Pharmacologic Treatment of Type 2 Diabetes in the U.S., Sweden, and Israel.

OBJECTIVE: To characterize and compare glucose-lowering medication use in type 2 diabetes in the U.S., Sweden, and Israel, including adoption of newer medications and prescribing patterns. RESEARCH DESIGN AND METHODS: We used data from the National Health and Nutrition Examination Survey (NHANES) from the U.S., the Stockholm CREAtinine Measurements (SCREAM) project from Sweden, and Maccabi Healthcare Services (Maccabi) from Israel. Specific pharmacotherapy for type 2 diabetes between 2007 and 2018 was examined. RESULTS: Use of glucose-lowering medications among patients with type 2 diabetes was substantially lower in NHANES and SCREAM than in Maccabi (66.0% in NHANES, 68.4% in SCREAM, and 88.1% in Maccabi in 2017-2018). Among patients who took at least one glucose-lowering medication in 2017-2018, metformin use was also lower in NHANES and SCREAM (74.1% in NHANES, 75.9% in SCREAM, and 92.6% in Maccabi) whereas sulfonylureas use was greater in NHANES (31.5% in NHANES, 16.0% in SCREAM, and 14.9% in Maccabi). Adoption of dipeptidyl peptidase 4 inhibitors and sodium-glucose cotransporter 2 inhibitors (SGLT2i) was slower in NHANES and SCREAM than in Maccabi. History of atherosclerotic cardiovascular disease, heart failure, reduced kidney function, or albuminuria was not consistently associated with greater use of SGLT2i or glucagon-like peptide 1 receptor agonists (GLP1RA) across the three countries. CONCLUSIONS: There were substantial differences in real-world use of glucose-lowering medications across the U.S., Sweden, and Israel, with more optimal pharmacologic management in Israel. Variation in access to care and medication cost across countries may have contributed to these differences. SGLT2i and GLP1RA use in patients at high risk was limited in all three countries during this time period.

Temporal patterns selection for All-Cause Mortality prediction in T2D with ANNs.

Mortality prevention in T2D elderly population having Chronic Kidney Disease (CKD) may be possible thorough risk assessment and predictive modeling. In this study we investigate the ability to predict mortality using heterogeneous Electronic Health Records data. Temporal abstraction is employed to transform the heterogeneous multivariate temporal data into a uniform representation of symbolic time intervals, from which then frequent Time Intervals Related Patterns (TIRPs) are discovered. However, in this study a novel representation of the TIRPs is introduced, which enables to incorporate them in Deep Learning Networks. We describe here the use of iTirps and bTirps, in which the TIRPs are represented by a integer and binary vector representing the time respectively. While bTirp represents whether a TIRP's instance was present, iTirp represents whether multiple instances were present. While the framework showed encouraging results, a major challenge is often the large number of TIRPs, which may cause the models to under-perform. We introduce a novel method for TIRPs' selection method, called TIRP Ranking Criteria (TRC), which is consists on the TIRP's metrics, such as the differences in its recurrences, its frequencies, and the average duration difference between the classes. Additionally, we introduce an advanced version, called TRC Redundant TIRP Removal (TRC-RTR), TIRPs that highly correlate are candidates for removal. Then the selected subset of iTirp/bTirps is fed into a Deep Learning architecture like a Recurrent Neural Network or a Convolutional Neural Network. Furthermore, a predictive committee is utilized in which raw data and iTirp data are both used as input. Our results show that iTirps-based models that use a subset of iTirps based on the TRC-RTR method outperform models that use raw data or models that use full set of discovered iTirps.

All-cause mortality prediction in T2D patients with iTirps.

Mortality in the type II diabetic elderly population can sometimes be prevented through intervention, for which risk assessment through predictive modeling is required. Since Electronic Health Records data are typically heterogeneous and sparse, the use of Temporal Abstraction and time intervals mining to discover frequent Time Intervals Related Patterns (TIRPs) is employed. While TIRPs are used as features for a predictive model, the temporal relations between them in general, and among each TIRP's instances are not represented. We introduce a novel TIRP based representation called integer-TIRP (iTirp) in which the TIRPs become channels containing values that represent the TIRP instances that were detected at each time point. Then the iTirp representation is fed into a Deep Learning architecture, that learns this kind of temporal relations, using a Recurrent Neural Network or a Convolutional Neural Network. Additionally, a predictive committee is introduced in which raw data and iTirp data are concatenated as inputs. Our results show that iTirps based models outperform the use of deep learning with raw data, resulting in 82% AUC.