Dataset Information

Crowd intelligence for the classification of fractures and beyond.

ABSTRACT: BACKGROUND: Medical diagnosis, like all products of human cognition, is subject to error. We tested the hypothesis that errors of diagnosis in the realm of fracture classification can be reduced by a consensus (group) diagnosis; and that digital imaging and Internet access makes feasible the compilation of a diagnostic consensus in real time. METHODS: Twelve orthopaedic surgeons were asked to evaluate 20 hip radiographs demonstrating a femoral neck fracture. The surgeons were asked to determine if the fractures were displaced or not. Because no reference standard is available, the maximal accuracy of the diagnosis of displacement can be inferred from inter-observer reliability: if two readers disagree about displacement, one of them must be wrong. That method was employed here. Additionally, virtual reader groups of 3 and 5 individual members were amalgamated, with the response of those groups defined by majority vote. The purpose of this step was to see if increasing the number of readers would improve accuracy. In a second experiment, to study the feasibility of amassing a reader group on the Internet in real time, 40 volunteers were sent 10 periodic email requests to answer questions and their response times were assessed. RESULTS: The mean kappa coefficient for individual inter-observer reliability for the diagnosis of displacement was 0.69, comparable to prior published values. For 3-member virtual reader groups, inter-observer reliability was 0.77; and for 5-member groups, it was 0.80. In the experiment studying the feasibility of amassing a reader group in real time, the mean response time was 594 minutes. For all cases, a 9-member group (theoretically 99% accurate) was amassed in 135.8 minutes or less. CONCLUSIONS: Consensus may improve diagnosis. Amassing a group for this purpose on the Internet is feasible.

SUBMITTER: Bernstein J

PROVIDER: S-EPMC3223187 | biostudies-other | 2011

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:BackgroundA scoping review to characterize the literature on the use of conversations in social media as a potential source of data for detecting adverse events (AEs) related to health products.MethodsOur specific research questions were (1) What social media listening platforms exist to detect adverse events related to health products, and what are their capabilities and characteristics? (2) What is the validity and reliability of data from social media for detecting these adverse events? MEDLINE, EMBASE, Cochrane Library, and relevant websites were searched from inception to May 2016. Any type of document (e.g., manuscripts, reports) that described the use of social media data for detecting health product AEs was included. Two reviewers independently screened citations and full-texts, and one reviewer and one verifier performed data abstraction. Descriptive synthesis was conducted.ResultsAfter screening 3631 citations and 321 full-texts, 70 unique documents with 7 companion reports available from 2001 to 2016 were included. Forty-six documents (66%) described an automated or semi-automated information extraction system to detect health product AEs from social media conversations (in the developmental phase). Seven pre-existing information extraction systems to mine social media data were identified in eight documents. Nineteen documents compared AEs reported in social media data with validated data and found consistent AE discovery in all except two documents. None of the documents reported the validity and reliability of the overall system, but some reported on the performance of individual steps in processing the data. The validity and reliability results were found for the following steps in the data processing pipeline: data de-identification (n = 1), concept identification (n = 3), concept normalization (n = 2), and relation extraction (n = 8). The methods varied widely, and some approaches yielded better results than others.ConclusionsOur results suggest that the use of social media conversations for pharmacovigilance is in its infancy. Although social media data has the potential to supplement data from regulatory agency databases; is able to capture less frequently reported AEs; and can identify AEs earlier than official alerts or regulatory changes, the utility and validity of the data source remains under-studied.Trial registrationOpen Science Framework ( https://osf.io/kv9hu/ ).

Project description:ImportanceRadiation therapy (RT) is a critical cancer treatment, but the existing radiation oncologist work force does not meet growing global demand. One key physician task in RT planning involves tumor segmentation for targeting, which requires substantial training and is subject to significant interobserver variation.ObjectiveTo determine whether crowd innovation could be used to rapidly produce artificial intelligence (AI) solutions that replicate the accuracy of an expert radiation oncologist in segmenting lung tumors for RT targeting.Design, setting, and participantsWe conducted a 10-week, prize-based, online, 3-phase challenge (prizes totaled $55 000). A well-curated data set, including computed tomographic (CT) scans and lung tumor segmentations generated by an expert for clinical care, was used for the contest (CT scans from 461 patients; median 157 images per scan; 77 942 images in total; 8144 images with tumor present). Contestants were provided a training set of 229 CT scans with accompanying expert contours to develop their algorithms and given feedback on their performance throughout the contest, including from the expert clinician.Main outcomes and measuresThe AI algorithms generated by contestants were automatically scored on an independent data set that was withheld from contestants, and performance ranked using quantitative metrics that evaluated overlap of each algorithm's automated segmentations with the expert's segmentations. Performance was further benchmarked against human expert interobserver and intraobserver variation.ResultsA total of 564 contestants from 62 countries registered for this challenge, and 34 (6%) submitted algorithms. The automated segmentations produced by the top 5 AI algorithms, when combined using an ensemble model, had an accuracy (Dice coefficient = 0.79) that was within the benchmark of mean interobserver variation measured between 6 human experts. For phase 1, the top 7 algorithms had average custom segmentation scores (S scores) on the holdout data set ranging from 0.15 to 0.38, and suboptimal performance using relative measures of error. The average S scores for phase 2 increased to 0.53 to 0.57, with a similar improvement in other performance metrics. In phase 3, performance of the top algorithm increased by an additional 9%. Combining the top 5 algorithms from phase 2 and phase 3 using an ensemble model, yielded an additional 9% to 12% improvement in performance with a final S score reaching 0.68.Conclusions and relevanceA combined crowd innovation and AI approach rapidly produced automated algorithms that replicated the skills of a highly trained physician for a critical task in radiation therapy. These AI algorithms could improve cancer care globally by transferring the skills of expert clinicians to under-resourced health care settings.

Dataset Information

Crowd intelligence for the classification of fractures and beyond.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets