Preloader
Seeing Is Not Enough: Knowledge-Grounded Active Inquiry from Uncertain Visual Evidence

Similar tongue findings can accompany different syndromes in traditional Chinese medicine (TCM), with decisive symptoms absent from the photograph. We present a framework for tongue assessment in which image and pulse findings guide targeted symptom inquiry and acquired answers refine the syndrome shortlist before reporting. Image/pulse predictions guide selection from a sourced symptom question bank. Known answers update the assessment used to select the next question.

A calibrated loss of support for the initial prediction triggers reassessment; a subsequent report requires fresh answers supporting a stable candidate. Question and answer records make these decisions inspectable. We construct 2,600 cases from distinct real tongue photographs, assigned syndromes, simulated symptom responses and rendered pulses; 2,599 enter five-fold source-disjoint evaluation and one is training-only. On clean images, image/pulse prediction alone achieves 46.4% fine-syndrome accuracy.

At acquisition cost 12, inquiry without image/pulse evidence reaches 34.4%, whereas their combination reaches 65.8% accuracy and 90.8% top-three inclusion. A same-prior, training-optimized static order reaches 59.4% and 87.3%, respectively. In a 200-case visual-training intervention within the same bank, the first question changes in 46.7% of cases and the inquiry NLL-cost curve improves. Component comparisons distinguish these acquisition gains from the coverage-cost tradeoff of reassessment.

These controlled results support image-guided acquisition of missing symptoms for ranked TCM decision support.

Source: arXiv cs.LG (Machine Learning) — Read the full article on the original site ↗