Research map / Architectures and efficiency / CNN design
ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network
Fei Li, Hong Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace CAML with MultiResCNN | ICD coding models · MIMIC-III full codes | micro-F1: +0.013 | Improved |
| replace CAML with MultiResCNN | ICD coding models · MIMIC-III full codes | macro-F1: 0.088 -> 0.085 | Hurt |
| replace CAML with MultiResCNN | ICD coding models · MIMIC-III full codes | micro-AUC: 0.986 -> 0.986 | No clear effect |
| replace DR-CAML with MultiResCNN | ICD coding models · MIMIC-III top-50 codes | macro-F1: +0.030 | Improved |
| replace DR-CAML with MultiResCNN | ICD coding models · MIMIC-III top-50 codes | micro-F1: +0.037 | Improved |
| replace DR-CAML with MultiResCNN | ICD coding models · MIMIC-II full codes | micro-F1: +0.007 | Improved |
| add multiple convolution filter sizes (ablation) | CNN for ICD coding · MIMIC-III full codes dev | P@8: 0.706 -> 0.736 | Improved |
| add residual convolution blocks (ablation) | CNN for ICD coding · MIMIC-III full codes dev | P@8: 0.706 -> 0.714 | Improved |
| combine multi-filter and residual convolution (ablation) | CNN for ICD coding · MIMIC-III full codes dev | P@8: 0.736 -> 0.741 | Improved |
| increase the number of multi-filter kernel sizes to k=3,5,9,15,19,25 (ablation) | MultiCNN · MIMIC-III full codes dev | P@8: 0.731 -> 0.735 -> 0.736 | Improved |
| increase residual block number from 1 to 2 (ablation) | ResCNN · MIMIC-III top-50 dev | Micro-F1: 0.645 -> 0.601 | Hurt |
| increase residual block number from 1 to 3 (ablation) | ResCNN · MIMIC-III top-50 dev | Micro-F1: 0.645 -> 0.585 | Hurt |
Closest papers by meaning
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.81)
- DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels (CVPR 2025 · similarity 0.80)
- Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection (NeurIPS 2024 · similarity 0.80)
- LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding (CVPR 2026 · similarity 0.80)
- MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output (CVPR 2025 · similarity 0.80)
- Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model (ICLR 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
