Analysis and evaluation of handwriting in patients with Parkinson's disease using kinematic, geometrical, and non-linear features.

BACKGROUND AND OBJECTIVES: Parkinson's disease is a neurological disorder that affects the motor system producing lack of coordination, resting tremor, and rigidity. Impairments in handwriting are among the main symptoms of the disease. Handwriting analysis can help in supporting the diagnosis and in monitoring the progress of the disease. This paper aims to evaluate the importance of different groups of features to model handwriting deficits that appear due to Parkinson's disease; and how those features are able to discriminate between Parkinson's disease patients and healthy subjects. METHODS: Features based on kinematic, geometrical and non-linear dynamics analyses were evaluated to classify Parkinson's disease and healthy subjects. Classifiers based on K-nearest neighbors, support vector machines, and random forest were considered. RESULTS: Accuracies of up to 93.1% were obtained in the classification of patients and healthy control subjects. A relevance analysis of the features indicated that those related to speed, acceleration, and pressure are the most discriminant. The automatic classification of patients in different stages of the disease shows κ indexes between 0.36 and 0.44. Accuracies of up to 83.3% were obtained in a different dataset used only for validation purposes. CONCLUSIONS: The results confirmed the negative impact of aging in the classification process when we considered different groups of healthy subjects. In addition, the results reported with the separate validation set comprise a step towards the development of automated tools to support the diagnosis process in clinical practice.

Study of the Automatic Detection of Parkison's Disease Based on Speaker Recognition Technologies and Allophonic Distillation.

The use of new tools to detect Parkinson's Disease (PD) from speech articulatory movements can have a considerable impact in the diagnosis of patients. In this study, a novel approach involving speaker recognition techniques with allophonic distillation is proposed and tested separately in four parkinsonian speech databases (205 patients and 186 controls in total). This new scheme provides values between 72% and 94% of accuracy in the automatic detection of PD, depending on the database, and improvements up to 9% respect to baseline techniques. Results not only point towards the importance of the segmentation of the speech for the differentiation of parkinsonian and control speakers but confirm previous findings about the relevance of plosives and fricatives in the detection of parkinsonian dysarthria.

Towards an automatic evaluation of the dysarthria level of patients with Parkinson's disease.

BACKGROUND: Parkinson's disease (PD) is a neurological disorder that produces motor and non-motor impairments. The evaluation of motor symptoms is currently performed following the third section of the Movement Disorder Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS-III); however, only one item of that scale is related to speech impairments. It is necessary to develop a specific scale such that considers those aspects related to speech impairments of the patients. AIMS: (i) To introduce and evaluate the suitability of a modified version of the Frenchay Dysarthria Assessment (m-FDA) scale to quantify the dysarthria level of PD patients; (ii) to objectively model dysarthric speech signals considering four speech dimensions; (iii) to develop a methodology, based on speech processing and machine learning methods, to automatically quantify/predict the dysarthria level of patients with PD. METHODS: The speech recordings are modeled using features extracted from several dimensions of speech: phonation, articulation, prosody, and intelligibility. The dysarthria level is quantified using linear and non-linear regression models. Speaker models based on i-vectors are also explored. RESULTS AND CONCLUSIONS: The m-FDA scale was introduced to assess the dysarthria level of patients with PD. Articulation features extracted from continuous speech signals to create i-vectors were the most accurate to quantify the dysarthria level, with correlations of up to 0.69 between the predicted m-FDA scores and those assigned by the phoniatricians. When the dysarthria levels were estimated considering dedicated speech exercises such as rapid repetition of syllables (DDKs) and read texts, the correlations were 0.64 and 0.57, respectively. In addition, the combination of several feature sets and speech tasks improved the results, which validates the hypothesis about the contribution of information from different tasks and feature sets when assessing dysarthric speech signals. The speaker models seem to be promising to perform individual modeling for monitoring the dysarthria level of PD patients. The proposed approach may help clinicians to make more accurate and timely decisions about the evaluation and therapy associated to the dysarthria level of patients. The proposed approach is a great step towards unobtrusive/ecological evaluations of patients with dysarthric speech without the need of attending medical appointments.

Automatic detection of Parkinson's disease in running speech spoken in three different languages.

The aim of this study is the analysis of continuous speech signals of people with Parkinson's disease (PD) considering recordings in different languages (Spanish, German, and Czech). A method for the characterization of the speech signals, based on the automatic segmentation of utterances into voiced and unvoiced frames, is addressed here. The energy content of the unvoiced sounds is modeled using 12 Mel-frequency cepstral coefficients and 25 bands scaled according to the Bark scale. Four speech tasks comprising isolated words, rapid repetition of the syllables /pa/-/ta/-/ka/, sentences, and read texts are evaluated. The method proves to be more accurate than classical approaches in the automatic classification of speech of people with PD and healthy controls. The accuracies range from 85% to 99% depending on the language and the speech task. Cross-language experiments are also performed confirming the robustness and generalization capability of the method, with accuracies ranging from 60% to 99%. This work comprises a step forward for the development of computer aided tools for the automatic assessment of dysarthric speech signals in multiple languages.

Childhood exposure to ambient polycyclic aromatic hydrocarbons is linked to epigenetic modifications and impaired systemic immunity in T cells.

BACKGROUND: Evidence suggests that exposure to polycyclic aromatic hydrocarbons (PAHs) increases atopy; it is unclear how PAH exposure is linked to increased severity of atopic diseases. OBJECTIVE: We hypothesized that ambient PAH exposure is linked to impairment of immunity in atopic children (defined as children with asthma and/or allergic rhinitis) from Fresno, California, an area with elevated ambient PAHs. METHODS: We recruited 256 subjects from Fresno, CA. Ambient PAH concentrations (ng/m(3) ) were measured using a spatial-temporal regression model over multiple time periods. Asthma diagnosis was determined by current NHLBI criteria. Phenotyping and functional immune measurements were performed from isolated cells. For epigenetic measurements, DNA was isolated and pyrosequenced. RESULTS: We show that higher average PAH exposure was significantly associated with impaired Treg function and increased methylation in the forkhead box protein 3 (FOXP3) locus (P < 0.05), conditional on atopic status. These epigenetic modifications were significantly linked to differential protein expression of FOXP3 (P < 0.001). Methylation was associated with cellular functional changes, specifically Treg dysfunction, and an increase in total plasma IgE levels. Protein expression of IL-10 decreased and IFN-γ increased as the extent of PAH exposure increased. The strength of the associations generally increased as the time window for average PAH exposure increased from 24 hr to 1 year, suggesting more of a chronic response. Significant associations with chronic PAH exposure and immune outcomes were also observed in subjects with allergic rhinitis. CONCLUSIONS AND CLINICAL RELEVANCE: Collectively, these results demonstrate that increased ambient PAH exposure is associated with impaired systemic immunity and epigenetic modifications in a key locus involved in atopy: FOXP3, with a higher impact on atopic children. The results suggest that increased atopic clinical symptoms in children could be linked to increased PAH exposure in air pollution.

Factors influencing relative speech intelligibility in patients with oral squamous cell carcinoma: a prospective study using automatic, computer-based speech analysis.

Oral squamous cell carcinoma (OSCC) and its treatment impair speech intelligibility by alteration of the vocal tract. The aim of this study was to identify the factors of oral cancer treatment that influence speech intelligibility by means of an automatic, standardized speech-recognition system. The study group comprised 71 patients (mean age 59.89, range 35-82 years) with OSCC ranging from stage T1 to T4 (TNM staging). Tumours were located on the tongue (n=23), lower alveolar crest (n=27), and floor of the mouth (n=21). Reconstruction was conducted through local tissue plasty or microvascular transplants. Adjuvant radiotherapy was performed in 49 patients. Speech intelligibility was evaluated before, and at 3, 6, and 12 months after tumour resection, and compared to that of a healthy control group (n=40). Postoperatively, significant influences on speech intelligibility were tumour localization (P=0.010) and resection volume (P=0.019). Additionally, adjuvant radiotherapy (P=0.049) influenced intelligibility at 3 months after surgery. At 6 months after surgery, influences were resection volume (P=0.028) and adjuvant radiotherapy (P=0.034). The influence of tumour localization (P=0.001) and adjuvant radiotherapy (P=0.022) persisted after 12 months. Tumour localization, resection volume, and radiotherapy are crucial factors for speech intelligibility. Radiotherapy significantly impaired word recognition rate (WR) values with a progression of the impairment for up to 12 months after surgery.

[Perceptual and automatic voice and speech analysis of chronic laryngitis and T1 vocal cord cancer]. / Perzeptive und maschinelle Stimm- und Sprechanalyse bei chronischer Laryngitis und T1-Stimmlippenkarzinom.

BACKGROUND: Patients with chronic laryngitis and T1 vocal cord cancer were compared using perceptual and text-based objective voice and speech analyses in order to determine which group is more affected in its ability to communicate and whether a distinction between the two pathologies is possible. PATIENTS AND METHODS: In all, 13 patients with histologically proven chronic laryngitis and 13 patients with T1 vocal cord cancer were compared perceptually by five speech therapists on the basis of seven criteria and objectively by a speech recognition system and prosodic analysis. RESULTS: Both, the data of the five speech therapists and the results of the automatic analysis revealed no significant differences between the two patient groups. CONCLUSION: A distinction between chronic laryngitis and T1 vocal cord carcinoma by mere voice and speech analysis is not possible, because the patient groups do not show significant differences in their voice quality.

Automatic, computer-based speech assessment on edentulous patients with and without complete dentures - preliminary results.

Dental rehabilitation of edentulous patients with complete dentures includes not only aesthetics and mastication of food, but also speech quality. It was the aim of this study to introduce and validate a computer-based speech recognition system (ASR) for automatic speech assessment in edentulous patients after dental rehabilitation with complete dentures. To examine the impact of dentures on speech production, the speech outcome of edentulous patients with and without complete dentures was compared. Twenty-eight patients reading a standardized text were recorded twice - with and without their complete dentures in situ. A control group of 40 healthy subjects with natural dentition was recorded under the same conditions. Speech quality was evaluated by means of a polyphone-based ASR according to the percentage of the word accuracy (WA). Speech acceptability assessment by expert listeners and the automatic rating of the WA by the ASR showed a high correlation (corr = 0.71). Word accuracy was significantly reduced in edentulous speakers (55.42 +/- 13.1) compared to the control group's WA (69.79 +/- 10.6). On the other hand, wearing complete dentures significantly increased the WA of the edentulous patients (60.00 +/- 15.6). Speech production quality is significantly reduced after complete loss of teeth. Reconstitution of speech production quality is an important part of dental rehabilitation and can be improved for edentulous patients by means of complete dentures. The ASR has proven to be a useful and easily applicable tool for automatic speech assessment in a standardized way.

[Intelligibility of children with bilateral and unilateral cleft lip and palate]. / Sprachverständlichkeit von Kindern mit bilateralen und unilateralen Lippen-Kiefer-Gaumen-Spalten.

OBJECTIVE: Data about the effect of unilateral or bilateral cleft lip and palate (CLP) on speech quality are inconsistent. In this study we firstly quantify the intelligibility of children with unilateral and bilateral CLP objectively by means of automatic speech recognition system (ASR). METHODS: Speech data of 72 German speaking children (8.7+/-3.0 years) with CLP thereof 17 children with bilateral CLP, 23 with CLP on the right side, and 32 on the left, were compared. A group of 159 children aged 9.1+/-2.9 years served as control group. To quantify intelligibility we calculated the word recognition rate (WR) as the percentage of correctly recognized words of a standardized speech test (PLAKSS). RESULTS: Between the 3 cleft groups, there was no significant difference in WR. Compared to the control group (WR mean 63.5%+/-12.1%), the patient group (WR mean 48.1%+/-16.3%) shows significant lower WR (p< 0.001). The WR rises with increasing age in the control group and in the patient groups with unilateral cleft significantly. This couldn't be observed in the children with bilateral CLP. In this group the males showed a significantly higher WR than the females. In the control group as in the patient groups with unilateral cleft there is no significant difference between girls and boys. CONCLUSIONS: Despite the greater extent of the malformation of children with a bilateral CLP, there is no significant difference to the children with only a unilateral cleft lip and palate.

[Automated postlaryngectomy telephone test]. / Automatisierung des Postlaryngektomie-Telefontests.

OBJECTIVE: In this study, an objective version of the postlaryngectomy telephone test (PLTT) for measuring speech intelligibility based on automatic speech recognition is presented. METHODS: Thirty-one patients with tracheoesophageal substitute voice (25 men and six women, 63.4+/-8.7 years) were evaluated by 11 naïve listeners. The automatic measurement of speech intelligibility was expressed by means of word accuracy and word recognition rates, or the percentage of correctly recognized words from a word sequence. These automatic measures were compared with the subjectively obtained PLTT values. RESULTS: The average PLTT intelligibility of the 11 naïve listeners was 47%; the automatically obtained word accuracy and word recognition rates were much lower (approximately 0% and 15%, respectively). The correlation between subjective and automatic evaluation, however, reached more than 0.9 in some of the examined cases. CONCLUSION: Automatic speech recognition provides an efficient, objective measure that is equivalent to the overall PLTT intelligibility value.

Automatic quantification of speech intelligibility of adults with oral squamous cell carcinoma.

OBJECTIVE: It has been the aim of the present study to introduce a novel automatic technique for the objective and quantitative assessment of speech intelligibility to the evaluation of postoperative outcome. PATIENTS AND METHODS: Forty-six patients with oral carcinomas, mean age 59.8 +/- 10.1 years, and an age-matched control group of 40 subjects without oral diseases. Recordings of a standard text read by the patients and the control group were analyzed by an automatic speech recognition system. RESULTS: For the patients, automatic speech recognition yielded word recognition rates between 8 and 82% (mean 49 +/- 19%), for the control group between 60 and 91% (76 +/- 7%). Automatic evaluation closely correlated with the experts' perceptual evaluation of intelligibility (r = -0.93; p < 0.01). The multi-rater kappa of the experts alone (0.55) differed only slightly from the multi-rater kappa of the experts and the speech recognition system (0.58). CONCLUSION: For adults with speech disorders, automatic speech recognition may serve as a valuable tool to assess global speech outcome after treatment of oral squamous cell carcinoma objectively and quantitatively for clinical and research purposes.

[Numeric quantification of intelligibility in schoolchildren with isolated and combined cleft palate]. / Numerische Quantifizierung der Verständlichkeit von Schulkindern mit isolierter und kombinierter Gaumenspalte.

OBJECTIVE: Even after adequate surgical and nonsurgical treatment, combined or isolated clefts often cause functional disorders, such as speech disorders. Speech disorders vary widely in extent and can take the form, for example, of specific features of articulation, with altered nasal emission and shifted articulation, leading to reduced speech intelligibility. So far it has not been possible to describe the relationship between cleft type and intelligibility except subjective, categorical evaluation. METHODS: Intelligibility of the speech as influenced by cleft palate in 58 children aged 9+/-2 was quantified objectively and numerically by means of automatic speech recognition technology in speech recordings for the PLAKSS test [test for psycholinguistic analysis of childhood speech impairments]. It was found that 33 children had a unilateral cleft lip and palate (CLP), 9, bilateral CLP, 10, isolated cleft palate, and 6, submucosal cleft palate. As a control group, 84 children aged 9+/-1 years and with physiological articulation were recruited from a mainstream school. Speech intelligibility is expressed as word accuracy, which means the percentage of correctly recognized words in a word sequence. RESULTS: Word accuracy levels in the control group were between 39% and 84% (mean 62%+/-10%), while the children with clefts achieved values between 0% and 73% (mean 42%+/-17%). There was no difference in intelligibility between children with isolated cleft palate and those with combined cleft type. Differences were, however, found between each group and the control group (p<0.01). CONCLUSION: Speech intelligibility of children with isolated cleft palate does not significantly differ from that of children with combined cleft type including the palate, as has been objectively quantified for the first time by objective methods. In the presence of speech disorders, the need for diagnosis and therapy is just as great in children with isolated cleft palate as in children with combined cleft types.

Interpolated markov chains for eukaryotic promoter recognition.

MOTIVATION: We describe a new content-based approach for the detection of promoter regions of eukaryotic protein encoding genes. Our system is based on three interpolated Markov chains (IMCs) of different order which are trained on coding, non-coding and promoter sequences. It was recently shown that the interpolation of Markov chains leads to stable parameters and improves on the results in microbial gene finding (Salzberg et al., Nucleic Acids Res., 26, 544-548, 1998). Here, we present new methods for an automated estimation of optimal interpolation parameters and show how the IMCs can be applied to detect promoters in contiguous DNA sequences. Our interpolation approach can also be employed to obtain a reliable scoring function for human coding DNA regions, and the trained models can easily be incorporated in the general framework for gene recognition systems. RESULTS: A 5-fold cross-validation evaluation of our IMC approach on a representative sequence set yielded a mean correlation coefficient of 0.84 (promoter versus coding sequences) and 0.53 (promoter versus non-coding sequences). Applied to the task of eukaryotic promoter region identification in genomic DNA sequences, our classifier identifies 50% of the promoter regions in the sequences used in the most recent review and comparison by Fickett and Hatzigeorgiou ( Genome Res., 7, 861-878, 1997), while having a false-positive rate of 1/849 bp.