EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Ethical AI Approach for Disease Diagnosis Using Prompt-Based History Summarisation

Maleeha Fathima, Moulana Mohammed

Journal of Studies in Science and Engineering · 30.06.2026 · 6 (1) · 460-487

DOI: 10.53898/josse2026631 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Studies in Science and Engineering, online erschienen am 30.06.2026. Verfasst von Maleeha Fathima und 1 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical history is a cornerstone of accurate diagnosis and effective treatment planning. In light of recent challenges such as the COVID-19 pandemic, the need for efficient, reliable, and secure history-taking methods has become more pressing than ever. Traditional approaches are often time-consuming, prone to human error, and reliant on subjective interpretation. This study proposes an AI-driven solution that automates patient history collection using prompt-based techniques, transforming complex, unstructured data into concise and coherent summaries. Ethical compliance and data privacy are central to the system's design, ensuring the secure handling of sensitive patient information. The integration of artificial intelligence, machine learning, and deep learning enhances both the accuracy of disease prediction and the overall efficiency of healthcare delivery. Through expert validation and responsible implementation, this research highlights the potential of generative AI to support early breast cancer diagnosis and improve the quality of patient care. We evaluated the fluency and semantic alignment of clinical text fields using auxiliary metrics, including ROUGE, BLEU, and BERTScore. Additionally, SHAP-based feature attribution was incorporated to interpret multi-class predictions. Together, these improvements provide a strong semantic foundation for evaluating and filtering decision support in medical AI systems.

Zitieren

APA

Fathima, M., & Mohammed, M. (2026). An Ethical AI Approach for Disease Diagnosis Using Prompt-Based History Summarisation. Journal of Studies in Science and Engineering, 6(1), 460-487. https://doi.org/10.53898/josse2026631

Vancouver

Fathima M, Mohammed M. An Ethical AI Approach for Disease Diagnosis Using Prompt-Based History Summarisation. Journal of Studies in Science and Engineering. 2026;6(1):460-487. doi:10.53898/josse2026631

BibTeX
@article{Fathima2026,
  author = {Fathima, Maleeha and Mohammed, Moulana},
  title = {An Ethical AI Approach for Disease Diagnosis Using Prompt-Based History Summarisation},
  journal = {Journal of Studies in Science and Engineering},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {460--487},
  doi = {10.53898/josse2026631}
}
Kostenlos starten →