Real-time arrhythmia detection using convolutional neural networks.

Cardiovascular diseases, such as heart attack and congestive heart failure, are the leading cause of death both in the United States and worldwide. The current medical practice for diagnosing cardiovascular diseases is not suitable for long-term, out-of-hospital use. A key to long-term monitoring is the ability to detect abnormal cardiac rhythms, i.e., arrhythmia, in real-time. Most existing studies only focus on the accuracy of arrhythmia classification, instead of runtime performance of the workflow. In this paper, we present our work on supporting real-time arrhythmic detection using convolutional neural networks, which take images of electrocardiogram (ECG) segments as input, and classify the arrhythmia conditions. To support real-time processing, we have carried out extensive experiments and evaluated the computational cost of each step of the classification workflow. Our results show that it is feasible to achieve real-time arrhythmic detection using convolutional neural networks. To further demonstrate the generalizability of this approach, we used the trained model with processed data collected by a customized wearable sensor from a lab setting, and the results shown that our approach is highly accurate and efficient. This research provides the potentials to enable in-home real-time heart monitoring based on 2D image data, which opens up opportunities for integrating both machine learning and traditional diagnostic approaches.

Influence of attachment strategy on the thermal stability of hybridized DNA on gold surfaces.

The thermal stabilities of double-stranded DNA hybrids immobilized on gold surfaces are shown to be significantly affected by the conformation of the hybrid. To analyze this behavior, DNA probes were immobilized using attachment strategies where the nucleotides within the strand had varying levels of interactions with the gold substrate. The abilities of these probes to form double-stranded hybrids with solution DNA targets were evaluated by surface plasmon resonance (SPR) over a temperature range 25-60 °C. The measurements were used to construct thermal stability profiles for hybrids in each conformation. We observe that DNA hybrids formed with probe strands that interact extensively with the gold surface have stability profiles that are shifted lower by 5-10 °C compared to hybrids formed with end-tethered probes that have fewer interactions with the surface. The results provide an understanding of the experimental conditions in which these weaker DNA hybrids can form and show the additional complexity of evaluating denaturation profiles generated from DNA on surfaces.