The application of large language models in medicine: A scoping review.

This study systematically reviewed the application of large language models (LLMs) in medicine, analyzing 550 selected studies from a vast literature search. LLMs like ChatGPT transformed healthcare by enhancing diagnostics, medical writing, education, and project management. They assisted in drafting medical documents, creating training simulations, and streamlining research processes. Despite their growing utility in assisted diagnosis and improving doctor-patient communication, challenges persisted, including limitations in contextual understanding and the risk of over-reliance. The surge in LLM-related research indicated a focus on medical writing, diagnostics, and patient communication, but highlighted the need for careful integration, considering validation, ethical concerns, and the balance with traditional medical practice. Future research directions suggested a focus on multimodal LLMs, deeper algorithmic understanding, and ensuring responsible, effective use in healthcare.

Heparin-free veno-arterial extracorporeal membrane oxygenation in lung transplantation: a retrospective cohort study.

BACKGROUND: In lung transplantation (LTx) surgery, veno-arterial extracorporeal membrane oxygenation (VA-ECMO) can provide mechanical circulatory support to patients with cardiopulmonary failure. However, the use of heparin in the administration of ECMO can increase blood loss during LTx. This study aimed to evaluate the safety of heparin-free V-A ECMO strategies. METHODS: From September 2019 to April 2022, patients who underwent lung transplantation at the First Affiliated Hospital of Guangzhou Medical University were retrospectively reviewed. A total of 229 patients were included, including 117 patients in the ECMO group and 112 in the non-ECMO group. RESULT: There was no significant difference in the incidence of thrombus events and bleeding requiring reoperation between the two groups. The in-hospital survival rate after single lung transplantation (SLTx) was 81.08%in the ECMO group and 85.14% in the Non-ECMO group, (P = 0.585). The in-hospital survival rate after double lung transplantation (DLTx) was 80.00% in the ECMO group and 92.11% in the Non-ECMO groups (P = 0.095). CONCLUSIONS: In conclusion, the findings of this study suggest that the heparin-free V-A ECMO strategy in lung transplantation is a safe approach that does not increase the incidence of perioperative thrombotic events or bleeding requiring reoperation.

Bi-DexHands: Towards Human-Level Bimanual Dexterous Manipulation.

Achieving human-level dexterity in robotics remains a critical open problem. Even simple dexterous manipulation tasks pose significant difficulties due to the high number of degrees of freedom and the need for cooperation among heterogeneous agents (e.g., finger joints). While some researchers have utilized reinforcement learning (RL) to control a single hand in manipulating objects, tasks that require coordinated bimanual cooperation are still under-explored due to the fewer suitable environments, which can result in difficulties and sub-optimal performance. To address these challenges, we introduce Bi-DexHands, a simulator with two dexterous hands featuring 20 bimanual manipulation tasks and thousands of target objects, designed to match various levels of human motor skills based on cognitive science research. We developed Bi-DexHands in Issac Gym, enabling highly efficient RL training at over 30,000 frames per second using a single NVIDIA RTX 3090. Based on Bi-DexHands, we present a comprehensive evaluation of popular RL algorithms in different settings, including single-agent/multi-agent RL, offline RL, multi-task RL, and meta RL. Our findings show that on-policy algorithms, such as PPO, can master simple manipulation tasks that correspond to those of 48-month-old babies, such as catching a flying object or opening a bottle. Furthermore, multi-agent RL can improve the ability to perform manipulations that require skilled bimanual cooperation, such as lifting a pot or stacking blocks. Despite achieving success in individual tasks, current RL algorithms struggle to learn multiple manipulation skills in most multi-task and few-shot learning scenarios. This highlights the need for further research and development within the RL community.

Object Detection of Flexible Objects with Arbitrary Orientation Based on Rotation-Adaptive YOLOv5.

It is challenging to accurately detect flexible objects with arbitrary orientation from monitoring images in power grid maintenance and inspection sites. This is because these images exhibit a significant imbalance between the foreground and background, which can lead to low detection accuracy when using a horizontal bounding box (HBB) as the detector in general object detection algorithms. Existing multi-oriented detection algorithms that use irregular polygons as the detector can improve accuracy to some extent, but their accuracy is limited due to boundary problems during the training process. This paper proposes a rotation-adaptive YOLOv5 (R_YOLOv5) with a rotated bounding box (RBB) to detect flexible objects with arbitrary orientation, effectively addressing the above issues and achieving high accuracy. Firstly, a long-side representation method is used to add the degree of freedom (DOF) for bounding boxes, enabling accurate detection of flexible objects with large spans, deformable shapes, and small foreground-to-background ratios. Furthermore, the further boundary problem induced by the proposed bounding box strategy is overcome by using classification discretization and symmetric function mapping methods. Finally, the loss function is optimized to ensure training convergence for the new bounding box. To meet various practical requirements, we propose four models with different scales based on YOLOv5, namely R_YOLOv5s, R_YOLOv5m, R_YOLOv5l, and R_YOLOv5x. Experimental results demonstrate that these four models achieve mean average precision (mAP) values of 0.712, 0.731, 0.736, and 0.745 on the DOTA-v1.5 dataset and 0.579, 0.629, 0.689, and 0.713 on our self-built FO dataset, exhibiting higher recognition accuracy and a stronger generalization ability. Among them, R_YOLOv5x achieves a mAP that is about 6.84% higher than ReDet on the DOTAv-1.5 dataset and at least 2% higher than the original YOLOv5 model on the FO dataset.

Dietary Zinc Intake Affects the Association Between Dietary Vitamin A and Depression: A Cross-Sectional Study.

Introduction: Dietary vitamin A concentrations correlate with depression. Zinc has been reported to be associated with lower depression. In addition, zinc is an important cofactor in the activation of vitamin A. However, there are few studies investigating relationships between of dietary zinc intake, dietary vitamin A intake and depression. Materials and Methods: The data for this study came from the National Health and Nutrition Examination Survey (NHANES) from 2005 to 2018 and involved 70,190 participants. We stratified participants by recommended dietary zinc intake (recommended dietary zinc intake for women: 8 mg/day, recommended dietary zinc intake for men: 11 mg/day). We further assessed the association between vitamin A and depression in participants with low and high zinc intake (interaction test) using univariate logistic regression of intake participants. Result: In the female population we grouped the population into low and high zinc intake groups using the recommended dietary zinc intake of 8 (mg/day), with an increase in total vitamin A, the risk of depression was significantly lower in the low zinc intake group (OR: 0.85 95 CI: 0.76-0.96), while the risk of depression was increased in the high zinc intake group (OR: 1.05 95 CI: 0.95 to 1.17). Thus, in the female population, there was a significant interaction between insufficient vitamin an intake and depression (interaction likelihood ratio test of p = 0.011). In the male population we grouped the population by the recommended dietary zinc intake of 11(mg/day). Again, the population was divided into two groups with low and high zinc intake, however we did not find significant results for the interaction (p = 0.743 for the interaction likelihood ratio test). Conclusion: Our findings suggest that zinc intake may influence the relationship between dietary vitamin A and depression. Of course, our findings require further randomized controlled trials to enhance the credibility.