Balancing Natural Language Processing Accuracy and Normalisation in Extracting Medical Insights

📅 2025-11-19
📈 Citations: 0
Influential: 0
📄 PDF

career value

179K/year
🤖 AI Summary
This study addresses the trade-off among accuracy, standardization, and computational efficiency in NLP for low-resource, non-English medical settings, using unstructured electronic health records from a Polish pediatric rehabilitation hospital. We propose a hybrid approach integrating rule-based systems—offering high precision and low computational cost—with multilingual large language models (LLMs)—providing strong generalization and adaptability. We systematically compare performance on demographic, clinical finding, and medication information extraction tasks using both original Polish text and machine-translated English text. Results show rule-based methods outperform LLMs in age and gender identification, while LLMs significantly improve drug name recognition accuracy. Critically, machine translation introduces non-negligible information loss, degrading downstream performance. This work establishes a new paradigm for resource-constrained, multilingual clinical NLP that balances accuracy, robustness, and practical deployability.

Technology Category

Application Category

📝 Abstract
Extracting structured medical insights from unstructured clinical text using Natural Language Processing (NLP) remains an open challenge in healthcare, particularly in non-English contexts where resources are scarce. This study presents a comparative analysis of NLP low-compute rule-based methods and Large Language Models (LLMs) for information extraction from electronic health records (EHR) obtained from the Voivodeship Rehabilitation Hospital for Children in Ameryka, Poland. We evaluate both approaches by extracting patient demographics, clinical findings, and prescribed medications while examining the effects of lack of text normalisation and translation-induced information loss. Results demonstrate that rule-based methods provide higher accuracy in information retrieval tasks, particularly for age and sex extraction. However, LLMs offer greater adaptability and scalability, excelling in drug name recognition. The effectiveness of the LLMs was compared with texts originally in Polish and those translated into English, assessing the impact of translation. These findings highlight the trade-offs between accuracy, normalisation, and computational cost when deploying NLP in healthcare settings. We argue for hybrid approaches that combine the precision of rule-based systems with the adaptability of LLMs, offering a practical path toward more reliable and resource-efficient clinical NLP in real-world hospitals.
Problem

Research questions and friction points this paper is trying to address.

Extracting structured medical insights from unstructured clinical text
Comparing rule-based methods and LLMs for EHR information extraction
Assessing trade-offs between accuracy, normalization, and computational costs
Innovation

Methods, ideas, or system contributions that make the work stand out.

Rule-based methods provide higher accuracy for information extraction
LLMs offer greater adaptability and scalability in processing
Hybrid approaches combine precision of rules with LLM flexibility
🔎 Similar Papers
No similar papers found.
P
Paulina Tworek
Personal Health Data Science Team, Sano - Centre for Computational Personalized Medicine, Krakow, Poland
M
Miłosz Bargieł
Personal Health Data Science Team, Sano - Centre for Computational Personalized Medicine, Krakow, Poland, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Krakow, Poland
Y
Yousef Khan
Personal Health Data Science Team, Sano - Centre for Computational Personalized Medicine, Krakow, Poland
T
Tomasz Pełech-Pilichowski
Institute of Computer Science, AGH University of Krakow, Krakow, Poland
M
Marek Mikołajczyk
Voivodeship Rehabilitation Hospital for Children in Ameryka, Ameryka, Poland
R
Roman Lewandowski
Institute of Management and Quality Sciences, Faculty of Economics, University of Warmia and Mazury, Olsztyn, Poland
J
Jose Sousa
Personal Health Data Science Team, Sano - Centre for Computational Personalized Medicine, Krakow, Poland