Small logo of ETH main building ETH Zurich : Computer Science : Pervasive Computing : Distributed Systems : Education : Student Projects : Abstract

Fatigue assessment through mobile technologies (M)

Status: Abgeschlossen


Multiple sclerosis (MS) is an autoimmune disease characterized by recurrent inflammation in areas of the central nervous system [1], which comprises the brain and spinal cord. With more than 2 million patients worldwide [2], MS is one of the leading causes of neurological disability in young adults. Like many other diseases, MS is a complex disease, and its course is influenced by a combination of genetics, environment and lifestyles factors. MS can cause a wide variety of symptoms such as fatigue, sensory problems, cognitive challenges, motor difficulties between others. Fatigue is a common symptom within the MS population, around 75 - 90% of patients has reported fatigue at some point [3, 4, 5]. Clinicians and scientists described fatigue as “a sub-jective lack of physical and/or mental energy that is perceived by the individual or caregiver to interfere with usual and desired activities” [6]. MS fatigue has a significant impact in the quality of life patients, it affects work performance as well as personal interactions [3]. Despite being highly prevalent and being a debilitating symptom, it is not well understood [7]. Furthermore, no objective measurement to diagnose and rate the level of fatigue is available. Current evaluation relies on subjective measurements reported by patients using fatigue scales, such as the fatigue severity scale [8]. Ayache et al. in [7], highlighted the need to better understand the underlying causes of fatigue as well as the implementation of new therapeutic strategies. There is evidence of the importance of the autonomic nervous system in fatigue [9], but this is poorly analyzed in the context of MS. Therefore, we propose to assess the role of autonomic dysfunction and stress levels in MS in the context of fatigue using continuous measurement of autonomic function.


[1] Sospedra M and Martin R. Immunology of multiple sclerosis.Annual Review of Inmmunology,65(23):683–747, 2005.
[2] National Multiple Sclerosis Society. Who gets ms? (epidemiology). Available at
[3] Fisk JD, Pontefract A, Ritvo PG, Archibald CJ, and Murray TJ. The impact of fatigueon patients with multiple sclerosis.The Canadian Journal of Neurological Science, 21:9–14,1994.
[4] Krupp LB and Pollina DA. Mechanisms and management of fatigue in progressive neurolog-ical disorders.Current Opinion on Neurology, 9:456–460, 1996.
[5] Lerdal A, Celius EG, Krupp L, and Dahl AA. A prospective study of patterns of fatigue inmultiple sclerosis.European Journal of Neurology, 14:1338–1343, 2007.
[6] Multiple Sclerosis Clinical Practice Guidelines.Fatigue and multiple sclerosis: evidence-basedmanagement strategies for fatigue in multiple sclerosis. Paralyzed Veterans of America, 1998.
[7] Ayache SS and Chalah MA. Fatigue in multiple sclerosis - insights into evaluation andmanagement.Clinical Neurophysiology, 47:139–171, 2017.
[8] Lauren Krupp, Nicholas Larocca, J Muir-Nash, and A.D. Steinberg. The fatigue severity scale.application to patients with multiple sclerosis and systemic lupus erythematosus. 46:1121–3,11 1989.
[9] Masaaki Tanaka, Seiki Tajima, Kei Mizuno, Akira Ishii, Yukuo, Teruhisa Miike, and Ya-suyoshi Watanabe. Frontier studies on fatigue, autonomic nerve dysfunction, and sleep-rhythm disorder.The Journal of Physiological Sciences, 65(6):483–498, 2015.


This project requires interest in machine learning, wearable technologies and mobile development. Students are expected to meet with their supervisors regularly to discuss current progress and next steps.

For more details please send us an email.

Student/Bearbeitet von: Pietro Oldrati
Contact/Ansprechpartner: Liliana Barrios

ETH ZurichDistributed Systems Group
Last updated December 16 2019 02:12:41 PM MET lb