Artificial Intelligence Interpretation of the Electrocardiogram: A State-of-the-Art Review.

PURPOSE OF REVIEW: Artificial intelligence (AI) is transforming electrocardiography (ECG) interpretation. AI diagnostics can reach beyond human capabilities, facilitate automated access to nuanced ECG interpretation, and expand the scope of cardiovascular screening in the population. AI can be applied to the standard 12-lead resting ECG and single-lead ECGs in external monitors, implantable devices, and direct-to-consumer smart devices. We summarize the current state of the literature on AI-ECG. RECENT FINDINGS: Rhythm classification was the first application of AI-ECG. Subsequently, AI-ECG models have been developed for screening structural heart disease including hypertrophic cardiomyopathy, cardiac amyloidosis, aortic stenosis, pulmonary hypertension, and left ventricular systolic dysfunction. Further, AI models can predict future events like development of systolic heart failure and atrial fibrillation. AI-ECG exhibits potential in acute cardiac events and non-cardiac applications, including acute pulmonary embolism, electrolyte abnormalities, monitoring drugs therapy, sleep apnea, and predicting all-cause mortality. Many AI models in the domain of cardiac monitors and smart watches have received Food and Drug Administration (FDA) clearance for rhythm classification, while others for identification of cardiac amyloidosis, pulmonary hypertension and left ventricular dysfunction have received breakthrough device designation. As AI-ECG models continue to be developed, in addition to regulatory oversight and monetization challenges, thoughtful clinical implementation to streamline workflows, avoiding information overload and overwhelming of healthcare systems with false positive results is necessary. Research to demonstrate and validate improvement in healthcare efficiency and improved patient outcomes would be required before widespread adoption of any AI-ECG model.

Complications following symptom-limited thoracentesis using suction.

BACKGROUND: Thoracentesis using suction is perceived to have increased risk of complications, including pneumothorax and re-expansion pulmonary oedema (REPO). Current guidelines recommend limiting drainage to 1.5 L to avoid REPO. Our purpose was to examine the incidence of complications with symptom-limited drainage of pleural fluid using suction and identify risk factors for REPO. METHODS: A retrospective cohort study of all adult patients who underwent symptom-limited thoracentesis using suction at our institution between January 1, 2004 and August 31, 2018 was performed, and a total of 10 344 thoracenteses were included. RESULTS: Pleural fluid ≥1.5 L was removed in 19% of the procedures. Thoracentesis was stopped due to chest discomfort (39%), complete drainage of fluid (37%) and persistent cough (13%). Pneumothorax based on chest radiography was detected in 3.98%, but only 0.28% required intervention. The incidence of REPO was 0.08%. The incidence of REPO increased with Eastern Cooperative Oncology Group performance status (ECOG PS) ≥3 compounded with ≥1.5 L (0.04-0.54%; 95% CI 0.13-2.06 L). Thoracentesis in those with ipsilateral mediastinal shift did not increase complications, but less fluid was removed (p<0.01). CONCLUSIONS: Symptom-limited thoracentesis using suction is safe even with large volumes. Pneumothorax requiring intervention and REPO are both rare. There were no increased procedural complications in those with ipsilateral mediastinal shift. REPO increased with poor ECOG PS and drainage ≥1.5 L. Symptom-limited drainage using suction without pleural manometry is safe.