A High-Precision Machine Learning Algorithm to Classify Left and Right Outflow Tract Ventricular Tachycardia.

INTRODUCTION: Multiple algorithms based on 12-lead ECG measurements have been proposed to identify the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT) locations from which ventricular tachycardia (VT) and frequent premature ventricular complex (PVC) originate. However, a clinical-grade machine learning algorithm that automatically analyzes characteristics of 12-lead ECGs and predicts RVOT or LVOT origins of VT and PVC is not currently available. The effective ablation sites of RVOT and LVOT, confirmed by a successful ablation procedure, provide evidence to create RVOT and LVOT labels for the machine learning model. METHODS: We randomly sampled training, validation, and testing data sets from 420 patients who underwent successful catheter ablation (CA) to treat VT or PVC, containing 340 (81%), 38 (9%), and 42 (10%) patients, respectively. We iteratively trained a machine learning algorithm supplied with 1,600,800 features extracted via our proprietary algorithm from 12-lead ECGs of the patients in the training cohort. The area under the curve (AUC) of the receiver operating characteristic curve was calculated from the internal validation data set to choose an optimal discretization cutoff threshold. RESULTS: The proposed approach attained the following performance: accuracy (ACC) of 97.62 (87.44-99.99), weighted F1-score of 98.46 (90-100), AUC of 98.99 (96.89-100), sensitivity (SE) of 96.97 (82.54-99.89), and specificity (SP) of 100 (62.97-100). CONCLUSIONS: The proposed multistage diagnostic scheme attained clinical-grade precision of prediction for LVOT and RVOT locations of VT origin with fewer applicability restrictions than prior studies.

Anesthesia information management systems: past, present, and future of anesthesia records.

Documenting a patient's anesthetic in the medical record is quite different from summarizing an office visit, writing a surgical procedure note, or recording other clinical encounters. Some of the biggest differences are the frequent sampling of physiologic data, volume of data, and diversity of data collected. The goal of the anesthesia record is to accurately and comprehensively capture a patient's anesthetic experience in a succinct format. Having ready access to physiologic trends is essential to allowing anesthesiologists to make proper diagnoses and treatment decisions. Although the value provided by anesthesia information management systems and their functions may be different than other electronic health records, the real benefits of an anesthesia information management system depend on having it fully integrated with the other health information technologies. An anesthesia information management system is built around the electronic anesthesia record and incorporates anesthesia-relevant data pulled from disparate systems such as laboratory, billing, imaging, communication, pharmacy, and scheduling. The ability of an anesthesia information management system to collect data automatically enables anesthesiologists to reliably create an accurate record at all times, regardless of other concurrent demands. These systems also have the potential to convert large volumes of data into actionable information for outcomes research and quality-improvement initiatives. Developing a system to validate the data is crucial in conducting outcomes research using large datasets. Technology innovations outside of healthcare, such as multitouch interfaces, near-instant software response times, powerful but simple search capabilities, and intuitive designs, have raised the bar for users' expectations of health information technology.

Alarm limit settings for early warning systems to identify at-risk patients.

AIM: This paper is a report of a study conducted to provide objective data to assist with setting alarm limits for early warning systems. BACKGROUND: Early warning systems are used to provide timely detection of patient deterioration outside of critical care areas, but with little data from the general ward population to guide alarm limit settings. Monitoring systems used in critical care areas are known for excellent sensitivity in detecting signs of deterioration, but give high false positive alarm rates, which are managed with nurses caring for two or fewer patients. On general wards, nurses caring for four or more patients will be unable to manage a high number of false alarms. Physiological data from a general ward population would help to guide alarm limit settings. METHODS: A dataset of continuous heart rate and respiratory rate data from a general ward population, previously collected from July 2003-January 2006, was analyzed for adult patients with no severe adverse events. Dataset modeling was constructed to analyze alarm frequency at varying heart rate and respiratory rate alarm limits. RESULTS: A total of 317 patients satisfied the inclusion criteria, with 780.71 days of total monitoring. Sample alarm settings appeared to optimize false positive alarm rates for the following settings: heart rate high 130-135, low 40-45; respiratory rate high 30-35, low 7-8. Rates for each selected limit can be added to calculate the total alarm frequency, which can be used to judge the impact on nurse workflow. CONCLUSION: Alarm frequency data will assist with evidence-based configuration of alarm limits for early warning systems.