Effect of voice recognition on radiologist reporting time.
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
OBJECTIVE: To study the effect that voice recognition (VR) has on radiologist reporting efficiency in a clinical setting and to identify variables associated with faster reporting time. METHODS: Five radiologists were observed during the routine reporting of 402 plain radiograph studies using either VR (n = 217)or conventional dictation (CD) (n = 185). Two radiologists were observed reporting 66 computed tomography (CT) studies using either VR (n = 39) or CD (n = 27). The time spent per reporting cycle, defined as the radiologist's time spent on a study from report finalization to the subsequent report finalization, was compared. As well, characteristics about the radiologist and their reporting style were collected and correlated against reporting time. RESULTS: For plain radiographs, radiologists took 13.4% (P= 0.048) more time to produce reports using VR, but there was significant variability between radiologists. Significant association with faster reporting times using VR included: English as a first language (r = -0.24), use of a template (r = -0.34), use of a headset microphone (r = -0.46), and increased experience with VR (r= -0.43). Experience as a staff radiologist and having a previous study for comparison did not correlate with reporting time. For CT, there was no significant difference in reporting time identified between VR and CD (P = 0.61). CONCLUSIONS: Overall, VR slightly decreases the reporting efficiency of radiologists. However, efficiency may be improved if English is a first language, a headset microphone, and macros and templates are used.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it