi Fischer 1 Kathy Stubblefield.
A LONGITUDINAL EXAMINATION OF THE EMERGENCE OF A HEALTHY CHAOTIC WALKING PATTERN IN NORMAL INFANT DEVELOPMENT Harbourne, R.T. 1, Kurz, M. 2, and DeJong,
PSEUDO-RELEVANCE FEEDBACK FOR MULTIMEDIA RETRIEVAL Seo Seok Jun.
Randomized double-blinded trial investigating the impact of a curriculum focused on error recognition on laparoscopic suturing training J Bingener, T Boyd,
Motor Control. Beyond babbling Three problems with motor babbling: –Random exploration is slow –Error-based learning algorithms are faster but error signals.
Results (continued) Results Abstract Methods The motor imagery group was read a detailed script and in summary asked to do the following during rest intervals:
Figure 3. Log-log plot of simulated oscillating phantom, assuming a Gaussian-shaped field. Field constants a 1 =a 2 =0.1. The data initially plateau, then.
G.G. Fluet, A.S. Merians, Q. Qiu, S. Saleh, V. Ruano, A.R. Delmonico & S.V. Adamovich.
1 Centre for Sport and Exercise Science, Sheffield Hallam University, U. K. 2 York Trials Unit, Department of Health Sciences, University of York, U. K.
Stats 845 Applied Statistics. This Course will cover: 1.Regression –Non Linear Regression –Multiple Regression 2.Analysis of Variance and Experimental.
Today.. Overview of my realist synthesis Reflections on the process
Breaking It Down Is Better Haptic Decomposition of Complex Movements Aids in Robot- Assisted Motor Learning J. Klein, S. Spencer, & D. Reinkensmeyer IEEE.
Team Dogecoin: An Experience in Predicting Hospital Readmissions Acknowledgements The Problem Hospitals in the UK must keep track of which patients, once.
Analyzing Expression Data: Clustering and Stats Chapter 16.
Chapter 20 Classification and Estimation Classification – Feature selection Good feature have four characteristics: –Discrimination. Features.
Chapter 9 Practice Schedules.
Motor Behavior Chapter 5. Motor Behavior Define motor behavior, motor development, motor control, and motor learning. What is the influence of readiness,
Author name here for Edited books chapter Assessing Balance and Designing Balance Programs chapter.
Data Analytics Framework for A Game-based Rehabilitation System Jiongqian (Albert) Liang*, David Fuhry*, David Maung*, Alexandra Borstad +, Roger Crawfis*,
Chapter 18 Therapeutic Exercise for Rehabilitation.
Date of download: 5/30/2016 Copyright © 2016 American Medical Association. All rights reserved. From: Robotic Devices as Therapeutic and Diagnostic Tools.
Mental practice in chronic stroke- results of a randomized, placebo- controlled trial.
National 4 & 5 Physical Education. Documents available on website Unit by Unit approach to Performance (package 1) Unit by Unit approach to Factors impacting.
Michael E. Levin, Jacqueline Pistorello,
A stroke is the leading cause of permanent impairment and disability
Michael Henehan, DO San Jose-O’Connor Hospital
NATURE NEUROSCIENCE 2007 Coordinated memory replay in the visual cortex and hippocampus during sleep Daoyun Ji & Matthew A Wilson Department of Brain.
Intervention to Advance Postural Transitions and Problem Solving Ability in Children With Cerebral Palsy Xin Zhang 1, Swati M. Surkar 2, Regina T. Harbourne.
2 Jarrod Blinch1, Youngdeok Kim1, Romeo Chua2 1
Community Delivery of TeenDrivingPlan
Gerald Dyer, Jr., MPH October 20, 2016
Therapeutic Exercise for Rehabilitation
Brahm Fleisch Research supported by the Zenex Foundation October 2017
Spatial STEM - C Evaluation of a Model Spatial Thinking Curriculum for Building Computational Skills in Elementary Grades K-5 A collaboratvive project.
Presentation transcript:

Adaptive Rehabilitation using Mixed-reality at Home: The ARM at Home study RIC Margaret Duff, Meghan Buell, and W. Zev Rymer Emory Steven Wolf and Aimee Reiss ASU Pavan Turaga, Nicole Lehrer, Michael Baran, Vinay Venkataraman, Loren Olson and Todd Ingalls CMU Thanassis Rikakis

Adaptive mixed reality rehabilitation  Computational assessment of movement  Abstract audio and visual feedback, evaluation and adaptation  Tangible sensing objects provide functional goals  Increase engagement and enhance motor learning through self-assessment of movement  Recover pre-morbid movement patterns and reduce compensation while increasing function

Completed at Banner Baywood Medical Center Evaluating outcomes of mixed reality compared to traditional therapy

AMRR improves function and kinematics  Both groups improved in the Wolf Motor Function Test  Every AMRR participant saw at least a 30% improvement in composite kinematic impairment measure (KIM), with a much more consistent distribution of improvement % change * AMRR group Control group

Issues to address  Neither group reported a significant change in impaired arm use / quality in ADLs  Long-term plan to both encourage functional and movement quality improvements  Continue therapy at home and with a greater variety of tasks

Scaling AMRR theories for home therapy

Home AMRR system  An engaging therapy environment at home  Task repetition, variability and intensity  Easy to use and understand in a largely unsupervised environment  Useful information (feedback) about task completion and movement quality

Feedback examples

Pilot study of unsupervised training  Test feasibility and effectiveness  Examine how people with stroke use and accept the system  Determine what further work is needed to accommodate the needs of the greatest percentage of people

Study protocol  1 week (3 sessions) of supervised training  4 weeks (12 sessions) of unsupervised training  Pre, post, and 4 week follow-up evaluations Participant demographics MedianRange Age (years) Months post stroke Fugl-Meyer (/66) N = 6 (6M, 0 F)

Wolf Motor Function Test Both FAS and time improve after therapy and are mostly retained at follow-up

Fugl-Meyer and Motor Activity Log FM scores improve after therapy and are retained at follow-up MAL scores are inconsistent after therapy and at follow-up

Kinematic results of trained task Velocity peak trained to about.6 m/s Inconsistent changes in horizontal trajectory

Participant acceptance of system

Preliminary outcomes  System was stable throughout  Successful unsupervised training  FM and WMFT improved after training  Kinematics and MAL were inconsistent

Current and future work  Improved hand function sensing  Track ADLs objectively and transfer therapy gains to everyday  Increased adaptability of therapy protocols  Better classification of movement impairments

Hand function sensing

More adaptive therapy protocols Current Protocol  Two set therapy tracks Future Considerations  Progression based on ability  Objects that vary more in complexity and weight  Variability within a set of reaches  Dissociate objects from table

Assessing the classifiers Problem - building high level metrics of efficiency for complex movements with reduced sensing Assessing new metrics for classifying movement  Correlation to kinematic assessment of simple tasks  Therapist ratings of simple to complex tasks, each rated in terms of overall performance and component performance  Components that are being trained on do not have one- to-one mapping with therapist ratings, which implies no supervised training data to build classifiers  But there is weak supervision !

Kinematic classifiers that drive feedback Curvedness – Measure of spatial error Too Fast / Too Slow – Measure of deviation in velocity profile Smoothness – Measure of variability in velocity profile

Cone grasp (simple, trained) Elevated touch (simple, semi-trained) Transport cylinder (complex, trained) Therapist rated tasks Video recordings of 3 tasks (5 trials each), performed once a week independent of therapy Treating therapist rated each reach, presented randomly

Rating system was developed to assign a score for each of the following: 1.Initial impression of overall trial (Modified FAS) 2.Trajectory 3.Compensation 4.Hand manipulation (grasp, touch) 5.Transport phase (if transport task) 6.Release phase (if transport task) 7.Final impression of overall trial (Modified FAS) If needed, explanation recorded if final impression is different than initial impression Therapist rated tasks

How does therapist rating help in tuning these classifiers? Assume a linear model of kinematic classifiers W1W1 W2W2 W3W3 W4W4 Cumulative Classifier Score

W 1 F 1 (T 1 ) + W 2 F 2 (T 2 ) + W 3 F 3 (T 3 ) + W 4 F 4 (T 4 ) + noise = Cost function = Use Nelder-Mead’s Simplex (fminsearch algorithm in MATLAB) to perform optimization Movement quality assessment Therapist Rating (R) {Initial impression of overall score}

Initial Results –3 participants (mild impairment) recorded at Emory –4 video recorded sessions each –Total of 55 reaches to grasp the cone

Initial Results Before optimization: Observe the overlap in score distributions, which implies classifiers are not tuned properly 45 Means are close

Initial Results Optimizing only the combination weights: The score distribution overlap does not get affected, suggesting that the problem really lies with the classifiers 45

Initial Results 45 Reduced overlap After optimization of weights and thresholds: score distribution overlap reduces

Conclusions  Changes in therapy protocols and tasks needed to benefit a larger subset of the population  Movement classifiers need to be generalized and improved, while staying accurate  Monitor and encourage transfer of therapy strategies to everyday life

Thank You!!!