||Multi-digit Coordination in patient with Trigger Digit during Natural Precision Grasping using Machine Learning and Deep Learning
||Department of BioMedical Engineering
Multi-Digit Force Coordination
Motor coordination is the combination of body movements created with the kinematic (spatial direction) and kinetic (force) parameters that result in intended actions. Trigger finger is a common symptom in hand, that affects the motor coordination, and results in hand functional impairment. With hand functional impairment, our movements cannot reach a certain level of motion quality to carry out normal activities. Previous studies used cylindrical grasp devices to investigate finger force coordination of the hand during precision grasping. However, data acquired is usually dynamic, multivariate, and high dimensional. While both machine learning and deep learning are powerful tools to analyze these complex data, they also have differences. Machine learning uses pre-defined features that have clinical meaning verified in previous studies to train the model. Deep learning use kernels to extract feature automatically during the training process, therefore, these features are still unknown and should be discussed. This study proposes a machine learning and deep learning approach to investigating finger forces coordination during grasping task and drinking task. 44 healthy subjects (39.5 years ± 7.6) and 54 trigger finger patients (57.6 years ± 8.0) participated in this study. We built and analyzed 2 supervised classification models (Random Forest and 1D-CNN). Random Forest gives feature importance from all extracted features. As for 1D-CNN, the Grad-CAM technique gives information on which phase is the most important for the model to make the classification. This study found out that Random Forest and 1D-CNN model can classify between two groups of subjects with an average accuracy of ~77%. Random Forest results suggest that the duration of trials is an important factor while not controlled in the experiment setting. 1D-CNN results suggest that the holding phase is the most important phase for the model to make the classification.
List of Figures VI
List of Tables VIII
Chapter 1 Introduction 1
1.1 Motor coordination 1
1.2 Trigger finger 2
1.3 Human hand motion 4
1.4 Finger force coordination 9
1.4.1 Grasping 9
1.4.2 Cylindrical grasping force coordination 10
1.5 Artificial Intelligence, Machine Learning, Deep Learning 13
1.6 Literature review 14
1.6.1 Finger force coordination in trigger finger patients 14
1.6.2 Machine Learning & Deep Learning in Human Hand Motion 14
1.6.3 Machine Learning and Deep Learning for Time Series Data 15
1.7 Motivation 16
1.8 Research Questions and Specific Aims 16
1.9 Data Acquisition 17
1.9.1 Device 17
1.9.2 Data collection 19
Chapter 2 Material and Methods 22
2.1 Participants 22
2.2 Data Review & Research Design 23
2.3 Preprocessing 24
2.3.1 Segmentation 24
2.3.2 Feature extraction 25
2.3.3 Resample and Zero padding 26
2.4 Splitting Data and Model Evaluation 27
2.5 Machine Learning model & Deep Learning model 28
2.5.1 Decision Tree (DT) & Random Forest (RF) 28
2.5.2 Convolution Neural Network. 29
2.5.2 Model Architecture 31
2.6 Gradient-weight Class Activation Mapping (Grad-CAM) 33
Chapter 3 Results 34
3.1 Model Performance 34
3.1.1 Random Forest 35
3.1.2 Brick Model 36
3.2 Model Interpretation 39
3.2.1 Feature Importance (Random Forest) 39
3.2.2 Phase Importance (Brick Model) 42
Chapter 4 Discussion 44
4.1 Model training and performance 44
4.2 Model Interpretation 45
4.3 Limitation 48
4.4 Future Work 49
Chapter 5 Conclusion 50
 K. Friston, "The free-energy principle: a unified brain theory?," Nature reviews neuroscience, vol. 11, no. 2, pp. 127-138, 2010.
 R. Magill and D. Anderson, Motor learning and control. McGraw-Hill Publishing, 2010.
 P. G. Fitzgibbons and A.-P. C. Weiss, "Hand manifestations of diabetes mellitus," The Journal of hand surgery, vol. 33, no. 5, pp. 771-775, 2008.
 S. Stahl, Y. Kanter, and E. Karnielli, "Outcome of trigger finger treatment in diabetes," Journal of diabetes and its complications, vol. 11, no. 5, pp. 287-290, 1997.
 A. H. Makkouk, M. E. Oetgen, C. R. Swigart, and S. D. Dodds, "Trigger finger: etiology, evaluation, and treatment," Current Reviews in Musculoskeletal Medicine, vol. 1, no. 2, pp. 92-96, 2008.
 J. A. McAuliffe, "Tendon disorders of the hand and wrist," The Journal of hand surgery, vol. 35, no. 5, pp. 846-853, 2010.
 J. S. Moore, "Flexor tendon entrapment of the digits (trigger finger and trigger thumb)," Journal of Occupational and Environmental Medicine, vol. 42, no. 5, pp. 526-545, 2000.
 T.-H. Yang et al., "Clinical and pathological correlates of severity classifications in trigger fingers based on computer-aided image analysis," Biomedical engineering online, vol. 13, no. 1, pp. 1-11, 2014.
 H. Guerini et al., "Sonographic appearance of trigger fingers," Journal of Ultrasound in Medicine, vol. 27, no. 10, pp. 1407-1413, 2008.
 M. J. Saldana, "Trigger digits: diagnosis and treatment," JAAOS-Journal of the American Academy of Orthopaedic Surgeons, vol. 9, no. 4, pp. 246-252, 2001.
 H.-R. Kim and S.-H. Lee, "Ultrasonographic assessment of clinically diagnosed trigger fingers," Rheumatology international, vol. 30, no. 11, pp. 1455-1458, 2010.
 J. Sato, Y. Ishii, and H. Noguchi, "Comparison of the thickness of pulley and flexor tendon between in neutral and in flexed positions of trigger finger," The open orthopaedics journal, vol. 10, p. 36, 2016.
 H. Miyamoto, T. Miura, H. Isayama, R. Masuzaki, K. Koike, and T. Ohe, "Stiffness of the first annular pulley in normal and trigger fingers," The Journal of hand surgery, vol. 36, no. 9, pp. 1486-1491, 2011.
 A. Spirig, B. Juon, Y. Banz, R. Rieben, and E. Vögelin, "Correlation between sonographic and in vivo measurement of A1 pulleys in trigger fingers," Ultrasound in medicine & biology, vol. 42, no. 7, pp. 1482-1490, 2016.
 M. Sbernardori, V. Mazzarello, and P. Tranquilli-Leali, "Scanning electron microscopic findings of the gliding surface of the A1 pulley in trigger fingers and thumbs," Journal of Hand Surgery (European Volume), vol. 32, no. 4, pp. 384-387, 2007.
 M. Ryzewicz and J. M. Wolf, "Trigger digits: principles, management, and complications," The Journal of hand surgery, vol. 31, no. 1, pp. 135-146, 2006.
 S. Akhtar, M. J. Bradley, D. N. Quinton, and F. D. Burke, "Management and referral for trigger finger/thumb," Bmj, vol. 331, no. 7507, pp. 30-33, 2005.
 M. Nagaoka, T. Yamaguchi, and S. Nagao, "Triggering at the distal A2 pulley," Journal of Hand Surgery (European Volume), vol. 32, no. 2, pp. 210-213, 2007.
 M. C. Staff. (2020, June 1st). Trigger finger [Online]. Available: https://www.mayoclinic.org/diseases-conditions/trigger-finger/symptoms-causes/syc-20365100?p=1.
 O. Khatib, K. Yokoi, O. Brock, K. Chang, and A. Casal, "Robots in human environments: Basic autonomous capabilities," The International Journal of Robotics Research, vol. 18, no. 7, pp. 684-696, 1999.
 T. Agcayazi, M. Foster, H. Kausche, M. Gordon, and A. Bozkurt, "Multi-axis stress sensor characterization and testing platform," HardwareX, vol. 5, p. e00048, 2019.
 K. Kiguchi and Y. Hayashi, "An EMG-based control for an upper-limb power-assist exoskeleton robot," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 4, pp. 1064-1071, 2012.
 L. Y. Chang, N. S. Pollard, T. M. Mitchell, and E. P. Xing, "Feature selection for grasp recognition from optical markers," in 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007: IEEE, pp. 2944-2950.
 Z. Ju, Y. Wang, W. Zeng, H. Cai, and H. Liu, "A modified EM algorithm for hand gesture segmentation in RGB-D data," in 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2014: IEEE, pp. 1736-1742.
 H. Liu, Z. Ju, X. Ji, C. S. Chan, and M. Khoury, "Human Motion Sensing and Recognition," in Studies in Computational Intelligence 675: Springer, 2017.
 S. Chen, H. Ma, C. Yang, and M. Fu, "Hand gesture based robot control system using leap motion," in International Conference on Intelligent Robotics and Applications, 2015: Springer, pp. 581-591.
 B. Bansal, "Gesture recognition: a survey," International Journal of Computer Applications, vol. 139, no. 2, pp. 8-10, 2016.
 R. S. Johansson and J. R. Flanagan, "Coding and use of tactile signals from the fingertips in object manipulation tasks," Nature Reviews Neuroscience, vol. 10, no. 5, pp. 345-359, 2009.
 J. R. Napier, "The prehensile movements of the human hand," The Journal of bone and joint surgery. British volume, vol. 38, no. 4, pp. 902-913, 1956.
 R. Tubiana, J.-M. Thomine, and E. Mackin, Examination of the hand and wrist. CRC Press, 1998.
 T. Iberall, "Human prehension and dexterous robot hands," The International Journal of Robotics Research, vol. 16, no. 3, pp. 285-299, 1997.
 R. S. Johansson, C. Hger, and L. Bäckström, "Somatosensory control of precision grip during unpredictable pulling loads. III. Impairments during digital anesthesia," Experimental brain research, vol. 89, no. 1, pp. 204-213, 1992.
 M. K. Budgeon, M. L. Latash, and V. M. Zatsiorsky, "Digit force adjustments during finger addition/removal in multi-digit prehension," Experimental brain research, vol. 189, no. 3, pp. 345-59, Aug 2008.
 J. K. Shim, B. S. Lay, V. M. Zatsiorsky, and M. L. Latash, "Age-related changes in finger coordination in static prehension tasks," (in eng), J Appl Physiol, vol. 97, no. 1, pp. 213-24, Jul 2004.
 V. M. Zatsiorsky, R. W. Gregory, and M. L. Latash, "Force and torque production in static multifinger prehension: biomechanics and control. I. Biomechanics," Biological cybernetics, vol. 87, no. 1, pp. 50-7, Jul 2002.
 M. P. Rearick and M. Santello, "Force synergies for multifingered grasping: effect of predictability in object center of mass and handedness," Experimental brain research, vol. 144, no. 1, pp. 38-49, May 2002.
 M. Santello and J. F. Soechting, "Force synergies for multifingered grasping," (in eng), Exp Brain Res, vol. 133, no. 4, pp. 457-67, Aug 2000.
 C. Craje, J. R. Lukos, C. Ansuini, A. M. Gordon, and M. Santello, "The effects of task and content on digit placement on a bottle," Experimental brain research, vol. 212, no. 1, pp. 119-24, Jul 2011.
 J. Lukos, C. Ansuini, and M. Santello, "Choice of contact points during multidigit grasping: effect of predictability of object center of mass location," The Journal of neuroscience : the official journal of the Society for Neuroscience, vol. 27, no. 14, pp. 3894-903, Apr 4 2007.
 L. Sartori, E. Straulino, and U. Castiello, "How objects are grasped: the interplay between affordances and end-goals," (in eng), PLoS One, Randomized Controlled Trial Research Support, Non-U.S. Gov't vol. 6, no. 9, p. e25203, 2011.
 N. J. Seo and T. J. Armstrong, "Effect of elliptic handle shape on grasping strategies, grip force distribution, and twisting ability," (in eng), Ergonomics, vol. 54, no. 10, pp. 961-70, Oct 2011.
 Z. M. Li, M. L. Latash, K. M. Newell, and V. M. Zatsiorsky, "Motor redundancy during maximal voluntary contraction in four-finger tasks," Experimental brain research, vol. 122, no. 1, pp. 71-8, Sep 1998.
 V. M. Zatsiorsky, F. Gao, and M. L. Latash, "Prehension synergies: effects of object geometry and prescribed torques," (in eng), Experimental brain research, Research Support, U.S. Gov't, P.H.S. vol. 148, no. 1, pp. 77-87, Jan 2003.
 L. C. Kuo, F. C. Su, W. L. Tung, K. Y. Lai, and I. M. Jou, "Kinematical and functional improvements of trigger digits after sonographically assisted percutaneous release of the A1 pulley," (in eng), Journal of orthopaedic research : official publication of the Orthopaedic Research Society, vol. 27, no. 7, pp. 891-6, Jul 2009.
 V. M. Zatsiorsky and M. L. Latash, "Multifinger prehension: an overview," (in eng), J Mot Behav, vol. 40, no. 5, pp. 446-76, Sep 2008.
 M. A. Oskoei and H. Hu, "Support vector machine-based classification scheme for myoelectric control applied to upper limb," IEEE transactions on biomedical engineering, vol. 55, no. 8, pp. 1956-1965, 2008.
 M. H. Schwartz, A. Rozumalski, W. Truong, and T. F. Novacheck, "Predicting the outcome of intramuscular psoas lengthening in children with cerebral palsy using preoperative gait data and the random forest algorithm," Gait & posture, vol. 37, no. 4, pp. 473-479, 2013.
 A. Rozumalski and M. H. Schwartz, "Crouch gait patterns defined using k-means cluster analysis are related to underlying clinical pathology," Gait & posture, vol. 30, no. 2, pp. 155-160, 2009.
 Y. Lu, G. Lu, X. Bu, and Y. Yu, "Classification of hand manipulation using bp neural network and support vector machine based on surface electromyography signal," IFAC-PapersOnLine, vol. 48, no. 28, pp. 869-873, 2015.
 H. Rahmati, H. Martens, O. M. Aamo, Ø. Stavdahl, R. Støen, and L. Adde, "Frequency analysis and feature reduction method for prediction of cerebral palsy in young infants," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 24, no. 11, pp. 1225-1234, 2016.
 S. G. Trost, M. Fragala-Pinkham, N. Lennon, and M. E. O'Neil, "Decision trees for detection of activity intensity in youth with cerebral palsy," Medicine and science in sports and exercise, vol. 48, no. 5, p. 958, 2016.
 F. C. Huang and J. L. Patton, "Movement distributions of stroke survivors exhibit distinct patterns that evolve with training," Journal of neuroengineering and rehabilitation, vol. 13, no. 1, p. 23, 2016.
 L. H. Kikkert et al., "Gait dynamics to optimize fall risk assessment in geriatric patients admitted to an outpatient diagnostic clinic," PloS one, vol. 12, no. 6, p. e0178615, 2017.
 M. Punt et al., "Characteristics of daily life gait in fall and non fall-prone stroke survivors and controls," Journal of neuroengineering and rehabilitation, vol. 13, no. 1, p. 67, 2016.
 T.-S. Wei, P.-T. Liu, L.-W. Chang, and S.-Y. Liu, "Gait asymmetry, ankle spasticity, and depression as independent predictors of falls in ambulatory stroke patients," PLoS One, vol. 12, no. 5, p. e0177136, 2017.
 A. Bagnall, J. Lines, A. Bostrom, J. Large, and E. Keogh, "The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances," Data Mining and Knowledge Discovery, vol. 31, no. 3, pp. 606-660, 2017.
 J. Lines and A. Bagnall, "Time series classification with ensembles of elastic distance measures," Data Mining and Knowledge Discovery, vol. 29, no. 3, pp. 565-592, 2015.
 M. G. Baydogan, G. Runger, and E. Tuv, "A bag-of-features framework to classify time series," IEEE transactions on pattern analysis and machine intelligence, vol. 35, no. 11, pp. 2796-2802, 2013.
 H. Deng, G. Runger, E. Tuv, and M. Vladimir, "A time series forest for classification and feature extraction," Information Sciences, vol. 239, pp. 142-153, 2013.
 A. Bostrom and A. Bagnall, "Binary shapelet transform for multiclass time series classification," in International conference on big data analytics and knowledge discovery, 2015: Springer, pp. 257-269.
 Z. Wang, W. Yan, and T. Oates, "Time series classification from scratch with deep neural networks: A strong baseline," in 2017 International joint conference on neural networks (IJCNN), 2017: IEEE, pp. 1578-1585.
 A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
 C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
 I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to sequence learning with neural networks," in Advances in neural information processing systems, 2014, pp. 3104-3112.
 P.-T. Chen, C.-J. Lin, I.-M. Jou, H.-F. Chieh, F.-C. Su, and L.-C. Kuo, "One digit interruption: the altered force patterns during functionally cylindrical grasping tasks in patients with trigger digits," PloS one, vol. 8, no. 12, p. e83632, 2013.
 P.-T. Chen, I.-M. Jou, C.-J. Lin, H.-F. Chieh, L.-C. Kuo, and F.-C. Su, "Is the control of applied digital forces during natural five-digit grasping affected by carpal tunnel syndrome?," Clinical Orthopaedics and Related Research®, vol. 473, no. 7, pp. 2371-2382, 2015.
 W. G. Hawkins, "Fourier transform resampling: theory and application," IEEE Transactions on Nuclear Science, vol. 44, no. 4, pp. 1543-1551, 1997.
 R. J. Lewis, "An introduction to classification and regression tree (CART) analysis," in Annual meeting of the society for academic emergency medicine in San Francisco, California, 2000, vol. 14.
 S. J. Russell and P. Norvig, Artificial intelligence: a modern approach. Malaysia; Pearson Education Limited, 2016.
 H. I. Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Muller, "Deep learning for time series classification: a review," Data Mining and Knowledge Discovery, vol. 33, no. 4, pp. 917-963, 2019.
 S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," arXiv preprint arXiv:1502.03167, 2015.
 R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-cam: Visual explanations from deep networks via gradient-based localization," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 618-626.
 H. Y. Chiu, H. Y. Hsu, L. C. Kuo, J. H. Chang, and F. C. Su, "Functional sensibility assessment. Part I: develop a reliable apparatus to assess momentary pinch force control," Journal of orthopaedic research : official publication of the Orthopaedic Research Society, vol. 27, no. 8, pp. 1116-21, Aug 2009.
 M. N. McDonnell, S. L. Hillier, M. C. Ridding, and T. S. Miles, "Impairments in precision grip correlate with functional measures in adult hemiplegia," Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology, vol. 117, no. 7, pp. 1474-80, Jul 2006.