Refine
Year of publication
- 2014 (1)
Document Type
- Article (1)
- Part of a Book (1)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- no (2)
Keywords
- Cost allocation (1)
- Fairness criteria (1)
- Indirect cost (1)
- Joint cost (1)
- Overhead cost (1)
- Tooling (1)
Effect of AI on performance of endoscopists to detect Barrett neoplasia: A Randomized Tandem Trial
()
Background and study aims
To evaluate the effect of an AI-based clinical decision support system (AI) on the performance and diagnostic confidence of endoscopists during the assessment of Barrett's esophagus (BE).
Patients and Methods
Ninety-six standardized endoscopy videos were assessed by 22 endoscopists from 12 different centers with varying degrees of BE experience.
The assessment was randomized into two video sets: Group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level.
Results
AI had a standalone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.6%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1 and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.7% (95% CI, 65.2% - 74.2%) to 78.0% (95% CI, 74.0% - 82.0%); specificity 67.3% (95% CI, 62.5% - 72.2%) to 72.7% (95 CI, 68.2% - 77.3%). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI.
Conclusion
BE nonexperts benefitted significantly from the additional AI. BE experts and nonexperts remained below the standalone performance of AI, suggesting that there may be other factors influencing endoscopists to follow or discard AI advice.
Purpose
Tooling is a common component of an industrial product’s manufacture. Specific tooling is devised to serve the fabrication of a particular product, while generic tooling can be used in the manufacture of multiple products. In the latter case, companies are confronted with the problem of fairly allocating the indirect costs of the tooling. This article studies how to allocate costs of generic tooling to single production orders.
Methodology
Ten allocation methods (AMs) are described that are in principle suited to the distribution of generic tooling costs to production orders. Since the presented methods have for the most part been discussed in differing contexts, we apply them to a specified generic tooling problem for comparison. Evaluation of the various methods is based on 16 criteria. Reasoning is supported by a computational Monte Carlo simulation. Furthermore, we suggest using the Analytical Hierarchy Process (AHP) to elaborate one final proposition concerning the most preferable allocation scheme.
Findings
The article reports the single allocation rules’ performances for different allocation scenarios. The described characteristics refer to fairness, efficiency, and simplicity as well as to empty-core performance. Using AHP analysis allows for the aggregation of the rules’ criteria ratings. Thus, especially suitable allocation schemes for the problem at hand are identified.
Practical implications
An allocation is required for budgeting reasons and also for the definition of projects’ bottom-up sales prices. Selecting the “right” AM is important, as a suboptimal AM can result in unfair allocation vectors, which will act as incentives to stop using the common resource, potentially leading to higher total costs.
Originality/value of the article
Research on the comparison of AMs is typically performed for certain purposes, such as enterprise networks, horizontal cooperative purchasing scenarios, or municipal service units. This article will augment the research evaluating AMs by introducing a novel set of evaluation criteria and by providing an in-depth comparison of AMs suited for the allocation of generic tooling costs.