Unlabelled: This research letter presents a cross-sectional analysis comparing the agreement between artificial intelligence models and nephrologists in responding to common patient questions about diabetic nephropathy.
Unlabelled: This research letter presents a cross-sectional analysis comparing the agreement between artificial intelligence models and nephrologists in responding to common patient questions about diabetic nephropathy.
Background: Diabetic ketoacidosis represents a significant and potentially life-threatening complication of diabetes, predominantly observed in individuals with type 1 diabetes (T1D). Studies have documented suboptimal adherence to diabetes management among children and adolescents, as evidenced by deficient ketone monitoring practices.
Objective: The aim of the study was to explore the potential for prediction of elevated ketone bodies from continuous glucose monitoring (CGM) and insulin data in pediatric and adult patients with T1D using a closed-loop system.
Methods: Participants used the Dexcom G6 CGM system and the iLet Bionic Pancreas system for insulin administration for up to 13 weeks. We used supervised binary classification machine learning, incorporating feature engineering to identify elevated ketone bodies (>0.6 mmol/L). Features were derived from CGM, insulin delivery data, and self-monitoring of blood glucose to develop an extreme gradient boosting-based prediction model. A total of 259 participants aged 6-79 years with over 49,000 days of full-time monitoring were included in the study.
Results: Among the participants, 1768 ketone samples were eligible for modeling, including 383 event samples with elevated ketone bodies (≥0.6 mmol/L). Insulin, self-monitoring of blood glucose, and current glucose measurements provided discriminative information on elevated ketone bodies (receiver operating characteristic area under the curve [ROC-AUC] 0.64-0.69). The CGM-derived features exhibited stronger discrimination (ROC-AUC 0.75-0.76). Integration of all feature types resulted in an ROC-AUC estimate of 0.82 (SD 0.01) and a precision recall-AUC of 0.53 (SD 0.03).
Conclusions: CGM and insulin data present a valuable avenue for early prediction of patients at risk of elevated ketone bodies. Furthermore, our findings indicate the potential application of such predictive models in both pediatric and adult populations with T1D.
Unlabelled: Type 2 diabetes mellitus affects over 500 million people globally, with 10%-20% requiring surgery. Patients with diabetes are at increased risk for perioperative complications, including prolonged hospital stays and higher mortality, primarily due to perioperative hyperglycemia. Managing blood glucose during the perioperative period is challenging, and conventional monitoring is often inadequate to detect rapid fluctuations. Clinical decision support systems (CDSS) are emerging tools to improve perioperative diabetes management by providing real-time glucose data and medication recommendations. This viewpoint examines the role of CDSS in perioperative diabetes care, highlighting their benefits and limitations. CDSS can help manage blood glucose more effectively, preventing both hyperglycemia and hypoglycemia. However, technical and integration challenges, along with clinician acceptance, remain significant barriers.
Unlabelled: Type 2 diabetes mellitus has seen a continuous rise in prevalence in recent years, and a similar trend has been observed in the increased availability of glucose-lowering drugs. There is a need to understand the variation in treatment response to these drugs to be able to predict people who will respond well or poorly to a drug. Electronic health records, clinical trials, and observational studies provide a huge amount of data to explore predictors of drug response. The use of artificial intelligence (AI), which includes machine learning and deep learning techniques, has the capacity to improve the prediction of treatment response in patients. AI can assist in the analysis of vast datasets to identify patterns and may provide valuable information on selecting an effective drug. Predicting an individual's response to a drug can aid in treatment selection, optimizing therapy, exploring new therapeutic options, and personalized medicine. This viewpoint highlights the growing evidence supporting the potential of AI-based methods to predict drug response with accuracy. Furthermore, the methods highlight a trend toward using ensemble methods as preferred models in drug response prediction studies.
Background: School-partnered interventions may improve health outcomes for children with type 1 diabetes, though there is limited evidence to support their effectiveness and sustainability. Family, school, or health system factors may interfere with intervention usability and implementation.
Objective: To identify and address potential implementation barriers during intervention development, we combined methods in user-centered design and implementation science to adapt an evidence-based psychosocial intervention, the collaborative care model, to a virtual school-partnered collaborative care (SPACE) model for type 1 diabetes between schools and diabetes medical teams.
Methods: We recruited patient, family, school, and health system partners (n=20) to cocreate SPACE through iterative, web-based design sessions using a digital whiteboard (phase 1). User-centered design methods included independent and group activities for idea generation, visual voting, and structured critique of the evolving SPACE prototype. In phase 2, the prototype was evaluated with the usability evaluation for evidence-based psychosocial interventions methods. School nurses reviewed the prototype and tasks in cognitive walkthroughs and completed the Intervention Usability Scale (IUS). Two members of the research team independently identified and prioritized (1-3 rating) discrete usability concerns. We evaluated the relationship between prioritization and the percentage of nurses reporting each usability issue with Spearman correlation. Differences in IUS scores by school nurse characteristics were assessed with ANOVA.
Results: In the design phase, the partners generated over 90 unique ideas for SPACE, prioritizing elements pertaining to intervention adaptability, team-based communication, and multidimensional outcome tracking. Following three iterations of prototype development, cognitive walkthroughs were completed with 10 school nurses (n=10, 100% female; mean age 48.5, SD 9.5 years) representing different districts and years of experience. Nurses identified 16 discrete usability issues (each reported by 10%-60% of participants). Two issues receiving the highest priority (3.0): ability to access a virtual platform (n=3, 30% of participants) and data-sharing mechanisms between nurses and providers (n=6, 60% of participants). There was a moderate correlation between priority rating and the percentage of nurses reporting each issue (ρ=0.63; P=.01). Average IUS ratings (77.8, SD 11.1; 100-point scale) indicated appropriate usability. There was no difference in IUS ratings by school nurse experience (P=.54), student caseload (P=.12), number of schools covered (P=.90), or prior experience with type 1 diabetes (P=.83), suggesting that other factors may influence usability. The design team recommended strategies for SPACE implementation to overcome high-priority issues, including training users
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：