Internship in Health Data Science/Bioinformatics (Master2 student) - GF0919
1A-B, rue Thomas Edison, Strassen 1445, Luxembourg
Using vocal data for health purposes constitutes a wide field of investigation that has been little explored so far. Regarding diabetes specifically, vocal data is a promising data source to identify, based on various acoustic features, digital vocal biomarkers associated with stress, anxiety, fear of hypoglycemia, emotions and clinical outcomes such as cardiovascular disease or glycemic control. Most common phonatory symptoms in type 2 diabetes are vocal tiring, fatigue and hoarseness. They are more frequent in people with diabetes (PWD) than in the general population and have been shown to impact PWD’s quality of life. Overall, PWD exhibit different voice characteristics from the general than population and are at increased risk of major adverse cardiac event and psychological complications. It seems feasible to identify, in a non invasive fashion, vocal biomarkers useful for diabetes management and prevention of diabetes-related complications.
Our team aims at identifying vocal biomarkers to design just-in-time intervention studies. The present project is dedicated to the identification of vocal biomarkers associated with patients’ emotions.
Training and research environment
The “Digital Epidemiology Hub” develops a transversal research activity within the Department of Population Health on modern approaches in digital epidemiology, at the frontier with data and computer sciences.
The Master student will directly contribute to the development of a large international initiative to integrate innovate digital data into modern epidemiological studies. He/she will lead a project on the analysis of a large annotated audio dataset (SenticNet/MELD) to decompose the audio signals and then apply AI-based algorithms and statistical approaches to identify features associated with emotions. He/She will have to take in charge the literature review, the pre-processing of the data, the data analysis and the writing of the scientific article. He/she will be supervised by Dr. G. Fagherazzi, Research Leader of the Digital Epidemiology Hub, in association with experts in audio signals and artificial intelligence methods. This internship position may lead to a PhD opportunity in digital epidemiology.
What we offer and conditions
- Students will have the opportunity to work in an interactive and international scientific environment, attend conferences by eminent scientists from abroad, and present their own work during lab meetings.
- They will receive training in digital epidemiology research and data science and will have the opportunity to gain skills in data analysis, AI methods applied to audio data.
- Applicants must be affiliated to their own University.
- English is mandatory.
- Master 2 students will receive 500 €/month unless they have their own funding source, e.g.Erasmus grant.
Available for 6-9 months (can be extendedaccording to the specific requirements of the University)- Full time- Start date : 2020
- Snoek, F. J., Pouwer, F., Welch, G. W. & Polonsky, W. H.
Diabetes-related emotional distress in Dutch and U.S. diabetic patients:
cross-cultural validity of the problem areas in diabetes scale. Diabetes
Care 23, 1305–1309 (2000).
- Ghosh, S. S., Ciccarelli, G., Quatieri, T. F. & Klein, A. Speaking one’s mind: Vocal biomarkers of depression and Parkinson disease. The Journal of the Acoustical Society of America 139, 2193–2193 (2016).
- Maor, E. et al. Voice Signal Characteristics Are Independently Associated With Coronary Artery Disease. Mayo Clin. Proc. 93, 840–847 (2018).
- Hamdan, A.-L., Jabbour, J., Nassar, J., Dahouk, I. & Azar, S. T. Vocal characteristics in patients with type 2 diabetes mellitus. Eur. Arch. Otorhinolaryngol. 269, 1489–1495 (2012).
- Hamdan, A.-L., Kurban, Z. & Azar, S. T. Prevalence of phonatory symptoms in patients with type 2 diabetes mellitus. Acta Diabetol. 50, 731–736 (2013).