Hongyu Luo1, Pierre-Alexandre Lee1, Ieuan Clay2, Martin Jaggi3, Valeria De Luca1. 1. Novartis Institutes for Biomedical Research, Basel, Switzerland. 2. Evidation Health Inc., San Mateo, California, USA. 3. Machine Learning and Optimization Laboratory, EPFL, Lausanne, Switzerland.
Abstract
BACKGROUND: Fatigue is a broad, multifactorial concept encompassing feelings of reduced physical and mental energy levels. Fatigue strongly impacts patient health-related quality of life across a huge range of conditions, yet, to date, tools available to understand fatigue are severely limited. METHODS: After using a recurrent neural network-based algorithm to impute missing time series data form a multisensor wearable device, we compared supervised and unsupervised machine learning approaches to gain insights on the relationship between self-reported non-pathological fatigue and multimodal sensor data. RESULTS: A total of 27 healthy subjects and 405 recording days were analyzed. Recorded data included continuous multimodal wearable sensor time series on physical activity, vital signs, and other physiological parameters, and daily questionnaires on fatigue. The best results were obtained when using the causal convolutional neural network model for unsupervised representation learning of multivariate sensor data, and random forest as a classifier trained on subject-reported physical fatigue labels (weighted precision of 0.70 ± 0.03 and recall of 0.73 ± 0.03). When using manually engineered features on sensor data to train our random forest (weighted precision of 0.70 ± 0.05 and recall of 0.72 ± 0.01), both physical activity (energy expenditure, activity counts, and steps) and vital signs (heart rate, heart rate variability, and respiratory rate) were important parameters to measure. Furthermore, vital signs contributed the most as top features for predicting mental fatigue compared to physical ones. These results support the idea that fatigue is a highly multimodal concept. Analysis of clusters from sensor data highlighted a digital phenotype indicating the presence of fatigue (95% of observations) characterized by a high intensity of physical activity. Mental fatigue followed similar trends but was less predictable. Potential future directions could focus on anomaly detection assuming longer individual monitoring periods. CONCLUSION: Taken together, these results are the first demonstration that multimodal digital data can be used to inform, quantify, and augment subjectively captured non-pathological fatigue measures.
BACKGROUND: Fatigue is a broad, multifactorial concept encompassing feelings of reduced physical and mental energy levels. Fatigue strongly impacts patient health-related quality of life across a huge range of conditions, yet, to date, tools available to understand fatigue are severely limited. METHODS: After using a recurrent neural network-based algorithm to impute missing time series data form a multisensor wearable device, we compared supervised and unsupervised machine learning approaches to gain insights on the relationship between self-reported non-pathological fatigue and multimodal sensor data. RESULTS: A total of 27 healthy subjects and 405 recording days were analyzed. Recorded data included continuous multimodal wearable sensor time series on physical activity, vital signs, and other physiological parameters, and daily questionnaires on fatigue. The best results were obtained when using the causal convolutional neural network model for unsupervised representation learning of multivariate sensor data, and random forest as a classifier trained on subject-reported physical fatigue labels (weighted precision of 0.70 ± 0.03 and recall of 0.73 ± 0.03). When using manually engineered features on sensor data to train our random forest (weighted precision of 0.70 ± 0.05 and recall of 0.72 ± 0.01), both physical activity (energy expenditure, activity counts, and steps) and vital signs (heart rate, heart rate variability, and respiratory rate) were important parameters to measure. Furthermore, vital signs contributed the most as top features for predicting mental fatigue compared to physical ones. These results support the idea that fatigue is a highly multimodal concept. Analysis of clusters from sensor data highlighted a digital phenotype indicating the presence of fatigue (95% of observations) characterized by a high intensity of physical activity. Mental fatigue followed similar trends but was less predictable. Potential future directions could focus on anomaly detection assuming longer individual monitoring periods. CONCLUSION: Taken together, these results are the first demonstration that multimodal digital data can be used to inform, quantify, and augment subjectively captured non-pathological fatigue measures.
Authors: Arne Mueller; Holger Hoefling; Timur Nuritdinow; Nicholas Holway; Matthias Schieker; Martin Daumer; Ieuan Clay Journal: Digit Biomark Date: 2018-08-02
Authors: Akane Sano; Amy Z Yu; Andrew W McHill; Andrew J K Phillips; Sara Taylor; Natasha Jaques; Elizabeth B Klerman; Rosalind W Picard Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2015
Authors: Jorge I Galván-Tejada; José M Celaya-Padilla; Victor Treviño; José G Tamez-Peña Journal: Comput Math Methods Med Date: 2015-10-04 Impact factor: 2.238
Authors: Ieuan Clay; Francesca Cormack; Szymon Fedor; Luca Foschini; Giovanni Gentile; Chris van Hoof; Priya Kumar; Florian Lipsmeier; Akane Sano; Benjamin Smarr; Benjamin Vandendriessche; Valeria De Luca Journal: J Med Internet Res Date: 2022-05-26 Impact factor: 7.076
Authors: Mauricio A Ramírez-Moreno; Patricio Carrillo-Tijerina; Milton Osiel Candela-Leal; Myriam Alanis-Espinosa; Juan Carlos Tudón-Martínez; Armando Roman-Flores; Ricardo A Ramírez-Mendoza; Jorge de J Lozoya-Santos Journal: Int J Environ Res Public Health Date: 2021-11-12 Impact factor: 3.390
Authors: Benjamin Harris Peterson Corman; Sritha Rajupet; Fan Ye; Elinor Randi Schoenfeld Journal: J Med Internet Res Date: 2022-01-26 Impact factor: 5.428