Dinithi Vithanage
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dinithi Vithanage has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ping Yu
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia
9 shared publications - Chao Deng
School of Medical, Indigenous and Health Sciences, University of Wollongong, Wollongong, Australia
8 shared publications - Lei Wang
University of Wollongong, Wollongong, Australia
4 shared publications - Mengyang Yin
Opal Healthcare, Level 11/420 George St, Sydney NSW 2000, Australia
3 shared publications - Yunshu Zhu
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia
3 shared publications - Zhenyu Zhang
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia
3 shared publications
Latest Publications
- Open Access
- 17 October 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (20) , 2614
Fine-Tuning Large Language Models for Effective Nutrition Support in Residential Aged Care: A Domain Expertise Approach
Background: Malnutrition is a serious health concern among older adults in residential aged care (RAC), and timely identification is critical for effective intervention. Recent advancements in transformer-based large language models (LLMs), such as RoBERTa, provide context-aware embeddings that improve predictive performance in clinical tasks. Fine-tuning these models on domain-specific corpora, like nursing progress notes, can further enhance their applicability in healthcare. Methodology: We developed a RAC domain-specific LLM by training RoBERTa on 500,000 nursing progress notes from RAC electronic health records (EHRs). The model’s embeddings were used for two downstream tasks: malnutrition note identification and malnutrition prediction. Long sequences were truncated and processed in segments of up to 1536 tokens to fit RoBERTa’s 512-token input limit. Performance was compared against Bag of Words, GloVe, baseline RoBERTa, BlueBERT, ClinicalBERT, BioClinicalBERT, and PubMed models. Results: Using 5-fold cross-validation, the RAC domain-specific LLM outperformed other models. For malnutrition note identification, it achieved an F1-score of 0.966, and for malnutrition prediction, it achieved an F1-score of 0.687. Conclusions: This approach demonstrates the feasibility of developing specialised LLMs for identifying and predicting malnutrition among older adults in RAC. Future work includes further optimisation of prediction performance and integration with clinical workflows to support early intervention.
- 17 October 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (20) , 2614
Open AccessFine-Tuning Large Language Models for Effective Nutrition Support in Residential Aged Care: A Domain Expertise Approach
Background: Malnutrition is a serious health concern among older adults in residential aged care (RAC), and timely identification is critical for effective intervention. Recent advancements in transformer-based large language models (LLMs), such as RoBERTa, provide context-aware embeddings that improve predictive performance in clinical tasks. Fine-tuning these models on domain-specific corpora, like nursing progress notes, can further enhance their applicability in healthcare. Methodology: We developed a RAC domain-specific LLM by training RoBERTa on 500,000 nursing progress notes from RAC electronic health records (EHRs). The model’s embeddings were used for two downstream tasks: malnutrition note identification and malnutrition prediction. Long sequences were truncated and processed in segments of up to 1536 tokens to fit RoBERTa’s 512-token input limit. Performance was compared against Bag of Words, GloVe, baseline RoBERTa, BlueBERT, ClinicalBERT, BioClinicalBERT, and PubMed models. Results: Using 5-fold cross-validation, the RAC domain-specific LLM outperformed other models. For malnutrition note identification, it achieved an F1-score of 0.966, and for malnutrition prediction, it achieved an F1-score of 0.687. Conclusions: This approach demonstrates the feasibility of developing specialised LLMs for identifying and predicting malnutrition among older adults in RAC. Future work includes further optimisation of prediction performance and integration with clinical workflows to support early intervention.
- Open Access
- 30 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 197 (Pt A) , 111013
A comprehensive evaluation of large language models for information extraction from unstructured electronic health records in residential aged care
- 30 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 197 (Pt A) , 111013
Open AccessA comprehensive evaluation of large language models for information extraction from unstructured electronic health records in residential aged care
- Open Access
- 7 August 2025
- Published by IOS Press
- Vol. 329, 799-803
Leveraging Retrieval Augmented Generation-Driven Large Language Models to Extract Dementia Agitation Symptoms and Triggers from Free-Text Nursing Notes
Unstructured electronic health records are a rich source of patient-specific information but are challenging for analysis due to inconsistent terminology, diverse data formats, and extensive free-text content. To address this, we developed a named entity recognition model leveraging retrieval-augmented generation (RAG) powered by generative artificial intelligence. The model identifies symptoms and triggers of agitation in dementia from nursing notes within residential aged care facilities (RACFs). By integrating RAG with few-shot learning, our re-ranking retrieval approach outperformed dense retrieval methods, achieving an accuracy of 0.87, an F1 score of 0.88, a recall of 0.90, and a precision of 0.86. This enhanced framework supports clinical decision-making, improving care quality and better management of dementia-related agitation in RACFs.
- 7 August 2025
- Published by IOS Press
- Vol. 329, 799-803
Open AccessLeveraging Retrieval Augmented Generation-Driven Large Language Models to Extract Dementia Agitation Symptoms and Triggers from Free-Text Nursing Notes
Unstructured electronic health records are a rich source of patient-specific information but are challenging for analysis due to inconsistent terminology, diverse data formats, and extensive free-text content. To address this, we developed a named entity recognition model leveraging retrieval-augmented generation (RAG) powered by generative artificial intelligence. The model identifies symptoms and triggers of agitation in dementia from nursing notes within residential aged care facilities (RACFs). By integrating RAG with few-shot learning, our re-ranking retrieval approach outperformed dense retrieval methods, achieving an accuracy of 0.87, an F1 score of 0.88, a recall of 0.90, and a precision of 0.86. This enhanced framework supports clinical decision-making, improving care quality and better management of dementia-related agitation in RACFs.
- Open Access
- 7 August 2025
- Published by IOS Press
- Vol. 329, 1868-1869
Prevalence of Agitation and Depression Amongst People with Dementia in Australian Residential Aged Facilities: A Cross-Sectional Study Using LLMs
This preliminary study investigates the prevalence of agitation and depression among dementia residents in Australian Residential Aged Care Facilities (RACFs), utilizing Llama 3.1-8B. Analysis of 9,658 nursing notes from 40 RACFs highlighted significant sex- and age-specific differences and symptom cooccurrence trends. High accuracy 84% and F1 scores 88% affirm the model’s effectiveness, underscoring AI’s potential for early symptom detection and personalized dementia care.
- 7 August 2025
- Published by IOS Press
- Vol. 329, 1868-1869
Open AccessPrevalence of Agitation and Depression Amongst People with Dementia in Australian Residential Aged Facilities: A Cross-Sectional Study Using LLMs
This preliminary study investigates the prevalence of agitation and depression among dementia residents in Australian Residential Aged Care Facilities (RACFs), utilizing Llama 3.1-8B. Analysis of 9,658 nursing notes from 40 RACFs highlighted significant sex- and age-specific differences and symptom cooccurrence trends. High accuracy 84% and F1 scores 88% affirm the model’s effectiveness, underscoring AI’s potential for early symptom detection and personalized dementia care.
- Open Access
- 7 August 2025
- Published by IOS Press
- Vol. 329, 638-642
Pilot Application of a Large Language Model to Identify Hospitalisation from Unstructured Electronic Health Records in Residential Aged Care Facilities
Older people in residential aged care facilities (RACFs) visit hospitals and utilise healthcare services more often than others in the community. Trends in hospitalization rates are essential for designing targeted aged care interventions to reduce preventable hospitalizations and optimize resource use. Unstructured free-text nursing notes in Australian RACFs provide updated health information but require significant manual annotation due to their lack of standardization for supervised learning applications. This manual process presents a significant barrier to efficient data mining and insight generation. To address these challenges, we developed a classification model leveraging a large language model (LLM) with few-shot prompting to identify hospitalisation records within unstructured nursing notes. We analysed six weeks of data for 970 residents; the balanced dataset includes 75 hospitalizations. The model achieved an accuracy of 92.4%, a recall of 92.0%, a precision of 79.3%, and an F1 score of 85.2%. Future research will focus on enhancing the model’s performance and expanding its capability to extract additional insights, such as the reasons, times, and dates of hospitalisation. These advancements aim to provide a more comprehensive understanding of hospitalisation patterns and support the development of more effective aged care services.
- 7 August 2025
- Published by IOS Press
- Vol. 329, 638-642
Open AccessPilot Application of a Large Language Model to Identify Hospitalisation from Unstructured Electronic Health Records in Residential Aged Care Facilities
Older people in residential aged care facilities (RACFs) visit hospitals and utilise healthcare services more often than others in the community. Trends in hospitalization rates are essential for designing targeted aged care interventions to reduce preventable hospitalizations and optimize resource use. Unstructured free-text nursing notes in Australian RACFs provide updated health information but require significant manual annotation due to their lack of standardization for supervised learning applications. This manual process presents a significant barrier to efficient data mining and insight generation. To address these challenges, we developed a classification model leveraging a large language model (LLM) with few-shot prompting to identify hospitalisation records within unstructured nursing notes. We analysed six weeks of data for 970 residents; the balanced dataset includes 75 hospitalizations. The model achieved an accuracy of 92.4%, a recall of 92.0%, a precision of 79.3%, and an F1 score of 85.2%. Future research will focus on enhancing the model’s performance and expanding its capability to extract additional insights, such as the reasons, times, and dates of hospitalisation. These advancements aim to provide a more comprehensive understanding of hospitalisation patterns and support the development of more effective aged care services.
- Open Access
- 20 February 2025
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 9 (2) , 191-219
Adapting Generative Large Language Models for Information Extraction from Unstructured Electronic Health Records in Residential Aged Care: A Comparative Analysis of Training Approaches
Information extraction (IE) of unstructured electronic health records is challenging due to the semantic complexity of textual data. Generative large language models (LLMs) offer promising solutions to address this challenge. However, identifying the best training methods to adapt LLMs for IE in residential aged care settings remains underexplored. This research addresses this challenge by evaluating the effects of zero-shot and few-shot learning, both with and without parameter-efficient fine-tuning (PEFT) and retrieval-augmented generation (RAG) using Llama 3.1-8B. The study performed named entity recognition (NER) to nursing notes from Australian aged care facilities (RACFs), focusing on agitation in dementia and malnutrition risk factors. Performance evaluation includes accuracy, macro-averaged precision, recall, and F1 score. We used non-parametric statistical methods to compare if the differences were statistically significant. Results show that zero-shot and few-shot learning, whether combined with PEFT or RAG, achieve comparable performance across the clinical domains when the same prompting template is used. Few-shot learning significantly outperforms zero-shot learning when neither PEFT nor RAG is applied. Notably, PEFT significantly improves model performance in both zero-shot and few-shot learning; however, RAG significantly improves performance only in few-shot learning. After PEFT, the performance of zero-shot learning reaches a comparable level with few-shot learning. However, few-shot learning with RAG significantly outperforms zero-shot learning with RAG. We also found a similar level of performance between few-shot learning with RAG and zero-shot learning with PEFT. These findings provide valuable insights for researchers, practitioners, and stakeholders to optimize the use of generative LLMs in clinical IE.
- 20 February 2025
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 9 (2) , 191-219
Open AccessAdapting Generative Large Language Models for Information Extraction from Unstructured Electronic Health Records in Residential Aged Care: A Comparative Analysis of Training Approaches
Information extraction (IE) of unstructured electronic health records is challenging due to the semantic complexity of textual data. Generative large language models (LLMs) offer promising solutions to address this challenge. However, identifying the best training methods to adapt LLMs for IE in residential aged care settings remains underexplored. This research addresses this challenge by evaluating the effects of zero-shot and few-shot learning, both with and without parameter-efficient fine-tuning (PEFT) and retrieval-augmented generation (RAG) using Llama 3.1-8B. The study performed named entity recognition (NER) to nursing notes from Australian aged care facilities (RACFs), focusing on agitation in dementia and malnutrition risk factors. Performance evaluation includes accuracy, macro-averaged precision, recall, and F1 score. We used non-parametric statistical methods to compare if the differences were statistically significant. Results show that zero-shot and few-shot learning, whether combined with PEFT or RAG, achieve comparable performance across the clinical domains when the same prompting template is used. Few-shot learning significantly outperforms zero-shot learning when neither PEFT nor RAG is applied. Notably, PEFT significantly improves model performance in both zero-shot and few-shot learning; however, RAG significantly improves performance only in few-shot learning. After PEFT, the performance of zero-shot learning reaches a comparable level with few-shot learning. However, few-shot learning with RAG significantly outperforms zero-shot learning with RAG. We also found a similar level of performance between few-shot learning with RAG and zero-shot learning with PEFT. These findings provide valuable insights for researchers, practitioners, and stakeholders to optimize the use of generative LLMs in clinical IE.
- Open Access
Evaluating approaches of training a generative large language model for multi-label classification of unstructured electronic health records
Multi-label classification of unstructured electronic health records (EHR) is challenging due to the semantic complexity of textual data. Identifying the most effective machine learning method for EHR classification is useful in real-world clinical settings. Advances in natural language processing (NLP) using large language models (LLMs) offer promising solutions. Therefore, this experimental research aims to test the effects of zero-shot and few-shot learning prompting, with and without parameter-efficient fine-tuning (PEFT) and retrieval-augmented generation (RAG) of LLMs, on the multi-label classification of unstructured EHR data from residential aged care facilities (RACFs) in Australia. The four clinical tasks examined are agitation in dementia, depression in dementia, frailty index, and malnutrition risk factors, using the Llama 3.1-8B. Performance evaluation includes accuracy, macro-averaged precision, recall, and F1 score, supported by non-parametric statistical analyses. Results indicate that both zero-shot and few-shot learning, regardless of the use of PEFT and RAG, demonstrate equivalent performance across the clinical tasks when using the same prompting template. Few-shot learning consistently outperforms zero-shot learning when neither PEFT nor RAG is applied. Notably, PEFT significantly enhances model performance in both zero-shot and few-shot learning; however, RAG improves performance only in few-shot learning. After PEFT, the performance of zero-shot learning is equal to that of few-shot learning across clinical tasks. Additionally, few-shot learning with RAG surpasses zero-shot learning with RAG, while no significant difference exists between few-shot learning with RAG and zero-shot learning with PEFT. These findings offer crucial insights into LLMs for researchers, practitioners, and stakeholders utilizing LLMs in clinical document analysis.
Open AccessEvaluating approaches of training a generative large language model for multi-label classification of unstructured electronic health records
Multi-label classification of unstructured electronic health records (EHR) is challenging due to the semantic complexity of textual data. Identifying the most effective machine learning method for EHR classification is useful in real-world clinical settings. Advances in natural language processing (NLP) using large language models (LLMs) offer promising solutions. Therefore, this experimental research aims to test the effects of zero-shot and few-shot learning prompting, with and without parameter-efficient fine-tuning (PEFT) and retrieval-augmented generation (RAG) of LLMs, on the multi-label classification of unstructured EHR data from residential aged care facilities (RACFs) in Australia. The four clinical tasks examined are agitation in dementia, depression in dementia, frailty index, and malnutrition risk factors, using the Llama 3.1-8B. Performance evaluation includes accuracy, macro-averaged precision, recall, and F1 score, supported by non-parametric statistical analyses. Results indicate that both zero-shot and few-shot learning, regardless of the use of PEFT and RAG, demonstrate equivalent performance across the clinical tasks when using the same prompting template. Few-shot learning consistently outperforms zero-shot learning when neither PEFT nor RAG is applied. Notably, PEFT significantly enhances model performance in both zero-shot and few-shot learning; however, RAG improves performance only in few-shot learning. After PEFT, the performance of zero-shot learning is equal to that of few-shot learning across clinical tasks. Additionally, few-shot learning with RAG surpasses zero-shot learning with RAG, while no significant difference exists between few-shot learning with RAG and zero-shot learning with PEFT. These findings offer crucial insights into LLMs for researchers, practitioners, and stakeholders utilizing LLMs in clinical document analysis.
- Open Access
- 25 January 2024
- Published by IOS Press
- Vol. 310, 700-704
Extracting Symptoms of Agitation in Dementia from Free-Text Nursing Notes Using Advanced Natural Language Processing
Nursing staff record observations about older people under their care in free-text nursing notes. These notes contain older people’s care needs, disease symptoms, frequency of symptom occurrence, nursing actions, etc. Therefore, it is vital to develop a technique to uncover important data from these notes. This study developed and evaluated a deep learning and transfer learning-based named entity recognition (NER) model for extracting symptoms of agitation in dementia from the nursing notes. We employed a Clinical BioBERT model for word embedding. Then we applied bidirectional long-short-term memory (BiLSTM) and conditional random field (CRF) models for NER on nursing notes from Australian residential aged care facilities. The proposed NER model achieves satisfactory performance in extracting symptoms of agitation in dementia with a 75% F1 score and 78% accuracy. We will further develop machine learning models to recommend the optimal nursing actions to manage agitation.
- 25 January 2024
- Published by IOS Press
- Vol. 310, 700-704
Open AccessExtracting Symptoms of Agitation in Dementia from Free-Text Nursing Notes Using Advanced Natural Language Processing
Nursing staff record observations about older people under their care in free-text nursing notes. These notes contain older people’s care needs, disease symptoms, frequency of symptom occurrence, nursing actions, etc. Therefore, it is vital to develop a technique to uncover important data from these notes. This study developed and evaluated a deep learning and transfer learning-based named entity recognition (NER) model for extracting symptoms of agitation in dementia from the nursing notes. We employed a Clinical BioBERT model for word embedding. Then we applied bidirectional long-short-term memory (BiLSTM) and conditional random field (CRF) models for NER on nursing notes from Australian residential aged care facilities. The proposed NER model achieves satisfactory performance in extracting symptoms of agitation in dementia with a 75% F1 score and 78% accuracy. We will further develop machine learning models to recommend the optimal nursing actions to manage agitation.
- 3 January 2024
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 8 (1) , 158-179
Contextual Word Embedding for Biomedical Knowledge Extraction: a Rapid Review and Case Study
Recent advancements in natural language processing (NLP), particularly contextual word embedding models, have improved knowledge extraction from biomedical and healthcare texts. However, limited comprehensive research compares these models. This study conducts a scoping review and compares the performance of the major contextual word embedding models for biomedical knowledge extraction. From 26 articles identified from Scopus, PubMed, PubMed Central, and Google Scholar between 2017 and 2021, 18 notable contextual word embedding models were identified. These include ELMo, BERT, BioBERT, BlueBERT, CancerBERT, DDS-BERT, RuBERT, LABSE, EhrBERT, MedBERT, Clinical BERT, Clinical BioBERT, Discharge Summary BERT, Discharge Summary BioBERT, GPT, GPT-2, GPT-3, and GPT2-Bio-Pt. A case study compared the performance of six representative models—ELMo, BERT, BioBERT, BlueBERT, Clinical BioBERT, and GPT-3—across text classification, named entity recognition, and question answering. The evaluation utilized datasets comprising biomedical text from tweets, NCBI, PubMed, and clinical notes sourced from two electronic health record datasets. Performance metrics, including accuracy and F1 score, were used. The results of this case study reveal that BioBERT performs the best in analyzing biomedical text, while Clinical BioBERT excels in analyzing clinical notes. These findings offer crucial insights into word embedding models for researchers, practitioners, and stakeholders utilizing NLP in biomedical and clinical document analysis.
- 3 January 2024
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 8 (1) , 158-179
Contextual Word Embedding for Biomedical Knowledge Extraction: a Rapid Review and Case Study
Recent advancements in natural language processing (NLP), particularly contextual word embedding models, have improved knowledge extraction from biomedical and healthcare texts. However, limited comprehensive research compares these models. This study conducts a scoping review and compares the performance of the major contextual word embedding models for biomedical knowledge extraction. From 26 articles identified from Scopus, PubMed, PubMed Central, and Google Scholar between 2017 and 2021, 18 notable contextual word embedding models were identified. These include ELMo, BERT, BioBERT, BlueBERT, CancerBERT, DDS-BERT, RuBERT, LABSE, EhrBERT, MedBERT, Clinical BERT, Clinical BioBERT, Discharge Summary BERT, Discharge Summary BioBERT, GPT, GPT-2, GPT-3, and GPT2-Bio-Pt. A case study compared the performance of six representative models—ELMo, BERT, BioBERT, BlueBERT, Clinical BioBERT, and GPT-3—across text classification, named entity recognition, and question answering. The evaluation utilized datasets comprising biomedical text from tweets, NCBI, PubMed, and clinical notes sourced from two electronic health record datasets. Performance metrics, including accuracy and F1 score, were used. The results of this case study reveal that BioBERT performs the best in analyzing biomedical text, while Clinical BioBERT excels in analyzing clinical notes. These findings offer crucial insights into word embedding models for researchers, practitioners, and stakeholders utilizing NLP in biomedical and clinical document analysis.