A Multi-Layer AI-Driven Decision Intelligence Framework for Enterprise and Healthcare System
Main Article Content
Abstract
This paper proposes a comprehensive multi-layer AI-driven decision intelligence framework designed for enterprise and healthcare systems, addressing critical limitations in existing AI implementations where data, models, and decision-making processes often operate in isolation, thereby restricting scalability, explainability, and real-world applicability. The proposed framework introduces five interconnected layers data, intelligence, decision, application, and analytics each performing a distinct role in transforming raw data into actionable insights. By integrating machine learning models, rule-based reasoning, and advanced analytics, the framework ensures adaptive, accurate, and transparent decision-making. A healthcare case scenario is utilized to validate the framework, demonstrating improvements in clinical decision support, resource allocation, and response time. The evaluation results indicate enhanced decision accuracy, reduced processing time, and improved operational efficiency compared to traditional approaches. This study contributes a scalable and domain-independent architecture that bridges the gap between AI models and actionable decisions, supporting future intelligent systems with better interpretability and performance.
Article Details
Section
How to Cite
References
[1] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016. DOI: https://doi.org/10.7551/mitpress/10243.001.0001
[2] T. Mitchell, Machine Learning. McGraw-Hill, 1997.
[3] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015. DOI: https://doi.org/10.1038/nature14539
[4] D. Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, pp. 484–489, 2016. DOI: https://doi.org/10.1038/nature16961
[5] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining predictions,” KDD, 2016. DOI: https://doi.org/10.1145/2939672.2939778
[6] F. Doshi-Velez and B. Kim, “Towards a rigorous science of interpretable ML,” arXiv, 2017. DOI: https://doi.org/10.48550/arXiv.1702.08608
[7] A. Adadi and M. Berrada, “Peeking inside the black-box: XAI survey,” IEEE Access, 2018. DOI: https://doi.org/10.1109/ACCESS.2018.2870052
[8] D. J. Power, “Decision support systems,” Journal of DSS, 2002.
[9] S. Shrestha et al., “Organizational decision intelligence,” MIS Quarterly Executive, 2019.
[10] E. J. Topol, Deep Medicine, Basic Books, 2019.
[11] A. Esteva et al., “Dermatologist-level classification of skin cancer,” Nature, 2017. DOI: https://doi.org/10.1038/nature21056
[12] Z. Obermeyer and E. J. Emanuel, “Predicting the future big data in healthcare,” NEJM, 2016. DOI: https://doi.org/10.1056/NEJMp1606181
[13] A. Rajkomar et al., “Scalable deep learning for healthcare,” npj Digital Medicine, 2018. DOI: https://doi.org/10.1038/s41746-018-0029-1
[14] D. Dixon et al., “AI predictive analytics in healthcare,” PMC, 2024. DOI: https://doi.org/10.2196/50890
[15] F. Provost and T. Fawcett, Data Science for Business. O’Reilly, 2013.
[16] V. Dhar, “Data science and prediction,” Communications of the ACM, 2013. DOI: https://doi.org/10.1145/2500499
[17] J. Manyika et al., “Big data: The next frontier,” McKinsey, 2011.
[18] T. Davenport and R. Ronanki, “Artificial intelligence for the real world,” Harvard Business Review, 2018.
[19] H. Kagermann, “Change through digitization,” Management of Permanent Change, 2015.
[20] M. Hammer, “Reengineering work,” Harvard Business Review, 1990.
[21] P. Jackson, Introduction to Expert Systems. Addison-Wesley, 1998.
[22] G. Marcus, “The next decade in AI: hybrid systems,” arXiv, 2020. DOI: https://doi.org/10.48550/arXiv.2002.06177
[23] N. Besold et al., “Neural-symbolic learning survey,” AI Journal, 2017. DOI: https://doi.org/10.1016/j.artint.2017.10.001
[24] N. Taimoor and S. Rehman, “AI and IoT healthcare systems survey,” 2022. DOI: https://doi.org/10.48550/arXiv.2209.05457
[25] S. Raghupathi and V. Raghupathi, “Big data analytics in healthcare,” Health Information Science, 2014. DOI: https://doi.org/10.1007/978-3-319-03095-1_3
[26] H. Cho et al., “Machine learning in health science research,” JMIR, 2024. DOI: https://doi.org/10.2196/50890
[27] M. Ghassemi et al., “Machine learning challenges in health,” arXiv, 2018. DOI: https://doi.org/10.48550/arXiv.1806.00388
[28] L. Bass, P. Clements, and R. Kazman, Software Architecture in Practice. Addison-Wesley, 2012.
[29] G. Hohpe and B. Woolf, Enterprise Integration Patterns. Addison-Wesley, 2003.
[30] M. Fowler, Patterns of Enterprise Application Architecture. Addison-Wesley, 2002.
[31] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, 2006. DOI: https://doi.org/10.1016/j.patrec.2005.10.010
[32] J. Davis and M. Goadrich, “Precision-recall vs ROC,” ICML, 2006. DOI: https://doi.org/10.1145/1143844.1143874
[33] S. Sreedharan et al., “Top cited AI healthcare articles,” 2020. DOI: https://doi.org/10.21037/jmai.2019.11.04
[34] A. Beam and I. Kohane, “Big data and ML in healthcare,” JAMA, 2018. DOI: https://doi.org/10.1001/jama.2017.18391
[35] C. Iwendi et al., “AI in IoT healthcare systems,” IEEE Access, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.2977962
[36] K. He et al., “Deep residual learning,” CVPR, 2016. DOI: https://doi.org/10.1109/CVPR.2016.90
[37] J. Schmidhuber, “Deep learning overview,” Neural Networks, 2015. DOI: https://doi.org/10.1016/j.neunet.2014.09.003
[38] A. Vaswani et al., “Attention is all you need,” NeurIPS, 2017. DOI: https://doi.org/10.48550/arXiv.1706.03762