Khoo Teck Puat Hospital (Abbreviation: KTPH) is a 795-bed general and acute care hospital located at Yishun in Singapore. Named after Singaporean hotelier, Khoo Teck Puat, the hospital is part of an integrated development together with the adjoining Yishun Community Hospital. The hospital was officially opened by Minister Mentor Lee Kuan Yew on 15 November 2010, but began seeing outpatients and day surgery patients on 28 March that year. Spanning over 3.5 hectares (8.6 acres) in the Yishun Central Area overlooking the scenic Yishun Pond. The hospital offers an extensive range of medical services and healthcare options for residents living in the north. As of October 2017, KTPH merged with the National Healthcare Group and is now known as Yishun Health, together with Yishun Community Hospital and Admiralty Medical Centre.
Accurate detection of ocular signs is essential for early diagnosis of eye diseases, but current AI approaches using facial or external ocular images include non-essential information, compromising performance and patient privacy. We conducted a multinational retrospective study of 2360 eyes from 1180 half-face images of thyroid eye disease patients across five racial groups from five hospitals in three countries. We developed a Dense Squeeze-and-Excitation Network (DSE-Net) to segment eyelid, conjunctiva, lacrimal caruncle, and eyeball, minimizing exposure and enhancing privacy. DSE-Net achieved Dice coefficient of 84.7%, 84.8%, 92.7%, and 95.1%, outperforming seven segmentation models. We then built SegmenView, employing LeNet, AlexNet, ResNet50, and VGGNet16 to detect eyelid edema, conjunctival erythema, caruncle or plica edema, and exophthalmos. SegmenView achieved internal Area Under the Curve (AUCs) of 71.09%, 80.81%, 90.07%, and 82.86%; external AUCs ranging 55.58%-84.29% across two test datasets, outperforming half-face and periocular models. We also compared SegmenView with four privacy-preserving methods, showing its superior ability to balance privacy protection with diagnostic accuracy. Additionally, visualizations based on Gradient-weighted Class Activation Mapping (Grad-CAM) further enhanced the model's interpretability. Our approach demonstrates high accuracy, generalizability, and potential for lightweight, privacy-preserving ocular sign detection.
Rapid advances in the diagnosis and treatment of thyroid eye disease (TED) have led to the development of three patient care guidelines by regional professional societies: the European Group on Graves’ Orbitopathy, the Oculoplastics and Orbital Diseases Group of the Chinese Medical Association Ophthalmology Branch/Thyroid Group of the Chinese Medical Association Endocrinology Branch, and the American Thyroid Association/European Thyroid Association. Although broad consensus can be found across the three guidelines, important differences could affect patient management. This review examines and compares the recommendations of these guidelines across 11 dimensions, from disease diagnosis to treatment strategies. We explore the possible root sources of these variations. The review also suggests future directions and potential implications, thus providing a comprehensive perspective of current and future management of TED.
In high-stakes domains such as healthcare, privacy concerns severely limit the use of real-world training data. Differentially private (DP) synthetic data offers a promising alternative with formal privacy guarantees, but achieving strong utility remains challenging for clinical note generation due to domain specificity and long-form text complexity. We present Term2Note, a method for synthesising full-length clinical notes under strong DP constraints. By structurally separating content and form, Term2Note generates section-wise note content conditioned on medical terms, with terms and notes privatised under separate DP constraints, and applies a DP quality maximiser to improve outputs. Experiments demonstrate that Term2Note produces synthetic notes with statistical properties closely aligned with real clinical notes, and that downstream models trained on these notes achieve performance comparable to those trained on real clinical data. Compared to existing DP text generation baselines, Term2Note substantially improves both fidelity and utility, without relying on label distribution assumptions, highlighting its effectiveness as a practical privacy-preserving alternative to real clinical notes.
IntroductionPreviously, we observed that subgroups of type 2 diabetes (T2D) - mild obesity-related diabetes (MOD), mild age-related diabetes (MARD), severe insulin-resistant diabetes (SIRD) - had distinct characteristics and complications. This study aims to investigate if movement behaviour also differs by T2D subgroup. Given that physical activity (PA) reduces the risk of complications, identifying less active subgroups could inform more targeted interventions.MethodsUsing age at T2D onset, body mass index, hbA1c, homeostasis model assessment 2 estimates of beta-cell function and insulin resistance, 706 study participants were classified into T2D subgroups. Using time spent in light PA, moderate-vigorous PA, day inactivity and night sleep per 24-hour, the participants were classified into three profiles. Regression models were used to examine the association between T2D subgroup (exposure) and movement behaviour (outcome).ResultsCompared to MOD, the relative risk ratio (RRR) of having the least active profile was 0.69 (95%CI 0.43-1.10), while the RRR of having the most active profile was 1.53 (95%CI 0.82-2.83) for MARD. The RRRs of having the least and most active profile was 1.32 (95%CI 0.85-2.04) and 1.44 (95%CI 0.76-2.72) respectively for SIRD.ConclusionUnderstanding the relationship between T2D subgroups and movement behaviour is a step towards advocating for PA intervention tailored to each subgroup's unique characteristics.
