Deep Learning Meets Oncology: A Paradigm Shift In Cancer Diagnosis And Precision Therapy
International Journal of Drug Delivery Technology · 25.05.2026 · 16 (36s)
DOI: 10.25258/ijddt.16.36s.57 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, erschienen am 25.05.2026. Verfasst von Sana Feroze und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Deep learning, a subset of artificial intelligence (AI), has rapidly emerged as a transformative force in oncology. It offers the potential to enhance diagnostic accuracy, reduce processing time, and enable personalized treatment strategies. However, its acceptance and practical integration into clinical workflows remain influenced by factors such as perceived effectiveness, trust, and institutional readiness.
Objective
This study aims to assess the perceptions of healthcare professionals regarding the effectiveness and trustworthiness of deep learning in cancer diagnosis and precision therapy, while also identifying key barriers to its adoption in oncology settings.
Methods
A quantitative, cross-sectional study was conducted using a structured questionnaire distributed to 250 healthcare professionals, including oncologists, radiologists, pathologists, medical researchers, and IT specialists. The instrument captured data across four sections: demographics, awareness and adoption, perceptions of effectiveness and trust, and implementation barriers. Descriptive statistics, reliability tests (Cronbach's Alpha, Split-Half), and normality tests (Shapiro-Wilk) were applied to analyze the data.
Results
Findings revealed a generally high perception of deep learning's effectiveness in improving cancer diagnosis. However, trust in AI decision-making was more varied. Shapiro-Wilk tests indicated that both key variables—effectiveness and trust—were not normally distributed. Reliability analysis showed low internal consistency between these constructs (Cronbach's Alpha = 0.19; Spearman-Brown = 0.19), suggesting that perceived effectiveness and trust are conceptually distinct. Visual data supported this conclusion, with histograms showing skewed distributions and a scatter plot indicating a weak correlation between effectiveness and trust.
Conclusion
While deep learning is widely recognized as a valuable tool in oncology, trust in its decision-making capabilities is not yet fully established among healthcare professionals. This gap highlights the importance of addressing ethical, educational, and practical barriers to adoption. Building trust through explainable AI models, clinician training, and validated use cases is essential for integrating deep learning into routine cancer care.
Zitieren
APA
Feroze, S., Rahmat, S. A., Nawazish, H., Naouss, B. A., Ahmed, A., & Ahmed, B. (2026). Deep Learning Meets Oncology: A Paradigm Shift In Cancer Diagnosis And Precision Therapy. International Journal of Drug Delivery Technology, 16(36s). https://doi.org/10.25258/ijddt.16.36s.57
Vancouver
Feroze S, Rahmat SA, Nawazish H, Naouss BA, Ahmed A, Ahmed B. Deep Learning Meets Oncology: A Paradigm Shift In Cancer Diagnosis And Precision Therapy. International Journal of Drug Delivery Technology. 2026;16(36s). doi:10.25258/ijddt.16.36s.57
BibTeX
@article{Feroze2026,
author = {Feroze, Sana and Rahmat, Syed Adnan and Nawazish, Hadia and Naouss, Bilal Abdulkader and Ahmed, Ashfaq and Ahmed, Bilal},
title = {Deep Learning Meets Oncology: A Paradigm Shift In Cancer Diagnosis And Precision Therapy},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {36s},
doi = {10.25258/ijddt.16.36s.57}
}
EUVIMED