Multimodal AI combining abdominal X-ray and clinical data predicts hospitalization in ED patients

A deep learning model integrating abdominal radiographs and early clinical text predicted hospital admission with an AUC of 0.86 after data augmentation, outperforming single-modality approaches. Retrospective study; no external validation reported.

• Retrospective study; sample size and external validation not stated.
• Multimodal model achieved AUC 0.86 after augmentation vs. 0.80 before.
• Single-center, retrospective design limits generalizability; no prospective validation reported.

RadPigeon summaries are original and for information only. They are not clinical advice.