Syncope-Do We Need AI?

Syncope is a form of transient loss of consciousness (TLOC) resulting from cerebral hypoperfusion and is characterized by rapid onset, short duration and spontaneous complete recovery [...].

Can Artificial Intelligence Enhance Syncope Management?: A JACC: Advances Multidisciplinary Collaborative Statement.

Syncope, a form of transient loss of consciousness, remains a complex medical condition for which adverse cardiovascular outcomes, including death, are of major concern but rarely occur. Current risk stratification algorithms have not completely delineated which patients benefit from hospitalization and specific interventions. Patients are often admitted unnecessarily and at high cost. Artificial intelligence (AI) and machine learning may help define the transient loss of consciousness event, diagnose the cause, assess short- and long-term risks, predict recurrence, and determine need for hospitalization and therapeutic intervention; however, several challenges remain, including medicolegal and ethical concerns. This collaborative statement, from a multidisciplinary group of clinicians, investigators, and scientists, focuses on the potential role of AI in syncope management with a goal to inspire creation of AI-derived clinical decision support tools that may improve patient outcomes, streamline diagnostics, and reduce health-care costs.

Novel Machine Learning Approach to Predict and Personalize Length of Stay for Patients Admitted with Syncope from the Emergency Department.

Background: Syncope, a common problem encountered in the emergency department (ED), has a multitude of causes ranging from benign to life-threatening. Hospitalization may be required, but the management can vary substantially depending on specific clinical characteristics. Models predicting admission and hospitalization length of stay (LoS) are lacking. The purpose of this study was to design an effective, exploratory model using machine learning (ML) technology to predict LoS for patients presenting with syncope. Methods: This was a retrospective analysis using over 4 million patients from the National Emergency Department Sample (NEDS) database presenting to the ED with syncope between 2016−2019. A multilayer perceptron neural network with one hidden layer was trained and validated on this data set. Results: Receiver Operator Characteristics (ROC) were determined for each of the five ANN models with varying cutoffs for LoS. A fair area under the curve (AUC of 0.78) to good (AUC of 0.88) prediction performance was achieved based on sequential analysis at different cutoff points, starting from the same day discharge and ending at the longest analyzed cutoff LoS ≤7 days versus >7 days, accordingly. The ML algorithm showed significant sensitivity and specificity in predicting short (≤48 h) versus long (>48 h) LoS, with an AUC of 0.81. Conclusions: Using variables available to triaging ED clinicians, ML shows promise in predicting hospital LoS with fair to good performance for patients presenting with syncope.

The Mysterious Case of an Athletic Woman with Recurrent Syncope and a "Normal" Heart.

A 53-year-old female with a history of sports participation presented to a community hospital emergency department for collapse. She was given a LifeVest® wearable cardioverter-defibrillator (WCD) (Zoll Medical Corp., Chelmsford, MA, USA) and scheduled to undergo cardiac magnetic resonance imaging (MRI) with gadolinium enhancement at a tertiary center. However, before the scheduled MRI scan could be performed, she developed tachycardia, for which the WCD alarmed. A dual-chamber implantable cardioverter-defibrillator was subsequently implanted. Assessment of a patient with syncope requires consideration of the idea that a life-threatening and recurrent arrhythmia may be a cause for the problem. However, current guidelines do not cover the routine use of WCDs in syncope. Additionally, the patient described here did not clearly meet United States Food and Drug Administration indications for the provision of an external defibrillator. We present this case to provoke discussion among colleagues regarding this patient's treatment plan.

Left atrial mechanical responses to right ventricular pacing in heart failure patients: implications for atrial fibrillation.

BACKGROUND: RV pacing (RVP), even with preserved atrioventricular (AV) synchrony, may lead to left atrial (LA) enlargement and atrial fibrillation. However, inciting events are unknown. We hypothesized that RVP acutely impairs LA function by mechanisms affecting atrial contraction and/or ventricular diastole. METHODS: LA function in ICD patients (n = 31, LVEF ≤ 40%) and controls (n = 14, LVEF > 50%) was contrasted between intrinsic conduction versus RVP during asynchronous (ICD, n = 17, control, n = 7), and synchronous (ICD, n = 14, control, n = 14) pacing at long (LAVd, 107 ±16 ms) and short (SAVd, 31 ± 5 ms) AV delays. LA maximal volume (LA(Max)), minimal volume (LA(Min)), and emptying fraction {LA(EmF) = (LA(Max) -LA(Min))/LA(Max)} were measured echocardiographically. Six-segment mean mitral annular tissue doppler E' (global E') assessed diastolic recoil during baseline and LAVd. RESULTS: In the ICD group, LA(Min) increased by 42% (P < 0.0009) during VVI, by 31% (P = 0.0002) during SAVd, and by 17% (P < 0.0007) during LAVd. LA(EmF) decreased by 44% (P < 0.0008), 27% (P < 0.0001), and by 15% (P = 0.003) during VVI, SAVd, and LAVd respectively. LA(Max) was unaltered. Global E' was reduced by 12%. In control, LA(Min) increased and LA(EmF) decreased significantly during VVI (82 and 58%) and SAVd (46 and 41%), but not during LAVd. CONCLUSION: In patients with LV dysfunction, RVP acutely impaired LA emptying, and increased minimal volume, most prominently when atrial contraction was impeded (VVI, DDD-SAVd) but also when completed (DDD-LAVd), indicating impaired diastolic recoil as an important mechanism. When LV function was normal, similar changes were present when atrial filling is impeded (VVI, SAVd), but not when completed (LAVd).