Harvard radiologists developed an explainable AI model to predict next-day radiology demand and manage staffing proactively.
Key Details
- 1Harvard Medical School experts built a machine learning model using a year's imaging demand data from two academic centers.
- 2The model predicts next-day clinical workload based on unread images, exams after 5 p.m., and next-day scheduled exams.
- 3AI predictions could allow radiology practices to plan or adjust staffing in anticipation of demand surges.
- 4Continuous learning maintains the model's accuracy over time.
- 5Growing imaging volume and workforce shortages are driving the need for such solutions.
Why It Matters
Proactively forecasting imaging demand with AI can help radiology departments address staffing challenges and reduce burnout. Such tools may become essential for efficient, resilient healthcare delivery as imaging workloads increase.
Source
Radiology Business
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.
•Radiology Business
Radiology AI Devices at Elevated Risk for FDA Recalls, Study Finds
Radiology AI devices are more likely to face FDA recalls, largely due to deviations from intended use and incomplete clinical data.