No abstract

BACKGROUND Atrial fibrillation (AF), a common cause of stroke, often is asymptomatic. Smartphones and smartwatches can detect AF using heart rate patterns inferred using photoplethysmography (PPG); however, enhanced accuracy is required to reduce false positives in screening populations. OBJECTIVE The purpose of this study was to test the hypothesis that a deep learning algorithm given raw, smartwatch-derived PPG waveforms would discriminate AF from normal sinus rhythm better than algorithms using heart rate alone. METHODS Patients presenting for cardioversion of AF (n 5 51) were given wrist-worn fitness trackers containing PPG sensors (Jawbone Health). Standard 12-lead electrocardiograms over-read by board-certified cardiac electrophysiologists were used as the reference standard. The accuracy of PPG signals to discriminate AF from sinus rhythm was evaluated by conventional measures of heart rate variability, a long short-term memory (LSTM) neural network given heart rate data only, and a deep convolutional-recurrent neural net (DNN) given the raw PPG data. RESULTS From among 51 patients with persistent AF (age 63.6 6 11.3 years; 78% male; 88% white), we randomly assigned 40 to train and 11 to test the algorithms. Whereas logistic regression analysis of heart rate variability yielded an area under the receiver operating characteristic curve (AUC) of 0.717 (sensitivity 0.741; specificity 0.584), the LSTM model given heart rate data exhibited AUC of 0.954 (sensitivity 0.810; specificity 0.921), and the DNN model given raw PPG data yielded the highest AUC of 0.983 (sensitivity 0.985; specificity 0.880). CONCLUSION A deep learning model given the raw PPG-based signal resulted in AF detection with high accuracy, performing better than conventional analyses relying on heart rate series data alone.

While concept-based methods for information retrievul can provide improved performance over more conventional techniques, they require large amounts of effort to acquire the concepts and their qualitative and quantitative relationships. This paper discusses an aschitecture for probabilistic concept-based information retrieval which addzesses the knowledge acquisition problem. The architecture makes use of the probabilistic networks technology for representing and reasoning about concepts and ineludes a knowledge acquisition component which partia]]y automates the construction of concept know1-edge bases from data.We describe two experiments that apply the architecture to the task of retrieving documents about tenorism from a set of documents from the Reuters news serv/ce. The experiments provide positive evidence that the architecture design is feasible and that there are advantages to concept-based methods. I IntroductionIn this paper we describe some preliminary research on the use of probabilistic networks for information retrieval. In particular, we introduce an architecture • This work was funded by ADS' Internal Research sad Development Prrogran~ for probabilistic, concept-based information retrieval (henceforth PCIR) that can be used to automatically generate relationships between concepts, and then reason about them given the evidence provided by individual documents. This is in contrast to our previons research on concept-based methods [12, 16,17], in which we were primarily interested in issues related to ~easonin8 about concepts and not so much concerned with issues related to the construction of the relationships. Our lons-term goal, however, ¢ontin-ues to be the development of techniques that can form the basis for an effective system to assist users in sortin 8 throu8h lurge volumes of time sensitive material. We have in mind such applications as the day-to-day momtorin 8 of newswires for specific topics of interest.

No abstract

No abstract