Improving medical experts' efficiency of misinformation detection: an exploratory study.

Fighting medical disinformation in the era of the pandemic is an increasingly important problem. Today, automatic systems for assessing the credibility of medical information do not offer sufficient precision, so human supervision and the involvement of medical expert annotators are required. Our work aims to optimize the utilization of medical experts' time. We also equip them with tools for semi-automatic initial verification of the credibility of the annotated content. We introduce a general framework for filtering medical statements that do not require manual evaluation by medical experts, thus focusing annotation efforts on non-credible medical statements. Our framework is based on the construction of filtering classifiers adapted to narrow thematic categories. This allows medical experts to fact-check and identify over two times more non-credible medical statements in a given time interval without applying any changes to the annotation flow. We verify our results across a broad spectrum of medical topic areas. We perform quantitative, as well as exploratory analysis on our output data. We also point out how those filtering classifiers can be modified to provide experts with different types of feedback without any loss of performance.

Active Annotation in Evaluating the Credibility of Web-Based Medical Information: Guidelines for Creating Training Data Sets for Machine Learning.

BACKGROUND: The spread of false medical information on the web is rapidly accelerating. Establishing the credibility of web-based medical information has become a pressing necessity. Machine learning offers a solution that, when properly deployed, can be an effective tool in fighting medical misinformation on the web. OBJECTIVE: The aim of this study is to present a comprehensive framework for designing and curating machine learning training data sets for web-based medical information credibility assessment. We show how to construct the annotation process. Our main objective is to support researchers from the medical and computer science communities. We offer guidelines on the preparation of data sets for machine learning models that can fight medical misinformation. METHODS: We begin by providing the annotation protocol for medical experts involved in medical sentence credibility evaluation. The protocol is based on a qualitative study of our experimental data. To address the problem of insufficient initial labels, we propose a preprocessing pipeline for the batch of sentences to be assessed. It consists of representation learning, clustering, and reranking. We call this process active annotation. RESULTS: We collected more than 10,000 annotations of statements related to selected medical subjects (psychiatry, cholesterol, autism, antibiotics, vaccines, steroids, birth methods, and food allergy testing) for less than US $7000 by employing 9 highly qualified annotators (certified medical professionals), and we release this data set to the general public. We developed an active annotation framework for more efficient annotation of noncredible medical statements. The application of qualitative analysis resulted in a better annotation protocol for our future efforts in data set creation. CONCLUSIONS: The results of the qualitative analysis support our claims of the efficacy of the presented method.

[Comparison of Cmac vs Vivasight devices in terms of time and effectiveness of intubation among medical students]. / Porównanie urzadzen Cmac vs Vivasight pod katem czasu i skutecznosci intubacji wsród studentów medycyny.

While analysing the use of the new videolaryngoscopes in the hands of the well experienced anaesthesiologists it is difficult to get answers to all intriguing questions and gain insights that might arise only from the untrained users. We can form a thesis that if a manikin, with the use of a particular device, is intubated quickly and effectively by the novices, it is probable that the more experienced operators will be even more satisfied with its use. AIM: The aim of our study was to evaluate the effectiveness of the use of these devices in the hands of the users untrained in intubation. We also wanted to find out what are the subjective perceptions of using the devices by unsuccessful users. We investigated intubation times, effectiveness as well as parameters such as tooth damage. The aim of the secondary and obvious benefit to students was familiarity Them with new advanced methods of clearing the upper respiratory tract with which they will probably meet in the future. MATERIALS AND METHODS: The study included 104 medical students. Every participant took three attempts to intubate the manikin using each device. The technical parameters of the devices have been studied by the experts from the Lodz University of Technology. RESULTS: The average time of intubation in the case of the Cmac was 28,3±10,1, while as regards the Vivasight the average time of intubation was 30,9±9,0. In order to check the statistical significance, the Mann - Whitney U test was used (p <0,005). A larger proportion of successful attempts that amounted to 60% were observed while using the CMAC. CONCLUSIONS: According to the subjective opinion of the students, the Cmac is easier to operate than the Vivasight. This study proved that videolaryngocopes can be a great tool for training new methods of intubation even during studies.