Towards Machine Learning-Based Detection of Running-Induced Fatigue in Real-World Scenarios: Evaluation of IMU Sensor Configurations to Reduce Intrusiveness

Physical fatigue is a recurrent problem in running that negatively affects performance and leads to an increased risk of being injured. Identification and management of fatigue helps reducing such negative effects, but is presently commonly based on subjective fatigue measurements. Inertial sensors can record movement data continuously, allowing recording for long durations and extensive amounts of data. Here we aimed to assess if inertial measurement units (IMUs) can be used to distinguish between fatigue levels during an outdoor run with a machine learning classification algorithm trained on IMU-derived biomechanical features, and what is the optimal configuration to do so. Eight runners ran 13 laps of 400 m on an athletic track at a constant speed with 8 IMUs attached to their body (feet, tibias, thighs, pelvis, and sternum). Three segments were extracted from the run: laps 2–4 (no fatigue condition, Rating of Perceived Exertion (RPE) = 6.0 ± 0.0); laps 8–10 (mild fatigue condition, RPE = 11.7 ± 2.0); laps 11–13 (heavy fatigue condition, RPE = 14.2 ± 3.0), run directly after a fatiguing protocol (progressive increase of speed until RPE ≥ 16) that followed lap 10. A random forest classification algorithm was trained with selected features from the 400 m moving average of the IMU-derived accelerations, angular velocities, and joint angles. A leave-one-subject-out cross validation was performed to assess the optimal combination of IMU locations to detect fatigue and selected sensor configurations were considered. The left tibia was the most recurrent sensor location, resulting in accuracies ranging between 0.761 (single left tibia location) and 0.905 (all IMU locations). These findings contribute toward a balanced choice between higher accuracy and lower intrusiveness in the development of IMU-based fatigue detection devices in running.

[1]  Konrad P. Kording,et al.  The need to approximate the use-case in clinical machine learning , 2017, GigaScience.

[2]  Jasper Reenalda,et al.  Kinematics and shock attenuation during a prolonged run on the athletic track as measured with inertial magnetic measurement units. , 2019, Gait & posture.

[3]  Eric S Wallace,et al.  Effects of fatigue on running mechanics associated with tibial stress fracture risk. , 2012, Medicine and science in sports and exercise.

[4]  G. Borg Psychophysical bases of perceived exertion. , 1982, Medicine and science in sports and exercise.

[5]  Roger M Enoka,et al.  Fatigue and fatigability in neurologic illnesses , 2013, Neurology.

[6]  W. Hoogkamer,et al.  Novice runners show greater changes in kinematics with fatigue compared with competitive runners , 2018, Sports biomechanics.

[7]  Jasper Reenalda,et al.  Continuous three dimensional analysis of running mechanics during a marathon by means of inertial magnetic measurement units to objectify changes in running mechanics. , 2016, Journal of biomechanics.

[8]  Jeroen Scheerder,et al.  Running across Europe: The rise and size of one of the largest sport markets , 2015 .

[9]  Zahra Sedighi Maman,et al.  A data-driven approach to modeling physical fatigue in the workplace using wearable sensors. , 2017, Applied ergonomics.

[10]  J. Hamill,et al.  Running injury and stride time variability over a prolonged run. , 2011, Gait & posture.

[11]  C. Napier,et al.  Moving Beyond Weekly 'Distance': Optimizing Quantification of Training Load in Runners. , 2020, The Journal of orthopaedic and sports physical therapy.

[12]  Detection of foot contact in treadmill running with inertial and optical measurement systems. , 2021, Journal of biomechanics.

[13]  L. Chiu,et al.  Compensatory changes in female running mechanics during a simulated 10 km race , 2018 .

[14]  Brian Caulfield,et al.  Binary classification of running fatigue using a single inertial measurement unit , 2017, 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[15]  Gerhard Tröster,et al.  Monitoring Kinematic Changes With Fatigue in Running Using Body-Worn Sensors , 2012, IEEE Transactions on Information Technology in Biomedicine.

[16]  Ehsan T. Esfahani,et al.  A machine learning approach to detect changes in gait parameters following a fatiguing occupational task , 2018, Ergonomics.

[17]  C. Foster,et al.  Validity and reliability of the session RPE method for monitoring exercise training intensity , 2006 .

[18]  A. Verhagen,et al.  Prevalence, incidence and course of lower extremity injuries in runners during a 12‐month follow‐up period , 2014, Scandinavian journal of medicine & science in sports.

[19]  Load, Overload, and Recovery in the Athlete: Select Issues for the Team Physician-A Consensus Statement. , 2019, Medicine and science in sports and exercise.

[20]  I. Davis,et al.  Relationship of Foot Strike Pattern and Landing Impacts during a Marathon. , 2019, Medicine and science in sports and exercise.

[21]  T. Besier,et al.  The influence of running velocity on resultant tibial acceleration in runners , 2018, Sports biomechanics.

[22]  Benedicte Vanwanseele,et al.  Influence of outdoor running fatigue and medial tibial stress syndrome on accelerometer-based loading and stability. , 2018, Gait & posture.

[23]  P. Thompson,et al.  Running as a Key Lifestyle Medicine for Longevity. , 2017, Progress in cardiovascular diseases.

[24]  Madalina Fiterau,et al.  Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities. , 2018, Journal of biomechanics.

[25]  Wannes Meert,et al.  Fatigue Prediction in Outdoor Runners Via Machine Learning and Sensor Fusion , 2018, KDD.

[26]  Carlo Menon,et al.  Fatigue Monitoring in Running Using Flexible Textile Wearable Sensors , 2020, Sensors.

[27]  Howard J Hillstrom,et al.  The effects of limb dominance and fatigue on running biomechanics. , 2014, Gait & posture.

[28]  Wayne F. Major The Benefits and Costs of Serious Running , 2001 .

[29]  K. Tamura,et al.  Asymmetry between lower limbs during rested and fatigued state running gait in healthy individuals. , 2017, Gait & posture.