cs.CLNov 16, 2026

Call-Efficient ICD-10 Code Prediction via Supervised Candidate Generation and Selective LLM Invocation

Authors: Ilia Kopanichuk, Daniil Kartashev, Yuri Bolkonsky, Petr Anokhin, Vladimir Makharev, Iaroslav Bespalov, Dmitry V. Dylov

Organizations: AIRI, Moscow, Russia · Moscow Institute of Physics and Technology, Dolgoprudny, Russia · Lomonosov Moscow State University, Moscow, Russia · Innopolis University, Innopolis, Russia · 

Abstract

Automatic assignment of ICD-10 codes from short clinical diagnosis text is a practical medical text classification and normalization task. The task is difficult because diagnosis phrases are short and noisy, the ICD-10 label space is hierarchical, and the class distribution is strongly imbalanced. This paper presents a call-efficient ICD-10 code prediction pipeline that combines transformer embeddings, tree-based supervised candidate generation, candidate-level reranking, and a gated LLM assistance. The evaluation uses a leakage-safe validation protocol: model and threshold selection are based on out-of-fold cross-validation predictions, while final reporting is performed on a locked test set with no shared source-file groups. The supervised conditional parent-code candidate generator reaches 74.32% Top-1 accuracy on the locked test set and 93.05% Top-10 candidate coverage. A direct zero-shot GPT-5.6-Sol baseline reaches 81.01% Top-1 accuracy, but requires an invocation of this large model for every diagnosis. The final deployable system, Pre-LLM fusion, reaches 81.24% OOF-CV accuracy and 83.19% locked-test accuracy while calling the LLM for only 31.97% of cases. This improves the locked-test error rate from 25.68% for the supervised parent-code baseline to 16.81%, corresponding to a 34.5% relative error reduction. The results show that the most effective role of the LLM is controlled reranking on uncertain examples rather than unrestricted coding or full-dataset invocation.

Figures & tables

Explore similar work

CardsList
  1. Instruction-Tuning Large Language Models with Medical Classification Data Improves ICD Coding of German Tumor Diagnoses

    Oct 15, 2025Stefan Lenz, Lakisha Ortiz Rosario, Georg Vollmar +4Automated Medical CodingLLM Fine-Tuning

  2. Beyond ICD Codes: Semantic IDs for Generative Medical Coding

    Oct 13, 2026Yihang Cheng, Qian Zhang, Yonghui +3Automated Medical CodingMedical LLMs