Baby steps in the path of modifying the role of cardiologists for interpreting EKG for AMI

Abstract Background EKG interpretation is slowly transitioning to a physician-free, Artificial Intelligence (AI)-driven endeavor. Our continued efforts to innovate follow a carefully laid stepwise approach, as follows: 1) Create an AI algorithm that accurately identifies STEMI against non-STEMI using a 12-lead EKG; 2) Challenging said algorithm by including different EKG diagnosis to the previous experiment, and now 3) To further validate the accuracy and reliability of our algorithm while also improving performance in a prehospital and hospital settings. Purpose To provide an accurate, reliable, and cost-effective tool for STEMI detection with the potential to redirect human resources into other clinically relevant tasks and save the need for human resources. Methods Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10-seconds length with sampling frequency of 500 [Hz], including the following balanced classes: unconfirmed and angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding the ones included in other classes). The label of each record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: The first and last 250 samples were discarded as they may contain a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI (STEMI in different locations of the myocardium – anterior, inferior and lateral); Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10; respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original dataset of angiographically confirmed STEMI. Results See Figure Attached – Preliminary STEMI Dataset Accuracy: 96.4%; Sensitivity: 95.3%; Specificity: 97.4% – Confirmed STEMI Dataset: Accuracy: 97.6%; Sensitivity: 98.1%; Specificity: 97.2%. Conclusions Our results remain consistent with our previous experience. By further increasing the amount and complexity of the data, the performance of the model improves. Future implementations of this technology in clinical settings look promising, not only in performing swift screening and diagnostic steps but also partaking in complex STEMI management triage. Funding Acknowledgement Type of funding source: None

Download Full-text

On: S. Hammer’s replies to N. C. Steenland, A. T. Herring, and W. C. Pearson’s discussions of “Airborne gravity is here” (GEOPHYSICS, 49, 310–311, March 1984; and 49, 470–477, April 1984).

Geophysics ◽

10.1190/1.1441831 ◽

1985 ◽

Vol 50 (1) ◽

pp. 170-170

Author(s):

M. J. Hall

Keyword(s):

Ground Truth ◽

New Method ◽

Airborne Gravity ◽

Pass Filter ◽

Low Pass Filter ◽

Low Pass

Hammer’s replies to Steenland’s, Herring’s and Pearson’s discussions of his paper, “Airborne gravity is here!,” are nothing short of incredulous. Both his paper and his replies would suggest that he did not expect those with experience in dynamic gravity to read them. Hammer accuses his critics of ignoring “…the low‐pass filter which was applied for realistic comparison with the airborne data.” I shall call this “Hammer’s Rule:” you filter the very standard against which you will compare any new method without concern for the truth. Hammer’s Rule frees us from annoyingly difficult rigor. If the airborne filter eliminates the anomaly, then so must the ground truth anomaly be eliminated. Fair is fair, and Hammer’s Rule gives a “realistic comparison” between something which is wrong and something which is wrong.

Download Full-text

Enhancing AI-guided STEMI detection algorithms by incorporating higher quality fiduciary EKG elements

European Heart Journal ◽

10.1093/ehjci/ehaa946.3554 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

S Mehta ◽

J Avila ◽

S Niklitschek ◽

F Fernandez ◽

C Villagran ◽

...

Keyword(s):

Performance Indicators ◽

Performance Metrics ◽

Ground Truth ◽

Machine Learning Techniques ◽

Dense Layer ◽

Detection Algorithms ◽

Complete Dataset ◽

Low Pass ◽

Normal Branch ◽

Low Pass Filters

Abstract Background As EKG interpretation paradigms to a physician-free milieu, accumulating massive quantities of distilled pre-processed data becomes a must for machine learning techniques. In our pursuit of reducing ischemic times in STEMI management, we have improved our Artificial Intelligence (AI)-guided diagnostic tool by following a three-step approach: 1) Increase accuracy by adding larger clusters of data. 2) Increase the breadth of EKG classifications to provide more precise feedback and further refine the inputs which ultimately reflects in better and more accurate outputs. 3) Improving the algorithms' ability to discern between cardiovascular entities reflected in the EKG records. Purpose To bolster our algorithm's accuracy and reliability for electrocardiographic STEMI recognition. Methods Dataset: A total of 7,286 12-lead EKG records of 10-seconds length with a sampling frequency of 500 Hz obtained from Latin America Telemedicine Infarct Network from April 2014 to December 2019. This included the following balanced classes: angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Labels of each record were manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. Order 5 digital low pass filters with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: Determined classes were “STEMI” and “Not-STEMI” (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original complete dataset of unconfirmed STEMI. Performance indicators (accuracy, sensitivity, and specificity) were calculated for each model and results were compared with our previous findings from past experiments. Results Complete STEMI data: Accuracy: 95.9% Sensitivity: 95.7% Specificity: 96.5%; Confirmed STEMI: Accuracy: 98.1% Sensitivity: 98.1% Specificity: 98.1%; Prior Data obtained in our previous experiments are shown below for comparison. Conclusion(s) After the addition of clustered pre-processed data, all performance indicators for STEMI detection increased considerably between both Confirmed STEMI datasets. On the other hand, the Complete STEMI dataset kept a strong and steady set of performance metrics when compared with past results. These findings not only validate the consistency and reliability of our algorithm but also connotes the importance of creating a pristine dataset for this and any other AI-derived medical tools. Funding Acknowledgement Type of funding source: None

Download Full-text

Trajectory Measurement of Radial Jet Drilling Wells: Improved Tool and Data Processing

Journal of Energy Resources Technology ◽

10.1115/1.4044622 ◽

2019 ◽

Vol 142 (3) ◽

Cited By ~ 1

Author(s):

Zhe Huang ◽

Zhongwei Huang ◽

Long Wu ◽

Yinao Su ◽

Chunyang Hong

Keyword(s):

Moving Average ◽

Cost Effective ◽

Circuit Board ◽

Pass Filter ◽

Low Pass Filter ◽

Failure Risk ◽

Time Operation ◽

Low Pass ◽

Current Design ◽

Trajectory Measurement

Abstract Drilling by high-pressure liquid jet, radial jet drilling (RJD) is a cost-effective technology to restimulate the production of old wells and the development of unconventional reservoirs. However, due to the unique process of 90 deg turning in the casing, hardly any traditional tool can be applied in the RJD trajectory measurement. Even minitools have been developed in the last few years; the increasing cost and unpredictable failure risk of lateral re-entrance are still non-negligible as the current design, much less than the huge measuring errors. In this paper, a new tool was proposed. Based on a special-shaped circuit board and separation of the supporting section, a fluid passageway was reserved in the measuring section to realize the measurement while or after the jet drilling without extra trips. It reduces the cost and failure risk of lateral re-entrance. Ample space in the supporting section was also provided, which meets the long-time operation requirements and establishes the base for real-time communication and trajectory control. Based on noise analyses, random walk is the main source of system noise in short-time measurements, and the effective measuring frequency is mostly in the range of 0–5 Hz. Therefore, autoregressive moving average (ARMA) models, Kalman filter, and low-pass filter were established for denoising. It allows us to analyze the data feature in more detail and extract the valid measuring data with improved accuracy. Considering performance tests result, the average errors of reckoned parameters were improved to less than 15%.

Download Full-text