EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Generative AI in clinical (2020–2025): a mini-review of applications, emerging trends, and clinical challenges

Nafiz Fahad, Riadul Islam Rabbi, Sumayea Benta Hasan, Fariya Sultana Prity, Rasel Ahmed, Farhana Ahmed, Md Jakir Hossen, Tze Hui Liew, Md Shohel Sayeed, Kah Ong Michael Goh

Frontiers in Digital Health · 03.11.2025 · 7

DOI: 10.3389/fdgth.2025.1653369 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Frontiers in Digital Health, online erschienen am 03.11.2025. Verfasst von Nafiz Fahad und 9 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Science and Technology (FIST), Multimedia University, Melaka, Malaysia. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative artificial intelligence (G-AI) has moved from proof-of-concept demonstrations to practical tools that augment radiology, dermatology, genetics, drug discovery, and electronic-health-record analysis. This mini-review synthesizes fifteen studies published between 2020 and 2025 that collectively illustrate three dominant trends: data augmentation for imbalanced or privacy-restricted datasets, automation of expert-intensive tasks such as radiology reporting, and generation of new biomedical knowledge ranging from molecular scaffolds to fairness insights. Image-centric work still dominates, with GANs, diffusion models, and Vision-Language Models expanding limited datasets and accelerating diagnosis. Yet narrative (EHR) and molecular design domains are rapidly catching up. Despite demonstrated accuracy gains, recurring challenges persist: synthetic samples may overlook rare pathologies, large multimodal systems can hallucinate clinical facts, and demographic biases can be amplified. Robust validation, interpretability techniques, and governance frameworks therefore, remain essential before G-AI can be safely embedded in routine care.

Schlagwörter

Stichwörter der Autor:innen

GANsVision-Language Modelsdiffusion modelselectronic-health-recordgenerative AI

Autor:innen und Institutionen

  • Faculty of Information Science and Technology (FIST), Multimedia University, Melaka, Malaysia.
  • Faculty of Engineering and Technology, Multimedia University, Melaka, Malaysia.
  • Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh.
  • Faculty of Science and Technology, American International University-Bangladesh, Dhaka, Bangladesh.
  • Center for Advanced Analytics (CAA), COE for Artificial Intelligence, Faculty of Engineering & Technology (FET), Multimedia University, Melaka, Malaysia.
  • Centre for Intelligent Cloud Computing (CICC), COE of Advanced Cloud, Faculty of Information Science & Technology, Multimedia University, Melaka, Malaysia.

Zitieren

APA

Fahad, N., Rabbi, R. I., Benta Hasan, S., Sultana Prity, F., Ahmed, R., Ahmed, F., Hossen, M. J., Liew, T. H., Sayeed, M. S., & Ong Michael Goh, K. (2025). Generative AI in clinical (2020–2025): a mini-review of applications, emerging trends, and clinical challenges. Frontiers in Digital Health, 7. https://doi.org/10.3389/fdgth.2025.1653369

Vancouver

Fahad N, Rabbi RI, Benta Hasan S, Sultana Prity F, Ahmed R, Ahmed F, et al. Generative AI in clinical (2020–2025): a mini-review of applications, emerging trends, and clinical challenges. Frontiers in Digital Health. 2025;7. doi:10.3389/fdgth.2025.1653369

BibTeX
@article{Fahad2025,
  author = {Fahad, Nafiz and Rabbi, Riadul Islam and Benta Hasan, Sumayea and Sultana Prity, Fariya and Ahmed, Rasel and Ahmed, Farhana and Hossen, Md Jakir and Liew, Tze Hui and Sayeed, Md Shohel and Ong Michael Goh, Kah},
  title = {Generative AI in clinical (2020–2025): a mini-review of applications, emerging trends, and clinical challenges},
  journal = {Frontiers in Digital Health},
  year = {2025},
  volume = {7},
  doi = {10.3389/fdgth.2025.1653369}
}
Kostenlos starten →