scholarly journals Evaluating the quality of voice assistants’ responses to consumer health questions about vaccines: an exploratory comparison of Alexa, Google Assistant and Siri

2019 ◽  
Vol 26 (1) ◽  
pp. e100075 ◽  
Author(s):  
Emily Couvillon Alagha ◽  
Rachel Renee Helbing
Keyword(s):  
Patient Education ◽  
Health Information ◽  
Vaccine Safety ◽  
Health Technology ◽  
High Variability ◽  
Consumer Health ◽  
Quality Of Voice ◽  
Audio Output ◽  
The Voice

ObjectiveTo assess the quality and accuracy of the voice assistants (VAs), Amazon Alexa, Siri and Google Assistant, in answering consumer health questions about vaccine safety and use.MethodsResponses of each VA to 54 questions related to vaccination were scored using a rubric designed to assess the accuracy of each answer provided through audio output and the quality of the source supporting each answer.ResultsOut of a total of 6 possible points, Siri averaged 5.16 points, Google Assistant averaged 5.10 points and Alexa averaged 0.98 points. Google Assistant and Siri understood voice queries accurately and provided users with links to authoritative sources about vaccination. Alexa understood fewer voice queries and did not draw answers from the same sources that were used by Google Assistant and Siri.ConclusionsThose involved in patient education should be aware of the high variability of results between VAs. Developers and health technology experts should also push for greater usability and transparency about information partnerships as the health information delivery capabilities of these devices expand in the future.

scholarly journals Dietary and herbal supplements for weight loss: assessing the quality of patient information online

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Jeremy Y. Ng ◽  
Saad Ahmed ◽  
Catherine Jiayi Zhang
Keyword(s):  
Weight Loss ◽  
Health Information ◽  
Healthcare Providers ◽  
The United States ◽  
Consumer Health Information ◽  
Consumer Health ◽  
High Quality ◽  
The Mean ◽  
The Impact

Abstract Background Given the high prevalence of dietary and herbal supplement (DHS) use in tandem with the growing ease of internet access, patients commonly search online for consumer health information about these products. One common reason for DHSs use includes weight loss. Healthcare providers need to be aware of the quality of online information about DHSs for weight loss so they can adequately counsel their patients and provide them with guidance surrounding the identification of high-quality information resources. This study aimed to assess the quality of online DHSs consumer health information for weight loss that a “typical” patient might access online. Methods Six search terms were used to generate the first 20 websites on the Google search engine in four countries: Australia, Canada, the United Kingdom, and the United States (n = 480 websites). After applying exclusion criteria, eligible websites were quality assessed using the DISCERN instrument. This tool is comprised of 16 questions, each evaluated on a 5-point scale. The averages and standard deviations for each DISCERN instrument item, in addition to overall summed scores between 15 and 75 were calculated. Results Across 87 eligible websites, the mean summed score was 44.80 (SD = 11.53), while the mean overall DISCERN score of each website was 2.72 (SD = 0.99). In general, websites detailed and achieved their specified aims and described treatment benefits. However, most websites failed to describe the impact of treatment on overall quality of life and the impact of a no treatment option. The highest-scoring websites were largely government or health portal websites, while the lowest-scoring websites were largely commercial in nature. Conclusion High variability in DISCERN instrument scores was found across all websites assessed. Healthcare providers should be aware of the fact that their patients may be accessing misinformation online surrounding the use of DHSs for weight loss. Therefore, it is important for healthcare providers to ensure that they are providing their patients with guidance on how to identify high-quality resources online, in order that safe, effective, and evidence-based decisions are made surrounding the use of DHSs for weight loss.

scholarly journals Cannabis for pain: a cross-sectional survey of the patient information quality on the Internet

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Jeremy Y. Ng ◽  
Darragh A. Dzisiak ◽  
Jessica B. Saini
Keyword(s):  
Health Information ◽  
Pain Treatment ◽  
Consumer Health Information ◽  
Cannabis Use ◽  
Online Information ◽  
Consumer Health ◽  
Cross Sectional Survey ◽  
Eligibility Criteria ◽  
Cross Sectional

Abstract Background Cannabis has increasingly become an alternative treatment for chronic pain, however, there is evidence of concomitant negative health effects with its long-term usage. Patients contemplating cannabis use for pain relief commonly see information online but may not be able to identify trustworthy and accurate sources, therefore, it is imperative that healthcare practitioners play a role in assisting them in discerning the quality of information. The present study assesses the quality of web-based consumer health information available at the intersection of cannabis and pain. Methods A cross-sectional quality assessment of website information was conducted. Three countries were searched on Google: Canada, the Netherlands, and the USA. The first 3 pages of generated websites were used in each of the 9 searches. Eligible websites contained cannabis consumer health information for pain treatment. Only English-language websites were included. Encyclopedias (i.e. Wikipedia), forums, academic journals, general news websites, major e-commerce websites, websites not publicly available, books, and video platforms were excluded. Information presented on eligible websites were assessed using the DISCERN instrument. The DISCERN instrument consists of three sections, the first focusing on the reliability of the publication, the second investigating individual aspects of the publication, and the third providing an overall averaged score. Results Of 270 websites identified across searches, 216 were duplicates, and 18 were excluded based on eligibility criteria, resulting in 36 eligible websites. The average summed DISCERN score was 48.85 out of 75.00 (SD = 8.13), and the average overall score (question 16) was 3.10 out of 5.00 (SD = 0.62). These overall scores were calculated from combining the scores for questions 1 through 15 in the DISCERN instrument for each website. Websites selling cannabis products/services scored the lowest, while health portals scored the highest. Conclusion These findings indicate that online cannabis consumer health information for the treatment/management of pain presents biases to readers. These biases included websites: (1) selectively citing studies that supported the benefits associated with cannabis use, while neglecting to mention those discussing its risks, and (2) promoting cannabis as “natural” with the implication that this equated to “safe”. Healthcare providers should be involved in the guidance of patients’ seeking and use of online information on this topic.

scholarly journals The voice of patients with laryngeal carcinoma after oncosurgery

2005 ◽  
Vol 13 (2) ◽  
pp. 76-78 ◽  
Author(s):  
Slobodan Mitrovic ◽  
Ljiljana Jovancevic
Keyword(s):  
Acoustic Analysis ◽  
Individual Characteristics ◽  
Secondary Importance ◽  
Laryngeal Function ◽  
Objective Parameter ◽  
Laryngeal Carcinomas ◽  
Before And After ◽  
Quality Of Voice ◽  
The Voice

The voice of patients indicated for surgical procedures in treating of dysphonia is already damaged before the operation. The problem, which exists at the level of glottis patients usually try to solve by compensative mechanisms. The quality of voice after the interventions in larynx depends on the type and width of resection, disturbance of physiological phonation mechanisms, and ability to establish optimal phonation automatism. The damage of laryngeal structure, especially its glottic part and vocal cords as its central part, no matter if they are just fibrous or they are partially or totally absent, leads into the development of substitutive phonation mechanisms. The most frequent substitutive mechanisms are: vestibular, ventricular, and chordoventricular phonation. There are some variations of these phonation mechanisms, which are conditioned not only by applied surgical technique, but as they are also individual characteristics, they can be the consequence of applied rehabilitation methods. The diagnosis of voice condition before and after the oncosurgical procedure is done by: laryngostroboscopy, subjective acoustic analysis of voice, and objective acoustic analysis of voice (sonography or computer analysis of acoustic signal). The most of laryngeal carcinomas appear in glottic region, so the function of phonation imposes itself as the objective parameter to measure the quality of life after the oncosurgery of larynx. That is the reason why according to the priority, it is just behind the principle of "oncologic radicalism". Phonation as the most complex laryngeal function seems to have secondary importance. All known operative techniques, especially partial resections, have the preservation of phonation as their goal.

scholarly journals Voice Pathology Identification using Deep Neural Networks

2019 ◽  
Vol 8 (4) ◽  
pp. 7447-7450
Keyword(s):  
Deep Neural Networks ◽  
External Factors ◽  
Mel Frequency Cepstral Coefficients ◽  
Vocal Cords ◽  
Voice Change ◽  
Human Voice ◽  
Quality Of Voice ◽  
The Voice ◽  
Voice Modulation

The human voice construction is a complex biological mechanism capable of Changing pitch and volume. Some Internal or External factors frequently damage the vocal cords and change quality of voice or do some alteration in the voice modulation. The effects are reflected in expression of speech and understanding of information said by the person. So it is important to examine problem at early stages of voice change and overcome from this problem. ML play a major role in identifying whether voice is pathological or normal in nature. Voice features are extracted by Implementing Mel-frequency Cepstral Coefficients (MFCC) method, and examined on the Convolutional Neural Network (CNN) to identify the category of voice.

A critical analysis of the literature on the Internet and consumer health information

2005 ◽  
Vol 11 (1_suppl) ◽  
pp. 41-43 ◽  
Author(s):  
J A Powell ◽  
P Lowe ◽  
F E Griffiths ◽  
M Thorogood
Keyword(s):  
Health Care ◽  
Health Information ◽  
Critical Analysis ◽  
Virtual Communities ◽  
Consumer Health Information ◽  
The Internet ◽  
Online Information ◽  
Consumer Health ◽  
Online Social Support

A critical review of the published literature investigating the Internet and consumer health information was undertaken in order to inform further research and policy. A qualitative, narrative method was used, consisting of a three-stage process of identification and collation, thematic coding, and critical analysis. This analysis identified five main themes in the research in this area: (1) the quality of online health information for consumers; (2) consumer use of the Internet for health information; (3) the effect of e-health on the practitioner-patient relationship; (4) virtual communities and online social support and (5) the electronic delivery of information-based interventions. Analysis of these themes revealed more about the concerns of health professionals than about the effect of the Internet on users. Much of the existing work has concentrated on quantifying characteristics of the Internet: for example, measuring the quality of online information, or describing the numbers of users in different health-care settings. There is a lack of qualitative research that explores how citizens are actually using the Internet for health care.

scholarly journals Question-driven summarization of answers to consumer health questions

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Max Savery ◽  
Asma Ben Abacha ◽  
Soumya Gayen ◽  
Dina Demner-Fushman
Keyword(s):  
Deep Learning ◽  
Health Information ◽  
Gold Standard ◽  
State Of The Art ◽  
Learning Approaches ◽  
Consumer Health ◽  
Automatic Summarization ◽  
Medical Expertise ◽  
Different Types

Abstract Automatic summarization of natural language is a widely studied area in computer science, one that is broadly applicable to anyone who needs to understand large quantities of information. In the medical domain, automatic summarization has the potential to make health information more accessible to people without medical expertise. However, to evaluate the quality of summaries generated by summarization algorithms, researchers first require gold standard, human generated summaries. Unfortunately there is no available data for the purpose of assessing summaries that help consumers of health information answer their questions. To address this issue, we present the MEDIQA-Answer Summarization dataset, the first dataset designed for question-driven, consumer-focused summarization. It contains 156 health questions asked by consumers, answers to these questions, and manually generated summaries of these answers. The dataset’s unique structure allows it to be used for at least eight different types of summarization evaluations. We also benchmark the performance of baseline and state-of-the-art deep learning approaches on the dataset, demonstrating how it can be used to evaluate automatically generated summaries.

scholarly journals Utilizing Digital Health Technologies for Patient Education in Lifestyle Medicine

2019 ◽  
Vol 14 (2) ◽  
pp. 137-142
Author(s):  
Anne Kuwabara ◽  
Sharlene Su ◽  
Jeffrey Krauss
Keyword(s):  
Patient Education ◽  
Learning Styles ◽  
Health Information ◽  
Technology Development ◽  
Care Delivery ◽  
Digital Health ◽  
Health Technology ◽  
Sufficient Evidence ◽  
Lifestyle Medicine ◽  
Health Technologies

Technology has redefined the way patients and providers communicate and obtain health information. The realm of digital health encompasses a diverse set of technologies, including mobile health, health information technology, wearable devices, telehealth and telemedicine, and personalized medicine. These technologies have begun to improve care delivery without the traditional constraints of distance, location, and time. A growing body of evidence supports the use of digital health technology for improving patient education and implementation of skills and behaviors integral to lifestyle medicine. Patient education can now be delivered in standard formats (eg, articles, written messages) as well a wide array of multimedia (video, audio, interactive games, etc), which may be more appropriate for certain topics and learning styles. In addition, patient engagement in their care plays an important role in improving health outcomes. Despite digital health technology development often outpacing its research, there is sufficient evidence to support the use of many current technologies in clinical practice. Digital health tools will continue to grow in their ability to cost-effectively monitor and encourage healthy behaviors at scale, and better methods of evaluation will likely increase clinician confidence in their use.

Quality of Voice and Prognostic Markers for the Recovery of Vocal Fold Paralysis After Thyroid Surgery

2019 ◽  
Vol 128 (12) ◽  
pp. 1104-1110 ◽  
Author(s):  
Rudolf Reiter ◽  
Adrienne Heyduck ◽  
Thomas Karl Hoffmann ◽  
Sibylle Brosch ◽  
Maria Anna Buchberger ◽  
...  
Keyword(s):  
Thyroid Gland ◽  
Vocal Fold ◽  
Complete Recovery ◽  
Vocal Fold Paralysis ◽  
Predicting Factors ◽  
Quality Of Voice ◽  
Thyroid Gland Surgery ◽  
The Voice

Objectives: This study is set to analyze clinicopathological factors predicting the recovery of unilateral vocal fold paralysis (UVP) in patients after thyroid gland surgery. The quality of voice was additionally assessed in these patients. Methods: The charts and videolaryngostroboscopy (VLS) examinations of 84 consecutive patients with a complete UVP after surgery of the thyroid gland were retrospectively reviewed. Patients were divided into 2 groups: patients who fully recovered from vocal fold paralysis and those who failed to recover after a follow-up of 12 months. The quality of voice was analyzed among other things by determining the Voice Handicap Index (VHI). Results: The UVP fully recovered in 52 of 84 (61.9%) patients. Positive mucosal waves (pMWs) on the paralyzed side, a minimal glottic gap <3 mm seen at the first postoperative VLS, age ≤50 years, and surgery duration ≤120 minutes were associated factors for a complete recovery of nerve function. The voice parameters improved independently from recovery of the paralysis in 90% of the patients. Conclusions: For patients with a poor prognosis of a UVP, early intervention may be beneficial. Thus, predicting factors for a full recovery of vocal fold motion would be a valuable tool. In our cohort, about 60% of recoveries could have been predicted using the above-mentioned parameters. Good quality of voice was independently reached in 90% of the cases.

Sign in / Sign up

Export Citation Format

Share Document