This article presents an integrated digital architecture designed for predictive surveillance of rare diseases, combining interoperability, automation, and artificial intelligence to address major challenges such as fragmented health data, delayed diagnosis, and limited continuous monitoring systems. Based on the author’s master’s research, the study proposes a modular ecosystem using FlutterFlow, Firebase, Supabase, N8N, Python, and analytical APIs to collect, normalize, process, and analyze clinical information in near real time. The architecture includes layers for data ingestion, intelligent routing, predictive modeling, clinical decision support, persistence, observability, privacy, and user interface. Results demonstrate technical feasibility, scalability potential, and the ability to generate personalized alerts and support smarter clinical workflows. The study concludes that innovation in healthcare depends not only on isolated algorithms, but on well-orchestrated digital infrastructures capable of transforming fragmented data into coordinated care for patients with rare diseases.
Paula Lopes Alvim Santilli (Sun,) studied this question.