The HS versus MS model, containing 12 features, achieved a blind accuracy of 0.772 955% CI 0.617 0.886) and an AUC of 0.842, as seen in Figure 4.
The 21 p-ranked features model for the HS versus CS subset achieved a blind accuracy of 0.797 955% CI 0.692 0.895) and an AUC of 0.882 as shown in Figure 4.
It is not however deemed possible to keep project staff tracking data collection for secondary outcomes (self reported outcomes) blinded to condition so the trial will only have double blind accuracy with respect to primary outcomes.
In addition to outcome measures, other variables analysed were age, sex, whether the injectate was intra-bursal or extra-bursal, duration of pain, opioid usage, adequacy of blinding, accuracy of injection, and obesity (body mass index ≥30).
The HS versus MS with z-transformation generated sixteen features and resulted in a blind test accuracy of 0.698 955% CI 0.557 0.879) and an AUC of 0.807.
The 12 feature model obtained for the HS versus CS classification, using the z-transformation, achieved a blind test accuracy of 0.825 955% CI 0.727 0.909) and an AUC of 0.882, as shown in Figure 5.
Because CAMEO evaluates blind prediction accuracy on prereleased target proteins, CAMEO data is well suited to demonstrate a method's performance in publications by means of an independent direct benchmark.
The results presented in this paper formed part of a wider prospective, blinded diagnostic accuracy study in which clinical examination and imaging variables (index tests) were compared with results of diagnostic injections of local anaesthetic (reference standard) into the SAB, ACJ and GHJ.
Quality assessment included a scoring of the following components: definition of study population, the likelihood of bias, adequate blinding, the accuracy of outcome measurements, duration of follow-up and selective loss-to follow-up, the appropriateness of the statistical analysis and the clinical relevance.
Blind tests demonstrated the accuracy of the prediction of actual annealing temperatures within ±0.5 °C.
Conventional localization methods usually suffer from different limitations, such as low accuracy and blind areas for Global Positioning System (GPS), high cost for Inertial Navigation System (INS), and low robustness for vision Simultaneously Localization and Mapping (vSLAM).
