scholarly journals Consumer health information and question answering: helping consumers find answers to their health-related information needs

2019 ◽  
Vol 27 (2) ◽  
pp. 194-201 ◽  
Author(s):  
Dina Demner-Fushman ◽  
Yassine Mrabet ◽  
Asma Ben Abacha
Keyword(s):  
Information Retrieval ◽  
Deep Learning ◽  
Real Life ◽  
Mean Average Precision ◽  
Consumer Health ◽  
National Library ◽  
Average Precision ◽  
Related Information ◽  
Health Related ◽  
Reciprocal Rank

Abstract Objective Consumers increasingly turn to the internet in search of health-related information; and they want their questions answered with short and precise passages, rather than needing to analyze lists of relevant documents returned by search engines and reading each document to find an answer. We aim to answer consumer health questions with information from reliable sources. Materials and Methods We combine knowledge-based, traditional machine and deep learning approaches to understand consumers’ questions and select the best answers from consumer-oriented sources. We evaluate the end-to-end system and its components on simple questions generated in a pilot development of MedlinePlus Alexa skill, as well as the short and long real-life questions submitted to the National Library of Medicine by consumers. Results Our system achieves 78.7% mean average precision and 87.9% mean reciprocal rank on simple Alexa questions, and 44.5% mean average precision and 51.6% mean reciprocal rank on real-life questions submitted by National Library of Medicine consumers. Discussion The ensemble of deep learning, domain knowledge, and traditional approaches recognizes question type and focus well in the simple questions, but it leaves room for improvement on the real-life consumers’ questions. Information retrieval approaches alone are sufficient for finding answers to simple Alexa questions. Answering real-life questions, however, benefits from a combination of information retrieval and inference approaches. Conclusion A pilot practical implementation of research needed to help consumers find reliable answers to their health-related questions demonstrates that for most questions the reliable answers exist and can be found automatically with acceptable accuracy.

Aplikasi Deteksi Kemiripan Tugas Paper

2017 ◽  
Vol 15 (2) ◽  
pp. 5
Author(s):  
Anthony Anggrawan ◽  
Azhari
Keyword(s):  
Information Retrieval ◽  
Vector Space ◽  
Vector Space Model ◽  
Mean Average Precision ◽  
Average Precision ◽  
Information Searching ◽  
Space Model ◽  
Model Method

Information searching based on users’ query, which is hopefully able to find the documents based on users’ need, is known as Information Retrieval. This research uses Vector Space Model method in determining the similarity percentage of each student’s assignment. This research uses PHP programming and MySQL database. The finding is represented by ranking the similarity of document with query, with mean average precision value of 0,874. It shows how accurate the application with the examination done by the experts, which is gained from the evaluation with 5 queries that is compared to 25 samples of documents. If the number of counted assignments has higher similarity, thus the process of similarity counting needs more time, it depends on the assignment’s number which is submitted.

scholarly journals The Quality of Online Health-Related Information – an Emergent Consumer Health Issue

2016 ◽  
Vol 62 (4) ◽  
pp. 408-421 ◽  
Author(s):  
Valentin Nădăşan
Keyword(s):  
Evaluation Criteria ◽  
The Internet ◽  
Consumer Health ◽  
Related Information ◽  
Quality Health ◽  
Health Related ◽  
Potential Risks ◽  
Treatment Procedures ◽  
The Relationship

AbstractThe Internet has become one of the main means of communication used by people who search for health-related information. The quality of online health-related information affects the users’ knowledge, their attitude, and their risk or health behaviour in complex ways and influences a substantial number of users in their decisions regarding diagnostic and treatment procedures.The aim of this review is to explore the benefits and risks associated with using the Internet as a source of health-related information; the relationship between the quality of the health-related information available on the Internet and the potential risks; the multiple conceptual components of the quality of health-related information; the evaluation criteria for quality health-related information; and the main approaches and initiatives that have been implemented worldwide to help improve users’ access to high-quality health-related information.

Online Health Information Consumers’ Learning across Health-Related Search Tasks from the Perspective of Retrieval Platform Switching (Preprint)

2021 ◽  
Author(s):  
Yijing Chen ◽  
Hanming Lin ◽  
Jin Zhang ◽  
Yiming Zhao
Keyword(s):  
Information Retrieval ◽  
Health Information ◽  
Information Search ◽  
Health Knowledge ◽  
Online Health Information ◽  
Related Information ◽  
Search Tasks ◽  
Health Related ◽  
Platform Switching ◽  
Information Consumers

BACKGROUND Online health information retrieval has been a top choice for acquiring health information and knowledge by millions worldwide. OBJECTIVE This study aims to investigate consumers’ modification of retrieval platform switch paths across health-related search tasks and learning via such a change. METHODS A lab user experiment was designed to obtain data on consumers’ health information search behavior. Participants accomplished health-related information search tasks. Screen movements were recorded by EV screen-recording software. The participants underwent in-depth interviews immediately after finishing the tasks. Screen recordings and interview data were both coded and analyzed. RESULTS Three types of learning, including the similar transfer learning, optimizing learning, and SERP-guided learning were identified based on five change patterns of retrieval platform switch paths adopted by health information consumers from task 1 to task 2. Health information consumers’ retrieval platform switch based on information usefulness evaluation. And they accessed different amounts and types of health knowledge from different retrieval platforms. CONCLUSIONS The results suggest that health information consumers exhibit learning both through retrieval platform switching and the knowledge they consume during the search process. This facilitates the assessment of a certain retrieval platform’s usefulness by measuring the amount and types of health knowledge in each search result. This study also contributes to the enhancement of consumers’ health information retrieval abilities, and to helping optimize health information retrieval platforms by increasing their exposure to consumers and increasing the matching degree between knowledge types and consumer needs.

scholarly journals Type ll Diabetic Patients’ Attitudes Toward Influenza and Covid-19 Vaccination

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. A351-A352
Author(s):  
Reisa Gilfix ◽  
Jack Elstein ◽  
Eleanor Elstein
Keyword(s):  
Real Life ◽  
Primary Source ◽  
Diabetic Patients ◽  
Potential Health ◽  
Mainstream Media ◽  
Telephone Interviews ◽  
Related Information ◽  
Health Related ◽  
The Media ◽  
History Of Use

Abstract Influenza vaccination (fluv) is free and easily accessible to diabetics in Quebec. The importance of vaccination (v) during the Covid19 (CV19) pandemic has been widely discussed in the media. To ascertain the receptiveness of type 2 diabetics (T2D) to fluv during the CV19 pandemic and their acceptance of an eventual CV19 vaccine (CVv) we carried out telephone interviews with 34 unselected T2D pts in Montreal, Quebec post the 1st wave of CV19 in that region. Pts were asked if they planned taking the fluv and/or an eventual CVv, reasons for reticence to v, and attitudes toward and compliance with public health (PH) directives. They were also asked their primary source of health related information. Recent HbA1c and insulin use were recorded. Thirty four T2Ds were surveyed, 22 M 50–87 yrs (mean 69.2) and 12 F 49–84 yrs (mean 68.8). Eleven M and 5 F were on insulin. HbA1c ranged from 5.9–13.0 (mean 7.3). None of the pts had recently discussed v with a healthcare provider (HCP). One pt received his health related information from Facebook, the others from mainstream media. None had contraindications to v. None had been diagnosed with CV19. Past influenza history was unknown. Forty one percent (14/34) of pts, 11 M 50–86 yrs (mean 66.0) and 3 F 49–66 yrs (mean 59.0) did not plan to take the fluv. They explained their decisions as never having taken fluv (12 pts) or having been ill despite having taken it (2 pts). Neither accessibility nor cost were issues. Two F, 62 and 66 yrs, who refused fluv also refused CVv. Six M aged 60–86 yrs (mean 70.5) and 1 F aged 73 yrs were planning to wait to access real life safety (6pts) or efficacy (1pt) data before accepting CVv. All pts claimed to be following PH guidelines including social distancing, hand washing, and mask recommendations; 91.2% (31/34) fully agreed with PH policies, 2 were in moderate agreement and 1 thought PH policy was not strict enough. Of the latter 3 pts none planned on taking the fluv. One planned taking the CVv, 1 planned not to, and the 3rd planned to wait before deciding. Despite a long history of use, recommendations by experts, and free and easy accessibility, T2D pts questioned after the 1st wave of CV19 are not convinced of the fluv’s importance. Despite high case numbers and being themselves at high risk, not all T2Ds are willing to unequivocally accept a potential Health Canada sanctioned CVv. This study underlines the important work HCPs have ahead in educating and reassuring pts with regard to vaccination.

scholarly journals Image-Based Plant Disease Identification by Deep Learning Meta-Architectures

Plants ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1451
Author(s):  
Muhammad Hammad Saleem ◽  
Sapna Khanchi ◽  
Johan Potgieter ◽  
Khalid Mahmood Arif
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
State Of The Art ◽  
Mean Average Precision ◽  
Single Shot ◽  
Average Precision ◽  
Crop Monitoring ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Agricultural Applications

The identification of plant disease is an imperative part of crop monitoring systems. Computer vision and deep learning (DL) techniques have been proven to be state-of-the-art to address various agricultural problems. This research performed the complex tasks of localization and classification of the disease in plant leaves. In this regard, three DL meta-architectures including the Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Networks (RFCN) were applied by using the TensorFlow object detection framework. All the DL models were trained/tested on a controlled environment dataset to recognize the disease in plant species. Moreover, an improvement in the mean average precision of the best-obtained deep learning architecture was attempted through different state-of-the-art deep learning optimizers. The SSD model trained with an Adam optimizer exhibited the highest mean average precision (mAP) of 73.07%. The successful identification of 26 different types of defected and 12 types of healthy leaves in a single framework proved the novelty of the work. In the future, the proposed detection methodology can also be adopted for other agricultural applications. Moreover, the generated weights can be reused for future real-time detection of plant disease in a controlled/uncontrolled environment.

scholarly journals DETECTION AND SEGMENTATION OF ENDOSCOPIC ARTEFACTS AND DISEASES USING DEEP ARCHITECTURES

2020 ◽  
Author(s):  
Nhan T. Nguyen ◽  
Dat Q. Tran ◽  
Dung B. Nguyen
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Detection Task ◽  
Mean Average Precision ◽  
Model Ensemble ◽  
Average Precision ◽  
Endoscopic Images ◽  
Feature Pyramid ◽  
Segmentation Task ◽  
Multiple Detectors

ABSTRACTWe describe in this paper our deep learning-based approach for the EndoCV2020 challenge, which aims to detect and segment either artefacts or diseases in endoscopic images. For the detection task, we propose to train and optimize EfficientDet—a state-of-the-art detector—with different EfficientNet backbones using Focal loss. By ensembling multiple detectors, we obtain a mean average precision (mAP) of 0.2524 on EDD2020 and 0.2202 on EAD2020. For the segmentation task, two different architectures are proposed: UNet with EfficientNet-B3 encoder and Feature Pyramid Network (FPN) with dilated ResNet-50 encoder. Each of them is trained with an auxiliary classification branch. Our model ensemble reports an sscore of 0.5972 on EAD2020 and 0.701 on EDD2020, which were among the top submitters of both challenges.

A Holistic Human Factors Evaluation Framework for the Design of Consumer Health Informatics Interventions

2009 ◽  
Vol 53 (16) ◽  
pp. 1003-1007 ◽  
Author(s):  
Teresa Zayas-Cabán ◽  
Jenna L. Marquard
Keyword(s):  
Human Factors ◽  
Health Informatics ◽  
Intervention Development ◽  
Evaluation Framework ◽  
Consumer Health Informatics ◽  
Consumer Health ◽  
Related Information ◽  
Technology Applications ◽  
Health Related ◽  
Care Outcomes

Health-related activities frequently occur outside of formal healthcare institutions, often in consumers' – “laypeople's” – homes. Within and near their homes, laypeople may use devices to self-monitor and self-manage wellness activities and chronic illnesses. They may keep health-related information records, using information technology applications to locate and retrieve information and communicate with formal and informal caregivers. Laypeople's engagement with the healthcare system and care outcomes rest on the quality of their interactions with, and use of, these devices and applications – jointly named consumer health informatics (CHI) interventions. Yet, engineering design and human factors evaluation methods are often omitted from the CHI intervention development process. This article presents a holistic human factors evaluation framework, and demonstrates how physical, cognitive and macroergonomic human factors perspectives can each improve the design and use of CHI interventions.

scholarly journals Deep learning-based detection of dental prostheses and restorations

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Toshihito Takahashi ◽  
Kazunori Nozaki ◽  
Tomoya Gonda ◽  
Tomoaki Mameno ◽  
Kazunori Ikebe
Keyword(s):  
Deep Learning ◽  
High Accuracy ◽  
Mean Average Precision ◽  
Learning Performance ◽  
Average Precision ◽  
Tooth Color ◽  
Photographic Images ◽  
Dental Prostheses ◽  
Learning Procedure ◽  
The Mean

AbstractThe purpose of this study is to develop a method for recognizing dental prostheses and restorations of teeth using a deep learning. A dataset of 1904 oral photographic images of dental arches (maxilla: 1084 images; mandible: 820 images) was used in the study. A deep-learning method to recognize the 11 types of dental prostheses and restorations was developed using TensorFlow and Keras deep learning libraries. After completion of the learning procedure, the average precision of each prosthesis, mean average precision, and mean intersection over union were used to evaluate learning performance. The average precision of each prosthesis varies from 0.59 to 0.93. The mean average precision and mean intersection over union of this system were 0.80 and 0.76, respectively. More than 80% of metallic dental prostheses were detected correctly, but only 60% of tooth-colored prostheses were detected. The results of this study suggest that dental prostheses and restorations that are metallic in color can be recognized and predicted with high accuracy using deep learning; however, those with tooth color are recognized with moderate accuracy.

scholarly journals Relevance Feedback using Genetic Algorithm on Information Retrieval for Indonesian Language Documents

2019 ◽  
Vol 5 (2) ◽  
pp. 171
Author(s):  
Salman Dziyaul Azmi ◽  
Retno Kusumaningrum
Keyword(s):  
Genetic Algorithm ◽  
Information Retrieval ◽  
Population Size ◽  
Relevance Feedback ◽  
Mean Average Precision ◽  
Average Precision ◽  
Mutation Probability ◽  
Average Recall ◽  
Crossover Probability ◽  
Standard Information

Background: The Rapid growth of technological developments in Indonesia had resulted in a growing amount of information. Therefore, a new information retrieval environment is necessary for finding documents that are in accordance with the user’s information needs.Objective: The purpose of this study is to uncover the differences between using Relevance Feedback (RF) with genetic algorithm and standard information retrieval systems without relevance feedback for the Indonesian language documents.Methods: The standard Information Retrieval (IR) System uses Sastrawi stemmer and Vector Space Model, while Genetic Algorithm-based (GA-based) relevance feedback uses Roulette-wheel selection and crossover recombination. The evaluation metrics are Mean Average Precision (MAP) and average recall based on user judgments.Results: By using two Indonesian language document datasets, namely abstract thesis and news dataset, the results show 15.2% and 28.6% increase in the corresponding MAP values for both datasets as opposed to the standard Information Retrieval System. A respective 7.1% and 10.5% improvement on the recall value at 10th position was also observed for both datasets. The best obtained genetic algorithm parameters for abstract thesis datasets were a population size of 20 with 0.7 crossover probability and 0.2 mutation probability, while for news dataset, the best obtained genetic algorithm parameters were a population size of 10 with 0.5 crossover probability and 0.2 mutation probability.Conclusion: Genetic Algorithm-based relevance feedback increases both values of MAP and average recall at 10th position of retrieved document. Generally, the best genetic algorithm parameters are as follows, mutation probability is 0.2, whereas the size of population size and crossover probability depends on the size of dataset and length of the query.Keywords: Genetic Algorithm, Information Retrieval, Indonesian language document, Mean Average Precision, Relevance Feedback 

scholarly journals How a Service User Knows the Level of Privacy and to Whom Trust in pHealth Systems?

2021 ◽  
Author(s):  
Pekka Ruotsalainen ◽  
Bernd Blobel
Keyword(s):  
Communication Networks ◽  
Service Provider ◽  
Service User ◽  
Rapid Development ◽  
Real Life ◽  
Personal Health Information ◽  
Personal Health ◽  
Related Information ◽  
Health Related ◽  
Multi Stakeholder

pHealth is a data (personal health information) driven approach that use communication networks and platforms as technical base. Often it’ services take place in distributed multi-stakeholder environment. Typical pHealth services for the user are personalized information and recommendations how to manage specific health problems and how to behave healthy (prevention). The rapid development of micro- and nano-sensor technology and signal processing makes it possible for pHealth service provider to collect wide spectrum of personal health related information from vital signs to emotions and health behaviors. This development raises big privacy and trust challenges especially because in pHealth similarly to eCommerce and Internet shopping it is commonly expected that the user automatically trust in service provider and used information systems. Unfortunately, this is a wrong assumption because in pHealth’s digital environment it almost impossible for the service user to know to whom to trust, and what the actual level of information privacy is. Therefore, the service user needs tools to evaluate privacy and trust of the service provider and information system used. In this paper, the authors propose a solution for privacy and trust as results of their antecedents, and for the use of computational privacy and trust. To answer the question, which antecedents to use, two literature reviews are performed and 27 privacy and 58 trust attributes suitable for pHealth are found. A proposal how to select a subset of antecedents for real life use is also provided.

Sign in / Sign up

Export Citation Format

Share Document