Project AURIONAI Use-Cases Research & Innovation
Healthcare

Clinical NLP and Trial Matching

LLM pipelines for patient-to-trial matching and coding.

LLM
1named models
401candidates
1deployments
0in Indonesia

Named Models

NIH National Library of MedicineTrialGPTNIH National Library of Medicine, National Cancer InstituteReleasednot in the notesRuns onnot in the notesClassLLMTrialGPTLLM-based patient-to-trial matching from NIH; close to clinician accuracy on more than 1,000 patient-criterion pairs and 40% less screening time in a pilot (Nature Communications 2024). The base LLM is not named.Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not stated
Where this comes from
Models the research names for this use case. Research, with sources on each model record.

Who Runs It

pilot, 1
National Institutes of HealthNIHCountry: USATrialGPTVendor: NIH NLMpilotDate–Clinicians spent 40% less screening time in a pilotEvidence: government statementConfidence: mediumSource: nih.gov
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

SEA-HELM leaderboard, 58 models, SEA average

A general benchmark for this model class, not a test on this use case. SEA average and per-language (incl. Indonesian) scores for open-weight models. Higher is better. Showing 10 of 11.

Alibaba (Qwen)Qwen3.6-35B-A3BAlibaba (Qwen) maintainer-run73.86Alibaba (Qwen)Qwen3.5-35B-A3BAlibaba (Qwen) maintainer-run73.55Googlegemma-3-27b-itGoogle maintainer-run64.54AI SingaporeGemma-SEA-LION-v4-27B-ITAI Singapore maintainer-run64.35OpenAIgpt-oss-20bOpenAI maintainer-run60.64MetaLlama-3.3-70B-InstructMeta maintainer-run60.44Alibaba (Qwen)Qwen3-8BAlibaba (Qwen) maintainer-run60.33Z.ai (Zhipu)GLM 4.7 FlashZ.ai (Zhipu) maintainer-run53.76GoogleGemma-3-4B-itGoogle maintainer-run47.84NVIDIANemotron 3 Nano 30B-A3BNVIDIA maintainer-run46.89
050100
AI SingaporeNemotron-SEA-LION-v4.8-120B-A12BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsAI SingaporeNemotron-SEA-LION-v4.8-30B-A3BAI Singapore, LLMReleasedSep 2026open weightsIndonesian statedhas scoreslast 18 monthsAI SingaporeQwen-SEA-LION-v4.5-27B-ITAI Singapore, LLMReleasedMay 2026open weightsIndonesian statedhas scoreslast 18 monthsAlibaba (Qwen)Qwen3.6-35B-A3BAlibaba (Qwen), LLMReleasedApr 2026open weightsruns on edgehas scoreslast 18 monthsNVIDIANemotron 3 SuperNVIDIA, LLMReleased2026open weightsIndonesian statedhas scoreslast 18 monthsNVIDIANemotron 3.5 Lightning 30B-A3BNVIDIA, LLMReleased2026open weightsIndonesian statedhas scoreslast 18 monthsOpenAIgpt-oss-120bOpenAI, LLMReleasedAug 2025open weightsIndonesian statedhas scoreslast 18 monthsIBMGranite 4.2 8BIBM, LLMReleasedSep 2026open weightshas scoreslast 18 monthsTencentHy4-previewTencent, LLMReleasedAug 2026open weightshas scoreslast 18 monthsZ.ai (Zhipu)GLM-5.3Z.ai (Zhipu), LLMReleasedAug 2026open weightshas scoreslast 18 months

Showing 10 of 401. All models of this class

Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Sources

  1. nih.gov/news-events/news-releases/nih-developed-ai-al... https://www.nih.gov/news-events/news-releases/nih-developed-ai-algorithm-matches-potential-volunteers-clinical-trials

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Clinical NLP and Trial Matching", https://aurion.semai.id/usecases/hc-clinical-trial-matching/, records of October 2026.