AI Model Based on Diaphragm Ultrasound to Improve the Predictive Performance of Invasive Mechanical Ventilation Weaning: Prospective Cohort Study
Combining ultrasound and clinical data for colearning improved the accuracy of the weaning outcome prediction. Multimodal learning based on automatic measurement of point-of-care ultrasonography and automated collection of objective clinical indicators greatly enhanced the practical operability and user-friendliness of the system. The proposed model offered promising potential for widespread clinical application in intensive care settings.
Authors
- Feier Song (ORCID: https://orcid.org/0000-0003-0881-1249)
- Xuanhui Chen (ORCID: https://orcid.org/0000-0002-4134-7057)
- Tiehe Qin (ORCID: https://orcid.org/0000-0001-7081-6644)
- Huiying Liang (ORCID: https://orcid.org/0000-0002-9987-8002)
- Huan Ma
- Huazhang Liu (ORCID: https://orcid.org/0000-0001-5322-7629)
- Daozheng Huang
- Shouhong Wang (ORCID: https://orcid.org/0000-0002-2624-6784)
Institutions
- Guangdong Academy of Medical Sciences (CN)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2025-09-08
- DOI
- https://doi.org/10.2196/72482
- Citations
- 4
- Primary Topic
- Respiratory Support and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 6.07