Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.03266 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908996591419392 |
|---|---|
| author | Munim, Alif Ma, Jun Ibrahim, Omar Abdalla, Alhusain Yin, Shuolin Chen, Leo Wang, Bo |
| author_facet | Munim, Alif Ma, Jun Ibrahim, Omar Abdalla, Alhusain Yin, Shuolin Chen, Leo Wang, Bo |
| contents | Large language models (LLMs) have rapidly advanced in clinical decision-making, yet the deployment of proprietary systems is hindered by privacy concerns and reliance on cloud-based infrastructure. Open-source alternatives allow local inference but often have large model sizes that limit their use in resource-constrained clinical settings. Here, we benchmark on-device LLMs from the gpt-oss (20b, 120b), Qwen3.5 (9B, 27B, 35B), and Gemma 4 (31B) families across three representative clinical tasks: general disease diagnosis, specialty-specific (ophthalmology) diagnosis and management, and simulation of human expert grading and evaluation. We compare their performance with state-of-the-art proprietary models (GPT-5.1, GPT-5-mini, and Gemini 3.1 Pro) and a leading open-source model (DeepSeek-R1), and we further evaluate the adaptability of on-device systems by fine-tuning gpt-oss-20b and Qwen3.5-35B on general diagnostic data. Across tasks, on-device models achieve performance comparable to or exceeding DeepSeek-R1 and GPT-5-mini despite being substantially smaller. In addition, fine-tuning remarkably improves diagnostic accuracy, with the fine-tuned Qwen3.5-35B reaching 87.9% and approaching the proprietary GPT-5.1 (89.4%). Among base on-device models, Gemma 4 31B achieved the strongest general diagnostic accuracy at 86.5%, exceeding GPT-5-mini and approaching the fine-tuned Qwen3.5-35B. Error characterization revealed that 87.2% of diagnostic errors across all models were clinically plausible differentials rather than off-topic predictions, and upper-bound analysis showed up to 93.2% attainable accuracy through improved answer selection. These findings highlight the potential of on-device LLMs to deliver accurate, adaptable, and privacy-preserving clinical decision support, offering a practical pathway for broader integration of LLMs into routine clinical practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03266 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking and Adapting On-Device LLMs for Clinical Decision Support Munim, Alif Ma, Jun Ibrahim, Omar Abdalla, Alhusain Yin, Shuolin Chen, Leo Wang, Bo Computation and Language Artificial Intelligence Large language models (LLMs) have rapidly advanced in clinical decision-making, yet the deployment of proprietary systems is hindered by privacy concerns and reliance on cloud-based infrastructure. Open-source alternatives allow local inference but often have large model sizes that limit their use in resource-constrained clinical settings. Here, we benchmark on-device LLMs from the gpt-oss (20b, 120b), Qwen3.5 (9B, 27B, 35B), and Gemma 4 (31B) families across three representative clinical tasks: general disease diagnosis, specialty-specific (ophthalmology) diagnosis and management, and simulation of human expert grading and evaluation. We compare their performance with state-of-the-art proprietary models (GPT-5.1, GPT-5-mini, and Gemini 3.1 Pro) and a leading open-source model (DeepSeek-R1), and we further evaluate the adaptability of on-device systems by fine-tuning gpt-oss-20b and Qwen3.5-35B on general diagnostic data. Across tasks, on-device models achieve performance comparable to or exceeding DeepSeek-R1 and GPT-5-mini despite being substantially smaller. In addition, fine-tuning remarkably improves diagnostic accuracy, with the fine-tuned Qwen3.5-35B reaching 87.9% and approaching the proprietary GPT-5.1 (89.4%). Among base on-device models, Gemma 4 31B achieved the strongest general diagnostic accuracy at 86.5%, exceeding GPT-5-mini and approaching the fine-tuned Qwen3.5-35B. Error characterization revealed that 87.2% of diagnostic errors across all models were clinically plausible differentials rather than off-topic predictions, and upper-bound analysis showed up to 93.2% attainable accuracy through improved answer selection. These findings highlight the potential of on-device LLMs to deliver accurate, adaptable, and privacy-preserving clinical decision support, offering a practical pathway for broader integration of LLMs into routine clinical practice. |
| title | Benchmarking and Adapting On-Device LLMs for Clinical Decision Support |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.03266 |