Hopeful and Concerned: Public Input on Building a Trustworthy Medical Information Commons.
Ontology highlight
ABSTRACT:
SUBMITTER: Deverka PA
PROVIDER: S-EPMC6730638 | biostudies-literature | 2019 Mar
REPOSITORIES: biostudies-literature
Publications
Hopeful and Concerned: Public Input on Building a Trustworthy Medical Information Commons.
Deverka Patricia A PA Gilmore Dierdre D Richmond Jennifer J Smith Zachary Z Mangrum Rikki R Koenig Barbara A BA Cook-Deegan Robert R Villanueva Angela G AG Majumder Mary A MA McGuire Amy L AL
The Journal of law, medicine & ethics : a journal of the American Society of Law, Medicine & Ethics 20190301 1
A medical information commons (MIC) is a networked data environment utilized for research and clinical applications. At three deliberations across the U.S., we engaged 75 adults in two-day facilitated discussions on the ethical and social issues inherent to sharing data with an MIC. Deliberants made recommendations regarding opt-in consent, transparent data policies, public representation on MIC governing boards, and strict data security and privacy protection. Community engagement is critical t ...[more]
Similar Datasets
Project description:Computer vision and deep learning have the potential to improve medical artificial intelligence (AI) by assisting in diagnosis, prediction, and prognosis. However, the application of deep learning to medical image analysis is challenging due to limited data availability and imbalanced data. While model performance is undoubtedly essential for medical image analysis, model trust is equally important. To address these challenges, we propose TRUDLMIA, a trustworthy deep learning framework for medical image analysis, which leverages image features learned through self-supervised learning and utilizes a novel surrogate loss function to build trustworthy models with optimal performance. The framework is validated on three benchmark data sets for detecting pneumonia, COVID-19, and melanoma, and the created models prove to be highly competitive, even outperforming those designed specifically for the tasks. Furthermore, we conduct ablation studies, cross-validation, and result visualization and demonstrate the contribution of proposed modules to both model performance (up to 21%) and model trust (up to 5%). We expect that the proposed framework will support researchers and clinicians in advancing the use of deep learning for dealing with public health crises, improving patient outcomes, increasing diagnostic accuracy, and enhancing the overall quality of healthcare delivery.
| S-EPMC10574977 | biostudies-literature
Project description:BackgroundInformation about effects of treatments based on unsystematic reviews of research evidence may be misleading. However, finding trustworthy information about the effects of treatments based on systematic reviews, which is accessible to patients and the public can be difficult. The objectives of this study were to identify and evaluate free sources of health information for patients and the public that provide information about effects of treatments based on systematic reviews.MethodsWe reviewed websites that we and our colleagues knew of, searched for government sponsored health information websites, and searched for online sources of health information that provide evidence-based information. To be included in our review, a website had to be available in English, freely accessible, and intended for patients and the public. In addition, it had to have a broad scope, not limited to specific conditions or types of treatments. It had to include a description of how the information is prepared and the description had to include a statement about using systematic reviews. We compared the included websites by searching for information about the effects of eight treatments.ResultsThree websites met our inclusion criteria: Cochrane Evidence, Informed Health, and PubMed Health. The first two websites produce content, whereas PubMed Health aggregated content. A fourth website that met our inclusion criteria, CureFacts, was under development. Cochrane Evidence provides plain language summaries of Cochrane Reviews (i.e. summaries that are intended for patients and the public). They are translated to several other languages. No information besides treatment effects is provided. Informed Health provides information about treatment effects together with other information for a wide range of topics. PubMed Health was discontinued in October 2018. It included a large number of systematic reviews of treatment effects with plain language summaries for Cochrane Reviews and some other reviews. None of the three websites included links to ongoing trials, and information about treatment effects was not reported consistently on any of the websites.ConclusionIt is possible for patients and the public to access trustworthy information about the effects of treatments using the two of the websites included in this review.
| S-EPMC6381637 | biostudies-literature
Project description:In 1996, an international group of representatives from national archives and libraries, universities, industry, publishing offices, and other government and private sector organizations first articulated the need for certified Trustworthy Digital Repositories (TDRs). Henceforth, multiple standards for TDRs have developed worldwide and their reviewers provide third party audit of digital repositories. Even though hundreds of repositories are currently certified, we do not know if audit and certification of TDRs actually matters. For example, we do not know if digital repositories are actually better at preserving digital information after certification than they were before. Additionally, we do not know if TDRs preserve digital information better than their counterparts, although TDR standards definitely promulgate this assumption. One way of assessing whether audit and certification of TDRs matters is to study its impact on TDRs' stakeholders (e.g., funders, data producers, data consumers). As an initial critical step forward, this study examines what certification-related information repositories actually include on their websites since repository websites provide a means of disseminating information. Using findings from a content analysis of 91 TDR-certified repository websites, this research examines: 1) written statements about TDR status, 2) the presence of TDR seals and their location, 3) whether the seals hyperlink to additional certification information, 4) the extent to which the certification process is explained, and 5) whether audit reports are shared. Nearly three-fourths of the repository websites provide TDR status statements and put seals in one or more places; nearly 60% post audit reports and link seals to additional certification information; and over one-third explain the certification process. Directions for future research and practical application of the results are discussed.
| S-EPMC7725354 | biostudies-literature
Project description:BackgroundDifferentiating between Crohn's disease (CD) and intestinal tuberculosis (ITB) with endoscopy is challenging. We aim to perform more accurate endoscopic diagnosis between CD and ITB by building a trustworthy AI differential diagnosis application.MethodsA total of 1271 electronic health record (EHR) patients who had undergone colonoscopies at Peking Union Medical College Hospital (PUMCH) and were clinically diagnosed with CD (n = 875) or ITB (n = 396) were used in this study. We build a workflow to make diagnoses with EHRs and mine differential diagnosis features; this involves finetuning the pretrained language models, distilling them into a light and efficient TextCNN model, interpreting the neural network and selecting differential attribution features, and then adopting manual feature checking and carrying out debias training.ResultsThe accuracy of debiased TextCNN on differential diagnosis between CD and ITB is 0.83 (CR F1: 0.87, ITB F1: 0.77), which is the best among the baselines. On the noisy validation set, its accuracy was 0.70 (CR F1: 0.87, ITB: 0.69), which was significantly higher than that of models without debias. We also find that the debiased model more easily mines the diagnostically significant features. The debiased TextCNN unearthed 39 diagnostic features in the form of phrases, 17 of which were key diagnostic features recognized by the guidelines.ConclusionWe build a trustworthy AI differential diagnosis application for differentiating between CD and ITB focusing on accuracy, interpretability and robustness. The classifiers perform well, and the features which had statistical significance were in agreement with clinical guidelines.
| S-EPMC10426047 | biostudies-literature
Project description:Policies in literacy and health need to address two perspectives: how basic literacy skills influence the health of populations and individuals; and health literacy — the degree to which individuals have the capacity to obtain, process, and understand basic health information and services needed to make appropriate health decisions. There are three potential areas for action to improve literacy and health literacy: the health system, the education system, and within the broader sphere of culture and society. Despite some increasing attention in the last 20 years, low literacy levels remain a major problem in Canada. Policies need to be sensitive to culture, especially among Aboriginal peoples, Francophones and new Canadians. Public policies are needed to: improve literacy outcomes (for example, support for a pan-Canadian literacy strategy, early childhood education and family literacy programs, and efforts to reduce high school drop out)improve health literacy (for example, support integrated policy and program development across sectors, integrated research and knowledge translation initiatives, and efforts to build links between literacy and health networks)reduce disparities by strengthening levels of literacy and health literacy among vulnerable groups. Electronic Supplementary MaterialSupplementary material is available for this article at 10.1007/BF03405372 and is accessible for authorized users.
| S-EPMC6976281 | biostudies-literature
Project description:To provide an online service learning opportunity for medical students during the COVID-19 pandemic, medical faculty and librarians developed and implemented a "Debunking Medical Myths" module in which students learned to search for emerging medical literature, evaluate evidence, and use that evidence to create an infographics debunking a COVID-19-related myth for a non-medical audience. The resultant infographics are visually appealing and designed to make complex health information easy to understand. The module was well-received by students, who demonstrated a nuanced understanding of the use of infographics to convey health information, and students' work was evaluated highly by community members.Supplementary informationThe online version contains supplementary material available at 10.1007/s40670-022-01541-w.
| S-EPMC8980765 | biostudies-literature
Project description:Sensors, and also actuators or external sources such as databases, serve as data sources in order to realise condition monitoring of industrial applications or the acquisition of characteristic parameters like production speed or reject rate. Modern facilities create such a large amount of complex data that a machine operator is unable to comprehend and process the information contained in the data. Thus, information fusion mechanisms gain increasing importance. Besides the management of large amounts of data, further challenges towards the fusion algorithms arise from epistemic uncertainties (incomplete knowledge) in the input signals as well as conflicts between them. These aspects must be considered during information processing to obtain reliable results, which are in accordance with the real world. The analysis of the scientific state of the art shows that current solutions fulfil said requirements at most only partly. This article proposes the multilayered information fusion system MACRO (multilayer attribute-based conflict-reducing observation) employing the μBalTLCS (fuzzified balanced two-layer conflict solving) fusion algorithm to reduce the impact of conflicts on the fusion result. The performance of the contribution is shown by its evaluation in the scope of a machine condition monitoring application under laboratory conditions. Here, the MACRO system yields the best results compared to state-of-the-art fusion mechanisms. The utilised data is published and freely accessible.
| S-EPMC5134457 | biostudies-literature
Project description:This paper presents a new approach to translate between Building Information Modeling (BIM) and Building Energy Modeling (BEM) that uses Modelica, an object-oriented declarative, equation-based simulation environment. The approach (BIM2BEM) has been developed using a data modeling method to enable seamless model translations of building geometry, materials, and topology. Using data modeling, we created a Model View Definition (MVD) consisting of a process model and a class diagram. The process model demonstrates object-mapping between BIM and Modelica-based BEM (ModelicaBEM) and facilitates the definition of required information during model translations. The class diagram represents the information and object relationships to produce a class package intermediate between the BIM and BEM. The implementation of the intermediate class package enables system interface (Revit2Modelica) development for automatic BIM data translation into ModelicaBEM. In order to demonstrate and validate our approach, simulation result comparisons have been conducted via three test cases using (1) the BIM-based Modelica models generated from Revit2Modelica and (2) BEM models manually created using LBNL Modelica Buildings library. Our implementation shows that BIM2BEM (1) enables BIM models to be translated into ModelicaBEM models, (2) enables system interface development based on the MVD for thermal simulation, and (3) facilitates the reuse of original BIM data into building energy simulation without an import/export process.
| S-EPMC4182875 | biostudies-other
Project description:BackgroundIn 2013, the Shanghai Hospital Development Center issued a policy to advocate public hospitals to report their information about costs on diseases. The objective was to evaluate the impact of interhospital disclosure of costs on diseases on medical costs and compare costs per case following information disclosure between hospitals of different rankings.MethodsThe study uses the hospital-level performance report issued by Shanghai Hospital Development Center in the fourth quarter of 2013, which covers quarterly aggregated hospital-level discharge data from 14 tertiary public hospitals participating in thyroid malignant tumors and colorectal malignant tumors information disclosure from the first quarter of 2012 to the third quarter of 2020. An interrupted time series model with segmented regression analysis is employed to examine changes in quarterly trends with respect to costs per case and length of stay before and after information disclosure. We identified high- and low-cost hospitals by ranking them on a costs per case basis per disease group.ResultsThis research identified significant differences in cost changes for thyroid malignant tumors and colorectal malignant tumors between hospitals after disclosing information. A hospital's discharge costs per case for thyroid malignant tumors increased significantly among top-cost hospitals (1629.251 RMB, P = 0.019), while decreased for thyroid and colorectal malignant tumors among low-cost hospitals (-1504.189 RMB, P = 0.003; -6511.650 RMB, P = 0.024, respectively).ConclusionOur findings indicate that information disclosure of costs on diseases results in changes in discharge costs per case. And low-cost hospitals continued to maintain their leading edge, whereas the high-cost hospitals changed their position in the industry by reducing discharge costs per case after information disclosure.
| S-EPMC10210391 | biostudies-literature
Project description:Speech understanding can be thought of as inferring progressively more abstract representations from a rapidly unfolding signal. One common view of this process holds that lower-level information is discarded as soon as higher-level units have been inferred. However, there is evidence that subcategorical information about speech percepts is not immediately discarded, but is maintained past word boundaries and integrated with subsequent input. Previous evidence for such subcategorical information maintenance has come from paradigms that lack many of the demands typical to everyday language use. We ask whether information maintenance is also possible under more typical constraints, and in particular whether it can facilitate accent adaptation. In a web-based paradigm, participants listened to isolated foreign-accented words in one of three conditions: subtitles were displayed concurrently with the speech, after speech offset, or not displayed at all. The delays between speech offset and subtitle presentation were manipulated. In a subsequent test phase, participants then transcribed novel words in the same accent without the aid of subtitles. We find that subtitles facilitate accent adaptation, even when displayed with a 6 second delay. Listeners thus maintained subcategorical information for sufficiently long to allow it to benefit adaptation. We close by discussing what type of information listeners maintain-subcategorical phonetic information, or just uncertainty about speech categories.
| S-EPMC6080756 | biostudies-literature