No abstract

The accuracy of wrist worn heart rate monitors based on photoplethysmography (PPG) is not fully clinically accepted. Therefore, we aimed to validate heart rate measurements of a commercially available PPG heart rate monitor, i.e. the Garmin Forerunner 225. Twelve healthy volunteers (six women; mean age: 28 years) performed a treadmill protocol consisting of: five minutes sitting, five minutes standing, 10 minutes walking at 4 km/h, 10 minutes walking at a gradient of 5% and intensity of 4-6 metabolic equivalents (METs), 10 minutes walking at a gradient of 8% and intensity of seven METs or more. Walking speeds were individually determined. Walking bouts were separated by a standardised five minute rest period. Heart rate was measured as the average of the last three minutes standing and of each walking bout. A three lead patch-based electrocardiogram (ECG; Zensor) was used as criterion method. Statistical analyses included Pearson's correlation (r), paired t-tests, root mean squared error (RMSE) and Bland?Altman plots. The mean values per three minutes of every condition did not differ significantly between the Garmin Forerunner 225 and the Zensor. RMSE was 3.01 beats per minute (bpm) or 2.89%. The Bland-Altman bias was 1.57 bpm. Limits of agreement (LoA) were wide, ranging from 32.53 to 29.40 bpm. However, Pearson's r ranged from 0.650 to 0.868 suggesting moderate to strong validity. Generally, mean heart rates, r values, RMSE and the Bland-Altman bias indicated good overall agreement in this sample of healthy adults, but wide LoA are making it difficult to trust individual measurements.

Automated detection of AF from the electrocardiogram (ECG) still remains a challenge. In this study we investigated two multivariate based classification techniques, Random Forests ( ) and k-nearest neighbor ( − ), for improved automated detection of AF from the ECG. We have compiled a new database from ECG data taken from existing sources. R-R intervals were then analyzed using four previously described R-R irregularity measurements:(1) The coefficient of sample entropy ( ) (2) The coefficient of variance ( ) (3) Root mean square of the successive differences ( ) and (4) median absolute deviation ( ). Using outputs from all four R-R irregularity measurements and − models were trained. RF classification improved AF detection over with overall specificity of 80.1% vs. 98.3% and positive predictive value of 51.8% vs. 92.1% with a reduction in sensitivity, 97.6% vs. 92.8%. − also improved specificity and PPV over however the sensitivity of this approach was considerably reduced (68.0%).

Vectorcardiograpic (VCG) parameters can supplement the diagnostic information of the 12-lead electrocardiogram (ECG). Nevertheless, the VCG is seldom recorded in modern-day practice. A common approach today is to derive the Frank VCG from the standard 12-lead ECG (distal limb electrode positions). There is, to date no direct method that allows for a transformation from 12-lead ECGs with proximal limb electrode positions (Mason-Likar (ML) 12-lead ECG), to Frank VCGs. In this research, we develop such a transformation (ML2VCG) by means of multivariate linear regression on a training data set of 545 ML 12-lead ECGs and corresponding Frank VCGs that were both extracted surface potential maps (BSPMs). We compare the performance of the ML2VCG method against an alternative approach (2step method) that utilizes two existing transformations that are applied consecutively (ML 12-lead ECG to standard 12-lead ECG and subsequently to Frank VCG). We quantify the performance of ML2VCG and 2step on an unseen test dataset (181 ML 12-lead ECGs and corresponding Frank VCGs again extracted from BSPMs) through root mean squared error (RMSE) values, calculated over the QRST, between actual and transformed Frank leads. The ML2VCG transformation achieved a reduction of the median RMSE values for leads X (13.9µV; p<.001), Y (15.1µV; p<.001) and Z (2.6µV; p=.001) when compared to the 2step transformation. Our results show that the 2step method may not be optimal when transforming ML 12-lead ECGs to Frank VCGs. The utilization of the herein developed ML2VCG transformation should thus be considered when transforming ML 12-lead ECGs to Frank VCGs.

No abstract

No abstract

Incorrect ADs reduce the interpreter's diagnostic accuracy indicating an automation bias. Non-CFs tend to agree more with the ADs in comparison to CFs, hence less expert physicians are more effected by automation bias. Incorrect ADs reduce the interpreter's confidence and also reduces the predictive power of confidence for predicting accuracy (even more so for non-CFs). Whilst a statistically significant model was developed, it is difficult to predict interpretation accuracy using machine learning on basic features such as interpreter confidence, age, reader experience and designation.

No abstract