Dataset Information

The easy-to-hard training advantage with real-world medical images.

ABSTRACT: Many medical professions require practitioners to perform visual categorizations in domains such as radiology, dermatology, and neurology. However, acquiring visual expertise is tedious and time-consuming and the perceptual strategies mediating visual categorization skills are poorly understood. In this paper, the Ease algorithm was developed to predict an item's categorization difficulty (Ease value) based on the item's perceptual similarity to all within-category items versus between-category items in the dataset. In this study, Ease values were used to construct an easy-to-hard and hard-to-easy training schedule for teaching melanoma diagnosis. Whereas previous visual training studies suggest that an easy-to-hard schedule benefits learning outcomes, no studies to date have demonstrated the easy-to-hard advantage with complex, real-world images. In our study, 237 melanoma and benign images were collected for training and testing purposes. The diagnostic accuracy of images was verified by an expert dermatologist. Based on their Ease values, the items were grouped into easy, medium, and hard categories, each containing an equal number of melanoma and benign lesions. During training, participants categorized images of skin lesions as either benign or melanoma and were given corrective feedback after each trial. In the easy-to-hard training condition, participants learned to categorize all the easy items first, followed by the medium items, and finally the hard items. Participants in the hard-to-easy training condition learned items in the reverse order. Post-training results showed that training in both conditions transferred to the classification of new melanoma and benign images. Participants in the easy-to-hard condition showed modest advantages both in the acquisition and retention of the melanoma diagnosis skills, but neither scheduling condition exhibited a gross advantage. The Ease values of the items predicted categorization accuracy after, but not before training, suggesting that the Ease algorithm is a promising tool for optimizing medical training in visual categorization.

SUBMITTER: Roads BD

PROVIDER: S-EPMC6168445 | biostudies-literature | 2018 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The easy-to-hard training advantage with real-world medical images.

Roads Brett D BD Xu Buyun B Robinson June K JK Tanaka James W JW

Cognitive research: principles and implications 20181003 1

Many medical professions require practitioners to perform visual categorizations in domains such as radiology, dermatology, and neurology. However, acquiring visual expertise is tedious and time-consuming and the perceptual strategies mediating visual categorization skills are poorly understood. In this paper, the Ease algorithm was developed to predict an item's categorization difficulty (Ease value) based on the item's perceptual similarity to all within-category items versus between-category ...[more]

PMID: 30280265

Similar Datasets

Project description:ObjectiveResearch suggests recently graduated urology residents do not feel ready for independent practice. We conducted a study to determine if Accreditation Council for Graduate Medical Education (ACGME) minimum case requirements, resident case logs, and graduating resident perceived readiness for practice are aligned with the procedural demand and needs of the current urology workforce.DesignCorrelative study comparing the association between (1) workforce demand and ACGME case requirements, and (2) workforce demand and perceived resident competency. Three distinct datasets were used; (1) the 2017 Medicare Part B National Summary Data File; (2) the 2017 National Data Report published by the ACGME; and (3) a graduating resident survey from Okhunov et al. SETTING: N/A.ParticipantsN/A.ResultsIn 2017, there were a total of 6,784,696 urologic cases performed through Medicare. We found nonsignificant positive associations between resident case logs (rho = 0.16, p = 0.5784), ACGME minimum procedure requirements (rho = 0.42, p = 0.1255), and Medicare procedural demand. Our 15 index procedures accounted for 21.1% (n = 1,431,775) of all Medicare cases, with a median number of 7706 procedures. Endopyelotomy was the least common procedure (n = 98), while cystoscopy was the most common (n = 980,623). Medicare case volume was positively correlated with graduating residents' procedural confidence (r = 0.86, p < 0.0001). We identified four categories with varied alignment of training and demand: (1) high volume and high confidence, (2) high volume and low confidence, (3) low volume and high confidence, and (4) low volume and low confidence.ConclusionsOptimizing urology residency training is time-sensitive and important. Using national Medicare data coupled with recently graduated urology resident survey results, we provide a guiding framework for improving the alignment of training with workforce demand. Informed by these results, we recommend altering training requirements to reflect these needs.

Dataset Information

The easy-to-hard training advantage with real-world medical images.

Publications

The easy-to-hard training advantage with real-world medical images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets