Andrea Bandini

Automatic identification of dysprosody in idiopathic Parkinson's disease

Abstract Parkinsons disease (PD) involves impairments of voice and speech (hypokinetic dysarthria). Dysprosody is one of the most common features of PD speech that includes alterations of rhythm and velocity of articulation. The aim of this study is the evaluation of dysprosody patterns in Parkinsonian patients during a sentence repetition task by means of a fully automated tool. Twenty PD patients (14 male and 6 female) and 19 healthy controls (9 male and 10 female) were tested. Results show significant differences between the two groups as far as the time interval between each sentence repetition (Tinter), the percent of speech time with respect to sentence duration (D%) and the Net Speech Rate (NSR – defined as the number of syllables of the sentence divided by the effective speech time) are concerned. In particular, Tinter is larger in PD patients while D% is higher in the control group. These results show that PD patients may exhibit longer pauses between each sentence repetition and a lower percentage of “speech time” during a whole repetition period. Thus, the decrease of D% leads to an increase of NSR. Other acoustic parameters (noise and F0 variability) did not show any significant difference. This study confirms that speech in PD patients is characterized by short rushes followed by unorthodox pauses. These results may lead to the development of a system for the automatic acoustic analysis which could significantly reduce the processing time in particular during pre-processing, that to date is a time-consuming and operator-dependent step especially in case of recordings of long duration.

Application of Pattern Recognition Techniques to the Classification of Full-Term and Preterm Infant Cry

OBJECTIVES Scientific and clinical advances in perinatology and neonatology have enhanced the chances of survival of preterm and very low weight neonates. Infant cry analysis is a suitable noninvasive complementary tool to assess the neurologic state of infants particularly important in the case of preterm neonates. This article aims at exploiting differences between full-term and preterm infant cry with robust automatic acoustical analysis and data mining techniques. STUDY DESIGN Twenty-two acoustical parameters are estimated in more than 3000 cry units from cry recordings of 28 full-term and 10 preterm newborns. METHODS Feature extraction is performed through the BioVoice dedicated software tool, developed at the Biomedical Engineering Lab, University of Firenze, Italy. Classification and pattern recognition is based on genetic algorithms for the selection of the best attributes. Training is performed comparing four classifiers: Logistic Curve, Multilayer Perceptron, Support Vector Machine, and Random Forest and three different testing options: full training set, 10-fold cross-validation, and 66% split. RESULTS Results show that the best feature set is made up by 10 parameters capable to assess differences between preterm and full-term newborns with about 87% of accuracy. Best results are obtained with the Random Forest method (receiver operating characteristic area, 0.94). CONCLUSIONS These 10 cry features might convey important additional information to assist the clinical specialist in the diagnosis and follow-up of possible delays or disorders in the neurologic development due to premature birth in this extremely vulnerable population of patients. The proposed approach is a first step toward an automatic infant cry recognition system for fast and proper identification of risk in preterm babies.

Effect of local blood flow in thermal regulation in diabetic patient

The presence of dysautonomia in diabetic neuropathy is correlated with impairment of vasomotor activity that drives blood microcirculation. Microcirculation, in turn, plays an important role in thermoregulation. In this work, we investigate the changes between two different physiological conditions of diabetic patients, induced by FREMS application, in the control of skin temperature, using a minimally invasive experiment. Skin is warmed up to a fixed temperature (44 °C) for a few minutes, then the heat source is turned off, letting the skin recover its physiological temperature. Both temperature and local blood flow, the latter measured with laser Doppler, are monitored during the experiment. A simple model of the cooling phase is used to evaluate the time constants involved in the process. Results indicate that significant differences exist in the model parameters between the two conditions.

Analysis of facial expressions in parkinson's disease through video-based automatic methods

BACKGROUND The automatic analysis of facial expressions is an evolving field that finds several clinical applications. One of these applications is the study of facial bradykinesia in Parkinsons disease (PD), which is a major motor sign of this neurodegenerative illness. Facial bradykinesia consists in the reduction/loss of facial movements and emotional facial expressions called hypomimia. NEW METHOD In this work we propose an automatic method for studying facial expressions in PD patients relying on video-based METHODS: 17 Parkinsonian patients and 17 healthy control subjects were asked to show basic facial expressions, upon request of the clinician and after the imitation of a visual cue on a screen. Through an existing face tracker, the Euclidean distance of the facial model from a neutral baseline was computed in order to quantify the changes in facial expressivity during the tasks. Moreover, an automatic facial expressions recognition algorithm was trained in order to study how PD expressions differed from the standard expressions. RESULTS Results show that control subjects reported on average higher distances than PD patients along the tasks. COMPARISON WITH EXISTING METHODS This confirms that control subjects show larger movements during both posed and imitated facial expressions. Moreover, our results demonstrate that anger and disgust are the two most impaired expressions in PD patients. CONCLUSIONS Contactless video-based systems can be important techniques for analyzing facial expressions also in rehabilitation, in particular speech therapy, where patients could get a definite advantage from a real-time feedback about the proper facial expressions/movements to perform.

Markerless Analysis of Articulatory Movements in Patients With Parkinson's Disease.

OBJECTIVES A large percentage of patients with Parkinsons disease have hypokinetic dysarthria, exhibiting reduced peak velocities of jaw and lips during speech. This limitation implies a reduction of speech intelligibility for such patients. This work aims at testing a cost-effective markerless approach for assessing kinematic parameters of hypokinetic dysarthria. STUDY DESIGN Kinematic parameters of the lips are calculated during a syllable repetition task from 14 Parkinsonian patients and 14 age-matched control subjects. METHODS Combining color and depth frames provided by a depth sensor (Microsoft Kinect), we computed the three-dimensional coordinates of main facial points. The peak velocities and accelerations of the lower lip during a syllable repetition task are considered to compare the two groups. RESULTS Results show that Parkinsonian patients exhibit reduced peak velocities of the lower lip, both during the opening and the closing phase of the mouth. In addition, peak values of acceleration are reduced in Parkinsonian patients, although with significant differences only in the opening phase with respect to healthy control subjects. CONCLUSIONS The novel contribution of this work is the implementation of an entirely markerless technique capable to detect signs of hypokinetic dysarthria for the analysis of articulatory movements during speech. Although a large number of Parkinsonian patients have hypokinetic dysarthria, only a small percentage of them undergoes speech therapy to increase their articulatory movements. The system proposed here could be easily implemented in a home environment, thus, increasing the percentage of patients who can perform speech rehabilitation at home.

Modelling of Thermal Hyperemia in the Skin of Type 2 Diabetic Patients

The microcirculatory response to thermal stimulation involves both an axon reflex and NO-mediated activation. The analysis of the microcirculatory flow following thermal stimulation may therefore enhance the detection of any impairment of the small unmyelinated fibres that are involved in the axon reflex. The aim of this work is to establish a method of non-invasive measurement of small fibre impairment. The microcirculatory flow in response to local heating is measured by using a laser Doppler instrument, and mathematically modelled to extract a set of quantitative parameters. The results confirm that there is a significant difference in the parameters modelling the axon reflex between diabetic and control subjects, while no significant difference is found in the parameters modelling the NO-mediated activation.

Smartphones Offer New Opportunities in Clinical Voice Research

Smartphone technology provides new opportunities for recording standardized voice samples of patients and sending the files by e-mail to the voice laboratory. This drastically improves the collection of baseline data, as used in research on efficiency of voice treatments. However, the basic requirement is the suitability of smartphones for recording and digitizing pathologic voices (mainly characterized by period perturbations and noise) without significant distortion. In this experiment, two smartphones (a very inexpensive one and a high-level one) were tested and compared with direct microphone recordings in a soundproof room. The voice stimuli consisted in synthesized deviant voice samples (median of fundamental frequency: 120 and 200 Hz) with three levels of jitter and three levels of added noise. All voice samples were analyzed using PRAAT software. The results show high correlations between jitter, shimmer, and noise-to-harmonics ratio measured on the recordings via both smartphones, the microphone, and measured directly on the sound files from the synthesizer. Smartphones thus appear adequate for reliable recording and digitizing of pathologic voices.

AVIM—A contactless system for infant data acquisition and analysis: Software architecture and first results

Abstract Traditional techniques for the diagnosis of neurological disorders are recently complemented by contact-less methods that provide a semi-quantitative assessment of the patient status. In this framework, the assessment of infants behaviour based on the analysis of audio and video recordings is appealing thanks to its unobtrusiveness and to the affordable costs of the equipment. This paper presents the architecture of a system, named AVIM, conceived for supporting clinical diagnosis in newborns with contact-less techniques. Its most innovative aspect is the ability of merging in a single tool the management of medical records and reports, audio/video data acquisition, handling and analysis, editing and filling out customized tests. Moreover, unlike other commercial or open source software tools, AVIM allows adding markers and notes while recording audio and video signals and provides detailed reports with both perceptual scores and acoustical and kinematical parameters of clinical interest computed through dedicated innovative techniques. AVIM is therefore a unique and flexible system that could successfully support the clinician during the entire process from the acquisition of the signals to the results. In addition to providing an appreciable decrease in investigation time, costs and errors, AVIM could support the diagnosis integrating clinicians’ qualitative analysis, based on subjective skills, with objective measurements. To highlight its capabilities, AVIM is applied here to the management and analysis of personal and clinical data of newborns audio/video recorded in 5 time points from 10 days to the 24th week of age, according to a specific protocol. Patient data, results of customized tests, tables and plots are provided in a user-friendly environment.

Testing software tools for newborn cry analysis using synthetic signals

Abstract Contactless techniques are of increasing clinical interest as they can provide advantages in terms of comfort and safety of the patient with respect to sensor-based methods. Therefore, they are particularly well suited for vulnerable patients such as newborns. Specifically the acoustical analysis of the infant cry is a contactless approach to assist the clinical specialist in the detection of abnormalities in infants with possible neurological disorders. Along with the perceptual analysis, the automated analysis of infant cry is usually performed through software tools that however might not be devoted to this specific signal. The newborn cry is a signal extremely difficult to analyze with standard techniques due to its quasi-stationarity and to very high range of frequencies of interest. Therefore software tools should be specifically set and used with caution. To address this issue three methods are tested and compared, one freely available and other two specifically built using different approaches: autoregressive adaptive models and wavelets. The three methods are compared using synthetic signals coming from a synthesizer developed for the generation of basic melodic shapes of the newborn cry. Results point out strengths and weaknesses of each method, thus suggesting their most appropriate use according to the goals of the analysis.

Phonetic analysis during treatment with rapid maxillary expander

OBJECTIVES To investigate possible changes and/or device-related impairments in phonetic habits produced by rapid maxillary expansion (RME). MATERIALS AND METHODS Thirty-five patients scheduled for RME were divided into two groups: Group A (banded two-arm Hyrax) and Group B (banded four-arm Hyrax). Speech samples were collected at six time points, before, during and after RME removal. Acoustical analysis was performed using PRAAT and BioVoice analysis tools. Ten volunteers completed a questionnaire on the acceptability of patients speech. Maxillary dimensions and palatal volume were measured on dental casts before and after expansion using a digital gauge. RESULTS Voice analysis showed an increase in the peak frequency of fricative consonants (/s/,/ʃ/) after expansion, whereas there was no change of formant frequencies of palatal consonants (/ɲ/,/ʎ/). Vowel /i/ displayed a lowering of the first formant frequency, and an increase in the second and third formant frequencies. After bonding, Group B showed both a greater reduction in the peak frequency of fricatives and a greater increase in the formant frequencies of palatal consonants than Group A. CONCLUSION Rapid maxillary expansion causes a slight phonetic change in the acoustical parameters of both consonants and vowels. The two-arm Hyrax caused less speech impairment than the four-arm Hyrax during the treatment.