The challenges of studying visual expertise in medical image diagnosis
Bibliographic record
Abstract
CONTEXT: Visual expertise is the superior visual skill shown when executing domain-specific visual tasks. Understanding visual expertise is important in order to understand how the interpretation of medical images may be best learned and taught. In the context of this article, we focus on the visual skill of medical image diagnosis and, more specifically, on the methodological set-ups routinely used in visual expertise research. METHODS: We offer a critique of commonly used methods and propose three challenges for future research to open up new avenues for studying characteristics of visual expertise in medical image diagnosis. The first challenge addresses theory development. Novel prospects in modelling visual expertise can emerge when we reflect on cognitive and socio-cultural epistemologies in visual expertise research, when we engage in statistical validations of existing theoretical assumptions and when we include social and socio-cultural processes in expertise development. The second challenge addresses the recording and analysis of longitudinal data. If we assume that the development of expertise is a long-term phenomenon, then it follows that future research can engage in advanced statistical modelling of longitudinal expertise data that extends the routine use of cross-sectional material through, for example, animations and dynamic visualisations of developmental data. The third challenge addresses the combination of methods. Alternatives to current practices can integrate qualitative and quantitative approaches in mixed-method designs, embrace relevant yet underused data sources and understand the need for multidisciplinary research teams. CONCLUSION: Embracing alternative epistemological and methodological approaches for studying visual expertise can lead to a more balanced and robust future for understanding superior visual skills in medical image diagnosis as well as other medical fields.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.131 | 0.322 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.007 | 0.004 |
| Science and technology studies | 0.005 | 0.051 |
| Scholarly communication | 0.014 | 0.021 |
| Open science | 0.005 | 0.014 |
| Research integrity | 0.006 | 0.009 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".