Search

To enhance the accuracy of learning models, it becomes imperative to train them on more extensive datasets. Unfortunately, access to such data is often restricted because data providers are hesitant to share their data due to privacy concerns. Hence, it is critical to develop obfuscation techniques that empower data providers to transform their datasets into new ones that ensure the desired level of privacy. In this paper, we present an approach where data providers utilize a neural network based on the autoencoder architecture to safeguard the sensitive components of their data while preserving the utility of the remaining parts. More specifically, within the autoencoder framework and after the encoding process, a classifier is used to extract the private feature from the dataset. This feature is then decorrelated from the other remaining features and subsequently subjected to noise. The proposed method is flexible, allowing data providers to adjust their desired level of privacy by changing the noise level. Additionally, our approach demonstrates superior performance in achieving the desired trade-off between utility and privacy compared to similar methods, all while maintaining a simpler structure. [ABSTRACT FROM AUTHOR]

Background: Diabetes is one of the most common chronic and costly diseases worldwide and type 2 diabetes is the most common type which accounts for about 90% of cases with diabetes. New medication-therapy regimens such as those containing linagliptin alone or in combination with other medications (within the category of DDP-4 inhibitors) must be evaluated in terms of efficacy and compared with other currently used drugs and then enter the medication list of the country. Hence, this study aimed to compare the clinical efficacy of the two drugs, i.e. linagliptin and sitagliptin, in patients with type 2 diabetes., Methods: A systematic review was conducted to identify all clinical trials published by 2015 which compared the two drugs in patients with type 2 diabetes. Using keywords such as "linagliptin", "type 2 diabetes mellitus", "sitagliptin" and related combinations, we searched databases including Scopus, PubMed, and Web of Science. The quality of the selected studies was evaluated using the Jadad score. Considering primary and secondary outcomes extracted from the reviewed studies, a network meta-analysis was used to conduct a systematic comparison between the two studied drugs., Results: This network meta-analysis included 32 studies (Linagliptin vs PLB: n = 8, Sitagliptin vs PLB: n = 13, Linagliptin + MET vs PLB + MET: n = 4, and Sitagliptin + MET vs PLB + MET: n = 7) and a total of 13,747 patients. The results showed no significant difference between linagliptin and sitagliptin in terms of key efficacy and safety outcomes such as HbA1c changes from baseline, body weight change from baseline, percentage of patients achieving HbA1c <7, and percentage of patients experiencing hypoglycemic events (p > 0.05). The results showed that the efficacy of the two drug regimens was the same., Conclusions: Based on the results, there was no significant difference between the two drugs, i.e. linagliptin and sitagliptin, in terms of efficacy; in other words, the efficacy of the two drugs was the same. Therefore, the use of these two drugs depends on their availability and cost. Graphical abstract of the network meta-analysis performed to evaluate the alternatives under the study.