Researchers developed a machine learning model that uses ultrasound and MRI data to predict cerebral blood flow in simulated microgravity for astronaut health.
Key Details
- 1Study used 36 healthy male participants in a 90-day head-down tilt bed rest (HDTBR) to simulate microgravity.
- 2Multimodal data collected included carotid Doppler ultrasound, 3D-pCASL brain MRI, and clinical metrics.
- 3Eight machine learning models tested; CatBoost delivered the best predictive performance (AUCs up to 0.92, accuracy up to 0.84).
- 4Model features were interpreted using SHAP, identifying BMI, ICA pulsatility index, and blood flow volume as top predictors.
- 5A web application was developed for real-time CBF prediction using clinical and ultrasound data, intended for spaceflight use.
- 6Limitations include exclusion of vertebral artery flow data and a male-only cohort.
Why It Matters
This ML-driven, imaging-integrated approach advances lightweight, non-invasive cerebral blood flow monitoring in space, potentially improving astronaut neurological care and illustrating cross-modal AI application in radiology. It also underscores the growing relevance of explainable AI and real-world deployment via web tools.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.
•EurekAlert
Rice University Aims to Revolutionize Imaging with Generative AI Cameras
Rice University receives NSF grant to develop AI-driven cameras that reconstruct images from minimal sensor data, promising advancements in efficient, intelligent imaging systems.