mHealth system for the early detection of infectious diseases using biomedical signals
AuthorsSanz Moreno, José; Gómez Pulido, José Manuel; Garcés Jiménez, Alberto; Calderón Gómez, Huriviades; Vargas Lombardo, Miguel; [et al.]
IdentifiersPermanent link (URI): http://hdl.handle.net/10017/56052
AffiliationUniversidad de Alcalá. Departamento de Ciencias de la Computación; Universidad de Alcalá. Departamento de Enfermería y Fisioterapia; Universidad de Alcalá. Departamento de Medicina y Especialidades Médicas
Sanz Moreno, J., Gómez Pulido, J., Garcés, A., Calderón Gómez, H., Vargas Lombardo, M., Castillo Sequera, J.L., Polo Luque, M.L., Toro, R. & Sención Martínez, G. 2020, “mHealth system for the early detection of infectious diseases using biomedical signals”, in Proceedings of the Latin American Congress on Automation and Robotics, LACAR 2019, Advances in Automation and Robotics Research, pp. 203-213.
Description / Notes
Latin American Congress on Automation and Robotics LACAR 2019, 30/10/2019-01/11/2019, Cali, Colombia.
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
© 2020 Springer Nature
Detection at an early stage of an infection is a major clinical challenge. An infection that is not diagnosed in time can not only seriously affect the health of the infected patient, but also spread and initiate a contagious approach towards other people. This paper deals with mHealth system for medical care and pre-diagnosis. The developed mHealth system use an Android App that collects physiological signals from the patients with a portable and easy-to-use sensors kit. The focus of the work is put on being able to build a low-cost system that using a very small amounts of data (one set record per patient and day). The processed data are uploaded to an online database to train a clinical decision support system to automatically diagnose infections. The mHealth system may be operated by the same personnel on site not requiring to be medical or computational skilled at all. The implementation takes five kinds of measures simultaneously (Electrodermal Activity, Body Temperature, Blood Pressure, Heart Beat Rate and Oxygen Saturation (SPO2)). A real implementation has been tested and results confirm that the sampling process can be done very fast and steadily Finally, the App usability was tested, showing a fast learning curve and no significant differences are observable in learning time by people with different skills or age. These usability factors are key for the mHealth system success.