Asynchronous Teleultrasound and In-Person Ultrasound: Comparing Diagnostic Accuracy
Bibliographic record
Abstract
What Is the Issue? Access to ultrasound services remains limited in many parts of Canada, with fewer than 28% of rural hospitals having in-house ultrasound, often resulting in patients being transferred to urban centres. Ultrasound imaging requires highly trained professionals, typically sonographers, for accurate diagnostic exams and interpretation. However, Canada and many other countries are facing a shortage of trained sonographers, which can impact access to timely care. As a portable and radiation-free modality, ultrasound is ideal for real-time soft-tissue imaging, though CT, MRI, and PET-CT may be preferred for more complex cases. Teleultrasound (TUS) has emerged to support an increase in ultrasound demand, particularly in resource-limited environments. TUS can be delivered in real time with remote guidance from a sonographic expert, or images can be sent asynchronously for expert interpretation. TUS can be used by a variety of health care professionals with minimal ultrasound training, but as asynchronous models expand, their comparability to standard in-person ultrasound requires further evaluation. What Did We Do? We received a request related to the use of asynchronous TUS to support policy decision-making. In response, we prepared this rapid review to summarize and critically appraise the available studies on the quality of health care provided with asynchronous TUS (unsupervised ultrasound with remote exam interpretation by an expert) as compared to the traditional service model of ultrasound. A literature search was conducted, limited to English-language reports published since 2019, to identify relevant studies and evidence-based guidelines. A single reviewer screened records for inclusion based on predefined criteria, critically appraised the included studies, extracted relevant data, and summarized the findings. What Did We Find? We found 11 cohort selection cross-sectional studies that examined health care quality (diagnostic accuracy, image quality, and acceptability) across various target conditions. Overall, asynchronous TUS was found to be an alternative method to the standard in-person model of ultrasound for identifying certain targeted conditions, when assessing diagnostic accuracy and exam image quality. Asynchronous TUS was accepted by patients and clinicians, based on a limited number of studies that examined this outcome. Asynchronous TUS was studied in a wide range of clinical indications in various settings, highlighting its growing role and potential for expanded application in clinical practice. There is uncertainty regarding the acceptable balance of sensitivity and specificity for each target condition. The heterogeneity of study results, potential bias, and a limited volume of recent evidence impacts the overall interpretability of findings. What Does This Mean? Asynchronous teleultrasound TUS could improve access to diagnostic imaging, particularly in underserved or low-resource settings where in-person ultrasound services are limited. Wider clinical adoption would depend on establishing standardized training, procedural protocols, and supportive regulatory frameworks to ensure quality, consistency, and patient safety across settings. The evidence shows potential for asynchronous TUS use in clinical practice, but variation in study quality and unclear diagnostic standards mean it should be used cautiously and evaluated carefully within specific clinical contexts. Further research is needed to enhance understanding of patient outcomes, define condition-specific diagnostic accuracy thresholds (i.e., acceptable balance of sensitivity and specificity), and explore the impact on health system performance.
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 | 0.056 | 0.300 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.006 |
| Bibliometrics | 0.010 | 0.010 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".