HISaaS: A Cloud-Based Framework for Semantic Enrichment of Legacy Health Databases Using OpenAI Embeddings

Legacy Information Systems (LIS) confront significant interoperability challenges, particularly at the database level. If existing solutions focus on data exchange, they fail to address the fundamental structural incompatibilities of Legacy Databases (LDBs). In this article, we present Health Information System as a Service (HISaaS), an innovative dual solution based on AI and Cloud Computing, designed either to update a LIS with a new modern HIS (Health Information System); or to completely propose a new IS. This new HIS is the result of the interoperability of several modern HIS. HISaaS uses Cloud computing as an interoperability environment, Natural Language Processing (NLP), and semantic similarity to analyze and enrich the already existing structure of the LDBs with new tables and/or new attributes from modern and interoperable external databases. This solution uses a vector-based approach relying on contextual embeddings from OpenAI models and cosine similarity measurement to accurately match schema elements. In the end, an evaluation based on real healthcare scenarios demonstrates the effectiveness of this HISaaS solution.

@article{Salmi2026,
  title     = {HISaaS: A Cloud-Based Framework for Semantic Enrichment of Legacy Health Databases Using OpenAI Embeddings},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {7},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Toufik Salmi and Abdeslem Dennai},
  doi       = {10.14569/IJACSA.2026.0170724},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170724}
}