Artificial Intelligence-Based Voice Assessment of Patients with Parkinson's Disease Off and On Treatment: Machine vs. Deep-Learning Comparison.

Parkinson's Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

Voice Analysis with Machine Learning: One Step Closer to an Objective Diagnosis of Essential Tremor.

BACKGROUND: Patients with essential tremor have upper limb postural and action tremor often associated with voice tremor. The objective of this study was to objectively examine voice tremor and its response to symptomatic pharmacological treatment in patients with essential tremor using voice analysis consisting of power spectral analysis and machine learning. METHODS: We investigated 58 patients (24 men; mean age ± SD, 71.7 ± 9.2 years; range, 38-85 years) and 74 age- and sex-matched healthy subjects (20 men; mean age ± SD, 71.0 ± 12.4 years; range, 43-95 years). We recorded voice samples during sustained vowel emission using a high-definition audio recorder. Voice samples underwent sound signal analysis, including power spectral analysis and support vector machine classification. We compared voice recordings in patients with essential tremor who did and did not manifest clinically overt voice tremor and in patients who were and were not under the symptomatic effect of the best medical treatment. RESULTS: Power spectral analysis demonstrated a prominent oscillatory activity peak at 2-6 Hz in patients who manifested a clinically overt voice tremor. Voice analysis with support vector machine classifier objectively discriminated with high accuracy between controls and patients who did and did not manifest clinically overt voice tremor and between patients who were and were not under the symptomatic effect of the best medical treatment. CONCLUSIONS: In patients with essential tremor, voice tremor is characterized by abnormal oscillatory activity at 2-6 Hz. Voice analysis, including power spectral analysis and support vector machine classification, objectively detected voice tremor and its response to symptomatic pharmacological treatment in patients with essential tremor. © 2021 International Parkinson and Movement Disorder Society.

Machine-Learning Analysis of Voice Samples Recorded through Smartphones: The Combined Effect of Ageing and Gender.

BACKGROUND: Experimental studies using qualitative or quantitative analysis have demonstrated that the human voice progressively worsens with ageing. These studies, however, have mostly focused on specific voice features without examining their dynamic interaction. To examine the complexity of age-related changes in voice, more advanced techniques based on machine learning have been recently applied to voice recordings but only in a laboratory setting. We here recorded voice samples in a large sample of healthy subjects. To improve the ecological value of our analysis, we collected voice samples directly at home using smartphones. METHODS: 138 younger adults (65 males and 73 females, age range: 15-30) and 123 older adults (47 males and 76 females, age range: 40-85) produced a sustained emission of a vowel and a sentence. The recorded voice samples underwent a machine learning analysis through a support vector machine algorithm. RESULTS: The machine learning analysis of voice samples from both speech tasks discriminated between younger and older adults, and between males and females, with high statistical accuracy. CONCLUSIONS: By recording voice samples through smartphones in an ecological setting, we demonstrated the combined effect of age and gender on voice. Our machine learning analysis demonstrates the effect of ageing on voice.

Acoustic analysis in stuttering: a machine-learning study.

Background: Stuttering is a childhood-onset neurodevelopmental disorder affecting speech fluency. The diagnosis and clinical management of stuttering is currently based on perceptual examination and clinical scales. Standardized techniques for acoustic analysis have prompted promising results for the objective assessment of dysfluency in people with stuttering (PWS). Objective: We assessed objectively and automatically voice in stuttering, through artificial intelligence (i.e., the support vector machine - SVM classifier). We also investigated the age-related changes affecting voice in stutterers, and verified the relevance of specific speech tasks for the objective and automatic assessment of stuttering. Methods: Fifty-three PWS (20 children, 33 younger adults) and 71 age-/gender-matched controls (31 children, 40 younger adults) were recruited. Clinical data were assessed through clinical scales. The voluntary and sustained emission of a vowel and two sentences were recorded through smartphones. Audio samples were analyzed using a dedicated machine-learning algorithm, the SVM to compare PWS and controls, both children and younger adults. The receiver operating characteristic (ROC) curves were calculated for a description of the accuracy, for all comparisons. The likelihood ratio (LR), was calculated for each PWS during all speech tasks, for clinical-instrumental correlations, by using an artificial neural network (ANN). Results: Acoustic analysis based on machine-learning algorithm objectively and automatically discriminated between the overall cohort of PWS and controls with high accuracy (88%). Also, physiologic ageing crucially influenced stuttering as demonstrated by the high accuracy (92%) of machine-learning analysis when classifying children and younger adults PWS. The diagnostic accuracies achieved by machine-learning analysis were comparable for each speech task. The significant clinical-instrumental correlations between LRs and clinical scales supported the biological plausibility of our findings. Conclusion: Acoustic analysis based on artificial intelligence (SVM) represents a reliable tool for the objective and automatic recognition of stuttering and its relationship with physiologic ageing. The accuracy of the automatic classification is high and independent of the speech task. Machine-learning analysis would help clinicians in the objective diagnosis and clinical management of stuttering. The digital collection of audio samples here achieved through smartphones would promote the future application of the technique in a telemedicine context (home environment).

GIDL: a rule based expert system for GenBank Intelligent Data Loading into the Molecular Biodiversity Database.

BACKGROUND: In the scientific biodiversity community, it is increasingly perceived the need to build a bridge between molecular and traditional biodiversity studies. We believe that the information technology could have a preeminent role in integrating the information generated by these studies with the large amount of molecular data we can find in bioinformatics public databases. This work is primarily aimed at building a bioinformatic infrastructure for the integration of public and private biodiversity data through the development of GIDL, an Intelligent Data Loader coupled with the Molecular Biodiversity Database. The system presented here organizes in an ontological way and locally stores the sequence and annotation data contained in the GenBank primary database. METHODS: The GIDL architecture consists of a relational database and of an intelligent data loader software. The relational database schema is designed to manage biodiversity information (Molecular Biodiversity Database) and it is organized in four areas: MolecularData, Experiment, Collection and Taxonomy. The MolecularData area is inspired to an established standard in Generic Model Organism Databases, the Chado relational schema. The peculiarity of Chado, and also its strength, is the adoption of an ontological schema which makes use of the Sequence Ontology. The Intelligent Data Loader (IDL) component of GIDL is an Extract, Transform and Load software able to parse data, to discover hidden information in the GenBank entries and to populate the Molecular Biodiversity Database. The IDL is composed by three main modules: the Parser, able to parse GenBank flat files; the Reasoner, which automatically builds CLIPS facts mapping the biological knowledge expressed by the Sequence Ontology; the DBFiller, which translates the CLIPS facts into ordered SQL statements used to populate the database. In GIDL Semantic Web technologies have been adopted due to their advantages in data representation, integration and processing. RESULTS AND CONCLUSIONS: Entries coming from Virus (814,122), Plant (1,365,360) and Invertebrate (959,065) divisions of GenBank rel.180 have been loaded in the Molecular Biodiversity Database by GIDL. Our system, combining the Sequence Ontology and the Chado schema, allows a more powerful query expressiveness compared with the most commonly used sequence retrieval systems like Entrez or SRS.

Voice in Parkinson's Disease: A Machine Learning Study.

INTRODUCTION: Parkinson's disease (PD) is characterized by specific voice disorders collectively termed hypokinetic dysarthria. We here investigated voice changes by using machine learning algorithms, in a large cohort of patients with PD in different stages of the disease, OFF and ON therapy. METHODS: We investigated 115 patients affected by PD (mean age: 68.2 ± 9.2 years) and 108 age-matched healthy subjects (mean age: 60.2 ± 11.0 years). The PD cohort included 57 early-stage patients (Hoehn &Yahr ≤ 2) who never took L-Dopa for their disease at the time of the study, and 58 mid-advanced-stage patients (Hoehn &Yahr >2) who were chronically-treated with L-Dopa. We clinically evaluated voices using specific subitems of the Unified Parkinson's Disease Rating Scale and the Voice Handicap Index. Voice samples recorded through a high-definition audio recorder underwent machine learning analysis based on the support vector machine classifier. We also calculated the receiver operating characteristic curves to examine the diagnostic accuracy of the analysis and assessed possible clinical-instrumental correlations. RESULTS: Voice is abnormal in early-stage PD and as the disease progresses, voice increasingly degradres as demonstrated by high accuracy in the discrimination between healthy subjects and PD patients in the early-stage and mid-advanced-stage. Also, L-dopa therapy improves but not restore voice in PD as shown by high accuracy in the comparison between patients OFF and ON therapy. Finally, for the first time we achieved significant clinical-instrumental correlations by using a new score (LR value) calculated by machine learning. CONCLUSION: Voice is abnormal in early-stage PD, progressively degrades in mid-advanced-stage and can be improved but not restored by L-Dopa. Lastly, machine learning allows tracking disease severity and quantifying the symptomatic effect of L-Dopa on voice parameters with previously unreported high accuracy, thus representing a potential new biomarker of PD.

High- versus low-dose proton pump inhibitors after endoscopic hemostasis in patients with peptic ulcer bleeding: a multicentre, randomized study.

BACKGROUND: The most effective schedule of proton pump inhibitor (PPI) administration following endoscopic hemostasis of bleeding ulcers remains uncertain. METHODS: Patients with actively bleeding ulcers and those with nonbleeding visible vessel or adherent clot were treated with epinephrine injection and/or thermal coagulation, and randomized to receive intravenous PPIs according to an intensive regimen (80 mg bolus followed by 8 mg/h as continuous infusion for 72 h) or a standard regimen (40 mg bolus daily followed by saline infusion for 72 h). After the infusion, all patients were given 20 mg PPI twice daily orally. The primary end point was the in-hospital rebleeding rate, as ascertained at the repeat endoscopy. RESULTS: Bleeding recurred in 28 of 238 patients (11.8%) receiving the intensive regimen, and in 19 of 236 (8.1%) patients receiving the standard regimen (P= 0.18). Most rebleeding episodes occurred during the initial 72-h infusion: 18 (7.6%) and 19 events (8.1%) in the intensive and standard groups, respectively (P= 0.32). Mean units of blood transfused were 1.7 +/- 2.1 in the intensive and 1.5 +/- 2.1 in the standard regimen group (P= 0.34). The duration of hospital stay was <5 days for 88 (37.0%) and 111 patients (47.0%) in the intensive and standard groups (P= 0.03). There were fewer surgical interventions in the standard versus intensive regimen (1 vs 3). Five patients in each treatment group died. CONCLUSIONS: Following endoscopic hemostasis of bleeding ulcers, standard-dose PPIs infusion was as effective as a high-dose regimen in reducing the risk of recurrent bleeding. (ClinicalTrials.gov number, NCT00374101).

Management of patients with nonvariceal upper gastrointestinal hemorrhage before and after the adoption of the Rockall score, in the Italian Gastroenterology Units.

OBJECTIVES: Nonvariceal upper gastrointestinal hemorrhage is a frequent reason for ordinary hospital admission. In Italy the use of prognostic scores to stratify the risk has not been adequately validated: the impact on clinical management of a rating system like the Rockall score remains to be established. RING is a 'register' that has been collecting hospital discharge files from hospital gastroenterology units, giving a broad picture of the patients admitted for this pathology. METHODS: We analyzed the hospital discharge files collected between 2001 and 2005 from 12 gastroenterology units, which issued more than 26,000 hospital discharge files for ordinary hospital admission and have been using the Rockall score for defining nonvariceal upper gastrointestinal hemorrhage since 2003. RESULTS: There were 2832 hospital discharge files with a main diagnosis of nonvariceal upper gastrointestinal hemorrhage: 1335 'before' the Rockall score was introduced, 1497 'after' the introduction. Patients' mean age was 67.7+/-16.7 years, with a male/female ratio of 1.7 and no significant changes over the years. There were no differences in the distribution of diagnoses in nonvariceal upper gastrointestinal hemorrhage patients before/after the introduction of the Rockall score, though the mean hospital stay became shorter (7.1+/-5.0 vs. 6.3+/-4.5 days), and mortality declined (2.8 vs. 2.3%), in parallel with the caselist as a whole. For 1102 ordinary hospital admission Rockall score was calculated. Diagnoses were more accurate: significantly fewer undefined causes and an increase in peptic ulcer. The mean Rockall score was 4.6+/-2.2: 17.8% low (0-2), 48.7% intermediate (3-5), and 33.5% high (>or=6). Mean hospital stay, rebleeding, and mortality were correlated with the severity of the score. CONCLUSION: The Rockall score enables the clinician to formulate a more precise diagnosis and substantially shortens the time in hospital, especially for patients at low-risk of rebleeding and death, so more resources can be dedicated to critically ill patients.

Results of endoscopic retrograde cholangiopancreatography in the treatment of biliary tract complications after orthotopic liver transplantation: our experience.

BACKGROUND/AIMS: Biliary tract complications are a common cause of morbidity and mortality after orthotopic liver transplantation. We report our experience in the use of ERCP in the treatment of post liver transplantation biliary complications. METHODOLOGY: Retrospectively we evaluated 34 patients who had undergone ERCP out of 460 who received a liver transplantation between January 1999 and December 2004. Eighteen patients presented biliary strictures, anastomotic in 12 cases and hilar in 6 cases; seven patients presented a biliary fistula and fifteen presented biliary stones in 8 cases associated to stricture and in 1 case to a fistula. Finally three patients underwent ERCP do to jaundice. The 18 patients with biliary strictures underwent sphincterotomy, dilation and stenting; the seven cases with fistulas were treated with a plastic biliary stent without sphincterotomy and the patients with biliary stones underwent sphincterotomy and endoscopic toilette of the common bile duct. RESULTS: An ERCP success rate of 97.7% was achieved without any significant complications. We obtained the resolution of all the biliary anastomotic strictures; resolution of hilar strictures was obtained in 66.6%. Biliary leak healed in 85.7% of patients. Complete endoscopic toilette was achieved in all the patients with biliary stones. CONCLUSIONS: In our experience ERCP has proved to be safe and effective in the treatment of post liver transplant biliary complications.

Boceprevir or telaprevir in hepatitis C virus chronic infection: The Italian real life experience.

AIM: To check the safety and efficacy of boceprevir/telaprevir with peginterferon/ribavirin for hepatitis C virus (HCV) genotype 1 in the real-world settings. METHODS: This study was a non-randomized, observational, prospective, multicenter. This study involved 47 centers in Italy. A database was prepared for the homogenous collection of the data, was used by all of the centers for data collection, and was updated continuously. All of the patients enrolled in this study were older than 18 years of age and were diagnosed with chronic infection due to HCV genotype 1. The HCV RNA testing was performed using COBAS-TaqMan2.0 (Roche, LLQ 25 IU/mL). RESULTS: All consecutively treated patients were included. Forty-seven centers enrolled 834 patients as follows: Male 64%; median age 57 (range 18-78), of whom 18.3% were over 65; mean body mass index 25.6 (range 16-39); genotype 1b (79.4%); diagnosis of cirrhosis (38.2%); and fibrosis F3/4 (71.2%). The following drugs were used: Telaprevir (66.2%) and PEG-IFN-alpha2a (67.6%). Patients were naïve (24.4%), relapsers (30.5%), partial responders (14.8%) and null responders (30.3%). Overall, adverse events (AEs) occurred in 617 patients (73.9%) during the treatment. Anemia was the most frequent AE (52.9% of cases), especially in cirrhotic. The therapy was stopped for 14.6% of the patients because of adverse events or virological failure (15%). Sustained virological response was achieved in 62.7% of the cases, but was 43.8% in cirrhotic patients over 65 years of age. CONCLUSION: In everyday practice, triple therapy is safe but has moderate efficacy, especially for patients over 65 years of age, with advanced fibrosis, non-responders to peginterferon + ribavirin.

An efficient algorithm for approximating geodesic distances in tree space.

The increasing use of phylogeny in biological studies is limited by the need to make available more efficient tools for computing distances between trees. The geodesic tree distance-introduced by Billera, Holmes, and Vogtmann-combines both the tree topology and edge lengths into a single metric. Despite the conceptual simplicity of the geodesic tree distance, algorithms to compute it don't scale well to large, real-world phylogenetic trees composed of hundred or even thousand leaves. In this paper, we propose the geodesic distance as an effective tool for exploring the likelihood profile in the space of phylogenetic trees, and we give a cubic time algorithm, GeoHeuristic, in order to compute an approximation of the distance. We compare it with the GTP algorithm, which calculates the exact distance, and the cone path length, which is another approximation, showing that GeoHeuristic achieves a quite good trade-off between accuracy (relative error always lower than 0.0001) and efficiency. We also prove the equivalence among GeoHeuristic, cone path, and Robinson-Foulds distances when assuming branch lengths equal to unity and we show empirically that, under this restriction, these distances are almost always equal to the actual geodesic.

Finding new genes for non-syndromic hearing loss through an in silico prioritization study.

At present, 51 genes are already known to be responsible for Non-Syndromic hereditary Hearing Loss (NSHL), but the knowledge of 121 NSHL-linked chromosomal regions brings to the hypothesis that a number of disease genes have still to be uncovered. To help scientists to find new NSHL genes, we built a gene-scoring system, integrating Gene Ontology, NCBI Gene and Map Viewer databases, which prioritizes the candidate genes according to their probability to cause NSHL. We defined a set of candidates and measured their functional similarity with respect to the disease gene set, computing a score ( S S M avg) that relies on the assumption that functionally related genes might contribute to the same (disease) phenotype. A Kolmogorov-Smirnov test, comparing the pair-wise distribution on the disease gene set with the distribution on the remaining human genes, provided a statistical assessment of this assumption. We found at a p-value < 2.2.10 (-16) that the former pair-wise is greater than the latter, justifying a prioritization strategy based on the functional similarity of candidate genes respect to the disease gene set. A cross-validation test measured to what extent the S S M avg ranking for NSHL is different from a random ordering: adding 15% of the disease genes to the candidate gene set, the ranking of the disease genes in the first eight positions resulted statistically different from a hypergeometric distribution with a p-value = 2.04.10(-5) and a power > 0.99. The twenty top-scored genes were finally examined to evaluate their possible involvement in NSHL. We found that half of them are known to be expressed in human inner ear or cochlea and are mainly involved in remodeling and organization of actin formation and maintenance of the cilia and the endocochlear potential. These findings strongly indicate that our metric was able to suggest excellent NSHL candidates to be screened in patients and controls for causative mutations.

Gabexate or somatostatin administration before ERCP in patients at high risk for post-ERCP pancreatitis: a multicenter, placebo-controlled, randomized clinical trial.

BACKGROUND: ERCP is frequently complicated by pancreatitis. The aims of this study were to assess the efficacy of somatostatin and gabexate for prevention of post-ERCP pancreatitis in high-risk patients and to determine predisposing factors for post-ERCP pancreatitis. A meta-analysis was conducted of all published studies on the use of somatostatin or gabexate for prevention of post-ERCP pancreatitis. METHODS: A double blind, multicenter, placebo-controlled trial was conducted in patients at high risk for post-ERCP pancreatitis. Patients were randomized to receive an intravenous infusion of somatostatin (750 mg), gabexate (500 mg), or placebo that was started 30 minutes before endoscopy and continued for 2 hours afterward. Patients were evaluated clinically and serum amylase levels determined at 4 and 24 hours after endoscopy. RESULTS: No significant difference in the occurrence of pancreatitis, hyperamylasemia, or abdominal pain was observed among placebo-, gabexate-, and somatostatin-treated patients. A sphincterotomy longer than 2 cm (p = 0.0001), more than 3 pancreatic injections (p = 0.0001), and unsuccessful cannulation (p = 0.008) were predictive of post-ERCP pancreatitis. Hyperamylasemia was predicted by more than 3 pancreatic injections (p = 0.0001) and sphincterotomy (p = 0.02). The meta-analysis of trials of short-term infusion of gabexate or somatostatin did not show efficacy for either drug. CONCLUSIONS: Short-term administration of gabexate or somatostatin in patients at high risk for pancreatitis is ineffective for prevention of ERCP-induced pancreatitis. Pancreatic injury is related to maneuvers used to obtain biliary access rather than to any patient characteristic or endoscopist experience.

Prophylaxis of ERCP-related pancreatitis: a randomized, controlled trial of somatostatin and gabexate mesylate.

BACKGROUND & AIMS: It still is debated whether post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis can be prevented by administering either somatostatin or gabexate mesylate. The aim of the study is to assess the efficacy of a 6.5-hour infusion of somatostatin or gabexate mesylate in preventing ERCP-related complications. METHODS: In a double-blind multicenter trial, 1127 patients undergoing ERCP were randomly assigned to intravenous administration of somatostatin (750 microg; n = 351), gabexate mesylate (500 mg; n = 381), or placebo (saline; n = 395). The drug infusion started 30 minutes before and continued for 6 hours after endoscopy. Patients were evaluated clinically, and serum amylase levels were determined at 4, 24, and 48 hours after endoscopy. RESULTS: No significant differences in incidences of pancreatitis, hyperamylasemia, or abdominal pain were observed among the placebo (4.8%, 32.6%, and 5.3%, respectively), somatostatin (6.3%, 26.8%, and 5.1%, respectively), and gabexate mesylate groups (5.8%, 31.5%, and 6.3%, respectively). Univariate analysis of patient characteristics and endoscopic maneuvers showed that a Freeman score >1 (P < 0.0001), >/=3 pancreatic injections (P < 0.00001), and precut sphincterotomy (P = 0.01) were significantly associated with post-ERCP pancreatitis. At multiple logistic regression analysis, >/=3 pancreatic injections (odds ratio [OR], 1.95; 95% confidence interval [CI], 1.45-2.63) and a Freeman score >1 (OR, 1.47; 95% CI, 1.11-1.94) retained their predictive power. CONCLUSIONS: Long-term (6.5-hr) administration of either somatostatin or gabexate mesylate is ineffective for the prevention of post-ERCP pancreatitis. Pancreatic injury seems to be related to difficulty in common bile duct access.