Evan Schulte
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Evan Schulte has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Kushal Dahal
Ferris State University College of Pharmacy , Big Rapids, Michigan
1 shared publication - Michael E. Klepser
Ferris State University
1 shared publication - Minji Sohn
College of Pharmacy, Ferris State University, Big Rapids, MI 49307, USA
1 shared publication - Mohamed Abusharkh
Software Engineering, Ferris State University, Grand Rapids, MI 49503, USA
1 shared publication
Latest Publications
- Open Access
- 27 February 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (5) , 2300
Feasibility of Using Large Language Models for Structured Medication Extraction from Clinical Text: A Comparative Analysis of Zero-Shot and Few-Shot Paradigms
The digitization of healthcare has been accompanied by a rapid expansion of electronic health records (EHRs); however, a significant proportion of critical patient data, specifically medication regimens, remains entrapped within unstructured clinical narratives. The inability to seamlessly compute this data hinders advancements in pharmacovigilance, clinical decision support, and population health management. This study presents a comprehensive, rigorous evaluation of the feasibility of deploying Large Language Models (LLMs) to automate the extraction of structured dosage information (Dose, Daily Frequency, Duration) from outpatient antimicrobial clinical notes sourced from the Collaboration to Harmonize Antimicrobial Registry Measures (CHARM) registry. We scrutinized the performance of five distinct open-weight architectures, namely GPT-OSS:20B, Gemma 2:9B, Mistral 7B, Qwen3:14B and Llama 3.2, across both Zero-Shot and Retrieval Augmented Generation (RAG)-based Few-Shot prompting paradigms. Our analysis reveals a fundamental architectural trade-off: the reasoning-optimized GPT-OSS:20B dominates the zero-shot landscape (F1 > 0.90) by leveraging abstract schema understanding, whereas the instruction-tuned Gemma 2:9B excels in the few-shot setting (F1 ~ 0.99), effectively utilizing examples as guardrails to surpass larger models. Conversely, smaller models (Mistral, Llama) exhibit a prohibitive “hallucination barrier,” rendering them unsafe for unsupervised clinical application. Furthermore, we identify “Inconsistent Unit Handling” and “Complex Temporal Logic” as persistent failure modes that resist simple scaling laws. This report provides a definitive framework for selecting model architectures based on the availability of few-shot examples and highlights the necessity of dynamic RAG strategies to achieve production-grade reliability in medical informatics.
- 27 February 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (5) , 2300
Open AccessFeasibility of Using Large Language Models for Structured Medication Extraction from Clinical Text: A Comparative Analysis of Zero-Shot and Few-Shot Paradigms
The digitization of healthcare has been accompanied by a rapid expansion of electronic health records (EHRs); however, a significant proportion of critical patient data, specifically medication regimens, remains entrapped within unstructured clinical narratives. The inability to seamlessly compute this data hinders advancements in pharmacovigilance, clinical decision support, and population health management. This study presents a comprehensive, rigorous evaluation of the feasibility of deploying Large Language Models (LLMs) to automate the extraction of structured dosage information (Dose, Daily Frequency, Duration) from outpatient antimicrobial clinical notes sourced from the Collaboration to Harmonize Antimicrobial Registry Measures (CHARM) registry. We scrutinized the performance of five distinct open-weight architectures, namely GPT-OSS:20B, Gemma 2:9B, Mistral 7B, Qwen3:14B and Llama 3.2, across both Zero-Shot and Retrieval Augmented Generation (RAG)-based Few-Shot prompting paradigms. Our analysis reveals a fundamental architectural trade-off: the reasoning-optimized GPT-OSS:20B dominates the zero-shot landscape (F1 > 0.90) by leveraging abstract schema understanding, whereas the instruction-tuned Gemma 2:9B excels in the few-shot setting (F1 ~ 0.99), effectively utilizing examples as guardrails to surpass larger models. Conversely, smaller models (Mistral, Llama) exhibit a prohibitive “hallucination barrier,” rendering them unsafe for unsupervised clinical application. Furthermore, we identify “Inconsistent Unit Handling” and “Complex Temporal Logic” as persistent failure modes that resist simple scaling laws. This report provides a definitive framework for selecting model architectures based on the availability of few-shot examples and highlights the necessity of dynamic RAG strategies to achieve production-grade reliability in medical informatics.