Article Figures & Data
Figures
- Figure 1. A–G Workflow of ThinkSono Guidance (it guides the operator through anatomical landmarks and indicates when to compress. ThinkSono Guidance analyses the images, and provides a remote diagnosis)
- Figure 2. Flowchart
Tables
ACEP score 1 No recognisable structures, no objective data can be gathered 2 Minimally recognisable structures, but insufficient for diagnosis 3 Minimal criteria met for diagnosis, recognisable structures but with some technical or other flaws 4 Minimal criteria met for diagnosis, all structures images well and diagnosis supported easily 5 Minimal criteria met for diagnosis, all structures images with excellent image quality and diagnosis completely supported - Table 2. Remote specialist reported diagnosis, index scan and sonographer diagnosis, and reference scan
Reference scan positive Reference scan negative Index scan positive 9% TP 9% FP Index scan negative 0% FN 83% TN FN = false negative. FP = false positive. TN = true negative. TP = true positive.
All scans Result Image qualitya 75% (68/91) scans with ACEP ≥3 Remote diagnosis 64% (58/91) scans included for diagnosis Risk triagingb 53% (48/91) of participants at low risk Scans considered for remote analysis Image qualitya 91% (68/75) scans with ACEP ≥3 Remote diagnosis 77% (58/75) scans included for diagnosis Risk triagingb 64% (48/75) of participants at low risk aDemonstrating adequate quality for remote interpretation. bSuggesting potential avoidance of a formal scan in secondary care
Risk category Criteria for designation High risk Incomplete examination At least 1 sequence with ACEP <3 Incompressible veins Other reasons deemed by reviewer, for example, considerations for differential diagnosis such as a Baker's Cyst Low risk Complete examination All cine-loop sequences with ACEP ≥3 All veins are identified as compressible ACEP = American College of Emergency Physicians
Supplementary Data
- KN_10.3399BJGPO.2024.0057.pdf -
Supplementary material is not copyedited or typeset, and is published as supplied by the author(s). The author(s) retain(s) responsibility for its accuracy.
In this issue
Evaluating the benefits of machine learning for diagnosing deep vein thrombosis compared with gold standard ultrasound: a feasibility study
LinkedIn
Jump to section
More in this TOC Section
Related Articles
Cited By...
Intended for Healthcare Professionals
