AI and Social Determinants of Health in Health Care: A Personal Perspective.

As a biomedical data scientist, when I think of the future of artificial intelligence in health care, the potential fills me with both excitement and caution. A promising area of innovation, AI can be used to assess the impact of social determinants of health on health outcomes, though more standardization is needed.

Clinical usability of deep learning-based saliency maps for occlusion myocardial infarction identification from the prehospital 12-Lead electrocardiogram.

Introduction: Deep learning (DL) models offer improved performance in electrocardiogram (ECG)-based classification over rule-based methods. However, for widespread adoption by clinicians, explainability methods, like saliency maps, are essential.

Methods: On a subset of 100 ECGs from patients with chest pain, we generated saliency maps using a previously validated convolutional neural network for occlusion myocardial infarction (OMI) classification.

Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting.

Accurate identification of acute coronary syndrome (ACS) in the prehospital sestting is important for timely treatments that reduce damage to the compromised myocardium. Current machine learning approaches lack sufficient performance to safely rule-in or rule-out ACS. Our goal is to identify a method that bridges this gap.

Challenges & barriers for real-time integration of drones in emergency cardiac care: Lessons from the United States, Sweden, & Canada.

Importance: Out-of-hospital cardiac arrest (OHCA) is a leading cause of morbidity and mortality in the US and Europe (∼600,000 incident events annually) and around the world (∼3.8 million). With every minute that passes without cardiopulmonary resuscitation or defibrillation, the probability of survival decreases by 10%.

Emergency Nurses' Recognition of and Perception of Sex Differences in Acute Coronary Syndrome Symptoms.

Introduction: Emergency nurses must quickly identify patients with potential acute coronary syndrome. However, no recent nationwide research has explored nurses' knowledge of acute coronary syndrome symptoms. The purpose of this study was to explore emergency nurses' recognition of acute coronary syndrome symptoms, including whether nurses attribute different symptoms to women and men.

Ventricular tachycardia and in-hospital mortality in the intensive care unit.

Background: Continuous electrocardiographic (ECG) monitoring is used to identify ventricular tachycardia (VT), but false alarms occur frequently.

Objective: The purpose of this study was to assess the rate of 30-day in-hospital mortality associated with VT alerts generated from bedside ECG monitors to those from a new algorithm among intensive care unit (ICU) patients.

Methods: We conducted a retrospective cohort study in consecutive adult ICU patients at an urban academic medical center and compared current bedside monitor VT alerts, VT alerts from a new-unannotated algorithm, and true-annotated VT.

Race-Based Differences in ST-Segment-Elevation Myocardial Infarction Process Metrics and Mortality From 2015 Through 2021: An Analysis of 178 062 Patients From the American Heart Association Get With The Guidelines-Coronary Artery Disease Registry.

Background: Systems of care have been developed across the United States to standardize care processes and improve outcomes in patients with ST-segment-elevation myocardial infarction (STEMI). The effect of contemporary STEMI systems of care on racial and ethnic disparities in achievement of time-to-treatment goals and mortality in STEMI is uncertain.

Methods: We analyzed 178 062 patients with STEMI (52 293 women and 125 769 men) enrolled in the American Heart Association Get With The Guidelines-Coronary Artery Disease registry between January 1, 2015, and December 31, 2021.

Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction.

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI.

Integrating multimodal information in machine learning for classifying acute myocardial infarction.

. Prompt identification and recognization of myocardial ischemia/infarction (MI) is the most important goal in the management of acute coronary syndrome. The 12-lead electrocardiogram (ECG) is widely used as the initial screening tool for patients with chest pain but its diagnostic accuracy remains limited.

An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients.

Background: False ventricular tachycardia (VT) alarms are common during in-hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies.

Purpose: The purpose of this study was: (1) to describe the creation of a VT database annotated by ECG experts and (2) to determine true vs.

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact.

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI.

Patient characteristics and outcomes of acute myocardial infarction presenting without ischemic pain: Insights from the Atherosclerosis Risk in Communities Study.

Background: Our objective was to describe characteristics of patients presenting with and without ischemic pain among those diagnosed with acute myocardial infarction (MI) using individual-level data from the Atherosclerosis Risk in Communities Study from 2005 to 2019.

Methods: Acute MI included events deemed definite or probable MI by a physician panel based on ischemic pain, cardiac biomarkers, and ECG evidence. Patient characteristics included age at hospitalization, sex, race/ethnicity, comorbidities (smoking status, diabetes, hypertension, history of previous stroke, MI, or cardiovascular procedure, and history of valvular disease or cardiomyopathy) and in-hospital complications occurring during the event of interest (pulmonary edema, pulmonary embolism, in-hospital stroke, pneumonia, cardiogenic shock, ventricular fibrillation).

Emergency Interhospital Transfer of Patients With ST-Segment-Elevation Myocardial Infarction: Call 9-1-1-The American Heart Association Mission: Lifeline Program.

The American Heart Association Mission: Lifeline program objectives are to improve the quality of care and outcomes for patients with ST-segment-elevation myocardial infarction. Every minute of delay in treatment adversely affects 1-year mortality. Transfer of patients safely and timely to hospitals with primary percutaneous coronary intervention capability is needed to improve outcomes.

Treatment Time and In-Hospital Mortality Among Patients With ST-Segment Elevation Myocardial Infarction, 2018-2021.

Importance: Recognizing the association between timely treatment and less myocardial injury for patients with ST-segment elevation myocardial infarction (STEMI), US national guidelines recommend specific treatment-time goals.

Objective: To describe these process measures and outcomes for a recent cohort of patients.

Design, Setting, And Participants: Cross-sectional study of a diagnosis-based registry between the second quarter of 2018 and the third quarter of 2021 for 114 871 patients with STEMI treated at 648 hospitals in the Get With The Guidelines-Coronary Artery Disease registry.

There is little association between prehospital delay, persistent symptoms, and post-discharge healthcare utilization in patients evaluated for acute coronary syndrome.

Aims: Test for an association between prehospital delay for symptoms suggestive of acute coronary syndrome (ACS), persistent symptoms, and healthcare utilization (HCU) 30-days and 6-months post hospital discharge.

Background: Delayed treatment for ACS increases patient morbidity and mortality. Prehospital delay is the largest factor in delayed treatment for ACS.

Impact of Using Drones in Emergency Medicine: What Does the Future Hold?

The use of unmanned aerial vehicles or "drones" has expanded in the last decade, as their technology has become more sophisticated, and costs have decreased. They are now used routinely in farming, environmental surveillance, public safety, commercial product delivery, recreation, and other applications. Health-related applications are only recently becoming more widely explored and accepted.

Systems of Care for ST-Segment-Elevation Myocardial Infarction: A Policy Statement From the American Heart Association.

The introduction of Mission: Lifeline significantly increased timely access to percutaneous coronary intervention for patients with ST-segment-elevation myocardial infarction (STEMI). In the years since, morbidity and mortality rates have declined, and research has led to significant developments that have broadened our concept of the STEMI system of care. However, significant barriers and opportunities remain.

Prehospital ECG with ST-depression and T-wave inversion are associated with new onset heart failure in individuals transported by ambulance for suspected acute coronary syndrome.

Background: Prehospital electrocardiogram(s) (ECG) can improve early detection of acute coronary syndrome (ST-segment elevation myocardial infarction [STEMI], non-STEMI, and unstable angina) and inform prehospital activation of cardiac catheterization lab; thus, reducing total ischemic time and improving patient outcomes. Less is known, however, about the association of prehospital ECG ischemic findings and long term adverse clinical events. With this in mind, this study was designed to examine the: 1) frequency of prehospital ECGs for acute myocardial ischemia (ST-elevation, ST-depression, and/or T-wave inversion); and, 2) whether any of these specific ECG features are associated with adverse clinical events within 30 day of initial presentation to the emergency department (ED).

Disparities in Emergency Medical Services Time Intervals for Patients with Suspected Acute Coronary Syndrome: Findings from the North Carolina Prehospital Medical Information System.

Background Timely emergency medical services (EMS) response, management, and transport of patients with suspected acute coronary syndrome (ACS) significantly reduce delays to emergency treatment and improve outcomes. We evaluated EMS response, scene, and transport times and adherence to proposed time benchmarks for patients with suspected ACS in North Carolina from 2011 to 2017. Methods and Results We conducted a population-based, retrospective study with the North Carolina Prehospital Medical Information System, a statewide electronic database of all EMS patient care reports.

Out-of-Hospital Cardiac Arrest Bystander Defibrillator Search Time and Experience With and Without Directional Assistance: A Randomized Simulation Trial in a Community Setting.

Introduction: Probability of survival after out-of-hospital cardiac arrest (OHCA) doubles when a bystander initiates cardiopulmonary resuscitation and uses an automated external defibrillator (AED) rapidly. National, state, and community efforts have increased placement of AEDs in public spaces; however, bystander AED use remains less than 2% in the United States. Little is known about the effect of giving bystanders directional assistance to the closest public access AED.

Delivery of Automated External Defibrillators via Drones in Simulated Cardiac Arrest: Users' Experiences and the Human-Drone Interaction.

Background: Survival after out-of-hospital cardiac arrest (OHCA) in the United States is approximately 10%. Automatic external defibrillators (AEDs) are effective when applied early, yet public access AEDs are used in <2% of OHCAs. AEDs are often challenging for bystanders to locate and are rarely available in homes, where 70% of OHCAs occur.

Unusual Fatigue and Failure to Utilize EMS Are Associated With Prolonged Prehospital Delay for Suspected Acute Coronary Syndrome.

Background: Rapid reperfusion reduces infarct size and mortality for acute coronary syndrome (ACS), but efficacy is time dependent. The aim of this study was to determine if transportation factors and clinical presentation predicted prehospital delay for suspected ACS, stratified by final diagnosis (ACS vs. no ACS).

Typical and Atypical Symptoms of Acute Coronary Syndrome: Time to Retire the Terms?

Studies indicate that symptoms labeled as "atypical" are more common in women evaluated for myocardial infarction (MI) and may contribute to the lower likelihood of a diagnosis and delayed treatment and result in poorer outcomes compared with men with MI. Atypical pain is frequently defined as epigastric or back pain or pain that is described as burning, stabbing, or characteristic of indigestion. Typical symptoms usually include chest, arm, or jaw pain described as dull, heavy, tight, or crushing.