智能:开发和应用一个多模态多器官创伤查模型的腹部伤害在紧急设置中的应用
Yaning Wang1, Jingfeng Zhang2, Mingyang Li1
1Department of Radiology, The First Hospital of Jilin University, No.1, Xinmin Street, Changchun 130021, China (Y.W., M.L., Z.M., J.W., K.H., Q.Y., L.Z., L.M., H.Z.).
Academic radiology
|December 17, 2024
概括
智能模型将深度学习与CT扫描和文本数据集成在一起,以快速诊断腹部创伤. 这种多式联络方法显著提高了诊断准确度,并减少了急诊室等待时间.
科学领域:
- 医学成像和诊断 医学成像和诊断
- 医疗保健中的人工智能
- 紧急医疗 紧急医疗
背景情况:
- 有效的急诊室创伤护理依赖于跨学科团队使用各种医疗数据进行快速诊断.
- 目前的诊断方法可能耗时,影响患者的治疗结果.
研究的目的:
- 使用深度学习构建腹部创伤的多式诊断模型.
- 在腹部创伤病例中提高固体器官评估的速度和准确性.
主要方法:
- 开发了SMART模型 (快速创伤多器官评估查),使用非对比CT扫描和非结构化文本数据的深度学习.
- 采用GPT-4嵌入式API用于文本特征提取 (SMART_GPT) 和nnU-Net/DenseNet121用于CT图像分析 (SMART_Image).
- 集成的多式联络数据 (SMART_GPT,SMART_Image,人口统计) 使用复合模型的后勤回归.
主要成果:
- 集成的SMART模型实现了93.8%的灵敏度和0.88.8的AUC.
- SMART_GPT (文本) 的敏感度为81.3% (AUC为0.88),SMART_Image (CT) 的敏感度为87.5% (AUC为0.81).
- 模拟显示,SMART可以将急诊室的等待时间减少64%以上.
结论:
- 智能模型为腹部创伤提供了快速,客观的诊断.
- 它提高了紧急护理的效率,并减少了患者的等待时间.
- 在各种紧急情况下促进多式联运选.
相关概念视频
Assessment of the Abdomen II: Percussion
190
Percussion is a fundamental technique used to assess the liver, spleen, and abdominal organs by tapping the abdomen and interpreting the resulting sounds. This method helps identify fluid, distention, and masses through variations in sound, such as the high-pitched tympany of air-filled areas and the dullness of solid masses. Understanding how to percuss these organs provides valuable information for healthcare professionals in diagnosing conditions early.
Percussion
Percussion is an essential...
Percussion
Percussion is an essential...
190
Flail Chest-II
160
Managing flail chest, a condition characterized by a segment of the chest wall moving independently from the rest of the thoracic cage, requires a comprehensive approach. It includes a thorough assessment of the patient's condition, a diagnostic evaluation to determine the extent of the injury, and the implementation of appropriate medical interventions tailored to the individual's needs.
Assessment:
1. Clinical Evaluation:
History:
Assessment:
1. Clinical Evaluation:
History:
160


