Skip to content
DraconiticResearch
Search Sources API
194,220 studies31 sourcesUpdated 48 min ago
Peer-reviewedCC BYScientific Reports

Interpretable deep learning framework for secure clinical data analytics

  • Mahmoud Ahmad Al-Khasawneh1
  • Deema Mohammed Alsekait2
  • Kholoud Alkayid3
  • Omar Kassem Khalil4
  • Abdulghani Bakur Alsayegh5
  • Amar Y. Jaffar5
  • P. Karthik6
  • K. M. Baalamurugan7
7 affiliations
  1. 1School of Computing, Horizon University College
  2. 2Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University
  3. 3Department of Computer Science, Faculty of Information Technology, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University
  4. 4Department of Information Technology, College of Engineering and Computing, Liwa University
  5. 5Computer and Network Engineering Department, College of Computing, Umm Al-Qura University
  6. 6Department of Electronics and Communication Engineering, Cambridge Institute of Technology
  7. 7School of Engineering and IT, Manipal Academy of Higher Education
Read full textPDFDOICite

Abstract

The growing use of artificial intelligence in the healthcare sector has facilitated the emergence of sophisticated clinical data analytics, but the most critical issues pertain to data privacy, model interpretability, and model trustworthiness. These problems still pose a challenge to its real-world application. This study proposes an interpretation of a deep learning framework for secure clinical data analytics. This proposes a privacy-preserving distributed learning framework in combination with a naturally interpretable model structure. The suggested framework enables parallel training across several healthcare facilities without compromising raw patient information, thereby keeping the data confidential without adversely affecting the analysis. An idea-driven deep learning framework is also presented to produce clinically significant intermediate representations that enable clear, interpretable predictions. Moreover, a new explanation stability mechanism is established to maintain the consistency and reliability of model explanations in distributed environments. To promote clinical safety, the decision module includes uncertainty to enable the system to detect predictions with low confidence and defer them to experts. Massive tests using actual clinical data on patient conditions can be conducted to demonstrate that the framework presented is much more successful than other methods with respect to predictiveness, interpretability, explanation stability, fairness, and calibration. Furthermore, the framework demonstrates that privacy preservation, interpretability, explanation reliability, and clinical usability can be jointly optimized within a unified learning architecture. The findings indicate the effectiveness of the suggested strategy in providing secure, transparent, and reliable clinical decision support, rendering it an appropriate strategy to implement in contemporary healthcare systems.

Related

  1. KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
    Krantee Singh, Vasudev Dehalwar
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicineCrossref
  2. HE-CloudML: a privacy-preserving framework for secure machine learning inference over encrypted cloud data using homomorphic encryption
    Abdullahi Ahmed Abdirahman, Abdirahman Osman Hashi, Ubaid Mohamed Dahir +1
    Scientific ReportsPeer-reviewedCC BYFull text1 citedGeneral medicineDOAJ
  3. From Clinical Free Text to Auditable Concepts: An Agentic Framework for Interpretable Prediction
    C. Ni, W. Liu, Q. Song +3
    medRxivPreprintCC BY-NC-NDFull textEpidemiology & public healthmedRxiv
  4. A leakage-aware and interpretable machine learning framework for ovarian cancer prediction using the PLCO screening dataset
    Sheela Lavanya J. M., Subbulakshmi P.
    Frontiers in OncologyPeer-reviewedCC BY 4.0Full textOncologyCrossrefDOAJ
  5. Clinical Correlates of Suicidal Ideation in Adults With Obsessive-Compulsive Disorder: An Interpretable Machine Learning Study
    B. A. Zaboski, E. F. Mattera, C. A. Pittenger
    medRxivPreprintCC BY-NC-NDFull textPsychiatry & mental healthmedRxiv

Cite

BibTeXRIS
BibTeX
@article{alkhasawneh2026interpretable,
  title = {{Interpretable deep learning framework for secure clinical data analytics}},
  author = {Mahmoud Ahmad Al-Khasawneh and Deema Mohammed Alsekait and Kholoud Alkayid and Omar Kassem Khalil and Abdulghani Bakur Alsayegh and Amar Y. Jaffar and P. Karthik and K. M. Baalamurugan},
  journal = {Scientific Reports},
  year = {2026},
  month = jul,
  doi = {10.1038/s41598-026-62055-8},
  url = {https://doi.org/10.1038/s41598-026-62055-8},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Interpretable deep learning framework for secure clinical data analytics
AU  - Mahmoud Ahmad Al-Khasawneh
AU  - Deema Mohammed Alsekait
AU  - Kholoud Alkayid
AU  - Omar Kassem Khalil
AU  - Abdulghani Bakur Alsayegh
AU  - Amar Y. Jaffar
AU  - P. Karthik
AU  - K. M. Baalamurugan
PY  - 2026
DA  - 2026/07/01
JO  - Scientific Reports
DO  - 10.1038/s41598-026-62055-8
UR  - https://doi.org/10.1038/s41598-026-62055-8
AB  - The growing use of artificial intelligence in the healthcare sector has facilitated the emergence of sophisticated clinical data analytics, but the most critical issues pertain to data privacy, model interpretability, and model trustworthiness. These problems still pose a challenge to its real-world application. This study proposes an interpretation of a deep learning framework for secure clinical data analytics. This proposes a privacy-preserving distributed learning framework in combination with a naturally interpretable model structure. The suggested framework enables parallel training across several healthcare facilities without compromising raw patient information, thereby keeping the data confidential without adversely affecting the analysis. An idea-driven deep learning framework is also presented to produce clinically significant intermediate representations that enable clear, interpretable predictions. Moreover, a new explanation stability mechanism is established to maintain the consistency and reliability of model explanations in distributed environments. To promote clinical safety, the decision module includes uncertainty to enable the system to detect predictions with low confidence and defer them to experts. Massive tests using actual clinical data on patient conditions can be conducted to demonstrate that the framework presented is much more successful than other methods with respect to predictiveness, interpretability, explanation stability, fairness, and calibration. Furthermore, the framework demonstrates that privacy preservation, interpretability, explanation reliability, and clinical usability can be jointly optimized within a unified learning architecture. The findings indicate the effectiveness of the suggested strategy in providing secure, transparent, and reliable clinical decision support, rendering it an appropriate strategy to implement in contemporary healthcare systems.
SN  - 2045-2322
ER  -