AI-facilitated individualized nutritional guidance with ABC-structured prompts improves short-term dietary intake adequacy and patient-reported symptoms after gastrointestinal cancer surgery: a randomized controlled trial.
Hao Chen, Wei Jiang, Meng Li et al.
✦ AI-curated · Sources linked
In 30 seconds
This single-center randomized controlled trial compared AI-facilitated, individualized and quantified dietary guidance plus clinician review with standard discharge advice in 90 patients after laparoscopic gastric or colorectal cancer surgery. At 30 days after discharge, energy intake adequacy (at least 90% of target) was achieved by 66.7% versus 40.0% of patients (OR 3.0, 95% CI 1.3-7.1, P = 0.01); protein adequacy was also higher. The intervention group reported improvements in several symptoms and required less provider time. The combined intervention does not establish an independent benefit from AI.
Key findings
- At 30 days, energy adequacy was 66.7% vs. 40.0% (OR 3.0, 95% CI 1.3-7.1, P = 0.01).
- Protein adequacy was 62.2% vs. 35.6% (OR 2.9, 95% CI 1.2-6.8, P = 0.01).
- GSRS total score was 2.1 vs. 2.5 (P = 0.03), with reported improvements in fatigue, nausea/vomiting, appetite loss, and gastrointestinal symptoms.
- Provider time per patient was 8.2 vs. 12.5 min (P < 0.001); weight change, serum nutritional markers, and complication rates did not differ significantly.
Why it matters
Post-discharge dietary advice after gastrointestinal cancer surgery may be more useful when tailored and quantified: this trial found better short-term intake adequacy and symptom reports than with generic advice. The findings also suggest a potential workflow benefit. However, the intervention bundled AI with individualization, written targets, and clinician review, so the results inform the package rather than AI's independent contribution.
What to keep in mind
The trial was single-center and assessed short-term outcomes. Because AI was combined with individualized quantified guidance and clinician review, its independent effect cannot be determined; longer-term nutritional or clinical benefit was not established.