Thanasis Tsanas

Chancellor's Fellow

Background

I studied Engineering for my undergraduate and masters degrees and completed a PhD in Applied Mathematics at the University of Oxford in September 2012. I have stayed at the University of Oxford to work as a research fellow in Biomedical Engineering and Applied Mathematics (2012-2016), Stipendiary Lecturer in Engineering Science (2014-2016) and Lecturer at the Said Business School (2016); since January 2017 I am a Chancellor’s Fellow in Data Science at the Usher Institute of Population Health and Informatics. 

I am the recipient of the National Greek State Scholarship (2003 & 2004) graduating as the top student in biomedical engineering in Athens, the BNFL prize for best undergraduate thesis at the University of Liverpool (2007), the CTA scholarship for my MSc at the University of Newcastle (2007), an Intel/EPSRC scholarship for my PhD at the University of Oxford (2008-2012), the student paper award at the NOLTA International meeting (2010), the Andrew Goudie award from St Cross College, University of Oxford, (2011), the EPSRC Doctoral Prize award (2012), the young scientist award at the international workshop MAVEBA (2013), and the EPSRC Statistics and Machine Learning award (2015). I was shortlisted in the final six candidates for the Papanikolaou prize (2011), and was part of the Oxford biomedical engineering team that won the annual Physionet/Computing in Cardiology Competition (2012) for “Predicting mortality of ICU patients”. I was an ‘Outstanding Reviewer’ for the journal Computers in Biology and Medicine (2015), and won a ‘Best reviewer award’ from the IEEE Journal of Biomedical Health Informatics (2015). 

Outside academics, I am a keen chess player having been the Greek under-20s champion (2003) and having participated in European and World Chess Championships.

Qualifications

BSc, BEng, MSc, PhD, FHEA

Open to PhD supervision enquiries?

Yes

Research summary

My research focuses on developing novel tools for data mining and extracting domain information through time series analysis, signal processing, and statistical machine learning. I have worked primarily on applications in healthcare and in particular neuroscience and mental disorders. For example, my PhD work focused on using speech to (a) differentiate healthy controls from people with Parkinson’s disease, and (b) to replicate a Parkinson’s disease symptom severity metric. Other applications of my work on speech-related projects include voice forensics, and even attempting to understand mouse communication through processing their vocalisations.

I have also developed generic tools for feature selection, that is identifying a robust subset of characteristics which is jointly maximally predictive of the outcome of interest. This can have diverse applications in cases where there are multiple characteristics or genes which are collected, and we are interested to focus on the most likely subset of the collected characteristics for further processing. Furthermore, I have developed a robust information fusion scheme aggregating multiple sources (or experts) to get the best outcome when sources (or experts) do not agree on the best diagnosis/course of action: under certain assumptions, I have shown it can outperform the single best expert in the cohort.

More recently, I have been working on developing algorithms to mine data collected from wearable sensors such as smartwatches. The aim is to provide an efficient, robust, objective way to characterise activity, sleep, and circadian rhythm patterns and assist people in daily living or monitor patient groups through treatment. Mining the data collected from these wearable sensors along with data collected from mobile phones offers an unprecedented opportunity to monitor longitudinal patterns at a large scale, and can help revolutionise contemporary healthcare.

Key results of my work have been featured in the news such as Reuters, ScienceDaily and MedicalXpress, and one of my research papers has been highlighted as a “key scientific article” in Renewable Energy and global innovations.

View all 28 publications on Research Explorer

Journal papers

  1. A. Tsanas, J.Y. Goulermas, V. Vartela, D. Tsiapras, G. Theodorakis, A.C. Fisher and P. Sfirakis: "The Windkessel model revisited: a qualitative analysis of the circulatory system", Medical Engineering and Physics, Vol. 31, No. 5, pp. 581-588, 2009 [link] PDF

  2. A. Tsanas, M.A. Little, P.E. McSharry, L.O. Ramig: "Accurate telemonitoring of Parkinson's disease progression by non-invasive speech tests", IEEE Transactions on Biomedical Engineering, Vol. 57, pp. 884-893, 2010 [linkPDF
  3. A. Tsanas, M.A. Little, P.E. McSharry, L.O. Ramig: "Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson’s disease symptom severity", Journal of the Royal Society Interface, Vol. 8, pp. 842-855, 2011 [linkPDF, see also the Electronic Supplementary Material [link] for more technical details. (Selected media coverage for this work appears here, and here.)
  4. A. Tsanas, M.A. Little, P.E. McSharry, J. Spielman, L.O. Ramig: "Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease", IEEE Transactions on Biomedical Engineering, Vol. 59, pp. 1264-1271, 2012 [link] PDF
  5. A. Tsanas, M.A. Little, P.E. McSharry, B.K. Scanlon, S. Papapetropoulos: "Statistical analysis and mapping of the Unified Parkinson’s Disease Rating Scale to Hoehn and Yahr staging", Parkinsonism and Related Disorders, Vol. 18 (5), pp. 697-699, 2012 [link] PDF
  6. P.G. Foukas, A. Zourla, S. Tsiodras, A. Tsanas, K. Leventakos, E. Chranioti, A. Spathis, C. Meristoudis, C. Chrelias, D. Kassanos, G. Petrikkos, P. Karakitsos, I. G. Panayiotides: "B-lymphocyte, macrophage, and mast cell density in the stroma underlying HPV-related cervical squamous epithelial lesions and their relationship to disease severity: an immunohistochemical study", Journal of Clinical and Experimental Pathology 2:105, 2012 [link] PDF
  7. A. Tsanas, A. Xifara: "Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools", Energy and Buildings, Vol. 49, pp. 560-567, 2012 [link] PDF, see also the Electronic Supplementary Material (The paper was highlighted as a “key scientific article” in Renewable Energy and global innovations)
  8. M. Kefala, S.G. Papageorgiou, C.K. Kontos, P. Economopoulou, A. Tsanas, V. Pappa, I.G. Panayiotides, V.G. Gorgoulis, E. Patsouris, P.G. Foukas: “Increased expression of phosphorylated NBS1, a key molecule of the DNA damage response machinery, is an adverse prognostic factor in patients with de novo myelodysplastic syndromes”, Leukemia Research, Vol. 37, pp. 1576-1582, 2013 [link], doi:10.1016/j.leukres.2013.08.018
  9. R. Kapal, A. Mehndiratta, P. Anandaraj, A. Tsanas: “Current impact, future prospects, and implications of mobile healthcare in India”, Central Asian Journal for Global Health, Vol.3 (1), 2014 [link] Open access
  10. A. Tsanas, M.A. Little, C. Fox, L.O. Ramig: “Objective automatic assessment of rehabilitative speech treatment in Parkinson’s disease”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 22(1), pp. 181-190, 2014 [link] PDF
  11. A. Tsanas, M. Zañartu, M.A. Little, C. Fox, L.O. Ramig, G.D. Clifford: “Robust fundamental frequency estimation in sustained vowels: detailed algorithmic comparisons and information fusion with adaptive Kalman filtering”, Journal of the Acoustical Society of America, Vol. 135, pp. 2885-2901, 2014 [link] PDF Open access
  12. A. Tsanas, G.D. Clifford: “Stage-independent, single lead EEG sleep spindle detection using the continuous wavelet transform and local weighted smoothing”, Frontiers in Human Neuroscience, Vol. 9:181, 2015 [link] PDF Open access
  13. B. Sheaves, K. Porcheret, A. Tsanas, C. Espie, R. Foster, D. Freeman, P.J. Harrison, K. Wulff, G.M. Goodwin: “Insomnia, nightmares, and chronotype as markers of risk for severe mental illness: results from a student population”, Sleep, Vol. 39(1), pp. 173-181, 2016 [link] PDF
  14. E. Naydenova, A. Tsanas, S. Howie, C. Casals-Pascual, M. De Vos: “The power of data mining in diagnosis of childhood pneumonia”, Journal of the Royal Society Interface 13:20160266, 2016 [link] PDF Open access (Selected media coverage for this work appears here, and here.)
  15. A. Tsanas, K.E.A. Saunders, A.C. Bilderbeck, N. Palmius, M. Osipov, G.D. Clifford, G.M. Goodwin, M. De Vos: “Daily longitudinal self-monitoring of mood variability in bipolar disorder and borderline personality disorder”, Journal of Affective Disorders, Vol. 205, pp. 225-233, 2016 [link] PDF, see also the Electronic Supplementary Material Open access
  16. N. Palmius, A. Tsanas, K.E.A. Saunders, A.C. Bilderbeck, J.R. Geddes, G.M. Goodwin, M. De Vos: “Detecting bipolar depression from geographic location data”, IEEE Transactions on Biomedical Engineering,  Vol. 64, No. 8, pp. 1761-1771, 2017 [link] PDF Open access
  17. E. San Segundo, A. Tsanas, P. Gomez-Vilda: “Euclidean distances as measures of speaker dissimilarity including identical twin pairs: a forensic investigation using source and filter voice characteristics,” Forensic Science International, Vol. 270, pp. 25-38, 2017 [link] PDF Open access
  18. A. Tsanas, K.E.A. Saunders, A.C. Bilderbeck, N. Palmius, G.M. Goodwin, M. De Vos: Clinical insight into latent variables of psychiatric questionnaires for mood symptom self-assessment, JMIR Mental Health Vol. 4, No. 2, pp. e15, 2017 [link] PDF Open access

 

Book chapters

  1. A. Tsanas, M.A. Little, P.E. McSharry: "A methodology for the analysis of medical data", Handbook of Systems and Complexity in Health, Eds. J.P. Sturmberg, and C.M. Martin, Springer, pp. 113-125 (chapter 7), 2013 [link] PDF
  2. P. Gómez-Vilda, A. Álvarez-Marquina, A. Tsanas, C.A. Lázaro-Carrascosa, V. Rodellar-Biarge, V. Nieto-Lluis, R. Martínez-Olalla: “Phonation biomechanics in quantifying Parkinson's disease symptom severity”, Recent Advances in Nonlinear Speech Processing, Vol. 48 of the series Smart Innovation, Systems and Technologies, Springer, pp. 93-102, 2016 [link]

 

Conference papers

  1. V. Vartela, A. Tsanas, D. Tsiapras, J.Y. Goulermas, V. Voudris: "Stress test: the application of mathematical models in daily clinical practice", 30th Panhellenic Cardiological Congress, Hellenic Cardiological Society, Athens, Greece, 29-31 October 2009 (in Greek)

  2. A. Tsanas, M.A. Little, P.E. McSharry, L.O. Ramig: "Enhanced classical dysphonia measures and sparse regression for telemonitoring of Parkinson's disease progression", IEEE Signal Processing Society, International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 594-597, Dallas, Texas, US, 14-19 March 2010 [link] PDF
  3. A. Tsanas, M.A. Little, P.E. McSharry, L.O. Ramig: "New nonlinear markers and insights into speech signal degradation for effective tracking of Parkinson’s disease symptom severity", International Symposium on Nonlinear Theory and its Applications (NOLTA), pp. 457-460, Krakow, Poland, 5-8 September 2010 (invited) PDF (won the student paper award)
  4. V. Vartela, A. Tsanas, D. Tsiapras, P. Sfirakis, V. Voudris: "A new mathematical approach investigating patient specific factors for the determination of clinically useful markers of cardiovascular status", 5th International Meeting of the Onassis Cardiac Surgery Center: current trends in cardiac surgery and cardiology, Athens, Greece, 16-18 September 2010 [link] PDF
  5. A. Tsanas, M.A. Little, P.E. McSharry, L.O. Ramig: "Robust parsimonious selection of dysphonia measures for telemonitoring of Parkinson's disease symptom severity", 7th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA), pp. 169-172, Florence, Italy, 25-27 August 2011 (invited) [link] PDF
  6. A. Johnson, N. Dunkley, L. Mayaud, A. Tsanas, A. Kramer, G. Clifford, "Patient‐specific predictions in the ICU using a Bayesian ensemble", Computing in Cardiology, pp. 249-252, Krakow, Poland, 9-12 September 2012 [link] PDF (Winning entry of the CinC2012 competition)
  7. A. Tsanas, M.A. Little, C. Fox, L.O. Ramig: “Automatic grouping of acceptable or unacceptable vocalizations in people with Parkinson disease”, 17th International congress of Parkinson’s disease and movement disorders, Sydney, Australia, 16-20 June 2013 (the abstract appeared in a supplementary issue of Movement Disorders, Vol. 28, S125-S125, 2013) [link]
  8. A. Tsanas, P. Gómez-Vilda: “Novel robust decision support tool assisting early diagnosis of pathological voices using acoustic analysis of sustained vowels”, Multidisciplinary Conference of Users of Voice, Speech and Singing (JVHC 13), pp. 3-12, Las Palmas de Gran Canaria, 27-28 June 2013 [link] PDF
  9. A. Tsanas: “Acoustic analysis toolkit for biomedical speech signal processing: concepts and algorithms”, 8th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA), pp. 37-40, Florence, Italy, 16-18 December 2013 (invited) [link] PDF (won the young scientist award)
  10. N. Palmius, M. Osipov, A. Bilderbeck, G. Goodwin, K. Saunders, A. Tsanas, G.D. Clifford: “A multi-sensor monitoring system for objective mental health management in resource constrained environments”, IET Appropriate Healthcare Technologies for low resource settings, London, UK, September 17-18 September 2014 [link] PDF
  11. A. Tsanas, G.D. Clifford, V. Vartela, P. Sfirakis: “Quantitative insights into the closed loop cardiovascular system using an electrical lumped element model”, Computing in Cardiology, pp. 509-512, Boston, US, 7-10 September 2014 [link] PDF
  12. P. Gómez-Vilda, A. Álvarez-Marquina, A. Tsanas, C.A. Lázaro-Carrascosa, V. Rodellar-Biarge, V. Nieto-Lluis, R. Martínez-Olalla, “Phonation biomechanics in quantifying Parkinson's disease symptom severity”, International Conference on Nonlinear Speech Processing (NOLISP 2015), Vietri Sul Mare, Italy, 18-20 May 2015 [link] PDF
  13. A.C. Bilderbeck, K.E.A. Saunders, G.D. Clifford, A. Tsanas, M. Osipov, P.J. Harrison, C.J. Harmer, A.C. Nobre, J. Geddes, G.M. Goodwin: “Daily and weekly mood ratings: relative contributions to the differentiation of bipolar disorder and borderline personality disorder”, 17th annual conference of the International society for bipolar disorders (ISBD 2015), Toronto, Canada, 3-6 June 2015
  14. E. Naydenova, A. Tsanas, C. Casals-Pascual, M. de Vos, S. Howie: “Smart diagnostic algorithms for automated detection of childhood pneumonia in resource-constrained settings”, IEEE Global Humanitarian Technology Conference (GHTC), pp. 377-384, Seattle, Washington, USA, 8-11 October 2015 [link] PDF Open access Elina’s presentation on Youtube
  15. S. Arora, A. Tsanas: “Discrimination of Parkinson's disease participants from healthy controls using telephone-quality voice recordings”, 20th International Congress of Parkinson’s Disease and Movement Disorders, Berlin, Germany, 19-23 June 2016 [link]
  16. K.E.A. Saunders, A.C. Bilderbeck, A. Tsanas, P.J. Harrison, C.J. Harmer, A.C. Nobre, J. Geddes, G.M. Goodwin: Stable instability: characterising the nature and degree of mood instability in bipolar disorder and borderline personality disorder, 18th Annual Conference of the International Society for Bipolar Disorders & 8th Biennial Conference of the International Society for Affective Disorders, Amsterdam, Netherlands, 13-16 July 2016
  17. N. Cooray, M. De Vos, A. Tsanas, “REM sleep behaviour disorder diagnostic tools – automatic REM detection”, MEIbioeng, Oxford, UK, 5-6 September 2016
  18. A. Tsanas, E. San Segundo, P. Gomez-Vilda: Exploring pause fillers in conversational speech for forensic phonetics: findings in a Spanish cohort including twins, 8th International Conference on Pattern Recognition Systems (ICPRS-17), Madrid, Spain, 11-13 July 2017 [link] PDF (in press)

 

This is a collection of datasets I have used in my research and which are made freely available. Please cite the relevant papers if you use these datasets in your research. The datasets have also been deposited in the standard UCI Machine Learning Repository.

 

Parkinson’s telemonitoring

[MATLAB]          [Excel]          UCI

This study looked into the problem of mapping dysphonia measures (speech signal characteristics) to a standard clinical metric of Parkinson’s disease symptom severity. The dataset comprises 5875 samples and 16 features to predict a real valued response (regression problem). It can also be used as a multi-class classification problem if the response is rounded to the nearest integer. More details can be found in my IEEE Transactions on Biomedical Engineering 2010 paper. Please include the following citation if you use it in your work:

======================================================================================================================================================================

Energy efficiency

[MATLAB]          [Excel]          UCI

This study looked into the problem of assessing heating load and cooling load (that is, energy efficiency) as a function of some building parameters. The dataset comprises 768 samples and 8 features to predict two real valued responses (regression problem). It can also be used as a multi-class classification problem if the response is rounded to the nearest integer. More details can be found in my Energy and Buildings 2012 paper. See also this Supplementary Material with additional information. Please include the following citation if you use it in your work:

======================================================================================================================================================================

LSVT Voice rehabilitation

[MATLAB]          [Excel]          UCI

This study uses 309 speech signal processing algorithms to characterize 126 signals from 14 individuals collected during voice rehabilitation. The aim is to replicate the experts’ assessment denoting whether these voice signals are considered “acceptable” or “unacceptable” (binary classification problem). More details can be found in my IEEE Transactions on Neural Systems and Rehabilitation Engineering 2014 paper. Please include the following citation if you use it in your work:

======================================================================================================================================================================

Sustained vowels /a/ with F0 ground truth

[Zipped data]

The accurate estimation of the fundamental frequency (F0) is a well-known challenging problem in the speech signal processing research community. Unfortunately, it is difficult to obtain objective ground truth values with contemporary approaches which rely on EGGs. Here, we used a sophisticated, state of the art physiological model of voice production to construct sustained /a/ vowels, where the exact ground truth of F0 values is known. We benchmarked 10 established F0 estimation algorithms, and proposed a novel fusion approach to further improve F0 estimates. We would like to encourage researchers to use this database when evaluating F0 estimation algorithms in order to benchmark results in this application. More details can be found in my IEEE Transactions on Neural Systems and Rehabilitation Engineering 2014 paper. (Note that here I am providing 130 *.wav files, and the ground truth values are provided in an Excel spreadsheet). Please include the following citation if you use it in your work: