Healthcare Technology Letters (Feb 2020)
Severity detection tool for patients with infectious disease
- Girmaw Abebe Tadesse,
- Tingting Zhu,
- Tingting Zhu,
- Nhan Le Nguyen Thanh,
- Nhan Le Nguyen Thanh,
- Nguyen Thanh Hung,
- Ha Thi Hai Duong,
- Truong Huu Khanh,
- Pham Van Quang,
- Duc Duong Tran,
- Lam Minh Yen,
- Rogier Van Doorn,
- Nguyen Van Hao,
- John Prince,
- Hamza Javed,
- Dani Kiyasseh,
- Le Van Tan,
- Louise Thwaites,
- David A. Clifton
Affiliations
- Girmaw Abebe Tadesse
- Institute of Biomedical Engineering, University of Oxford
- Tingting Zhu
- Institute of Biomedical Engineering, University of Oxford
- Tingting Zhu
- Institute of Biomedical Engineering, University of Oxford
- Nhan Le Nguyen Thanh
- Children's Hospital Number 1
- Nhan Le Nguyen Thanh
- Children's Hospital Number 1
- Nguyen Thanh Hung
- Children's Hospital Number 1
- Ha Thi Hai Duong
- Hospital for Tropical Diseases
- Truong Huu Khanh
- Children's Hospital Number 1
- Pham Van Quang
- Children's Hospital Number 1
- Duc Duong Tran
- Hospital for Tropical Diseases
- Lam Minh Yen
- Oxford Clinical Research Unit
- Rogier Van Doorn
- Oxford University Clinical Research Unit
- Nguyen Van Hao
- Hospital for Tropical Diseases
- John Prince
- Institute of Biomedical Engineering, University of Oxford
- Hamza Javed
- Institute of Biomedical Engineering, University of Oxford
- Dani Kiyasseh
- Institute of Biomedical Engineering, University of Oxford
- Le Van Tan
- Oxford Clinical Research Unit
- Louise Thwaites
- Oxford Clinical Research Unit
- David A. Clifton
- Institute of Biomedical Engineering, University of Oxford
Abstract
Hand foot and mouth disease (HFMD) and tetanus are serious infectious diseases in low- and middle-income countries. Tetanus, in particular, has a high mortality rate and its treatment is resource-demanding. Furthermore, HFMD often affects a large number of infants and young children. As a result, its treatment consumes enormous healthcare resources, especially when outbreaks occur. Autonomic nervous system dysfunction (ANSD) is the main cause of death for both HFMD and tetanus patients. However, early detection of ANSD is a difficult and challenging problem. The authors aim to provide a proof-of-principle to detect the ANSD level automatically by applying machine learning techniques to physiological patient data, such as electrocardiogram waveforms, which can be collected using low-cost wearable sensors. Efficient features are extracted that encode variations in the waveforms in the time and frequency domains. The proposed approach is validated on multiple datasets of HFMD and tetanus patients in Vietnam. Results show that encouraging performance is achieved. Moreover, the proposed features are simple, more generalisable and outperformed the standard heart rate variability analysis. The proposed approach would facilitate both the diagnosis and treatment of infectious diseases in low- and middle-income countries, and thereby improve patient care.
Keywords
- support vector machines
- cardiology
- electrocardiography
- patient care
- neurophysiology
- patient diagnosis
- diseases
- learning (artificial intelligence)
- patient treatment
- medical signal processing
- medical computing
- health care
- feature extraction
- severity detection tool
- infectious disease
- hfmd
- serious infectious diseases
- middle-income countries
- high mortality rate
- resource-demanding
- young children
- enormous healthcare resources
- autonomic nervous system dysfunction
- tetanus patients
- difficult problem
- proof-of-principle
- ansd level
- physiological patient data
- electrocardiogram
- photoplethysmogram waveforms
- low-cost wearable sensors
- frequency domains
- support vector machine
- classifying ansd levels
- standard heart rate variability analysis
- patient care
