Objective: The prevalence of complementary and alternative medicine(CAM) usage among patients with type 2 diabetes mellitus(T2DM) in Indonesia is high. However, to date, little is known about why Indonesian T2DM patie...Objective: The prevalence of complementary and alternative medicine(CAM) usage among patients with type 2 diabetes mellitus(T2DM) in Indonesia is high. However, to date, little is known about why Indonesian T2DM patients choose CAM therapies, how their knowledge, attitude and practice(KAP) of CAM affects their choices, or how demographics correlate with patient choices. Therefore, this study aimed to investigate the KAP and predictors of CAM usage in T2DM patients in Indonesia.Methods: This was an observational, cross-sectional study. Patients were interviewed using a questionnaire. Chi-square tests or Fisher’s exact tests were used to compare demographic and clinical data, as well as KAP assessments, between T2DM patients who use and do not use CAM. Multivariate logistic regression analyses were used to investigate predictors of CAM usage.Results: A total of 628 T2DM patients were enrolled in the study. CAM therapies were used by 341 patients(54.3%). The most common therapies were herbs and spiritual healing, used by 100.0% and 68.3% of CAM-using patients, respectively. CAM therapies were frequently recommended by family members(91.5%), and CAM users had significantly more knowledge and more positive attitudes toward CAM therapies than nonusers. Among users, 66% said they would not follow their healthcare providers’ instructions to not use CAM therapies, and 69.5% said they would not disclose their plan to use CAM therapies with their healthcare provider. Neither demographic nor clinical characteristics were associated with CAM use. The factors that best predicted the use of CAM therapies were their availability and low cost(odds ratio [OR] = 4.59;95% confidence interval [CI]: 3.01–7.01), the belief that CAM therapies were safe(OR = 2.04;95% CI: 1.40–2.95), the belief that CAM therapies could help with diabetes control(OR = 1.75;95% CI: 1.15–2.66), and the belief that CAM therapies could help maintain physical health(OR = 1.68;95% CI: 1.13–2.49).Conclusion: CAM therapy users were more knowledgeable a展开更多
互补产品推荐旨在为用户提供经常一起购买的产品,以满足共同的需求。现有的互补产品推荐方法大多考虑对产品的内容特性(视觉和文本内容)建模,而没有考虑用户购买产品的偏好。为此设计了一种融合用户偏好的互补产品推荐模型(complementar...互补产品推荐旨在为用户提供经常一起购买的产品,以满足共同的需求。现有的互补产品推荐方法大多考虑对产品的内容特性(视觉和文本内容)建模,而没有考虑用户购买产品的偏好。为此设计了一种融合用户偏好的互补产品推荐模型(complementary product recommendation models that integrate user preferences, CPRUP)。该模型首先计算产品之间图像和文本特征的互补关系;然后将知识图谱与注意力机制相结合,基于n-hop邻居挖掘用户历史购买产品之间的相关性,提出一种基于知识图谱的用户表征来提取用户对互补产品的偏好;最后基于神经网络实现互补关系与用户偏好的共同学习。使用Amazon数据集进行实验,提出的CPRUP模型与次优基线模型相比,ACC提升了5%,precision提升了4%,表明CPRUP模型可以更准确地为用户推荐互补产品。展开更多
基金financially supported by grants from Ministry of Research and Technology/National Research and Innovation Agency,Indonesia。
文摘Objective: The prevalence of complementary and alternative medicine(CAM) usage among patients with type 2 diabetes mellitus(T2DM) in Indonesia is high. However, to date, little is known about why Indonesian T2DM patients choose CAM therapies, how their knowledge, attitude and practice(KAP) of CAM affects their choices, or how demographics correlate with patient choices. Therefore, this study aimed to investigate the KAP and predictors of CAM usage in T2DM patients in Indonesia.Methods: This was an observational, cross-sectional study. Patients were interviewed using a questionnaire. Chi-square tests or Fisher’s exact tests were used to compare demographic and clinical data, as well as KAP assessments, between T2DM patients who use and do not use CAM. Multivariate logistic regression analyses were used to investigate predictors of CAM usage.Results: A total of 628 T2DM patients were enrolled in the study. CAM therapies were used by 341 patients(54.3%). The most common therapies were herbs and spiritual healing, used by 100.0% and 68.3% of CAM-using patients, respectively. CAM therapies were frequently recommended by family members(91.5%), and CAM users had significantly more knowledge and more positive attitudes toward CAM therapies than nonusers. Among users, 66% said they would not follow their healthcare providers’ instructions to not use CAM therapies, and 69.5% said they would not disclose their plan to use CAM therapies with their healthcare provider. Neither demographic nor clinical characteristics were associated with CAM use. The factors that best predicted the use of CAM therapies were their availability and low cost(odds ratio [OR] = 4.59;95% confidence interval [CI]: 3.01–7.01), the belief that CAM therapies were safe(OR = 2.04;95% CI: 1.40–2.95), the belief that CAM therapies could help with diabetes control(OR = 1.75;95% CI: 1.15–2.66), and the belief that CAM therapies could help maintain physical health(OR = 1.68;95% CI: 1.13–2.49).Conclusion: CAM therapy users were more knowledgeable a
文摘互补产品推荐旨在为用户提供经常一起购买的产品,以满足共同的需求。现有的互补产品推荐方法大多考虑对产品的内容特性(视觉和文本内容)建模,而没有考虑用户购买产品的偏好。为此设计了一种融合用户偏好的互补产品推荐模型(complementary product recommendation models that integrate user preferences, CPRUP)。该模型首先计算产品之间图像和文本特征的互补关系;然后将知识图谱与注意力机制相结合,基于n-hop邻居挖掘用户历史购买产品之间的相关性,提出一种基于知识图谱的用户表征来提取用户对互补产品的偏好;最后基于神经网络实现互补关系与用户偏好的共同学习。使用Amazon数据集进行实验,提出的CPRUP模型与次优基线模型相比,ACC提升了5%,precision提升了4%,表明CPRUP模型可以更准确地为用户推荐互补产品。
