Objective Assessment of Pathological Voice Using Artificial Intelligence Based on the GRBAS Scale

2021 ◽  
Author(s):  
Tsuyoshi Kojima ◽  
Shintaro Fujimura ◽  
Koki Hasebe ◽  
Yusuke Okanoue ◽  
Otsuki Shuya ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Objective Assessment ◽  
Pathological Voice

ARTIFICIAL INTELLIGENCE CRIMES

2019 ◽  
pp. 10-13
Author(s):  
V.A. Tyrranen ◽  
Keyword(s):  
Artificial Intelligence ◽  
Information Security ◽  
Criminal Law ◽  
Computer Technology ◽  
Objective Assessment ◽  
Criminal Prosecution ◽  
Legal Personality ◽  
Legitimate Interests ◽  
Widespread Dissemination

The article is devoted to current threats to information security associated with the widespread dissemination of computer technology. The author considers one of the aspects of cybercrime, namely crime using artificial intelligence. The concept of artificial intelligence is analyzed, a definition is proposed that is sufficient for effective enforcement. The article discusses the problems of criminalizing such crimes, the difficulties of solving the issue of legal personality and delinquency of artificial intelligence are shown. The author gives various cases, explaining why difficulties arise in determining the person responsible for the crime, gives an objective assessment of the possibility of criminal prosecution of the creators of the software, in the work of which there were errors that caused harm to the rights protected by criminal law and legitimate interests.

scholarly journals Artificial Intelligence Application for Vocal Fold Disease Prediction Through Voice Recognition: Development and Usability Study (Preprint)

2020 ◽  
Author(s):  
Hao-Chun Hu ◽  
Shyue-Yih Chang ◽  
Chuen-Heng Wang ◽  
Kai-Jun Li ◽  
Hsiao-Yun Cho ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Primary Care ◽  
Convolutional Neural Network ◽  
Vocal Fold ◽  
Voice Recognition ◽  
Spasmodic Dysphonia ◽  
Adductor Spasmodic Dysphonia ◽  
Normal Voice ◽  
Pathological Voice

BACKGROUND Dysphonia influences the quality of life by interfering with communication. However, laryngoscopic examination is expensive and not readily accessible in primary care units. Experienced laryngologists are required to achieve an accurate diagnosis. OBJECTIVE This study sought to detect various vocal fold diseases through pathological voice recognition using artificial intelligence. METHODS We collected 29 normal voice samples and 527 samples of individuals with voice disorders, including vocal atrophy (n=210), unilateral vocal paralysis (n=43), organic vocal fold lesions (n=244), and adductor spasmodic dysphonia (n=30). The 556 samples were divided into two sets: 440 samples as the training set and 116 samples as the testing set. A convolutional neural network approach was applied to train the model and findings were compared with human specialists. RESULTS The convolutional neural network model achieved a sensitivity of 0.70, a specificity of 0.90, and an overall accuracy of 65.5% for distinguishing normal voice, vocal atrophy, unilateral vocal paralysis, organic vocal fold lesions, and adductor spasmodic dysphonia. Compared to human specialists, the overall accuracy was 58.6% and 49.1% for the two laryngologists, and 38.8% and 34.5% for the two general ear, nose, and throat doctors. CONCLUSIONS We developed an artificial intelligence-based screening tool for common vocal fold diseases, which possessed high specificity after training with our Mandarin pathological voice database. This approach has clinical potential to use artificial intelligence for general vocal fold disease screening via voice and includes a quick survey during a general health examination. It can be applied in telemedicine for areas that lack laryngoscopic abilities in primary care units.

A prospective blinded study of 1000 cases analyzing the role of artificial intelligence: Watson for oncology and change in decision making of a Multidisciplinary Tumor Board (MDT) from a tertiary care cancer center.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 6533-6533 ◽  
Author(s):  
S.P. Somashekhar ◽  
Martín-J. Sepúlveda ◽  
Edward H Shortliffe ◽  
Rohit Kumar C ◽  
Amit Rauthan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Objective Assessment ◽  
Tertiary Care ◽  
Tumor Board ◽  
Cancer Center ◽  
Cognitive Computing ◽  
High Quality ◽  
Phenotypic Data ◽  
Multidisciplinary Tumor Board

6533 Background: Artificial intelligence is being used to provide support for information-intensive decision making. In this report, we present our experience in explaining how artificial intelligence adds value to MDT’s decision making ability & paves way for personalized therapy. Methods: 1000 cases involving breast, lung, and colorectal cancer were evaluated by a multidisciplinary tumor board at a major cancer center in India between 2016 and 2018. After the tumor board decision was made, MDT was presented with the Watsons recommendations contemporaneously. MDT reviewed their decision after going through Watson’s recommendations and also the evidences that it put forth supporting its decision. Cases in which decision was changed, objective assessment was done by asking MDT to quote the reasons for reviewing and changing their decision. Results: Of 1000 cases, breast, lung, colon & rectal cancers were 620, 130,126 & 124 respectively. There were 712 non-metastatic & 288 metastatic cases. Mean age of the patients was 54.3 ± 12.2. Treatment concordance was observed in 92% for all cancers combined, 93% for rectal cancer, 92% for breast cancer, 89% for lung cancer, and 81% for colon cancer.MDT changed their decision in 136 cases (13.6%). The reasons for tumour board to change their decision was, Watson provided recent evidences for newer treatment in 55%, better personalized alternative in 30% & new insights from genotypic and phenotypic data and evolving clinical experiences in 15% of time. Conclusions: The study suggest that cognitive computing decision support system holds substantial promise to reduce the cognitive burden on oncologists by providing expert, updated, recent evidence-based insights for treatment-related decision-making. The 13.6 % incremental advantage over and above in a tertiary cancer centre with functioning MDT speaks in itself the value of having a learned colleague like Watson for oncology at our disposal. It will certainly add more value in settings lacking ready access to high quality cancer expertise and information. These systems can be valuable adjuncts to strong patient-clinician relationships in the delivery of high quality cancer care.

scholarly journals 154 Can we improve the accuracy and reproducibility of left ventricular ejection fraction from 2D echocardiography using artificial intelligence? A validation against cardiac magnetic resonance

2020 ◽  
Vol 21 (Supplement_1) ◽  
Author(s):  
A Popoff ◽  
H Langet ◽  
P Piro ◽  
C Ropert ◽  
P Allain ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Image Quality ◽  
Ejection Fraction ◽  
Cardiac Function ◽  
Objective Assessment ◽  
Left Ventricular ◽  
Lv Volumes

Abstract Funding Acknowledgements Philips BACKGROUND Accurate and reproducible echocardiographic measurements are paramount for objective assessment and follow-up of the cardiac function. However, manual contouring – e.g., for determining left ventricular (LV) volumes and ejection fraction (EF) – is limited by image quality and operator experience. Meanwhile, despite the wider availability of (semi-)automated tools, strong multimodal validation is still lacking for their widespread and safe use in the clinical routine. PURPOSE To evaluate the accuracy and reproducibility of an Artificial Intelligence (AI)-based semi-automated tool to compute LV volumes and EF, in comparison with manual contouring, using cardiac magnetic resonance (cMR) as reference. METHODS Manual and AI measurements from echocardiography were compared to measurements from cMR in a retrospective two-centre study. One hundred fourteen patients in sinus rhythm were included; among those, 85 had abnormal LV function (56 dilated and 29 hypertrophic). Three successive cardiac cycles were available for apical 4- and 2-chamber views. Two senior (A1 and B1) and one junior (A2) cardiologists contoured the ED and ES endocardial borders in the cardiac cycle of their choice, while blinded to quantitative outcomes. For AI analysis, a deep convolutional neural networks model was used to segment the LV cavity on the frames selected by the three observers. This model was trained using ED and ES manual contouring from senior cardiologist A1 on an independent single-centre dataset that consisted of 700 apical 4- and 2-chamber views. The same biplane Simpson’s method was used to compute all LV volumes and EF. RESULTS Despite challenging image quality (poor: 6%; fair: 33%; high: 61%, as rated by observers), the majority of the AI segmentations were deemed acceptable (75% in total; 80% for images of high quality). Overall, inter-observer agreement was better by AI than by manual contouring (ICC = 0.99 vs. 0.89, 1.00 vs. 0.95 and 0.95 vs. 0.89 for LVED, LVES and LVEF respectively, all p < 0.001). For LVED and LVES, agreement vs. cMR was higher by AI (80.95 ± 39.09; -46.42 ± 38.29) than by manual contouring for junior observer A2 (-81.47 ± 43; -51.88 ± 40.43), although still lower than by manual contouring for the best senior observer (-54.71 ± 31.44; -32.75 ± 32.80), see upper part in figure below. LVEF bias was reduced near to zero by AI, with slightly higher variability than by manual contouring ([-0.91; -0.05] ± [8.47; 10.17] vs. [-0.19; 5.44] ± [7.75; 8.79]), see lower part in figure below. CONCLUSION The AI model generalized well to different sites, observers and image quality. Compared to manual contouring, LV volumes and EF by AI showed comparable or improved accuracy and higher reproducibility. These findings demonstrate the value of AI-based tools, with potential for full automation, for objective assessment and follow-up of the cardiac function. Abstract 154 Figure.

scholarly journals Differences among COVID-19, Bronchopneumonia and Atypical Pneumonia in Chest High Resolution Computed Tomography Assessed by Artificial Intelligence Technology

2021 ◽  
Vol 11 (5) ◽  
pp. 391
Author(s):  
Robert Chrzan ◽  
Monika Bociąga-Jasik ◽  
Amira Bryll ◽  
Anna Grochowska ◽  
Tadeusz Popiela
Keyword(s):  
Artificial Intelligence ◽  
Computed Tomography ◽  
High Resolution ◽  
Objective Assessment ◽  
Ground Glass ◽  
Future Research ◽  
Atypical Pneumonia ◽  
Automatic Assessment ◽  
High Resolution Computed Tomography ◽  
Volume Percentage

The aim of this study was to compare the results of automatic assessment of high resolution computed tomography (HRCT) by artificial intelligence (AI) in 150 patients from three subgroups: pneumonia in the course of COVID-19, bronchopneumonia and atypical pneumonia. The volume percentage of inflammation and the volume percentage of “ground glass” were significantly higher in the atypical (respectively, 11.04%, 8.61%) and the COVID-19 (12.41%, 10.41%) subgroups compared to the bronchopneumonia (5.12%, 3.42%) subgroup. The volume percentage of consolidation was significantly higher in the COVID-19 (2.95%) subgroup compared to the atypical (1.26%) subgroup. The percentage of “ground glass” in the volume of inflammation was significantly higher in the atypical (89.85%) subgroup compared to the COVID-19 (79.06%) subgroup, which in turn was significantly higher compared to the bronchopneumonia (68.26%) subgroup. HRCT chest images, analyzed automatically by artificial intelligence software, taking into account the structure including “ground glass” and consolidation, significantly differ in three subgroups: COVID-19 pneumonia, bronchopneumonia and atypical pneumonia. However, the partial overlap, particularly between COVID-19 pneumonia and atypical pneumonia, may limit the usefulness of automatic analysis in differentiating the etiology. In our future research, we plan to use artificial intelligence for objective assessment of the dynamics of pulmonary lesions during COVID-19 pneumonia.

Development of a Laparoscopic Box Trainer Based on Open Source Hardware and Artificial Intelligence for Objective Assessment of Surgical Psychomotor Skills

2018 ◽  
Vol 25 (4) ◽  
pp. 380-388 ◽  
Author(s):  
Gustavo A. Alonso-Silverio ◽  
Fernando Pérez-Escamirosa ◽  
Raúl Bruno-Sanchez ◽  
José L. Ortiz-Simon ◽  
Roberto Muñoz-Guerrero ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Augmented Reality ◽  
Characteristic Curve ◽  
Objective Assessment ◽  
Training System ◽  
Surgical Skills ◽  
Raspberry Pi ◽  
Psychomotor Skills ◽  
Laparoscopic Instrument

Background. A trainer for online laparoscopic surgical skills assessment based on the performance of experts and nonexperts is presented. The system uses computer vision, augmented reality, and artificial intelligence algorithms, implemented into a Raspberry Pi board with Python programming language. Methods. Two training tasks were evaluated by the laparoscopic system: transferring and pattern cutting. Computer vision libraries were used to obtain the number of transferred points and simulated pattern cutting trace by means of tracking of the laparoscopic instrument. An artificial neural network (ANN) was trained to learn from experts and nonexperts’ behavior for pattern cutting task, whereas the assessment of transferring task was performed using a preestablished threshold. Four expert surgeons in laparoscopic surgery, from hospital “Raymundo Abarca Alarcón,” constituted the experienced class for the ANN. Sixteen trainees (10 medical students and 6 residents) without laparoscopic surgical skills and limited experience in minimal invasive techniques from School of Medicine at Universidad Autónoma de Guerrero constituted the nonexperienced class. Data from participants performing 5 daily repetitions for each task during 5 days were used to build the ANN. Results. The participants tend to improve their learning curve and dexterity with this laparoscopic training system. The classifier shows mean accuracy and receiver operating characteristic curve of 90.98% and 0.93, respectively. Moreover, the ANN was able to evaluate the psychomotor skills of users into 2 classes: experienced or nonexperienced. Conclusion. We constructed and evaluated an affordable laparoscopic trainer system using computer vision, augmented reality, and an artificial intelligence algorithm. The proposed trainer has the potential to increase the self-confidence of trainees and to be applied to programs with limited resources.

Objective Assessment of Hearing in Children: Update on Procedures and Protocols

2011 ◽  
Vol 21 (2) ◽  
pp. 50-58
Author(s):  
James W. Hall ◽  
Anuradha R. Bantwal
Keyword(s):  
Psychosocial Development ◽  
Otoacoustic Emissions ◽  
Objective Assessment ◽  
Behavioral Assessment ◽  
Auditory Brainstem ◽  
Test Battery ◽  
Auditory Evoked Responses ◽  
Brainstem Response ◽  
Assessment Techniques ◽  
Pediatric Populations

Early identification and diagnosis of hearing loss in infants and young children is the first step toward appropriate and effective intervention and is critical for optimal communicative and psychosocial development. Limitations of behavioral assessment techniques in pediatric populations necessitate the use of an objective test battery to enable complete and accurate assessment of auditory function. Since the introduction of the cross-check principle 35 years ago, the pediatric diagnostic test battery has expanded to include, in addition to behavioral audiometry, acoustic immittance measures, otoacoustic emissions, and multiple auditory evoked responses (auditory brainstem response, auditory steady state response, and electrocochleography). We offer a concise description of a modern evidence-based audiological test battery that permits early and accurate diagnosis of auditory dysfunction.

Sign in / Sign up

Export Citation Format

Share Document