Daily Endocrinology Research Analysis

BACKGROUND: Automated insulin delivery (AID) systems have been shown to improve glycaemic outcomes in people with type 1 diabetes managed with insulin pump therapy. No randomised studies have evaluated the benefits of tubeless AID in both adults and children with suboptimal glycaemia compared with multiple daily injections. We aimed to evaluate the safety and efficacy of a tubeless AID system compared with multiple daily injections in this population. METHODS: RADIANT was a multicentre, international, parallel-group, open-label, randomised, controlled trial done in 19 hospitals in the UK, Belgium, and France. Participants aged 4-70 years with type 1 diabetes managed with multiple daily injections and continuous glucose monitoring and who had HbA FINDINGS: Between Sept 11, 2023, and April 26, 2024, 188 participants were randomly assigned to the AID group (n=125) or the control group (n=63). The AID group had a greater reduction in HbA INTERPRETATION: Results from this trial show the clinical efficacy of direct transition from multiple daily injections to tubeless AID in adults and children with type 1 diabetes, with no safety concerns, supporting AID as a therapeutic option within standard of care for people with type 1 diabetes. FUNDING: Insulet Corporation.

BACKGROUND: Deep learning has shown promise in diabetes management but faces challenges in real-world application due to its "black-box" nature, characterized by opaque internal decision-making processes. Explainable artificial intelligence (XAI) methods have been proposed to enhance model transparency. However, most of current XAI methods applied in the medical field often ignore the interaction of features in complex environments and pose deviation from clinical domain knowledge. METHODS: Our study used two Electronic Health Record (EHR) cohorts of hospitalized patients with type 2 diabetes (T2DM), including an internal dataset of 1,275 inpatients (mean age 58.5 ± 14.3 years) and an external dataset of 292 patients (mean age 69.3 ± 14.5 years). We introduce an expert-guided XAI framework to improve the transparency and trustworthiness of deep learning models for insulin titration in diabetes management. The framework utilizes a post-hoc XAI model named Shapley Taylor Interaction Index (STII) to capture the impact of feature interactions. Additionally, the model is refined iteratively in a doctor-in-the-loop (DIL) process by encoding clinical constraints to align with medical expertise. RESULTS: Here we show that our STII-DIL model could explore the interaction factors and reduce unreasonable explanations compared with other explanation models. The final XAI system explanations demonstrated strong alignment with experts' explanations and increased correctness by expert evaluation An AI-human collaboration study revealed that insulin titration accuracy significantly improved for junior clinicians with STII-DIL assistance, while senior clinicians showed minimal change. Both junior and senior clinicians reported increased confidence when using the STII-DIL system. CONCLUSIONS: We present an explainable deep learning framework that combines post-hoc XAI and expert domain knowledge to provide transparent and expert-aligned explanations for insulin titration in type 2 diabetes management. This framework enhances decision-making accuracy and confidence, especially for junior clinicians, and may facilitate broader clinical adoption of AI-assisted decision-making tools. This study addresses the need for transparent and reliable artificial intelligence (AI) tools in diabetes care. We developed an explainable deep learning system that helps doctors adjust insulin doses by showing how different clinical factors contribute to its recommendations. The system combines an AI explanation method with guidance from medical experts, allowing the model to be refined to better match real clinical reasoning. We found that this approach produced clearer and more accurate explanations and supported better decision-making, especially for junior clinicians. Both junior and senior clinicians also reported greater confidence when using the system. These findings suggest that explainable AI may improve safety and support wider clinical use of AI-assisted diabetes management.

CONTEXT: Acromegaly poses clinical challenges in terms of early diagnosis and intervention. Therefore, the development of novel diagnostic tools is essential. Although artificial intelligence (AI) models based on external appearance have been proposed, privacy concerns have limited their use. OBJECTIVE: To develop a privacy-conscious deep learning model for detecting acromegaly using hand images. METHODS: This nationwide multicenter study enrolled 716 patients (317 with acromegaly and 399 controls) and 11 480 images from 15 Japanese pituitary centers. The inclusion criteria were age ≥18 years and care received at the participating facilities. Hand images focusing on the dorsal and fist sign, excluding the palm/fingerprint regions, were used to develop the model. The data were split into training/validation (12 centers) and test (3 centers) datasets. A ResNet-50-based model was trained using PyTorch with data augmentation and 5-fold cross-validation. For each patient, the predictions were averaged over 4 images. The performance of the model was compared with that of endocrinologists. RESULTS: The model achieved a sensitivity of 0.89, specificity of 0.91, positive predictive value of 0.88, negative predictive value of 0.93, F1-score of 0.89, and an area under the receiver operating characteristic curve of 0.96, outperforming specialists (F1-score range: 0.43-0.63). CONCLUSION: This study highlights the utility of dorsal hand and fist sign as diagnostic clues for acromegaly, which the AI model captured more accurately than endocrinologists. Using this privacy-conscious feature, this model can be deployed in public settings like health checkups. Further validation using larger datasets, including healthy individuals and diverse diseases, is necessary.