RESUMO
Aims: European and American clinical guidelines for implantable cardioverter defibrillators are insufficiently accurate for ventricular arrhythmia (VA) risk stratification, leading to significant morbidity and mortality. Artificial intelligence offers a novel risk stratification lens through which VA capability can be determined from the electrocardiogram (ECG) in normal cardiac rhythm. The aim of this study was to develop and test a deep neural network for VA risk stratification using routinely collected ambulatory ECGs. Methods and results: A multicentre case-control study was undertaken to assess VA-ResNet-50, our open source ResNet-50-based deep neural network. VA-ResNet-50 was designed to read pyramid samples of three-lead 24â h ambulatory ECGs to decide whether a heart is capable of VA based on the ECG alone. Consecutive adults with VA from East Midlands, UK, who had ambulatory ECGs as part of their NHS care between 2014 and 2022 were recruited and compared with all comer ambulatory electrograms without VA. Of 270 patients, 159 heterogeneous patients had a composite VA outcome. The mean time difference between the ECG and VA was 1.6 years (â ambulatory ECG before VA). The deep neural network was able to classify ECGs for VA capability with an accuracy of 0.76 (95% confidence interval 0.66-0.87), F1 score of 0.79 (0.67-0.90), area under the receiver operator curve of 0.8 (0.67-0.91), and relative risk of 2.87 (1.41-5.81). Conclusion: Ambulatory ECGs confer risk signals for VA risk stratification when analysed using VA-ResNet-50. Pyramid sampling from the ambulatory ECGs is hypothesized to capture autonomic activity. We encourage groups to build on this open-source model. Question: Can artificial intelligence (AI) be used to predict whether a person is at risk of a lethal heart rhythm, based solely on an electrocardiogram (an electrical heart tracing)? Findings: In a study of 270 adults (of which 159 had lethal arrhythmias), the AI was correct in 4 out of every 5 cases. If the AI said a person was at risk, the risk of lethal event was three times higher than normal adults. Meaning: In this study, the AI performed better than current medical guidelines. The AI was able to accurately determine the risk of lethal arrhythmia from standard heart tracings for 80% of cases over a year away-a conceptual shift in what an AI model can see and predict. This method shows promise in better allocating implantable shock box pacemakers (implantable cardioverter defibrillators) that save lives.
RESUMO
BACKGROUND: A small proportion of lamina I neurons of the spinal cord project upon the hindbrain and are thought to engage descending pathways that modulate the behavioural response to peripheral injury. Early postnatal development of nociception in rats is associated with exaggerated and diffuse cutaneous reflexes with a gradual refinement of responses over the first postnatal weeks related to increased participation of inhibitory networks. This study examined the postnatal development of lamina I projection neurons from postnatal day 3 (P3) until P48. RESULTS: At P3, a subset of lamina I neurons were found to express the neurokinin 1 (NK1) receptor. Using fluorogold retrograde tracing, we found that the NK1 positive neurons projected upon the parabrachial nucleus (PB) within the hindbrain. Using c-fos immunohistochemistry, we showed that lamina I and PB neurons in P3 rats responded to noxious stimulation of the periphery. Finally, ablation of lamina I neurons with substance-P saporin conjugates at P3 resulted in increased mechanical sensitivity from P45 onwards compared to control animals of the same age. CONCLUSIONS: These results suggest that the lamina I pathway is present and functional at least from P3 and required for establishing and fine-tuning mechanical sensitivity in adult rats.