Kitti Akkhawatthanakun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kitti Akkhawatthanakun has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chakkrit Termritthikun
Naresuan University, Thailand
2 shared publications - Konlakorn Wongpatikaseree
Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand
2 shared publications - Lalita Narupiyakul
Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakorn Pathom 73170, Thailand
2 shared publications - Narit Hnoohom
Mahidol University, Thailand
2 shared publications - Paisarn Muneesawang
Mahidol University, Thailand
2 shared publications
Latest Publications
- Open Access
- 4 March 2026
- Published by MDPI AG in Informatics
- Vol. 13 (3) , 39
Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding
Automating ICD-10 coding from discharge summaries remains demanding because coders analyze clinical narratives while justifying decisions. This study compares three automation patterns: PLM-ICD as a standalone deep learning system emitting 15 codes per case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM audit to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3B-Instruct, Llama-3.2-3B-Instruct, Phi-4-mini-instruct) to large-scale (Sonnet-4.5). Precision guided evaluation because coders still supply any missing diagnoses. PLM-ICD alone reached 55.8% precision while always surfacing 15 suggestions. LLM-only generation lagged severely (1.5–34.6% precision) and produced inconsistent output sizes. The agentic audit delivered the best trade-off: compact LLMs reviewed the 15 candidates, discarded weak evidence, and returned 2–8 high-confidence codes. Llama-3.2-3B-Instruct, for example, improved from 1.5% as a generator to 55.1% as a verifier while trimming false positives by 73%. These results show that positioning LLMs as quality controllers, rather than primary generators, yields reliable support for clinical coding teams, while formal recall/F1 reporting remains future work for fully autonomous implementations.
- 4 March 2026
- Published by MDPI AG in Informatics
- Vol. 13 (3) , 39
Open AccessIntegrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding
Automating ICD-10 coding from discharge summaries remains demanding because coders analyze clinical narratives while justifying decisions. This study compares three automation patterns: PLM-ICD as a standalone deep learning system emitting 15 codes per case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM audit to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3B-Instruct, Llama-3.2-3B-Instruct, Phi-4-mini-instruct) to large-scale (Sonnet-4.5). Precision guided evaluation because coders still supply any missing diagnoses. PLM-ICD alone reached 55.8% precision while always surfacing 15 suggestions. LLM-only generation lagged severely (1.5–34.6% precision) and produced inconsistent output sizes. The agentic audit delivered the best trade-off: compact LLMs reviewed the 15 candidates, discarded weak evidence, and returned 2–8 high-confidence codes. Llama-3.2-3B-Instruct, for example, improved from 1.5% as a generator to 55.1% as a verifier while trimming false positives by 73%. These results show that positioning LLMs as quality controllers, rather than primary generators, yields reliable support for clinical coding teams, while formal recall/F1 reporting remains future work for fully autonomous implementations.
- Open Access
- 24 December 2025
- Published by MDPI AG in Preprints.org
Integrating Agentic AI to Automate ICD-10 Medical Coding
Automating ICD-10 coding from discharge summaries remains demanding because coders analyze clinical narratives while justifying decisions. This study compares three automation patterns: PLM-ICD as a standalone deep learning system emitting 15 codes per case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM filter to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3B, Llama-3.2-3B, Phi-4-mini) through large scale (Sonnet-4.5). Precision guided evaluation because coders still supply any missing diagnoses. PLM-ICD alone reached 55.8% precision while always surfacing 15 suggestions. LLM-only generation lagged severely (1.5--34.6% precision) and produced inconsistent output sizes. The agentic filter delivered the best trade-off: compact LLMs reviewed the 15 candidates, discarded weak evidence, and returned 2--8 high-confidence codes. Llama-3.2-3B, for example, improved from 1.5% as a generator to 55.1% as a verifier while trimming false positives by 73%. These results show that positioning LLMs as quality controllers, rather than primary generators, yields reliable support for clinical coding teams, while formal recall/F1 reporting remains future work for fully autonomous implementations.
- 24 December 2025
- Published by MDPI AG in Preprints.org
Open AccessIntegrating Agentic AI to Automate ICD-10 Medical Coding
Automating ICD-10 coding from discharge summaries remains demanding because coders analyze clinical narratives while justifying decisions. This study compares three automation patterns: PLM-ICD as a standalone deep learning system emitting 15 codes per case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM filter to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3B, Llama-3.2-3B, Phi-4-mini) through large scale (Sonnet-4.5). Precision guided evaluation because coders still supply any missing diagnoses. PLM-ICD alone reached 55.8% precision while always surfacing 15 suggestions. LLM-only generation lagged severely (1.5--34.6% precision) and produced inconsistent output sizes. The agentic filter delivered the best trade-off: compact LLMs reviewed the 15 candidates, discarded weak evidence, and returned 2--8 high-confidence codes. Llama-3.2-3B, for example, improved from 1.5% as a generator to 55.1% as a verifier while trimming false positives by 73%. These results show that positioning LLMs as quality controllers, rather than primary generators, yields reliable support for clinical coding teams, while formal recall/F1 reporting remains future work for fully autonomous implementations.