Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models

Ma’aitah, Mohammad Khaleel Sallam; Helwan, Abdulkader; Radwan, Abdelrahman

doi:10.3390/jpm15020045

Open AccessArticle

Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models

by

Mohammad Khaleel Sallam Ma’aitah

^1,*

,

Abdulkader Helwan

^2,*

and

Abdelrahman Radwan

¹

Electrical Engineering/Robotics and Artificial Intelligence Engineering, Faculty of Engineering & Technology, Applied Science Private University, Amman 11931, Jordan

²

Department of Health, Medicine and Caring Sciences, Linköping University, 581 85 Linköping, Sweden

^*

Authors to whom correspondence should be addressed.

J. Pers. Med. 2025, 15(2), 45; https://doi.org/10.3390/jpm15020045

Submission received: 9 December 2024 / Revised: 6 January 2025 / Accepted: 14 January 2025 / Published: 24 January 2025

(This article belongs to the Special Issue Application of Artificial Intelligence in Personalized Medicine: Diagnosis and Treatment)

Download

Browse Figures

Versions Notes

Abstract

Background: Large language models (LLMs) have seen a significant boost recently in the field of natural language processing (NLP) due to their capabilities in analyzing words. These autoregressive models prove robust in classification tasks where texts need to be analyzed and classified. Objectives: In this paper, we explore the power of base LLMs such as Generative Pre-trained Transformer 2 (GPT-2), Bidirectional Encoder Representations from Transformers (BERT), Distill-BERT, and TinyBERT in diagnosing acute inflammations of the urinary bladder and nephritis of the renal pelvis. Materials and Methods: the LLMs were trained and tested using supervised fine-tuning (SFT) on a dataset of 120 examples that include symptoms that may indicate the occurrence of these two conditions. Results: By employing a supervised fine-tuning method and carefully crafted prompts to present the data, we demonstrate the feasibility of using minimal training data to achieve a reasonable diagnostic, with overall testing accuracies of 100%, 100%, 94%, and 79%, for GPT-2, BERT, Distill-BERT, and TinyBERT, respectively.

Keywords: large language models; LLMs; NLP; autoregressive; transformer; GPT-2; BERT; Distill-BERT; TinyBERT; supervised fine-tuning; SFT

Share and Cite

MDPI and ACS Style

Ma’aitah, M.K.S.; Helwan, A.; Radwan, A. Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models. J. Pers. Med. 2025, 15, 45. https://doi.org/10.3390/jpm15020045

AMA Style

Ma’aitah MKS, Helwan A, Radwan A. Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models. Journal of Personalized Medicine. 2025; 15(2):45. https://doi.org/10.3390/jpm15020045

Chicago/Turabian Style

Ma’aitah, Mohammad Khaleel Sallam, Abdulkader Helwan, and Abdelrahman Radwan. 2025. "Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models" Journal of Personalized Medicine 15, no. 2: 45. https://doi.org/10.3390/jpm15020045

APA Style

Ma’aitah, M. K. S., Helwan, A., & Radwan, A. (2025). Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models. Journal of Personalized Medicine, 15(2), 45. https://doi.org/10.3390/jpm15020045

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Urinary Bladder Acute Inflammations and Nephritis of the Renal Pelvis: Diagnosis Using Fine-Tuned Large Language Models

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI