The growing popularity of wearable devices for continuous sensing has made personal health data increasingly available, yet methods for data interpretation are still a work in progress. This paper investigates potential under-utilization of wearable device data in diabetes management and develops an analytic approach - GlucoMine - to uncover individualized patterns in extended periods of such data to support and improve care. In addition, we conduct a user study with clinicians to assess and compare conventional tools used for reviewing wearable device data in diabetes management with the proposed solution. Using 3-6 months of continuous glucose monitor (CGM) data from 54 patients with type 1 diabetes, we found that: 1) the recommended practice of reviewing only short periods (e.g., the most recent 2-weeks) of CGM data based on correlation analysis is not sufficient for finding hidden patterns of poor management; 2) majority of subjects (96% in this study) had clinically-recognized episodes of recurrent adverse glycemic events observable from analysis of extended periods of their CGM data; 3) majority of clinicians (89% in this study) believe there is benefit to be gained in having an algorithm for extracting patterns of adverse glycemic events from longer periods of wearable device data. Findings from our user study also provides insights, including strengths and weakness of various data presentation tools, to guide development of better solutions that improve the use of wearable device data for patient care.
Background: Artificial intelligence (AI) has the potential to dramatically alter healthcare by enhancing how we diagnosis and treat disease. One promising AI model is ChatGPT, a large general-purpose language model trained by OpenAI. The chat interface has shown robust, human-level performance on several professional and academic benchmarks. We sought to probe its performance and stability over time on surgical case questions. Methods: We evaluated the performance of ChatGPT-4 on two surgical knowledge assessments: the Surgical Council on Resident Education (SCORE) and a second commonly used knowledge assessment, referred to as Data-B. Questions were entered in two formats: open-ended and multiple choice. ChatGPT output were assessed for accuracy and insights by surgeon evaluators. We categorized reasons for model errors and the stability of performance on repeat encounters. Results: A total of 167 SCORE and 112 Data-B questions were presented to the ChatGPT interface. ChatGPT correctly answered 71% and 68% of multiple-choice SCORE and Data-B questions, respectively. For both open-ended and multiple-choice questions, approximately two-thirds of ChatGPT responses contained non-obvious insights. Common reasons for inaccurate responses included: inaccurate information in a complex question (n=16, 36.4%); inaccurate information in fact-based question (n=11, 25.0%); and accurate information with circumstantial discrepancy (n=6, 13.6%). Upon repeat query, the answer selected by ChatGPT varied for 36.4% of inaccurate questions; the response accuracy changed for 6/16 questions. Conclusion: Consistent with prior findings, we demonstrate robust near or above human-level performance of ChatGPT within the surgical domain. Unique to this study, we demonstrate a substantial inconsistency in ChatGPT responses with repeat query. This finding warrants future consideration and presents an opportunity to further train these models to provide safe and consistent responses. Without mental and/or conceptual models, it is unclear whether language models such as ChatGPT would be able to safely assist clinicians in providing care.
To the best of our knowledge, there are no published data on the historical and recent use of CGM in clinical trials of pharmacological agents used in the treatment of diabetes. We analyzed 2,032 clinical trials of 40 antihyperglycemic therapies currently on the market with a study start date between 1 January 2000 and 31 December 2019. According to ClinicalTrials.gov, 119 (5.9%) of these trials used CGM. CGM usage in clinical trials has increased over time, rising from <5% before 2005 to 12.5% in 2019. However, it is still low given its inclusion in the American Diabetes Association’s latest guidelines and known limitations of A1C for assessing ongoing diabetes care.
Despite the growing momentum behind a movement to augment adoption of continuous glucose monitoring (CGM) in clinical practice and investigation, to the best of our knowledge, there are no published data on the historical and recent use of CGM in clinical trials of pharmacologic agents used in the treatment of diabetes. We analyzed 2,032 clinical trials of 40 diabetes therapies currently on the market with a study start date between 1 January 2000 and 31 December 2019. According to ClinicalTrials.gov listings, 119 (5.9%) of these trials used CGM. CGM usage in clinical trials has increased over time, rising from <5% before 2005 to 12.5% in 2019. However, it is still low given its inclusion in the American Diabetes’s Association’s latest guidelines and known limitations of A1C for assessing ongoing diabetes care.
Despite the growing momentum behind a movement to augment adoption of continuous glucose monitoring (CGM) in clinical practice and investigation, to the best of our knowledge, there are no published data on the historical and recent use of CGM in clinical trials of pharmacologic agents used in the treatment of diabetes. We analyzed 2,032 clinical trials of 40 diabetes therapies currently on the market with a study start date between 1 January 2000 and 31 December 2019. According to ClinicalTrials.gov listings, 119 (5.9%) of these trials used CGM. CGM usage in clinical trials has increased over time, rising from <5% before 2005 to 12.5% in 2019. However, it is still low given its inclusion in the American Diabetes’s Association’s latest guidelines and known limitations of A1C for assessing ongoing diabetes care.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.