Evaluation and Comparison of Artificial Intelligence Vision Aids: Orcam MyEye 1 and Seeing AI

2021 ◽  
pp. 0145482X2110274
Author(s):  
Christina Granquist ◽  
Susan Y. Sun ◽  
Sandra R. Montezuma ◽  
Tu M. Tran ◽  
Rachel Gage ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Human Performance ◽  
Visual Impairments ◽  
Light Level ◽  
Viewing Distance ◽  
Light Perception ◽  
Time To Completion ◽  
Significant Difference ◽  
Text Reading ◽  
Size Contrast

Introduction: We compared the print-to-speech properties and human performance characteristics of two artificial intelligence vision aids, Orcam MyEye 1 (a portable device) and Seeing AI (an iPhone and iPad application). Methods: There were seven participants with visual impairments who had no experience with the two reading aids. Four participants had no light perception. Two individuals with measurable acuity and one with light perception were tested while blindfolded. We also tested performance with text of varying appearance in varying viewing conditions. To evaluate human performance, we asked the participants to use the devices to attempt 12 reading tasks similar to activities of daily living. We assessed the ranges of text attributes for which reading was possible, such as print size, contrast, and light level. We also assessed if individuals could complete tasks with the devices and measured accuracy and completion time. Participants also completed a survey concerning the two aids. Results: Both aids achieved greater than 95% accuracy in text recognition for flat, plain word documents and ranged from 13 to 57% accuracy for formatted text on curved surfaces. Both aids could read print sizes as small as 0.8M (20/40 Snellen equivalent, 40 cm viewing distance). Individuals successfully completed 71% and 55% ( p = .114) of tasks while using Orcam MyEye 1 and Seeing AI, respectively. There was no significant difference in time to completion of tasks ( p = .775). Individuals believed both aids would be helpful for daily activities. Discussion: Orcam MyEye 1 and Seeing AI had similar text-reading capability and usability. Both aids were useful to users with severe visual impairments in performing reading tasks. Implications for Practitioners: Selection of a reading device or aid should be based on individual preferences and prior familiarity with the platform, since we found no clear superiority of one solution over the other.

scholarly journals Artificial intelligence-based education assists medical students’ interpretation of hip fracture

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Chi-Tung Cheng ◽  
Chih-Chi Chen ◽  
Chih-Yuan Fu ◽  
Chung-Hsien Chaou ◽  
Yu-Tung Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Medical Education ◽  
Hip Fracture ◽  
Medical Students ◽  
Medical Image ◽  
Learning System ◽  
Significant Difference ◽  
Dynamic Collaboration ◽  
Increase In Accuracy ◽  
Image Learning

Abstract Background With recent transformations in medical education, the integration of technology to improve medical students’ abilities has become feasible. Artificial intelligence (AI) has impacted several aspects of healthcare. However, few studies have focused on medical education. We performed an AI-assisted education study and confirmed that AI can accelerate trainees’ medical image learning. Materials We developed an AI-based medical image learning system to highlight hip fracture on a plain pelvic film. Thirty medical students were divided into a conventional (CL) group and an AI-assisted learning (AIL) group. In the CL group, the participants received a prelearning test and a postlearning test. In the AIL group, the participants received another test with AI-assisted education before the postlearning test. Then, we analyzed changes in diagnostic accuracy. Results The prelearning performance was comparable in both groups. In the CL group, postlearning accuracy (78.66 ± 14.53) was higher than prelearning accuracy (75.86 ± 11.36) with no significant difference (p = .264). The AIL group showed remarkable improvement. The WithAI score (88.87 ± 5.51) was significantly higher than the prelearning score (75.73 ± 10.58, p < 0.01). Moreover, the postlearning score (84.93 ± 14.53) was better than the prelearning score (p < 0.01). The increase in accuracy was significantly higher in the AIL group than in the CL group. Conclusion The study demonstrated the viability of AI for augmenting medical education. Integrating AI into medical education requires dynamic collaboration from research, clinical, and educational perspectives.

Endoscopic prediction of submucosal invasion in Barrett’s cancer with the use of Artificial Intelligence: A pilot Study

Endoscopy ◽  
2020 ◽  
Author(s):  
Alanna Ebigbo ◽  
Robert Mendel ◽  
Tobias Rückert ◽  
Laurin Schuster ◽  
Andreas Probst ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Pilot Study ◽  
White Light ◽  
Submucosal Invasion ◽  
Learning System ◽  
Endoscopic Images ◽  
Barrett’S Cancer ◽  
Significant Difference ◽  
Sensitivity Specificity

Background and aims: The accurate differentiation between T1a and T1b Barrett’s cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett’s cancer white-light images. Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett’s cancer. Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett’s cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.

scholarly journals Comparison of predicted psychological distress among workers between artificial intelligence and psychiatrists: a cross-sectional study in Tsukuba Science City, Japan

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e046265
Author(s):  
Shotaro Doki ◽  
Shinichiro Sasahara ◽  
Daisuke Hori ◽  
Yuichi Oi ◽  
Tsukasa Takahashi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Psychological Distress ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
Explanatory Variables ◽  
The Neural Network ◽  
Significant Difference ◽  
Total Data

ObjectivesPsychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.DesignCross-sectional study.SettingWe conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.ParticipantsAn AI model of the neural network and six psychiatrists.Primary outcomeThe accuracies of the AI model and psychiatrists for predicting psychological distress.MethodsIn total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.ResultsThe accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.ConclusionsA machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

scholarly journals Artificial Intelligence: The Attitude of the Public and Representatives of Various Industries

2021 ◽  
Vol 14 (8) ◽  
pp. 339
Author(s):  
Tatjana Vasiljeva ◽  
Ilmars Kreituss ◽  
Ilze Lulle
Keyword(s):  
Artificial Intelligence ◽  
Primary Data ◽  
Structured Interviews ◽  
The Public ◽  
Qualitative And Quantitative ◽  
Public Survey ◽  
Significant Difference ◽  
Main Factors ◽  
Negative Factors ◽  
Near Future

This paper looks at public and business attitudes towards artificial intelligence, examining the main factors that influence them. The conceptual model is based on the technology–organization–environment (TOE) framework and was tested through analysis of qualitative and quantitative data. Primary data were collected by a public survey with a questionnaire specially developed for the study and by semi-structured interviews with experts in the artificial intelligence field and management representatives from various companies. This study aims to evaluate the current attitudes of the public and employees of various industries towards AI and investigate the factors that affect them. It was discovered that attitude towards AI differs significantly among industries. There is a significant difference in attitude towards AI between employees at organizations with already implemented AI solutions and employees at organizations with no intention to implement them in the near future. The three main factors which have an impact on AI adoption in an organization are top management’s attitude, competition and regulations. After determining the main factors that influence the attitudes of society and companies towards artificial intelligence, recommendations are provided for reducing various negative factors. The authors develop a proposition that justifies the activities needed for successful adoption of innovative technologies.

scholarly journals The Combined Effects of Sports Smart Bracelet and Multi-Component Exercise Program on Exercise Motivation among the Elderly in Macau

Medicina ◽  
2021 ◽  
Vol 57 (1) ◽  
pp. 34
Author(s):  
Cheuk Kei Lao ◽  
Bing Long Wang ◽  
Richard S. Wang ◽  
Hsiao Yun Chang
Keyword(s):  
Artificial Intelligence ◽  
Exercise Training ◽  
Training Programs ◽  
Exercise Program ◽  
The Elderly ◽  
Control Group ◽  
Exercise Motivation ◽  
Sport Training ◽  
Study Results ◽  
Significant Difference

Background and objectives: Faced with the serious problem of an aging population, exercise is one of the most effective ways to maintain the health of the elderly. In recent years, with the popularization of smartphones, the elderly have increasingly accepted technological products that incorporate artificial intelligence (AI). However, there is not much research on using artificial intelligence bracelets to enhance elders’ motivation and participation in exercise. Therefore, the purpose of this study is to evaluate the effectiveness of the combination of sports smart bracelets and multi-sport training programs on the motivation of the elderly in Macau. Materials and Methods: The study was conducted with a randomized trial design in a 12 week multi-sport exercise training intervention. According to the evaluation, a total of sixty elders’ pre- and post-test data were included in this study. Results: After 12 weeks of multi-sport exercise training, the evaluation scores on the exercise motivation scale (EMS) increased significantly in the group wearing exercise bracelets and those taking part in the multi-component exercise program, and the degree of progress reached a statistically significant level, but the control group did not show any statistically significant difference. The influence of the combination of sports smart bracelets and multi-sport training programs on elders’ motivation is clearer. Conclusions: The use of sports smart bracelets by elderly people in conjunction with diverse exercise training can effectively enhance elders’ motivation and increase their participation in regular exercise. The combination of sports smart bracelets and multi-sport training programs is worth promoting in the elderly population.

scholarly journals L’EFFICACITÉ DE LA MÉTHODE D’APPRENTISSAGE BRAINSTORMING POUR COMPRENDRE LE TEXTE DESCRIPTIF EN FRANÇAIS POUR LES ÉLÈVES DE LA CLASSE X AU LYCÉE 2 MAGELANG

2019 ◽  
Vol 8 (1) ◽  
Author(s):  
Riri Restiarti ◽  
Sudarwoto Sudarwoto ◽  
Neli Purwani
Keyword(s):  
French Text ◽  
Language Learning ◽  
Reading Skills ◽  
T Test ◽  
French Language ◽  
Learning Method ◽  
Significant Difference ◽  
Post Test ◽  
Text Reading ◽  
French Language Learning

Dans le processus d’apprentissage du français, la plupart des élèves lisent le texte français sans comprendre le sens. Pour surmonter ce problème, la méthode brainstorming peut être appliqué pour que les élèves soient plus actifs et comprennent le contenu du texte. La méthode brainstorming oblige les élèves à donner leurs opinions afin que l’apprentissage ne soit pas dominé par des élèves intelligents. L’objectif de cette recherche est de décrire l’efficacité de l’apprentissage du français en utilisant la méthode brainstorming pour la compréhension écrite du texte descriptif pour la classe X au lycée 2 Magelang. C’est une recherche expérimentale, utilisant pre-test et post-test. Les échantillons dans cette recherche sont les élèves dans la classe X IPA 3 et X IPA 4. La technique d’échantillonnage est random sampling, pour collecter les données j’ai utilisé la documentation et le test. Cette recherche a utilisé la validité du contenu. J’ai utilisé la formule de KR 21 pour assurer la fiabilité de résultat. Je les ai analysés en utilisant de t-test. Cette recherche montre que l’utilisation de la méthode brainstorming est efficace pour la compétence de compréhension écrite du texte descriptif français pour les élèves à la classe X au lycée 2 Magelang. Le résultat de t-test montre une différence significative que tcalcul = 8.86 plus grand de ttab = 2.05. C'est-à-dire que l’apprentissage avec la méthode brainstorming est efficace pour améliorer la capacité de la compréhension écrite du texte descriptif français. In the process of French language learning, most of the students are only able to spell French text, without understanding its meaning. To overcome this problem, can be applied the brainstorming method to encourage students to be more active in understanding the content of the text. The brainstorming method requires students to argue, therefore learning is not only dominated by students who are good at it. The purpose of this research is to describe whether learning French using brainstorming method as learning method in reading descriptive text of the X grade students at SMA N 2 Magelang is effective or not. This research is an experimental research with pre-test and post-test. The population in this research is the students in Class X IPA SMA N 2 Magelang. The respondents in this study are students in X IPA 3 and X IPA 4. To collect the data is documentation and test. This research uses the content validity. Level of trust instrument is measured by the formula KR 21. The data was analyzed using the formula t-test. In addition, to know the material that understood by the students the data was analyzed using the formula effect size. This research shows that the brainstorming learning method is effective for descriptive text Reading Skills of 10th grade students of SMA N 2 Magelang. The results of the t-test shows a significant difference that tvalue more than ttable, the result is 8.6 more than 1.07. Therefore, learning by using brainstorming method is effective to improve reading skills of descriptive text in French.

scholarly journals Misconceptions in the health technology industry that are delaying the translation of artificial intelligence technology into relevant clinical applications

2021 ◽  
Vol 54 (4) ◽  
pp. 243-245
Author(s):  
Fabíola Macruz
Keyword(s):  
Artificial Intelligence ◽  
Human Performance ◽  
Health Technology ◽  
Medical Community ◽  
Technology Industry ◽  
Diagnosis And Prognosis ◽  
Starting Point ◽  
Causative Factors ◽  
The Status ◽  
Artificial Intelligence Technology

Abstract There is great optimism that artificial intelligence (AI), as it disrupts the medical world, will provide considerable improvements in all areas of health care, from diagnosis to treatment. In addition, there is considerable evidence that AI algorithms have surpassed human performance in various tasks, such as analyzing medical images, as well as correlating symptoms and biomarkers with the diagnosis and prognosis of diseases. However, the mismatch between the performance of AI-based software and its clinical usefulness is still a major obstacle to its widespread acceptance and use by the medical community. In this article, three fundamental concepts observed in the health technology industry are highlighted as possible causative factors for this gap and might serve as a starting point for further evaluation of the structure of AI companies and of the status quo.

scholarly journals STUDENTS WITH VISUAL IMPAIRMENTS: BRAILLE READING RATE

2015 ◽  
Vol 3 (1) ◽  
pp. 1-5
Author(s):  
Daniela Dimitrova Radojichikj
Keyword(s):  
Visual Impairment ◽  
Visual Impairments ◽  
Reading Rate ◽  
Reading Performance ◽  
Braille Reader ◽  
Significant Difference

A comparison reading performance was done between 8 students who are using Braille and 14 students who are using enlarged print to read. Reading performance was determined using reading rate (words per minute, wpm). Reading rate results showed no significant difference (p>0.05) between those using the Braille (16.62±11.61 wpm) and those using the enlarged print (27.21±24.89 wpm). This study has shown that Braille reader students read at lower reading rate compared to print reader students with visual impairment.

Self-Esteem and Empathy in Sighted and Visually Impaired Preadolescents

2005 ◽  
Vol 99 (5) ◽  
pp. 276-285 ◽  
Author(s):  
Nora Griffin-Shirley ◽  
Sandra L. Nes
Keyword(s):  
Visually Impaired ◽  
Visual Impairments ◽  
Self Esteem ◽  
Significant Difference

This article reports on a study of self-esteem and empathy among 71 students with visual impairments and 88 sighted students. No significant difference was found between the two groups of students in their levels of self-esteem, empathy toward others, and bonding with pets.

Sign in / Sign up

Export Citation Format

Share Document