The impact of AI suggestions on radiologists' decisions: a pilot study of explainability and attitudinal priming interventions in mammography examination.

Various studies have shown that medical professionals are prone to follow the incorrect suggestions offered by algorithms, especially when they have limited inputs to interrogate and interpret such suggestions and when they have an attitude of relying on them. We examine the effect of correct and incorrect algorithmic suggestions on the diagnosis performance of radiologists when (1) they have no, partial, and extensive informational inputs for explaining the suggestions (study 1) and (2) they are primed to hold a positive, negative, ambivalent, or neutral attitude towards AI (study 2). Our analysis of 2760 decisions made by 92 radiologists conducting 15 mammography examinations shows that radiologists' diagnoses follow both incorrect and correct suggestions, despite variations in the explainability inputs and attitudinal priming interventions. We identify and explain various pathways through which radiologists navigate through the decision process and arrive at correct or incorrect decisions. Overall, the findings of both studies show the limited effect of using explainability inputs and attitudinal priming for overcoming the influence of (incorrect) algorithmic suggestions.

Use of Chest Imaging in the Diagnosis and Management of COVID-19: A WHO Rapid Advice Guide.

The World Health Organization (WHO) undertook the development of a rapid guide on the use of chest imaging in the diagnosis and management of coronavirus disease 2019 (COVID-19). The rapid guide was developed over 2 months by using standard WHO processes, except for the use of "rapid reviews" and online meetings of the panel. The evidence review was supplemented by a survey of stakeholders regarding their views on the acceptability, feasibility, impact on equity, and resource use of the relevant chest imaging modalities (chest radiography, chest CT, and lung US). The guideline development group had broad expertise and country representation. The rapid guide includes three diagnosis recommendations and four management recommendations. The recommendations cover patients with confirmed or who are suspected of having COVID-19 with different levels of disease severity, throughout the care pathway from outpatient facility or hospital entry to home discharge. All recommendations are conditional and are based on low certainty evidence (n = 2), very low certainty evidence (n = 2), or expert opinion (n = 3). The remarks accompanying the recommendations suggest which patients are likely to benefit from chest imaging and what factors should be considered when choosing the specific imaging modality. The guidance offers considerations about implementation, monitoring, and evaluation, and also identifies research needs. Published under a CC BY 4.0 license. Online supplemental material is available for this article.

Evaluation of Effective Dashboards: Key Concepts and Criteria.

OBJECTIVE: The aim of this study is to offer appropriate criteria to evaluate effective dashboards for healthcare organizations. METHOD: In a Delphi study, a team of information technology consultants were asked to determine a set of user interface requirements for evaluating, building or selecting the dashboard. In the first round, a list of main features or criteria to be used was determined based on the panel's rating,. RESULTS: In this study, it was revealed that a set of key criteria for evaluating the dashboards can be used for all types of dashboards. These criteria were classified into 7 main categories including user customization, knowledge discovery, security, information delivery, alerting, visual design, and integration and system connectivity. CONCLUSION: Choosing good criteria for selecting effective dashboards for healthcare organizations is very critical because these organizations follow a data-intensive and technology-driven environment. This study revealed the importance of key criteria which can guarantee development of an evaluation checklist.

Data Standards in Tele-radiology.

Data standards play an important role to provide interoperability among different system. As other applications of telemedicine, the tele-radiology needs these standards to work properly. In this article, we conducted a review to introduce some data standards about tele-radiology. By searching PUBMED and Google Scholar database, we find more relevant articles about data standards in tele-radiology. Three categories of standards identified, including data interchange, document and terminology standards. Data interchange standards, including those which facilitate the understanding of the format of a massage between systems, such as DICOM and HL7. Document standards, including those which facilitate the contents of a massage, such as DICOM SR and HL7 CDA. And terminology standards, including those which facilitate the understanding of concepts of the domain. Since, the harmonization between different standards are important to meet interoperability, so the more effort is needed to conduct harmonization between tele-radiology standards and other domain.

Enhance hospital performance from intellectual capital to business intelligence.

Business intelligence (BI) refers to technologies, tools, and practices for collecting, integrating, analyzing, and presenting large volumes of information to enable better decision making. The aim of this study is to provide a general overview of BI and its impacts on improving hospital performance. In this paper, literature is reviewed on the concept, classification, and structure of intellectual capital and BI. Research on the building of BI and its impact on the performance of hospitals are briefly summarized. Some areas in healthcare which can utilize BI benefits, including radiology, are also discussed. Used properly, BI is an effective communication tool that can enable hospitals to reach strategic goals and objectives and can also help eliminate information asymmetry.

Findings of bilateral coronary to pulmonary artery fistula in 64-multislice computed tomographic angiography: correlation with catheter angiography.

A 63-year-old man, who underwent conventional coronary angiography, because of a finding of a confusing vascular structure, was referred for 64-multislice spiral computed tomography (MSCT). His MSCT showed bilateral coronary-pulmonary artery fistula from both right and left coronary arteries via a dilated fistulous vascular malformation. Considering its reasonably high spatial and temporal resolutions, MSCT is regarded as a valuable technique to clarify the diagnosis in incidentally found equivocal cases of coronary fistula in conventional coronary angiography.