Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

Guan, Zhouyu; Li, Huating; Liu, Ruhan; Cai, Chun; Liu, Yuexing; Li, Jiajia; Wang, Xiangning; Huang, Shan; Wu, Liang; Liu, Dan; Yu, Shujie; Wang, Zheyuan; Shu, Jia; Hou, Xuhong; Yang, Xiaokang; Jia, Weiping; Sheng, Bin

doi:10.1016/j.xcrm.2023.101213

Cited by 57 publications

(15 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The increasing data exchange between devices, EHRs, and other sources opens up more possibilities for using AI in diabetes care 95,96 . There are potentially many other AI applications that could benefit from IPDM, such as supporting automated screening and classification of diabetes, predicting the onset and complications of diabetes, for example, diabetic retinopathy as well as automated decision support, care coordination, task planning and lifestyle management including health education 97 . In the past decade, population research has increasingly used real‐world data from community settings.…”

Section: Health System Structure and Functions To Support Ipdmmentioning

confidence: 99%

“…The use of patient data is very sensitive and it is crucial to prioritize data security and safety measures when developing and using algorithms. This is because incorrect responses could potentially harm patients 97,110 …”

Section: Health System Structure and Functions To Support Ipdmmentioning

confidence: 99%

“…A health ecosystem can help overcome organizational and technological challenges through a combined strategy for IPDM service provision, an interoperable data infrastructure, research and development (including AI), public–private partnerships, fundraising and governance 166–169 . Such an eco‐system is also suitable for collecting real‐world data for the development and evaluation AI‐based solutions 97 …”

Section: Implementation Of Digitally Enabled Ipdmmentioning

confidence: 99%

“…95,96 There are potentially many other AI applications that could benefit from IPDM, such as supporting automated screening and classification of diabetes, predicting the onset and complications of diabetes, for example, diabetic retinopathy as well as automated decision support, care coordination, task planning and lifestyle management including health education. 97 In the past decade, population research has increasingly used real-world data from community settings. This includes both health and non-health data sources to optimize diabetes care and generate real-world evidence.…”

Section: Artificial Intelligencementioning

confidence: 99%

“…This is because incorrect responses could potentially harm patients. 97,110 In the context of IPDM, it is crucial to ensure that healthcare providers can access interoperable patient data as they are exchanged across different care settings. 111 Patients and healthcare providers need to be able to trust the digital technologies that are being used in diabetes care.…”

Section: Artificial Intelligencementioning

confidence: 99%

See 4 more Smart Citations

What is meant by ‘integrated personalized diabetes management’: A view into the future and what success should look like

Guldemond

2024

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

Integrated personalized diabetes management (IPDM) has emerged as a promising approach to improving outcomes in patients with diabetes mellitus (DM). This care approach emphasizes the integration and coordination of different providers, including physicians, nurses, dietitians, social workers and pharmacists. The goal of IPDM is to provide patients with personalized care that is tailored to their needs. This review addresses the concept of integrated care and the use of technology (including data, software applications and artificial intelligence) as well as managerial, regulatory and financial aspects. The implementation and upscaling of digitally enabled IPDM are discussed, with elaboration of successful practices and related evidence. Finally, recommendations are made. It is concluded that the adoption of digitally enabled IPDM on a global level is inevitable, considering the challenges created by an increasing prevalence of patients with DM and the need for better outcomes and improvement of health system sustainability.

show abstract

Section: Health System Structure and Functions To Support Ipdmmentioning

confidence: 99%

Section: Health System Structure and Functions To Support Ipdmmentioning

confidence: 99%

Section: Implementation Of Digitally Enabled Ipdmmentioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

See 3 more Smart Citations

What is meant by ‘integrated personalized diabetes management’: A view into the future and what success should look like

Guldemond

2024

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

show abstract

A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms

Qian,

Sheng,

Chen

et al. 2024

JAMA Ophthalmol

View full text Add to dashboard Cite

ImportanceMyopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings.ObjectivesTo evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists.Design, Setting, and ParticipantsThe Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024.ExposureDL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation.Main Outcomes and MeasuresMM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE).ResultsThe 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P &lt; .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P &lt; .001).Conclusions and RelevanceIn this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

show abstract

Myopic Maculopathy Analysis Using Multi-task Learning and Pseudo Labeling

Kim,

Nam

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

Cited by 57 publications

References 143 publications

What is meant by ‘integrated personalized diabetes management’: A view into the future and what success should look like

What is meant by ‘integrated personalized diabetes management’: A view into the future and what success should look like

A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms

Myopic Maculopathy Analysis Using Multi-task Learning and Pseudo Labeling

Contact Info

Product

Resources

About