Key result
A multi-modal deep learning framework utilizing wearable sensor data and cross-domain transfer learning achieved F1-scores of 97.9% for tetanus and 66.6% for HFMD in predicting autonomic nervous system dysfunction severity.
Why the study?
Monitoring deterioration in tetanus and HFMD often requires expensive monitors, while existing methods underutilize multi-modal physiological data and deep learning for triage in low-resource settings.
Does a machine learning framework using multi-modal physiological data from wearable devices accurately predict the severity of ANSD in patients with infectious diseases?
Does a machine learning framework using multi-modal physiological data from wearable devices accurately predict the severity of ANSD in patients with infectious diseases?
A machine learning framework utilizing data from low-cost wearable devices shows potential for rapid triage and severity prediction of autonomic nervous system dysfunction in infectious diseases in developing regions.
In low and middle income countries, infectious diseases continue to have a significant impact, particularly amongst the poorest in society. Tetanus and hand foot and mouth disease (HFMD) are two such diseases and, in both, death is associated with autonomic nervous system dysfunction (ANSD). Currently, photoplethysmogram or electrocardiogram monitoring is used to detect deterioration in these patients, however expensive clinical monitors are often required. In this study, we employ low-cost and mobile wearable devices to collect patient vital signs unobtrusively; and we develop machine learning algorithms for automatic and rapid triage of patients that provide efficient use of clinical resources. Existing methods are mainly dependent on the prior detection of clinical features with limited exploitation of multi-modal physiological data. Moreover, the latest developments in deep learning (e.g. cross-domain transfer learning) have not been sufficiently applied for infectious disease diagnosis. In this paper, we present a fusion of multi-modal physiological data to predict the severity of ANSD with a hierarchy of resource-aware decision making. First, an on-site triage process is performed using a simple classifier. Second, personalised longitudinal modelling is employed that takes the previous states of the patient into consideration. We have also employed a spectrogram representation of the physiological waveforms to exploit existing networks for cross-domain transfer learning, which avoids the laborious and data intensive process of training a network from scratch. Results show that the proposed framework has promising potential in supporting severity grading of infectious diseases in low-resources settings, such as in the developing world.
No takes yet. Share an insight, caveat, or question.
Tadesse et al. (2020) studied Tetanus and Hand, Foot and Mouth Disease (HFMD) (n=84). Multi-modal deep learning framework (CNN + LSTM) vs. Hand-crafted features with traditional machine learning was evaluated on F1-score for predicting autonomic nervous system dysfunction severity. A multi-modal deep learning framework utilizing wearable sensor data and cross-domain transfer learning achieved F1-scores of 97.9% for tetanus and 66.6% for HFMD in predicting autonomic nervous system dysfunction severity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: