Cancer Diagnosis Categorization in Electronic Health Records Using Large Language Models and BioBERT: Model Performance Evaluation Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917014847619072 |
|---|---|
| author | Hashtarkhani, Soheil Rashid, Rezaur Brett, Christopher L Chinthala, Lokesh Kumsa, Fekede Asefa Zink, Janet A Davis, Robert L Schwartz, David L Shaban-Nejad, Arash |
| author_facet | Hashtarkhani, Soheil Rashid, Rezaur Brett, Christopher L Chinthala, Lokesh Kumsa, Fekede Asefa Zink, Janet A Davis, Robert L Schwartz, David L Shaban-Nejad, Arash |
| contents | Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise for automating diagnosis classification, their comparative performance and clinical reliability require systematic evaluation. The aim of this study is to evaluate the performance of 4 large language models (GPT-3.5, GPT-4o, Llama 3.2, and Gemini 1.5) and BioBERT in classifying cancer diagnoses from structured and unstructured electronic health records data. We analyzed 762 unique diagnoses (326 International Classification of Diseases (ICD) code descriptions, 436free-text entries) from 3456 records of patients with cancer. Models were tested on their ability to categorize diagnoses into 14predefined categories. Two oncology experts validated classifications. BioBERT achieved the highest weighted macro F1-score for ICD codes (84.2) and matched GPT-4o in ICD code accuracy (90.8). For free-text diagnoses, GPT-4o outperformed BioBERT in weighted macro F1-score (71.8 vs 61.5) and achieved slightly higher accuracy (81.9 vs 81.6). GPT-3.5, Gemini, and Llama showed lower overall performance on both formats. Common misclassification patterns included confusion between metastasis and central nervous system tumors, as well as errors involving ambiguous or overlapping clinical terminology. Although current performance levels appear sufficient for administrative and research use, reliable clinical applications will require standardized documentation practices alongside robust human oversight for high-stakes decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12813 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cancer Diagnosis Categorization in Electronic Health Records Using Large Language Models and BioBERT: Model Performance Evaluation Study Hashtarkhani, Soheil Rashid, Rezaur Brett, Christopher L Chinthala, Lokesh Kumsa, Fekede Asefa Zink, Janet A Davis, Robert L Schwartz, David L Shaban-Nejad, Arash Computation and Language Artificial Intelligence Machine Learning Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise for automating diagnosis classification, their comparative performance and clinical reliability require systematic evaluation. The aim of this study is to evaluate the performance of 4 large language models (GPT-3.5, GPT-4o, Llama 3.2, and Gemini 1.5) and BioBERT in classifying cancer diagnoses from structured and unstructured electronic health records data. We analyzed 762 unique diagnoses (326 International Classification of Diseases (ICD) code descriptions, 436free-text entries) from 3456 records of patients with cancer. Models were tested on their ability to categorize diagnoses into 14predefined categories. Two oncology experts validated classifications. BioBERT achieved the highest weighted macro F1-score for ICD codes (84.2) and matched GPT-4o in ICD code accuracy (90.8). For free-text diagnoses, GPT-4o outperformed BioBERT in weighted macro F1-score (71.8 vs 61.5) and achieved slightly higher accuracy (81.9 vs 81.6). GPT-3.5, Gemini, and Llama showed lower overall performance on both formats. Common misclassification patterns included confusion between metastasis and central nervous system tumors, as well as errors involving ambiguous or overlapping clinical terminology. Although current performance levels appear sufficient for administrative and research use, reliable clinical applications will require standardized documentation practices alongside robust human oversight for high-stakes decision-making. |
| title | Cancer Diagnosis Categorization in Electronic Health Records Using Large Language Models and BioBERT: Model Performance Evaluation Study |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.12813 |