Search

© 2021 Owner/Author.focuses on both long-term engaging spoken dialogue systems and text-based chatbots, as well as conversational recommender systems. The goal of the workshop is to stimulate discussion around problems, challenges, possible solutions and research directions regarding the exploitation of natural language processing and machine learning techniques to learn user features and to use them to personalize the dialogue in the next generation of intelligent conversational agents.

The 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP'21), 21 juni 2021, Item does not contain fulltext, The Personalized Intelligent Conversational Agents workshop focuses on both long-term engaging spoken dialogue systems and text-based chatbots, as well as conversational recommender systems. The goal of the workshop is to stimulate discussion around problems, challenges, possible solutions and research directions regarding the exploitation of natural language processing and machine learning techniques to learn user features and to use them to personalize the dialogue in the next generation of intelligent conversational agents.

Background: TAVR is a safe alternative to surgical aortic valve replacement (SAVR); how-ever, sex-related differences are still debated. This research aimed to examine gender differences in a real-world transcatheter aortic valve replacement (TAVR) cohort. Methods: All-comer aor-tic stenosis (AS) patients undergoing TAVR with a Medtronic valve across 19 Italian sites were prospectively included in the Italian Clinical Service Project (NCT01007474) between 2007 and 2019. The primary endpoint was 1-year mortality. We also investigated 3-year mortality, and ischemic and hemorrhagic endpoints, and we performed a propensity score matching to assemble patients with similar baseline characteristics. Results: Out of 3821 patients, 2149 (56.2%) women were en-rolled. Compared with men, women were older (83 ± 6 vs. 81 ± 6 years, p < 0.001), more likely to present severe renal impairment (GFR ≤ 30 mL/min, 26.3% vs. 16.3%, p < 0.001) but had less previous cardiovascular events (all p < 0.001), with a higher mean Society of Thoracic Surgeons (STS) score (7.8% ± 7.1% vs. 7.2 ± 7.5, p < 0.001) and a greater mean aortic gradient (52.4 ± 15.3 vs. 47.3 ± 12.8 mmHg, p < 0.001). Transfemoral TAVR was performed more frequently in women (87.2% vs. 82.1%, p < 0.001), with a higher rate of major vascular complications and life-threatening bleeding (3.9% vs. 2.4%, p = 0.012 and 2.5% vs. 1.4%, p = 0.024). One-year mortality differed between female and male (11.5% vs. 15.0%, p = 0.002), and this difference persisted after adjustment for sig-nificant confounding variables (Adj.HR1yr 1.47, 95%IC 1.18–1.82, p < 0.001). Three-year mortality was also significantly lower in women compared with men (19.8% vs. 24.9%, p < 0.001) even after adjustment for age, STS score, eGFR, diabetes and severe COPD (Adj.HR3yr 1.42, 95%IC 1.21–1.68, p < 0.001). These results were confirmed in 689 pairs after propensity score matching. Conclusion: Despite higher rates of peri-procedural compl

Background: Coronavirus disease 2019 (COVID-19) has caused an unprecedented change in the apparent epidemiology of acute coronary syndromes (ACS). However, the interplay between this disease, changes in pollution, climate, and aversion to activation of emergency medical services represents a challenging conundrum. We aimed at appraising the impact of COVID-19, weather, and environment features on the occurrence of ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) in a large Italian region and metropolitan area. Methods and results: Italy was hit early on by COVID-19, such that state of emergency was declared on January 31, 2020, and national lockdown implemented on March 9, 2020, mainly because the accrual of cases in Northern Italy. In order to appraise the independent contribution on changes in STEMI and NSTEMI daily rates of COVID-19, climate and pollution, we collected data on these clinical events from tertiary care cardiovascular centers in the Lazio region and Rome metropolitan area. Multilevel Poisson modeling was used to appraise unadjusted and adjusted effect estimates for the daily incidence of STEMI and NSTEMI cases. The sample included 1448 STEMI and 2040 NSTEMI, with a total of 2882 PCI spanning 6 months. Significant reductions in STEMI and NSTEMI were evident already in early February 2020 (all p<0.05), concomitantly with COVID-19 spread and institution of national countermeasures. Changes in STEMI and NSTEMI were inversely associated with daily COVID-19 tests, cases, and/or death (p<0.05). In addition, STEMI and NSTEMI incidences were associated with daily NO2, PM10, and O3 concentrations, as well as temperature (p<0.05). Multi-stage and multiply adjusted models highlighted that reductions in STEMI were significantly associated with COVID-19 data (p<0.001), whereas changes in NSTEMI were significantly associated with both NO2 and COVID-19 data (both p<0.001). Conclusions: Reductions in STEMI

Contains fulltext : 220912.pdf (Publisher’s version ) (Closed access), Nonculprit lesions are frequently observed in patients with ST-segment elevation myocardial infarction. Results from recent randomized clinical trials suggest that complete revascularization after ST-segment elevation myocardial infarction improves outcomes. In this state-of-the-art paper, the authors review these trials and consider how best to determine which nonculprit lesions require revascularization and when this should be performed.

Item does not contain fulltext, BACKGROUND: To date, no specific drug-eluting stent (DES) has fully proven its superiority over others in patients with ST-segment elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention. OBJECTIVES: The purpose of this study was to compare the safety and efficacy of coronary artery stents in STEMI patients in a patient-level network meta-analysis. METHODS: Eligible studies were dedicated randomized controlled trials comparing different stents in STEMI patients undergoing percutaneous coronary intervention with at least 12 months of clinical follow-up. Of 19 studies identified from the published data, individual patient data were collected in 15 studies with 10,979 patients representing 87.7% of patients in the overall network of evidence. The primary endpoint was the composite of cardiac death, reinfarction, or target lesion revascularization. RESULTS: Overall, 8,487 (77.3%) of 10,979 STEMI patients were male and the mean age was 60.7 years. At a median follow-up of 3 years, compared with bare-metal stents (BMS), patients treated with paclitaxel-, sirolimus-, everolimus-, or biolimus-eluting stents had a significantly lower risk of the primary endpoint (adjusted hazard ratios [HRs]: 0.74 [95% confidence interval (CI): 0.63 to 0.88], 0.65 [95% CI: 0.49 to 0.85], 0.70 [95% CI: 0.53 to 0.91], and 0.66 [95% CI: 0.49 to 0.88], respectively). The risk of primary endpoint was not different between patients treated with BMS and zotarolimus-eluting stents (adjusted HR: 0.83 [95% CI: 0.51 to 1.38]). Among patients treated with DES, no significant difference in the risk of the primary outcome was demonstrated. Treatment with second-generation DES was associated with significantly lower risk of definite or probable stent thrombosis compared with BMS (adjusted HR: 0.61 [95% CI: 0.42 to 0.89]) and first-generation DES (adjusted HR: 0.56 [95% CI: 0.36 to 0.88]). CONCLUSIONS: In STEMI patients, DES were superior to BMS with respect to long-term effica

In the last years, hundreds of social networks sites have been launched with both professional (e.g., LinkedIn) and non-professional (e.g., MySpace, Facebook) orientations. This resulted in a renewed information overload problem, but it also provided a new and unforeseen way of gathering useful, accurate and constantly updated information about user interests and tastes. Content-based recommender systems can leverage the wealth of data emerging by social networks for building user profiles in which representations of the user interests are maintained. The idea proposed in this paper is to extract content-based user profiles from the data available in the LinkedIn social network, to have an image of the users' interests that can be used to recommend interesting academic research papers. A preliminary experiment provided interesting results which deserve further attention. © 2011 ACM.

Item does not contain fulltext, BACKGROUND: Hypertension is a well known risk factor for atherosclerosis. However, data on the prognostic impact of hypertension in patients with ST elevation myocardial infarction (STEMI) are inconsistent and mainly related to studies performed in the thrombolytic era, with very few data in patients undergoing primary angioplasty. Therefore, the aim of the current study was to evaluate the impact hypertension on clinical outcome in STEMI patients undergoing primary PCI with BMS or DES. METHODS: Our population is represented by 6298 STEMI patients undergoing primary angioplasty included in the DESERT database from 11 randomized trials comparing DES vs BMS for STEMI. RESULTS: Hypertension was observed in 2764 patients (43.9%), and associated with ageing (p<0.0001), female gender (p<0.001), diabetes (p<0.0001), hypercholesterolemia (p<0.0001), previous MI (p=0.002), previous revascularization (p=0.002), longer time-to-treatment (p<0.001), preprocedural TIMI 3 flow, and with a lower prevalence of smoking (41% vs 53.9%, p<0.001) and anterior MI (42% vs 45.9%, p=0.002). Hypertension was associated with impaired postprocedural TIMI 0-2 flow (Adjusted OR [95% CI]=1.22 [1.01-1.47], p=0.034). At a follow-up of 1201+/-440days, hypertension was associated with higher mortality (adjusted HR [95% CI]=1.24 [1.01-1.54], p=0.048), reinfarction (adjusted HR [95% CI]=1.31 [1.03-1.66], p=0.027), stent thrombosis (adjusted HR [95% CI]=1.29 [0.98-1.71], p=0.068) and TVR (adjusted HR [95% CI]=1.22 [1.04-1.44], p=0.013). CONCLUSIONS: This study showed that among STEMI patients undergoing primary angioplasty with DES or BMS, hypertension is independently associated with impaired epicardial reperfusion, mortality, reinfarction and TVR, and a trend in higher ST.

Item does not contain fulltext, BACKGROUND: Several concerns have emerged on the higher risk of in-stent thrombosis after drug-eluting stent (DES) implantation, especially in the setting of STEMI patients. Few data have even been reported in high-risk patients, such as those with anterior MI. Therefore this represents the aim of the current study. METHODS: The literature was scanned by formal searches of electronic databases (MEDLINE and CENTRAL). We examined all completed randomized trials of DES for STEMI. The following key words were used for study selection: randomized trial, myocardial infarction, reperfusion, primary angioplasty, stenting, DES, sirolimus-eluting stent (SES), Cypher, paclitaxel-eluting stent (PES), Taxus. No language restrictions were enforced. RESULTS: Individual patient's data were obtained from 11 out of 13 trials, including a total of 2,782 patients with anterior MI [1,739 or 62.5 % randomized to DES and 1,043 or 37.5 % randomized to bare-metal stent (BMS)]. At long-term follow-up, no significant benefit was observed with DES as compared to BMS in terms of mortality [9.8 vs 10.9 %, HR (95 % CI) = 0.81 (0.61, 1.07), p = 0.13, p heterogeneity = 0.18], reinfarction [8.8 vs 6.4 %, respectively; HR (95 % CI) = 1.14 (0.80, 1.61), p = 0.47, p heterogeneity = 0.82], and stent thrombosis [5.6 vs 5 %, OR (95 % CI) = 0.88 (0.59, 1.30), p = 0.51, p heterogeneity = 0.65], whereas DES was associated with a significant reduction in terms of target-vessel revascularization (TVR) [13.7 vs 23.4 %; OR (95 % CI) = 0.56 (0.46, 0.69), p < 0.0001, p het = 0.81] that was observed at both early (within 1 year) [7 vs 14.7 %, HR (95 % CI) = 0.56 (0.46, 0.69), p < 0.0001, p het = 0.81] and late (>1 year) follow-up [7.2 vs 9 %, HR (95 % CI) = 0.67 (0.47, 0.96), p = 0.03, p het = 0.96]. CONCLUSIONS: This study showed that among patients with anterior STEMI undergoing primary angioplasty, SES and PES, as compared to BMS, are associated with a significant reduction in TVR at long-term follow-up. No conc

Item does not contain fulltext, Primary percutaneous coronary intervention (pPCI) has improved survival as compared to thrombolysis. Concerns still remain regarding the risk of stent thrombosis in the setting of STEMI, especially after drug-eluting stent (DES) implantation. Therefore, the aim of this study was to report on the timing of stent thrombosis (ST) with both DES and bare metal stents (BMS) and its prognostic significance in patients undergoing pPCI. The Drug-Eluting Stent in Primary Angioplasty (DESERT) cooperation is based on a pooled database including individual data of randomised trials that evaluate the long-term safety and effectiveness of DES as compared to BMS in patients undergoing pPCI for STEMI. Follow-up data were collected for 3-6 years after the procedure. ST was defined as definite or probable, based on the ARC definition. The study population consists of 6,274 STEMI patients undergoing primary angioplasty with BMS or DES. At 1201 +/- 440 days, ST occurred in 267 patients (4.25%). Most of the events were acute or subacute (within 30 days) and very late (> 1 years), with different distribution between DES vs BMS. Patients with ST were more often diabetic (21.7% vs 15.1%, p=0.005), more frequently had post-procedural TIMI 0-2 flow (14.0% vs 9.3%, p = 0.01), and were less often treated with dual antiplatelet therapy at one year follow-up. Diabetes (p = 0.036), post-procedural TIMI 0-2 Flow (p = 0.013) and ischaemia time > 6 hours (p = 0.03) were independent predictors of ST. Post-procedural TIMI 0-2 flow (p = 0.001) and ischaemia time > 6 hours (p < 0.001) were independent predictors of early ST, ischaemia time > 6 hours (p = 0.05) was independent predictor of late ST, whereas diabetes (p = 0.022) and use of DES (p = 0.002) were independent predictors of very late ST. ST was associated with a significantly higher mortality (23.6% vs 6%, p < 0.001). The greatest impact on mortality was observed with subacute (40.4%) and late (20.9%) ST, as compared to acute (12.5%) and very la

Item does not contain fulltext, OBJECTIVE: Diabetes has been shown to be associated with worse survival and repeat target vessel revascularization (TVR) after primary angioplasty. The aim of the current study was to evaluate the impact of diabetes on long-term outcome in patients undergoing primary angioplasty treated with bare metal stents (BMS) and drug-eluting stents (DES). RESEARCH DESIGN AND METHODS: Our population is represented by 6,298 ST-segment elevation myocardial infarction (STEMI) patients undergoing primary angioplasty included in the DESERT database from 11 randomized trials comparing DES with BMS. RESULTS: Diabetes was observed in 972 patients (15.4%) who were older (P < 0.001), more likely to be female (P < 0.001), with higher prevalence of hypertension (P < 0.001), hypercholesterolemia (P < 0.001), and longer ischemia time (P < 0.001), and without any difference in angiographic and procedural characteristics. At long-term follow-up (1,201 +/- 441 days), diabetes was associated with higher rates of death (19.1% vs. 7.4%; P < 0.0001), reinfarction (10.4% vs. 7.5%; P < 0.001), stent thrombosis (7.6% vs. 4.8%; P = 0.002) with similar temporal distribution--acute, subacute, late, and very late--between diabetic and control patients, and TVR (18.6% vs. 15.1%; P = 0.006). These results were confirmed in patients receiving BMS or DES, except for TVR, there being no difference observed between diabetic and nondiabetic patients treated with DES. The impact of diabetes on outcome was confirmed after correction for baseline confounding factors (mortality, P < 0.001; repeat myocardial infarction, P = 0.006; stent thrombosis, P = 0.007; TVR, P = 0.027). CONCLUSIONS: This study shows that among STEMI patients undergoing primary angioplasty, diabetes is associated with worse long-term mortality, reinfarction, and stent thrombosis in patients receiving DES and BMS. DES implantation, however, does mitigate the known deleterious effect of diabetes on TVR after BMS.

Item does not contain fulltext, BACKGROUND: Concerns have emerged regarding a higher risk of stent thrombosis after drug-eluting stent (DES) implantation, especially in the setting of ST-segment elevation myocardial infarction (STEMI). Our objective was to perform a meta-analysis using individual patient data to evaluate the long-term safety and effectiveness of DES compared with bare-metal stents (BMS) in patients undergoing primary percutaneous coronary intervention for STEMI. DATA SOURCES: Formal searches of electronic databases (MEDLINE and CENTRAL) and scientific session presentations from January 2000 to June 2011. STUDY SELECTION: We examined all completed randomized trials of DES for STEMI. DATA EXTRACTION: Individual patient data. DATA SYNTHESIS: Individual patient data were obtained from 11 of 13 trials identified, including a total of 6298 patients (3980 [63.2%] randomized to DES [99% sirolimus-eluting or paclitaxel-eluting stents] and 2318 [36.8%] randomized to BMS). At long-term follow-up (mean [SD], 1201 [440] days), DES implantation significantly reduced the occurrence of target-vessel revascularization (12.7% vs 20.1%; hazard ratio [95% CI], 0.57 [0.50-0.66]; P < .001, P value for heterogeneity, .20), without any significant difference in terms of mortality, reinfarction, and stent thrombosis. However, DES implantation was associated with an increased risk of very late stent thrombosis and reinfarction. CONCLUSIONS: The present pooled patient-level meta-analysis demonstrates that among patients with STEMI undergoing primary percutaneous coronary intervention, sirolimus-eluting and paclitaxel-eluting stents compared with BMS are associated with a significant reduction in target-vessel revascularization at long-term follow-up. Although there were no differences in cumulative mortality, reinfarction, or stent thrombosis, the incidence of very late reinfarction and stent thrombosis was increased with these DES.

This paper presents MyMusic, a system that exploits social media sources for generating personalized music playlists. This work is based on the idea that information extracted from social networks, such as Facebook and Last.fm, might be effectively exploited for personalization tasks. Indeed, information related to music preferences of users can be easily gathered from social platforms and used to define a model of user interests. The use of social media is a very cheap and effective way to overcome the classical cold start problem of recommender systems. In this work we enriched social media-based playlists with new artists related to those the user already likes. Specifically, we compare two different enrichment techniques: the first leverages the knowledge stored on DBpedia, the structured version of Wikipedia, while the second is based on the content-based similarity between descriptions of artists. The final playlist is ranked and finally presented to the user that can listen to the songs and express her feedbacks. A prototype version of MyMusic was made available online in order to carry out a preliminary user study to evaluate the best enrichment strategy. The preliminary results encouraged keeping on this research. © 2012 Springer-Verlag.

Personalized electronic program guides help users overcome information overload in the TV and video domain by exploiting recommender systems that automatically compile lists of novel and diverse video assets, based on implicitly or explicitly defined user preferences. In this context, we assume that user preferences can be specified by program genres (documentary, sports, ...) and that an asset can be labeled by one or more program genres, thus allowing an initial and coarse preselection of potentially interesting assets. As these assets may come from various sources, program genre labels may not be consistent among these sources, or not even be given at all, while we assume that each asset has a possibly short textual description. In this paper, we tackle this problem by considering whether those textual descriptions can be effectively used to automatically retrieve the most related TV shows for a specific program genre. More specifically, we compare a statistical approach called logistic regression with an enhanced version of the commonly used vector space model, called random indexing, where the latter is extended by means of a negation operator based on quantum logic. We also apply a new feature generation technique based on explicit semantic analysis for enriching the textual description associated to a TV show with additional features extracted from Wikipedia. © 2012 Springer-Verlag.