StrawHealth: A Modular AI-Assisted Healthcare Information Platform with Symptom Screening, Health-Risk Assessment, Medical Report Parsing, Nutrition Rules, and Retrieval-Augmented Guidance

StrawHealth demonstrates a unified, practical approach to personal digital health assistance. By integrating symptom screening, chronic diabetes risk calculation, automated lab report parsing, rule-based nutrition planning, and retrieval-augmented health Q&A into a single responsive Flask web application, it addresses the fragmentation of existing online tools. Empirical evaluation establishes robust performance across core machine learning components, achieving a 78.83% macro F1-score on synthetic symptom data and an 82.94% ROC-AUC on public health-risk data. StrawHealth serves as a transparent, open-source prototype demonstrating how modular software integration and responsible ethical disclaimers can make digital health decision-support tools safer and more accessible.

[1] H. L. Semigran, J. A. Linder, C. Gidengil, and A. Mehrotra, "Evaluation of symptom checkers for self diagnosis and triage: audit study," BMJ, vol. 351, p. h3480, 2015, doi: 10.1136/bmj.h3480. [2] F. Rustam, Z. Imtiaz, A. Mehmood, V. Rupapara, G. S. Choi, S. Din, and I. Ashraf, "Automated disease diagnosis and precaution recommender system using supervised machine learning," Multimedia Tools and Applications, vol. 81, no. 22, pp. 31929–31952, 2022, doi: 10.1007/s11042-022-12897-2. [3] R. H. Koushal, C. V. S. Pranav, R. K. Gupta, K. H. Verma, and N. C. Mair, "AI-Powered Symptom Checker Chatbot in Regional Languages," in Proc. 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), 2025, doi: 10.1109/IATMSI64286.2025.10985720. [4] S. Gaikwad, P. Awatade, Y. Sirdeshmukh, and C. Prasad, "Diet Plan and Home Exercise Recommendation System Using Smart Watch," in Proc. 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIHI), 2023, doi: 10.1109/ICAIHI57871.2023.10489367. [5] UCI Machine Learning Repository, "CDC Diabetes Health Indicators," Dataset ID 891, doi: 10.24432/C53919. [Online]. Available: https://archive.ics.uci.edu/dataset/891/cdc+diabetes+health+indicators. Accessed: Oct. 21, 2026. [6] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [Online]. Available: https://www.jmlr.org/papers/v12/pedregosa11a.html. [7] R. Smith, "An Overview of the Tesseract OCR Engine," in Proc. Ninth International Conference on Document Analysis and Recognition (ICDAR), 2007, pp. 629–633, doi: 10.1109/ICDAR.2007.4376991. [8] N. Reimers and I. Gurevych, "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks," in Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 3982–3992, doi: 10.18653/v1/D19-1410. [9] P. Lewis et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," in Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020. [10] L. M. Amugongo, P. Mascheroni, S. Brooks, S. Doering, and J. Seidel, "Retrieval augmented generation for large language models in healthcare: A systematic review," PLOS Digital Health, vol. 4, no. 6, e0000877, 2025, doi: 10.1371/journal.pdig.0000877.