通过使用人工智能在低资源环境中进行胸部X射线检测儿童肺炎:试点研究
Taofeeq Oluwatosin Togunwa1,2, Abdulhammed Opeyemi Babatunde1,2, Oluwatosin Ebunoluwa Fatade3
1College of Medicine, University of Ibadan, Ibadan, Nigeria.
PLOS digital health
|September 24, 2025
概括
人工智能 (AI) 在低资源环境中对儿童肺炎的诊断显示出希望. 然而,人工智能模型需要本地验证,因为在应用于不同的医疗保健环境时,性能显著下降.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 全球健康 全球健康
背景情况:
- 肺炎是低收入和中等收入国家 (LMICs) 5岁以下死亡的主要原因,由有限的诊断专业知识加剧.
- 人工智能 (AI) 提供了从胸部X射线图 (CXR) 中改善肺炎诊断准确性和速度的潜力.
- 现有的人工智能模型往往缺乏对来自LMIC的潜在临床数据的验证,这阻碍了现实世界的适用性.
研究的目的:
- 开发和验证人工智能模型用于儿童肺炎检测,使用可能的尼日利亚胸部X射线 (CXR) 数据.
- 评估在美国数据上训练的AI模型在对尼日利亚CXR应用时的性能.
- 识别人工智能在LMICs儿童肺炎诊断方面的挑战和绩效差距.
主要方法:
- 在尼日利亚伊巴丹进行了一项多中心横截面研究,从第三级和私人诊断中心前性地收集CXR.
- 使用来自美国的开源儿科CXR数据集开发了一个AI模型,然后在尼日利亚的CXR上进行了测试.
- 用准确度,精度,回忆度,F1得分和曲线下面积 (AUC) 来评估模型性能,放射科医生的共识作为参考标准.
主要成果:
- 人工智能模型在内部测试中实现了高性能 (86%准确率,0.93AUC),但在使用尼日利亚数据进行外部测试时的性能明显较低 (58%准确率,0.65AUC).
- 精度和回忆有所不同,外部数据集的精度 (从0.83到0.62) 和回忆 (从0.98到0.48) 显著下降.
- 该研究强调了人工智能模型的内部验证与其应用于不同的医疗保健环境之间的显著性能差异.
结论:
- 人工智能证明了儿童肺炎诊断的潜力,但在各种医疗环境中应用时面临重大挑战.
- 绩效差异强调了需要使用来自LMICs的本地来源数据进行AI模型适应和验证的需要.
- 在非洲开发强大,与当地相关的数据集对于非洲医疗保健系统中可持续和独立的人工智能发展至关重要.
相关概念视频
Pneumonia III: Complications and Assessment
786
Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:
786
Radiological Investigation I: X-ray and CT
1.1K
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
1.1K
Assessment of Respiration
1.8K
The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
1.8K


