BACKGROUND AND PURPOSE Studies with very long follow-up are scarce in patients with cryptogenic stroke and patent foramen ovale (PFO). Little is known about the etiology of recurrent cerebrovascular events (CVE) in PFO patients. METHODS We collected information on recurrent CVE in 308 patients with cryptogenic stroke and PFO and sought to determine concurrent stroke causes that had emerged or...

Men have been reported to have a higher incidence of recurrent venous thromboembolism than women. However, it is not known if this gender effect holds among different racial/ethnic groups and for both venous thrombosis and pulmonary embolism. We conducted a retrospective analysis of 18- to 65-year-old Caucasian, African-American and Hispanic cases hospitalized in California with unprovoked veno...

Recurrent events are frequently observed in biomedical studies, and often more than one type of event is of interest. Follow-up time may be censored due to loss to follow-up or administrative censoring. We propose a class of semi-parametric marginal means/rates models, with a general relative risk form, for assessing the effect of covariates on the censored event processes of interest. We formu...

TAMPERE UNIVERSITY OF TECHNOLOGY Master‘s Degree Programme in Signal Processing PARASCANDOLO, GIAMBATTISTA: Recurrent neural networks for polyphonic sound event detection Master of Science Thesis, 66 pages November 2015 Major: Signal Processing Minor: Learning and Intelligent Systems Examiners: Tuomas Virtanen, Heikki Huttunen

Recurrent event data arise in many biomedical and engineering studies when failure events can occur repeatedly over time for each study subject. In this article, we are interested in nonparametric estimation of the hazard function for gap time. A penalized likelihood model is proposed to estimate the hazard as a function of both gap time and covariate. Method for smoothing parameter selection i...

Traditional event detection methods heavily rely on manually engineered rich features. Recent deep learning approaches alleviate this problem by automatic feature engineering. But such efforts, like tradition methods, have so far only focused on single-token event mentions, whereas in practice events can also be a phrase. We instead use forward-backward recurrent neural networks (FBRNNs) to det...

1 Summary. Interval-censored recurrent event data arise when event occurence is only determined at periodic assessment times. Nonparametric estimates of rate and mean functions are readily obtained in this settings, but lack the smoothness usually anticipated for the underlying event process. We describe local likelihood methods which generate smooth estimates of rate and mean functions, and as...

Recurrent event data are largely characterized by the rate function but smoothing techniques for estimating the rate function have never been rigorously developed or studied in statistical literature. This paper considers the moment and least squares methods for estimating the rate function from recurrent event data. With an independent censoring assumption on the recurrent event process, we st...

Statistical Scripts are probabilistic models of sequences of events. For example, a script model might encode the information that the event “Smith met with the President” should strongly predict the event “Smith spoke to the President.” We present a number of results improving the state of the art of learning statistical scripts for inferring implicit events. First, we demonstrate that incorpo...

Gap time hazard estimation is of particular interest in recurrent event data. This article proposes a fully nonparametric approach for estimating the gap time hazard. Smoothing spline analysis of variance (ANOVA) decompositions are used to model the log gap time hazard as a joint function of gap time and covariates, and general frailty is introduced to account for between-subject heterogeneity ...