Ivana Jankovic
Research Subjects
Ivana Jankovic has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Adela Kapuścińska
Carelon Digital Platforms, Design & User Research, Elevance Health, Poland
1 shared publication - Alexandra J. Lansky
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
1 shared publication Allison Bradee
1 shared publicationDana Lazar
Yale University School of Medicine, New Haven, Connecticut
1 shared publicationDavin C. Ashraf
1 shared publication- Eleanor R. Burgess
Carelon Digital Platforms, Design & User Research, Elevance Health, United States
1 shared publication
Latest Publications
- 12 November 2026
- Published by Elsevier in Ophthalmology
Fourteen-Year Changes in Operative Time and Reimbursement for Ophthalmic Surgery
- 12 November 2026
- Published by Elsevier in Ophthalmology
Fourteen-Year Changes in Operative Time and Reimbursement for Ophthalmic Surgery
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Healthcare AI Treatment Decision Support: Design Principles to Enhance Clinician Adoption and Trust
Artificial intelligence (AI) supported clinical decision support (CDS) technologies can parse vast quantities of patient data into meaningful insights for healthcare providers. Much work is underway to determine the technical feasibility and the accuracy of AI-driven insights. Much less is known about what insights are considered useful and actionable by healthcare providers, their trust in the insights, and clinical workflow integration challenges. Our research team used a conceptual prototype based on AI-generated treatment insights for type 2 diabetes medications to elicit feedback from 41 U.S.-based clinicians, including primary care and internal medicine physicians, endocrinologists, nurse practitioners, physician assistants, and pharmacists. We contribute to the human-computer interaction (HCI) community by describing decision optimization and design objective tensions between population-level and personalized insights, and patterns of use and trust of AI systems. We also contribute a set of 6 design principles for AI-supported CDS.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessHealthcare AI Treatment Decision Support: Design Principles to Enhance Clinician Adoption and Trust
Artificial intelligence (AI) supported clinical decision support (CDS) technologies can parse vast quantities of patient data into meaningful insights for healthcare providers. Much work is underway to determine the technical feasibility and the accuracy of AI-driven insights. Much less is known about what insights are considered useful and actionable by healthcare providers, their trust in the insights, and clinical workflow integration challenges. Our research team used a conceptual prototype based on AI-generated treatment insights for type 2 diabetes medications to elicit feedback from 41 U.S.-based clinicians, including primary care and internal medicine physicians, endocrinologists, nurse practitioners, physician assistants, and pharmacists. We contribute to the human-computer interaction (HCI) community by describing decision optimization and design objective tensions between population-level and personalized insights, and patterns of use and trust of AI systems. We also contribute a set of 6 design principles for AI-supported CDS.
- 21 October 2020
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 15 (1) , 174-176
Proposed Use of Continuous Glucose Monitoring for Care of Critically Ill COVID-19 Patients
Coronavirus disease 2019 (COVID-19) has disproportionately affected patients with diabetes. Mounting evidence has shown that adequate inpatient glycemic control may decrease the risk of mortality. In critically ill patients, insulin drips are the most effective means of controlling blood glucose. However, resource limitations such as the availability of protective equipment and nursing time have discouraged the use of insulin drips during COVID-19. In this commentary, we review existing evidence on the importance of glycemic control in COVID-19 patients with diabetes and propose a protocol for utilizing continuous glucose monitors (CGMs) to improve glycemic control by decreasing the need for bedside management in critically ill COVID-19 patients.
- 21 October 2020
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 15 (1) , 174-176
Proposed Use of Continuous Glucose Monitoring for Care of Critically Ill COVID-19 Patients
Coronavirus disease 2019 (COVID-19) has disproportionately affected patients with diabetes. Mounting evidence has shown that adequate inpatient glycemic control may decrease the risk of mortality. In critically ill patients, insulin drips are the most effective means of controlling blood glucose. However, resource limitations such as the availability of protective equipment and nursing time have discouraged the use of insulin drips during COVID-19. In this commentary, we review existing evidence on the importance of glycemic control in COVID-19 patients with diabetes and propose a protocol for utilizing continuous glucose monitors (CGMs) to improve glycemic control by decreasing the need for bedside management in critically ill COVID-19 patients.
- 1 June 2020
- Published by American Diabetes Association in Diabetes
- Vol. 69 (Supplement)
1235-P: Identifying Trends in the Management of Inpatient Diabetes at a University Teaching Hospital, 2008-2018
Introduction: A substantial proportion of inpatients experience hyperglycemia during hospitalization. Use of basal insulin has been recommended by ADA guidelines since 2007, however the uptake of this recommendation has been slow. Here, we characterize the adoption of basal insulin in inpatients at one adult academic hospital. Methods: De-identified data from the hospital’s electronic health record repository was used to identify a cohort of patients who received subcutaneous insulin during their hospitalization between 03/26/2008 and 12/30/2018. To capture patients for whom a generalist could be expected to manage their hyperglycemia, we excluded patients receiving insulin via pump, U-500 insulin, single doses >100U, or insulins ordered < 10 times, as well as those with a creatinine > 2mg/dL at any time during admission. Results: In the cohort of 61,947 inpatient encounters in which insulin was given, no basal insulin was ordered in 61%, decreasing from a 78% in 2008 to 53% in 2018. The annual number of encounters in which insulin was given increased >20% over the decade. The proportions of blood glucoses (BGs) > 200 mg/dL (28% vs. 14%) or <70 mg/dL (1.2% vs. 0.6%) were higher for patients ordered for basal insulin. Although hypoglycemia decreased over time (1.2% to 0.9% of BGs), hyperglycemia increased (16% to 26% of BGs). Conclusions: Despite improvements since basal insulin became a guidelines recommendation, the rate of inpatient basal insulin orders remained < 50% as of 2018 at one academic center. The number of patients receiving insulin and the proportion of hyperglycemia has increased, whereas the incidence of hypoglycemia in this population decreased over time. Disclosure: I. Jankovic: None. J. Chen: None. Funding: Diabetes, Endocrinology, and Metabolism Training Grant (5T32DK007217-44)
- 1 June 2020
- Published by American Diabetes Association in Diabetes
- Vol. 69 (Supplement)
1235-P: Identifying Trends in the Management of Inpatient Diabetes at a University Teaching Hospital, 2008-2018
Introduction: A substantial proportion of inpatients experience hyperglycemia during hospitalization. Use of basal insulin has been recommended by ADA guidelines since 2007, however the uptake of this recommendation has been slow. Here, we characterize the adoption of basal insulin in inpatients at one adult academic hospital. Methods: De-identified data from the hospital’s electronic health record repository was used to identify a cohort of patients who received subcutaneous insulin during their hospitalization between 03/26/2008 and 12/30/2018. To capture patients for whom a generalist could be expected to manage their hyperglycemia, we excluded patients receiving insulin via pump, U-500 insulin, single doses >100U, or insulins ordered < 10 times, as well as those with a creatinine > 2mg/dL at any time during admission. Results: In the cohort of 61,947 inpatient encounters in which insulin was given, no basal insulin was ordered in 61%, decreasing from a 78% in 2008 to 53% in 2018. The annual number of encounters in which insulin was given increased >20% over the decade. The proportions of blood glucoses (BGs) > 200 mg/dL (28% vs. 14%) or <70 mg/dL (1.2% vs. 0.6%) were higher for patients ordered for basal insulin. Although hypoglycemia decreased over time (1.2% to 0.9% of BGs), hyperglycemia increased (16% to 26% of BGs). Conclusions: Despite improvements since basal insulin became a guidelines recommendation, the rate of inpatient basal insulin orders remained < 50% as of 2018 at one academic center. The number of patients receiving insulin and the proportion of hyperglycemia has increased, whereas the incidence of hypoglycemia in this population decreased over time. Disclosure: I. Jankovic: None. J. Chen: None. Funding: Diabetes, Endocrinology, and Metabolism Training Grant (5T32DK007217-44)