scholarly journals A Personalized System for Conversational Recommendations

2004 ◽  
Vol 21 ◽  
pp. 393-428 ◽  
Author(s):  
C. A. Thompson ◽  
M. H. Goker ◽  
P. Langley

Searching for and making decisions about information is becoming increasingly difficult as the amount of information and number of choices increases. Recommendation systems help users find items of interest of a particular type, such as movies or restaurants, but are still somewhat awkward to use. Our solution is to take advantage of the complementary strengths of personalized recommendation systems and dialogue systems, creating personalized aides. We present a system -- the Adaptive Place Advisor -- that treats item selection as an interactive, conversational process, with the program inquiring about item attributes and the user responding. Individual, long-term user preferences are unobtrusively obtained in the course of normal recommendation dialogues and used to direct future conversations with the same user. We present a novel user model that influences both item search and the questions asked during a conversation. We demonstrate the effectiveness of our system in significantly reducing the time and number of interactions required to find a satisfactory item, as compared to a control group of users interacting with a non-adaptive version of the system.

Author(s):  
ChunYan Yin ◽  
YongHeng Chen ◽  
Wanli Zuo

AbstractPreference-based recommendation systems analyze user-item interactions to reveal latent factors that explain our latent preferences for items and form personalized recommendations based on the behavior of others with similar tastes. Most of the works in the recommendation systems literature have been developed under the assumption that user preference is a static pattern, although user preferences and item attributes may be changed through time. To achieve this goal, we develop an Evolutionary Social Poisson Factorization (EPF$$\_$$ _ Social) model, a new Bayesian factorization model that can effectively model the smoothly drifting latent factors using Conjugate Gamma–Markov chains. Otherwise, EPF$$\_$$ _ Social can obtain the impact of friends on social network for user’ latent preferences. We studied our models with two large real-world datasets, and demonstrated that our model gives better predictive performance than state-of-the-art static factorization models.


Author(s):  
Vicente Arturo Romero Zaldivar ◽  
Daniel Burgos ◽  
Abelardo Pardo

Recommendation Systems are central in current applications to help the user find relevant information spread in large amounts of data. Most Recommendation Systems are more effective when huge amounts of user data are available. Educational applications are not popular enough to generate large amount of data. In this context, rule-based Recommendation Systems seem a better solution. Rules can offer specific recommendations with even no usage information. However, large rule-sets are hard to maintain, reengineer, and adapt to user preferences. Meta-rules can generalize a rule-set which provides bases for adaptation. In this chapter, the authors present the benefits of meta-rules, implemented as part of Meta-Mender, a meta-rule based Recommendation System. This is an effective solution to provide a personalized recommendation to the learner, and constitutes a new approach to Recommendation Systems.


VASA ◽  
2005 ◽  
Vol 34 (4) ◽  
pp. 243-249 ◽  
Author(s):  
Drinda ◽  
Neumann ◽  
Pöhlmann ◽  
Vogelsang ◽  
Stein ◽  
...  

Background: Prostanoids are used in the treatment of Raynaud’s phenomenon and acral perfusion disorders secondary to collagenosis. In subjective terms, intravenous administration of these agents produces success in more than 50% of patients. The therapeutic outcome of clinical administration of alprostadil or iloprost may vary from individual to individual. Patients and methods: The following variables were analysed in a cross-over study in 27 patients with collagenosis and Raynaud’s phenomenon: plasma viscosity and erythrocyte aggregation (rheological variables), partial pressure of oxygen and laser Doppler flowmetry in the finger region, and lymphocyte phenotyping and interleukin (IL) determinations (immunological variables). Results: Laser Doppler flowmetry revealed significant differences between patients with secondary Raynaud’s phenomenon and a control group of 25 healthy subjects. Laser Doppler readings did not change significantly as a result of the treatments. Therapy with iloprost produced a reduction in IL-1beta, L-selectin (CD 62 L) and IL-6. Conclusion: The change in immunological variables due to iloprost may explain the long-term effects of prostaglandins in the treatment of Raynaud’s phenomenon. From our results it is not possible to infer any preference for iloprost or alprostadil.


1987 ◽  
Vol 57 (01) ◽  
pp. 55-58 ◽  
Author(s):  
J F Martin ◽  
T D Daniel ◽  
E A Trowbridge

SummaryPatients undergoing surgery for coronary artery bypass graft or heart valve replacement had their platelet count and mean volume measured pre-operatively, immediately post-operatively and serially for up to 48 days after the surgical procedure. The mean pre-operative platelet count of 1.95 ± 0.11 × 1011/1 (n = 26) fell significantly to 1.35 ± 0.09 × 1011/1 immediately post-operatively (p <0.001) (n = 22), without a significant alteration in the mean platelet volume. The average platelet count rose to a maximum of 5.07 ± 0.66 × 1011/1 between days 14 and 17 after surgery while the average mean platelet volume fell from preparative and post-operative values of 7.25 ± 0.14 and 7.20 ± 0.14 fl respectively to a minimum of 6.16 ± 0.16 fl by day 20. Seven patients were followed for 32 days or longer after the operation. By this time they had achieved steady state thrombopoiesis and their average platelet count was 2.44 ± 0.33 × 1011/1, significantly higher than the pre-operative value (p <0.05), while their average mean platelet volume was 6.63 ± 0.21 fl, significantly lower than before surgery (p <0.001). The pre-operative values for the platelet volume and counts of these patients were significantly different from a control group of 32 young males, while the chronic post-operative values were not. These long term changes in platelet volume and count may reflect changes in the thrombopoietic control system secondary to the corrective surgery.


Author(s):  
Blaurock-Busch E

The heavy metal burden of patients with Autism spectrum disorders (ASD) has been widely discussed [1-5]. Present knowledge suggests that ASD patients, compared to ‘normal’s’ show a greater metal burden, which may be a cause of the ASD pathogenesis, possibly due to a limited detoxification potential. We thus aimed to evaluate if the metal burden of ASD children is due to comprised detoxification ability, and if missing of enzymes such as the glutathione-S-transferases provide an explanation, or if additional factors play a role. Genetically, we noticed a slight difference in the detoxification ability of the ASD group compared to the Control group. In the ASD group, carrier of the genotype GSTT1 null genotype (i.e. the homozygous loss) are 1.7 times more common as in the Control group and the GSTT1 allele is more frequent in the ASD patient collective. These findings are not statistically significant but indicate a trend. In addition, our data indicates that levels of potentially toxic metals in blood and hair of both groups demonstrate a similar immediate and long-term exposure. However, 36% of the ASD group showed signs of zinc deficiency compared to 11% of the Control group and this points towards inefficiency of the Phase I detoxification pathway. More research is needed to explore the role of other elements in the detoxification pathway.


2019 ◽  
Author(s):  
Francisco Jesús Represas Carrera Sr ◽  
Ángel Alfredo Martínez Ques Sr ◽  
Ana Clavería Fontán Sr

BACKGROUND Diabetes mellitus is currently a major public health problem worldwide. It is traditionally approached in a clinical inpatient relationship between the patient and the healthcare professional. However, the rise of new technologies, particularly mobile applications, is revolutionizing the traditional healthcare model through the introduction of telehealthcare. OBJECTIVE (1) To assess the effects of mobile applications for improving healthy lifestyles on the quality of life and metabolic control of diabetes mellitus in adult patients. (2) To describe the characteristics of the mobile applications used, identify the healthy lifestyles they target, and describe any adverse effects their use may have. METHODS Review of systematic reviews and meta-analysis, following the guidelines of the Cochrane Collaboration and the Joanna Briggs Institute. We included studies that used any mobile application aimed at helping patients improve self-management of diabetes mellitus by focusing on healthy lifestyles. Studies needed to include a control group receiving regular care without the use of mobile devices. In May 2018, a search was conducted in Medline, Embase, Cochrane, LILACS, PsychINFO, Cinahl and Science Direct, updated in May 2019. The methodological quality of the studies was assessed using the Amstar-2 tool. RESULTS Seven systematic reviews of 798 articles were initially selected for analysis. The interventions had a duration of between 1 and 12 months. Mobile applications focused singly or simultaneously on different lifestyles aspects (diet, physical exercise, motivation, blood glucose levels, etc.). There are significant changes in HbA1c values, body weight and BMI, although in others, such as lipid profile, quality of life, or blood pressure, there is no clear improvement. CONCLUSIONS There is clear evidence that the use of mobile applications improves glycemic control in diabetic patients in the short term. There is a lack of evidence in its long-term benefits. It is thus necessary to carry out further studies to learn about the long-term effectiveness of mobile applications aimed at promoting the healthy lifestyles of diabetic patients. CLINICALTRIAL PROSPERO Register: CRD42019133685


2021 ◽  
pp. 1-11
Author(s):  
Stefanie Bruschke ◽  
Uwe Baumann ◽  
Timo Stöver

Background: The cochlear implant (CI) is a standard procedure for the treatment of patients with severe to profound hearing loss. In the past, a standard healing period of 3–6 weeks occurred after CI surgery before the sound processor was initially activated. Advancements of surgical techniques and instruments allow an earlier initial activation of the processor within 14 days after surgery. Objective: Evaluation of the early CI device activation after CI surgery within 14 days, comparison to the first activation after 4–6 weeks, and assessment of the feasibility and safety of the early fitting over a 12 month observation period were the objectives of this study. Method: In a prospective study, 127 patients scheduled for CI surgery were divided into early fitting group (EF, n = 67) and control group (CG, n = 60). Individual questionnaires were used to evaluate medical and technical outcomes of the EF. Medical side effects, speech recognition, and follow-up effort were compared with the CG within the first year after CI surgery. Results: The early fitting was feasible in 97% of the EF patients. In the EF, the processor was activated 25 days earlier than in the CG. No major complications were observed in either group. At the follow-up appointments, side effects such as pain and balance problems occurred with comparable frequency in both groups. At initial fitting, the EF showed a significantly higher incidence of medical minor complications (p < 0.05). When developing speech recognition within the first year of CI use, no difference was observed. Furthermore, the follow-up effort within the first year after CI surgery was comparable in both groups. Conclusions: Early fitting of the sound processor is a feasible and safe procedure with comparable follow-up effort. Although more early minor complications were observed in the EF, there were no long-term wound healing problems caused by the early fitting. Regular inspection of the magnet strength is recommended as part of the CI follow-up since postoperative wound swelling must be expected. The early fitting procedure enabled a clear reduction in the waiting time between CI surgery and initial sound processor activation.


2021 ◽  
Author(s):  
Baoshan Li ◽  
Xin Zhang ◽  
Yi Man ◽  
Jiadong Xie ◽  
Wei Hu ◽  
...  

Abstract Porcine small intestine submucosa (SIS) biologic patch has been used in inguinal hernia repair. However, there are little data available to assess the long-term effect after repair. This study aimed to explore the long-term effect of SIS patch in open inguinal hernia repair. Sevent-six patients with unilateral inguinal hernia were treated with Lichtenstein tension-free hernia repair using SIS patch (Beijing Datsing Bio-Tech Co., Ltd.) and Surgisis patch (COOK, USA) in Tianjin Union Medical Center and China-Japan Friendship Hospital. In the trial, the long-term efficacy of the treatment group and the control group were compared. A total of 66 patients in both groups received long-term follow-up (&gt; 5 years) after surgery, with a follow-up rate of 86.8%. During the follow-up period, there was one case of recurrence, one case of chronic pain in the control group. There was no statistically significant difference (P &gt; 0.05) in terms of recurrence, chronic pain, foreign body sensation and infection between the two groups of patients. After long-term observations, it has been found that the porcine small intestinal submucosa (SIS) biological patch is safe and effective for inguinal hernia Lichtenstein repair, and has a low recurrence rate and complication rate.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Michał Waszczykowski ◽  
Bożena Dziankowska-Bartkowiak ◽  
Michał Podgórski ◽  
Jarosław Fabiś ◽  
Arleta Waszczykowska

AbstractThe aim of this study was to estimate the long-term results of complex and supervised rehabilitation of the hands in systemic sclerosis (SSc) patients. Fifty-one patients were enrolled in this study: 27 patients (study group) were treated with a 4-week complex, supervised rehabilitation protocol. The control group of 24 patients was prescribed a home exercise program alone. Both groups were evaluated at baseline and after 1-, 3-, 6-, and 12-months of follow-up with the Disability of the Arm, Shoulder and Hand Questionnaire (DAHS) as the primary outcome, pain (VAS—visual analog scale), Cochin Hand Function Scale (CHFS), Health Assessment Questionnaire Disability Index (HAQ-DI), Scleroderma-HAQ (SHAQ), range of motion (d-FTP—delta finger to palm, Kapandji finger opposition test) and hand grip and pinch as the secondary outcomes. Only the study group showed significant improvements in the DASH, VAS, CHFS and SHAQ after 1, 3 and 6 months of follow-up (P = 0.0001). Additionally, moderate correlations between the DASH, CHFS and SHAQ (R = 0.7203; R = 0.6788; P = 0.0001) were found. Complex, supervised rehabilitation improves hand and overall function in SSc patients up to 6 months after the treatment but not in the long term. The regular repetition of this rehabilitation program should be recommended every 3–6 months to maintain better hand and overall function.


Sign in / Sign up

Export Citation Format

Share Document