Stability is a critical consideration in the implementation of an automatic algorithm. Some measurements can typically be more accurate than expert manual measurements but still make large errors in the presence of co...
Stability is a critical consideration in the implementation of an automatic algorithm. Some measurements can typically be more accurate than expert manual measurements but still make large errors in the presence of confounders. This can be especially true in situations where signal averaging or high sampling rates are present, there is a low signal to noise ratio or there is an atypical morphology. When a consistent accurate measurement is difficult to make manually, then it is also difficult to manually validate that measurement's automatic measurement. This increases the criticality of stability further. JTp Measurements with high natural variability (like R to R intervals) need to have their stability evaluated with respect to truth annotations. Measurements that change more slowly like JTp can be evaluated even in the absence of truth annotations. Slow change allows one to substitute consistency for stability. First we measure JTp consistency over time under near ideal conditions. Then we repeat the analysis in the presence of different categories of confounders. Each test set's lessened consistency helps to illuminate the algorithm's difficulty with the properties common to that test set. Methods We used the PhysioNet QT Database. Additionally Noise Stress Test data was added to the records in controlled amounts. Measurement consistency was calculated in each test set. To relate the impact of variation on performance accuracy in each of those test sets, QTe measurements are also performed. Calculating JTp relative consistency with respect to the companion algorithm's annotated QTe measurement's consistency normalizes the analysis. This relates the analysis to a better understood measurement. Results It was found that changing from QTe to JTe generally increased the variability of the intervals over a record. The combined record average fared worse than the median due to an increased number of outliers. Similarly changing from QTe to QTp resulted in higher overa
ECG detection of ST-segment Elevation Myocardial Infarction (STEMI) in the presence of left bundle-branch block (LBBB) has long been a challenge. The purpose of this study was to add Selvester criteria (the 10% rule) ...
详细信息
ISBN:
(纸本)9781424473182
ECG detection of ST-segment Elevation Myocardial Infarction (STEMI) in the presence of left bundle-branch block (LBBB) has long been a challenge. The purpose of this study was to add Selvester criteria (the 10% rule) to Sgarbossa criteria for further improved detection of STEMI in LBBB and report the combined performance. Source data of the study group (143 with acute MI and 239 controls) comes from multiple sources. Elements of the Sgarbossa criteria and Selvester criteria (ST elevation ≥ 10% of |S|-|R| plus STEMI limits) were tested separately and in combination with the Sgarbossa discordant ST elevation replaced by the 10% rule. The combined Sgarbossa and Selvester criteria improved the sensitivity to 39%, specificity to 89%, positive likelihood ratio to 3.6 and the negative likelihood ratio to 0.68 compared with 30% sensitivity, 88% specificity, 2.5 positive likelihood ratio and 0.80 negative likelihood ratio with Sgarbossa criteria alone.
The bull's eye plot has been successfully introduced in multiple cardiac imaging diagnostic modalities and standardized by AHA in recent years. The ECG estimated myocardial infarct (MI) size is a quantitative meas...
详细信息
ISBN:
(纸本)9781424473182
The bull's eye plot has been successfully introduced in multiple cardiac imaging diagnostic modalities and standardized by AHA in recent years. The ECG estimated myocardial infarct (MI) size is a quantitative measure of the size of the infarct region in left ventricular myocardium and is a proven tool to assist cardiologists in clinical decision making. MI size has been presented as a percentage of the left ventricle (LV) mass based on Selvester ECG scoring system. The scoring system has 50 ECG criteria with corresponding points. The reported MI size is not associated with a specific location in LV. This study applied the Selvester scoring system and bull's eye plot to create a quantitative MI size presentation with visual location in the LV. The automated Selvester scoring algorithm was validated using a database of 688 ECGs with and without MI. The automated ECG-MI size was tested against two cardiologists' manual scores resulting in 94% correlation.
暂无评论