Applied Sciences
| Open Access | Multimodal Intelligence in Strategic and Clinical Decision Support: Integrating Prompt Engineering with Privacy-Preserving Business Analytics
Marcus A. Thorne , Department of Data Science, University of California, Berkeley, CA, USA Li Wei , Institute for High-Performance Computing, National University of Singapore, SingaporeAbstract
Background: The exponential growth of data across industrial and healthcare sectors has necessitated a paradigm shift from traditional data processing to advanced Business Intelligence (BI) and multimodal analytics. While BI has established itself as a cornerstone of competitive advantage in the corporate sector, its integration with clinical informatics and emerging artificial intelligence methodologies—specifically prompt engineering—remains a complex, evolving frontier.
Methods: This study employs a systematic qualitative meta-synthesis of literature ranging from 1994 to 2025. We analyze 25 key sources spanning business management, medical informatics, and computational linguistics to construct a unified framework for modern data utility.
Results: The analysis reveals that successful BI implementation relies heavily on organizational readiness and ethical data governance rather than software capabilities alone. In healthcare, the convergence of Electronic Health Records (EHR) with predictive data mining is accelerating the shift toward precision medicine. Furthermore, the emergence of few-shot prompt learning and multimodal approaches offers a solution to the "label scarcity" problem, enabling richer feature extraction without extensive manual annotation.
Conclusion: The future of analytics lies in the symbiotic relationship between structured BI frameworks and unstructured, multimodal AI interpretations. Organizations must prioritize privacy-preserving technologies, such as k-anonymity, while adopting agile prompt engineering techniques to maintain competitive viability and clinical safety.
Keywords
Business Intelligence, Precision Medicine, Multimodal Learning, Prompt Engineering
References
Bellazzi, R. and Zupan, B., (2008). Predictive data mining in clinical medicine: current issues and guidelines. International journal of medical informatics, 77(2), pp.81-97. https://doi.org/10.1016/j.ijmedinf.2007.06.004
Burton, L.C., Anderson, G.F. and Kues, I.W., (2004). Using electronic health records to help coordinate care. The Milbank Quarterly, 82(3), pp.457-481. https://doi.org/10.1111/j.1468-0009.2008.00533.x
Chaudhuri, S., Dayal, U. and Narasayya, V., (2011). An overview of business intelligence technology. Communications of the ACM, 54(8), pp.88-98. https://doi.org/10.1145/1978542.1978562
Collins, F.S. and Varmus, H., (2015). A new initiative on precision medicine. New England journal of medicine, 372(9), pp.793-795. https://doi.org/10.1056/NEJMp1500523
Ehimuan, B., Akindote, O.J., Olorunsogo, T., Anyanwu, A. and Olorunsogo, T., (2024). Mental health and social media in the US: A review: Investigating the potential links between online platforms and mental well-being among different age groups. International Journal of Science and Research Archive, 11(1), pp. 464-477.
El Emam, K. and Dankar, F.K., (2008). Protecting privacy using k-anonymity. Journal of the American Medical Informatics Association, 15(5), pp.627-637. https://doi.org/10.1197/jamia.M271
El Morr, C. and Subercaze, J., (2010). Knowledge management in healthcare. In Handbook of research on developments in e-health and telemedicine: Technological and social perspectives (pp. 490-510). IGI Global. https://doi.org/10.4018/978-1-61520-670-4.ch027
Lo, L.S. (2023). The CLEAR Path: A Framework for Enhancing Information Literacy Through Prompt Engineering. The Journal of Academic Librarianship, 49, 102720.
Ahmed, T., Pai, K.S., Devanbu, P., & Barr, E. (2023). Improving Few-Shot Prompts with Relevant Static Analysis Products. arXiv preprint arXiv:2304.06815. Available online: https://arxiv.org/abs/2304.06815
Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., & Khan, F.S. (2023). MaPLe: Multi-modal Prompt Learning. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 18–22 June 2023; pp. 19113–19122.
Jourdan, Z., Rainer, R. K., & Marshall, T. E. (2008). Business intelligence: An analysis of the literature. Information systems management, 25(2), 121-131.
Fitriana, R., Eriyatno, T. D., & Djatna, T. (2011). Progress in business intelligence system research: a literature review. International Journal of Basic & Applied Sciences IJBAS-IJENS, 11(03), 118503-6464.
El-Adaileh, N. A., & Foster, S. (2019). Successful business intelligence implementation: a systematic literature review. Journal of Work-Applied Management.
Aruldoss, M., Travis, M. L., & Venkatesan, V. P. (2014). A survey on recent research in business intelligence. Journal of Enterprise Information Management.
Gaardboe, R., & Jonasen, T. S. (2018). Business intelligence success factors: a literature review. Journal of Information Technology Management, 29(1), 1-15.
Patel, D. B. (2025). Leveraging BI for Competitive Advantage: Case Studies from Tech Giants. Frontiers in Emerging Engineering & Technologies, 2(04), 15–21. Retrieved from https://irjernet.com/index.php/feet/article/view/166
Houstis, E., Fakas, G., & Vavalis, M. (2022). A Systematic Survey of Business Intelligence Literature Using Machine Learning Techniques. Journal of Economics & Management Research. SRC/JESMR-167. J Econ Managem Res.
Dhar, V., & Stein, R. (1997). Seven methods for transforming corporate data into business intelligence. Prentice-Hall, Inc.1
Hallaq, J. H., & Steinhorst, K. (1994). Business intelligence methods—How ethical. Journal of Business Ethics, 213(10), 787-794.
Gupta, K., & Jiwani, N. (2021). A systematic Overview of Fundamentals and Methods of Business Intelligence. International Journal of Sustainable Development in Computing Science, 3(3), 31-46.
Obeidat, M., North, M., Richardson, R., & Rattanak, V. (2015). Business intelligence technology, applications, and trends.
Download and View Statistics
Copyright License
Copyright (c) 2025 Marcus A. Thorne, Li Wei
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.