Point-of-care wound visioning technology: Reproducibility and accuracy of a wound measurement app
Bibliographic record
Abstract
BACKGROUND: Current wound assessment practices are lacking on several measures. For example, the most common method for measuring wound size is using a ruler, which has been demonstrated to be crude and inaccurate. An increase in periwound temperature is a classic sign of infection but skin temperature is not always measured during wound assessments. To address this, we have developed a smartphone application that enables non-contact wound surface area and temperature measurements. Here we evaluate the inter-rater reliability and accuracy of this novel point-of-care wound assessment tool. METHODS AND FINDINGS: The wounds of 87 patients were measured using the Swift Wound app and a ruler. The skin surface temperature of 37 patients was also measured using an infrared FLIR™ camera integrated with the Swift Wound app and using the clinically accepted reference thermometer Exergen DermaTemp 1001. Accuracy measurements were determined by assessing differences in surface area measurements of 15 plastic wounds between a digital planimeter of known accuracy and the Swift Wound app. To evaluate the impact of training on the reproducibility of the Swift Wound app measurements, three novice raters with no wound care training, measured the length, width and area of 12 plastic model wounds using the app. High inter-rater reliabilities (ICC = 0.97-1.00) and high accuracies were obtained using the Swift Wound app across raters of different levels of training in wound care. The ruler method also yielded reliable wound measurements (ICC = 0.92-0.97), albeit lower than that of the Swift Wound app. Furthermore, there was no statistical difference between the temperature differences measured using the infrared camera and the clinically tested reference thermometer. CONCLUSIONS: The Swift Wound app provides highly reliable and accurate wound measurements. The FLIR™ infrared camera integrated into the Swift Wound app provides skin temperature readings equivalent to the clinically tested reference thermometer. Thus, the Swift Wound app has the advantage of being a non-contact, easy-to-use wound measurement tool that allows clinicians to image, measure, and track wound size and temperature from one visit to the next. In addition, this tool may also be used by patients and their caregivers for home monitoring.
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 | 0.038 | 0.088 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".