A Two-Step Approach to Overcoming Data Imbalance in the Development of an Electrocardiography Data Quality Assessment Algorithm: A Real-World Data Challenge.

Continuously acquired biosignals from patient monitors contain significant amounts of unusable data. During the development of a decision support system based on continuously acquired biosignals, we developed machine and deep learning algorithms to automatically classify the quality of ECG data. A total of 31,127 twenty-s ECG segments of 250 Hz were used as the training/validation dataset. Data quality was categorized into three classes: acceptable, unacceptable, and uncertain. In the training/validation dataset, 29,606 segments (95%) were in the acceptable class. Two one-step, three-class approaches and two two-step binary sequential approaches were developed using random forest (RF) and two-dimensional convolutional neural network (2D CNN) classifiers. Four approaches were tested on 9779 test samples from another hospital. On the test dataset, the two-step 2D CNN approach showed the best overall accuracy (0.85), and the one-step, three-class 2D CNN approach showed the worst overall accuracy (0.54). The most important parameter, precision in the acceptable class, was greater than 0.9 for all approaches, but recall in the acceptable class was better for the two-step approaches: one-step (0.77) vs. two-step RF (0.89) and one-step (0.51) vs. two-step 2D CNN (0.94) (p < 0.001 for both comparisons). For the ECG quality classification, where substantial data imbalance exists, the 2-step approaches showed more robust performance than the one-step approach. This algorithm can be used as a preprocessing step in artificial intelligence research using continuously acquired biosignals.

Synaptic correlates of associative fear memory in the lateral amygdala.

Successful adaptation to the environment requires an accurate response to external threats by recalling specific memories. Memory formation and recall require engram cell activity and synaptic strengthening among activated neuronal ensembles. However, elucidation of the underlying neural substrates of associative fear memory has remained limited without a direct interrogation of extinction-induced changes of specific synapses that encode a specific auditory fear memory. Using dual-eGRASP (enhanced green fluorescent protein reconstitution across synaptic partners), we found that synapses among activated neuronal ensembles or activated synaptic ensembles showed a significantly larger spine morphology at auditory cortex (AC)-to-lateral amygdala (LA) projections after auditory fear conditioning in mice. Fear extinction reversed these enhanced synaptic ensemble spines, whereas re-conditioning with the same tone and shock restored the spine size of the synaptic ensemble. We suggest that synaptic ensembles encode and represent different fear memory states.