Athanasios Tsanas

Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease

There has been considerable recent research into the connection between Parkinsons disease (PD) and speech impairment. Recently, a wide range of speech signal processing algorithms (dysphonia measures) aiming to predict PD symptom severity using speech signals have been introduced. In this paper, we test how accurately these novel algorithms can be used to discriminate PD subjects from healthy controls. In total, we compute 132 dysphonia measures from sustained vowels. Then, we select four parsimonious subsets of these dysphonia measures using four feature selection algorithms, and map these feature subsets to a binary classification response using two statistical classifiers: random forests and support vector machines. We use an existing database consisting of 263 samples from 43 subjects, and demonstrate that these new dysphonia measures can outperform state-of-the-art results, reaching almost 99% overall classification accuracy using only ten dysphonia features. We find that some of the recently proposed dysphonia measures complement existing algorithms in maximizing the ability of the classifiers to discriminate healthy controls from PD subjects. We see these results as an important step toward noninvasive diagnostic decision support in PD.

Insomnia, Nightmares, and Chronotype as Markers of Risk for Severe Mental Illness: Results from a Student Population.

STUDY OBJECTIVES To group participants according to markers of risk for severe mental illness based on subsyndromal symptoms reported in early adulthood and evaluate attributes of sleep across these risk categories. METHODS An online survey of sleep and psychiatric symptomatology (The Oxford Sleep Survey) was administered to students at one United Kingdom university. 1403 students (undergraduate and postgraduate) completed the survey. The median age was 21 (interquartile range = 20-23) and 55.60% were female. The cross-sectional data were used to cluster participants based on dimensional measures of psychiatric symptoms (hallucinations, paranoia, depression, anxiety, and (hypo)mania). High, medium, and low symptom groups were compared across sleep parameters: insomnia symptoms, nightmares, chronotype, and social jet lag. RESULTS Insomnia symptoms, nightmares frequency, and nightmare-related distress increased in a dose-response manner with higher reported subsyndromal psychiatric symptoms (low, medium, and high). The high-risk group exhibited a later chronotype (mid sleep point for free days) than the medium- or low-risk group. The majority of participants (71.7%) in the high-risk group screened positive for insomnia and the median nightmare frequency was two per 14 days (moderately severe pathology). CONCLUSIONS Insomnia, nightmares, and circadian phase delay are associated with increased subsyndromal psychiatric symptoms in young people. Each is a treatable sleep disorder and might be a target for early intervention to modify the subsequent progression of psychiatric disorder.

Robust fundamental frequency estimation in sustained vowels: Detailed algorithmic comparisons and information fusion with adaptive Kalman filtering

There has been consistent interest among speech signal processing researchers in the accurate estimation of the fundamental frequency (F(0)) of speech signals. This study examines ten F(0) estimation algorithms (some well-established and some proposed more recently) to determine which of these algorithms is, on average, better able to estimate F(0) in the sustained vowel /a/. Moreover, a robust method for adaptively weighting the estimates of individual F(0) estimation algorithms based on quality and performance measures is proposed, using an adaptive Kalman filter (KF) framework. The accuracy of the algorithms is validated using (a) a database of 117 synthetic realistic phonations obtained using a sophisticated physiological model of speech production and (b) a database of 65 recordings of human phonations where the glottal cycles are calculated from electroglottograph signals. On average, the sawtooth waveform inspired pitch estimator and the nearly defect-free algorithms provided the best individual F(0) estimates, and the proposed KF approach resulted in a ∼16% improvement in accuracy over the best single F(0) estimation algorithm. These findings may be useful in speech signal processing applications where sustained vowels are used to assess vocal quality, when very accurate F(0) estimation is required.

Daily longitudinal self-monitoring of mood variability in bipolar disorder and borderline personality disorder.

Background Traditionally, assessment of psychiatric symptoms has been relying on their retrospective report to a trained interviewer. The emergence of smartphones facilitates passive sensor-based monitoring and active real-time monitoring through time-stamped prompts; however there are few validated self-report measures designed for this purpose. Methods We introduce a novel, compact questionnaire, Mood Zoom (MZ), embedded in a customised smart-phone application. MZ asks participants to rate anxiety, elation, sadness, anger, irritability and energy on a 7-point Likert scale. For comparison, we used four standard clinical questionnaires administered to participants weekly to quantify mania (ASRM), depression (QIDS), anxiety (GAD-7), and quality of life (EQ-5D). We monitored 48 Bipolar Disorder (BD), 31 Borderline Personality Disorders (BPD) and 51 Healthy control (HC) participants to study longitudinal (median±iqr: 313±194 days) variation and differences of mood traits by exploring the data using diverse time-series tools. Results MZ correlated well (|R|>0.5,p<0.0001) with QIDS, GAD-7, and EQ-5D. We found statistically strong (|R|>0.3,p<0.0001) differences in variability in all questionnaires for the three cohorts. Compared to HC, BD and BPD participants exhibit different trends and variability, and on average had higher self-reported scores in mania, depression, and anxiety, and lower quality of life. In particular, analysis of MZ variability can differentiate BD and BPD which was not hitherto possible using the weekly questionnaires. Limitations All reported scores rely on self-assessment; there is a lack of ongoing clinical assessment by experts to validate the findings. Conclusions MZ could be used for efficient, long-term, effective daily monitoring of mood instability in clinical psychiatric practice.

The Windkessel model revisited: a qualitative analysis of the circulatory system.

In this paper, we derive a comprehensive computational model to estimate the arterial pressure and the cardiac output of humans, by refining and adapting the well-established equations of the Windkessel theory. The model inputs are based on patient specific factors such as age, sex, smoking and fitness habits as well as the use of specific drugs. The models outputs correlate very strongly with physiological observations, with a low error of approximately 5% for the arterial pressure.

Statistical analysis and mapping of the unified Parkinson’s Disease rating scale to Hoehn and Yahr staging

* Asterisk denotes corresponding author. Affiliations: 1 Systems Analysis, Modelling and Prediction (SAMP), Department of Engineering Science, University of Oxford, Oxford, UK 2 Oxford Centre for Industrial and Applied Mathematics (OCIAM), University of Oxford, Oxford, UK 3 Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA 4 Smith School of Enterprise and the Environment, University of Oxford, Oxford, UK 5 Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA 6 Sierra-Pacific Mental Illness Research, Education, and Clinical Center, VA Palo Alto Health Care System, Palo Alto, CA, USA 7 Department of Neurology, Miller School of Medicine, University of Miami, USA

A Methodology for the Analysis of Medical Data

Imagine a subject going to the clinic for a medical diagnosis, for example to assess the functionality of his cardiovascular system. The doctor requests a number of clinical tests (for example, stress test to obtain the electro-cardiogram (ECG) and Doppler ultrasound), takes into account a number of other factors (for example the demographics of the subject), and makes his final diagnosis using the current data and his prior knowledge. For his diagnosis, the doctor will usually compute somecharacteristicsof the original raw signal. For example, when the raw signal is the ECG, clinicians may want to use the mean heart rate or the heart rate variability (these characteristics may also be readily provided by medical software) because experience has taught them these characteristics are useful in diagnosis.

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.

The expression of activated forms of key proteins of the DNA damage response machinery (pNBS1, pATM and γH2AX) was assessed by means of immunohistochemistry in bone marrow biopsies of 74 patients with de novo myelodysplastic syndromes (MDS) and compared with 15 cases of de novo acute myeloid leukemia (AML) and 20 with reactive bone marrow histology. Expression levels were significantly increased in both MDS and AML, compared to controls, being higher in high-risk than in low-risk MDS. Increased pNBS1 and γH2AX expression possessed a significant negative prognostic impact for overall survival in MDS patients, whereas pNBS1 was an independent marker of poor prognosis.

Euclidean Distances as measures of speaker similarity including identical twin pairs: A forensic investigation using source and filter voice characteristics

Highlights • Assessment of speaker similarity combining source and filter voice characteristics.• Feature selection method to determine the most parsimonious feature subset.• Testing with very similar-sounding speakers, i.e. monozygotic twins (MZ).• Testing using high quality and telephone-filtered recordings.• Significant differences between same-speaker and different-speaker comparisons.

Variability in phase and amplitude of diurnal rhythms is related to variation of mood in bipolar and borderline personality disorder

Variable mood is an important feature of psychiatric disorders. However, its measurement and relationship to objective measureas of physiology and behaviour have rarely been studied. Smart-phones facilitate continuous personalized prospective monitoring of subjective experience and behavioural and physiological signals can be measured through wearable devices. Such passive data streams allow novel estimates of diurnal variability. Phase and amplitude of diurnal rhythms were quantified using new techniques that fitted sinusoids to heart rate (HR) and acceleration signals. We investigated mood and diurnal variation for four days in 20 outpatients with bipolar disorder (BD), 14 with borderline personality disorder (BPD) and 20 healthy controls (HC) using a smart-phone app, portable electrocardiogram (ECG), and actigraphy. Variability in negative affect, positive affect, and irritability was elevated in patient groups compared with HC. The study demonstrated convincing associations between variability in subjective mood and objective variability in diurnal physiology. For BPD there was a pattern of positive correlations between mood variability and variation in activity, sleep and HR. The findings suggest BPD is linked more than currently believed with a disorder of diurnal rhythm; in both BPD and BD reducing the variability of sleep phase may be a way to reduce variability of subjective mood.