Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65507
Volume:
10 |
6 |
Jun 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Engineering
Sinhgad Academy Of Engineering
Computer Engineering
Sinhgad Academy Of Engineering
Computer Engineering
Sinhgad Academy Of Engineering
Computer Engineering
Sinhgad Academy Of Engineering
Computer Engineering
Sinhgad Academy Of Engineering
MediScope is an implemented disease surveillance platform that combines web data acquisition, natural language processing, machine learning, and interactive analytics in a single web-based system. The platform ingests outbreak-related content from the World Health Organization (WHO) RSS feed, the Centers for Disease Control and Prevention (CDC) RSS feed, the disease.sh API, and the WHO Global Health Observatory (GHO) API. A backend pipeline built in Python processes raw articles, classifies outbreak relevance using a TF-IDF and Logistic Regression model with keyword fallback, extracts diseases and locations through a spaCy-driven multi-stage pipeline, enriches incomplete records with WHO GHO disease statistics, and persists the resulting outbreaks in MongoDB Atlas. The processed information is exposed through a Flask REST API and consumed by a React 19 frontend developed with Vite and Tailwind CSS. The user interface provides a summary dashboard, geospatial map view, disease detail pages, comparative analysis, symptom-based search, email alert subscription, and an analytics page. The present work is an implementation paper rather than an experimental benchmark study. Accordingly, it documents the actual architecture, modules, API surface, data flow, and current limitations of the deployed codebase. Quantitative evaluation metrics such as accuracy, precision, recall, F1-score, and throughput benchmarks have not yet been formally recorded in the implementation and are therefore not reported in this paper.
KEYWORDS
This paper presented MediScope as a complete implementation of a web-based disease surveillance platform integrating data acquisition, NLP, machine learning, cloud persistence, REST delivery, and interactive visualization. The project successfully demonstrates that official health feeds, public APIs, rule-enhanced NLP, and modern web interfaces can be combined into a coherent operational system for outbreak monitoring. An important contribution of the implementation is the bridging of multiple data modalities within a single application. Narrative news articles, structured health indicators, user subscriptions, and interactive geospatial views are all connected through one codebase, which is a meaningful systems-engineering outcome for academic project work. The current implementation is practically useful for exploratory surveillance, educational demonstration, and further research-oriented extension. Future enhancement should prioritize quantitative evaluation, alert workflow correction, consistent severity modeling, processing automation, broader disease coverage, and test-driven hardening for production deployment.
[1] J. S. Brownstein, C. C. Freifeld, and L. C. Madoff, “Digital disease detection - harnessing the web for public health surveillance,” N. Engl. J. Med., vol. 360, no. 21, pp. 2153-2157, 2009. [2] R. Chunara, J. R. Andrews, and J. S. Brownstein, “Social and news media enable estimation of epidemiological patterns early in the 2010 Haitian cholera outbreak,” Am. J. Trop. Med. Hyg., vol. 86, no. 1, pp. 39-45, 2012. [3] D. Lazer, R. Kennedy, G. King, and A. Vespignani, “The parable of Google Flu: traps in big data analysis,” Science, vol. 343, no. 6176, pp. 1203-1205, 2014. [4] M. Honnibal and I. Montani, “spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing,” 2017. [5] G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer, “Neural architectures for named entity recognition,” in Proc. NAACL-HLT, 2016, pp. 260-270. [6] G. Salton and C. Buckley, “Term-weighting approaches in automatic text retrieval,” Inf. Process. Manage., vol. 24, no. 5, pp. 513-523, 1988. [7] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825-2830, 2011. [8] World Health Organization, “Disease Outbreak News,” [Online]. Available: https://www.who.int/emergencies/disease-outbreak-news. [Accessed: Jun. 24, 2026]. [9] World Health Organization, “Global Health Observatory API,” [Online]. Available: https://ghoapi.azureedge.net/api/. [Accessed: Jun. 24, 2026]. [10] Centers for Disease Control and Prevention, “CDC Newsroom RSS Feeds,” [Online]. Available: https://tools.cdc.gov/api/v2/resources/media/316422.rss. [Accessed: Jun. 24, 2026].
Publication Date
6/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...