Graphical Modeling and Analysis for Discovering Hidden Relationships between Diseases and Symptoms: A Data-driven Approach for Differential Diagnosis and Symptom Co-occurrence

Document Type : Original Article

Authors
Sepideh Ghaffari 1
Roghaye Khasha 2
1 Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
2 Assistant Professor, Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
10.48305/him.2026.45792.1346
Abstract
Abstract

Introduction: Understanding hidden relationships between diseases and symptoms is one of the fundamental challenges in differential diagnosis and comorbidity analysis in medicine. Given the complexity of clinical interactions, identifying shared patterns among diseases can play a crucial role in improving the diagnostic process and clinical decision-making. This study proposes a data-driven, graph-based analytical framework for modeling and uncovering hidden relationships between diseases and symptoms.

Methods: This study utilized the publicly available Disease–Symptom Prediction Dataset from the Kaggle platform, consisting of 4920 records covering 41 diseases and 131 unique symptoms. Using a linear combination of occurrence frequency indices and the kappa coefficient, a weighted bipartite disease–symptom graph was constructed. Disease–disease and symptom–symptom unipartite graphs were then extracted, and their network structures were analyzed using the Louvain, Greedy Modularity, and Girvan–Newman clustering algorithms.

Results: The results indicated that the symptom fatigue and the disease dengue fever played a key role in the disease–symptom network. Disease clustering using the Louvain and Greedy Modularity algorithms identified meaningful clusters of related diseases. Symptom clustering with the Louvain algorithm revealed six clinically interpretable clusters, which could be useful for rapid disease identification. Moreover, seemingly unrelated symptoms could be associated with a common disease, while specific symptom clusters can guide the diagnosis of particular diseases.

Conclusion: The findings indicate that graph-based analysis can serve as an effective tool for uncovering hidden relationships between diseases and symptoms and can play an important role in improving differential diagnosis and designing intelligent decision-support systems.
Keywords
Differential Disease Diagnosis
Symptom Co-occurrence
Medical Network Analysis
Bipartite Graph
Community Detection
Subjects
1. Yang Z, Liu H, Yu H, Hu F. Multi-view disease-symptom association prediction based on disease knowledge graph embedding. In2023 IEEE International Conference on Medical Artificial Intelligence (MedAI) 2023 Nov 18 (pp. 133-142). IEEE. Beijing, China.
2. Pechsiri C, Piriyakul R. Construction of disease-symptom knowledge graph from web-board documents. Applied Sciences. 2022 Jun 29;12(13):6615.
3. Lamba D, Hsu WH, Alsadhan M. Predictive analytics and machine learning for medical informatics: A survey of tasks and techniques. InMachine learning, big data, and IoT for medical informatics 2021 Jan 1 (pp. 1-35). Academic Press.
4. Liang M, Zhu S, Zhang W, Knobf MT, Ye Z. Symptom network approach for management in cancer care. Asia-Pacific Journal of Oncology Nursing. 2024 May 1;11(5).
5. Kuang Y, Jing F, Sun Y, Zhu Z, Xing W. Symptom networks in older adults with cancer: a network analysis. Journal of Geriatric Oncology. 2024 Apr 1;15(3):101718.
6. Finamore P, Spruit MA, Schols JM, Antonelli Incalzi R, Wouters EF, Janssen DJ. Clustering of patients with end-stage chronic diseases by symptoms: a new approach to identify health needs. Aging clinical and experimental research. 2021 Feb;33(2):407-17.
7. Shirazi S, Albadvi A, Akhondzadeh E, Farzadfar F, Teimourpour B. A new application of community detection for identifying the real specialty of physicians. International journal of medical informatics. 2020 Aug 1;140:104161.
8. Bacciu D, Errica F, Micheli A, Podda M. A gentle introduction to deep learning for graphs. Neural Networks. 2020 Sep 1;129:203-21.
9. Hosseini M, Galavi E. Community Detection in Social Networks Using Deep Learning Approach. Business Intelligence Management Studies. 2023 Jun 22;11(44):83-112. [In Persian]
10. Gottlieb A, Stein GY, Ruppin E, Sharan R. PREDICT: a method for inferring novel drug indications with application to personalized medicine. Molecular systems biology. 2011 Jun 7;7(1):496.
11. Li JQ, Rong ZH, Chen X, Yan GY, You ZH. MCMDA: Matrix completion for MiRNA-disease association prediction. Oncotarget. 2017 Feb 3;8(13):21187.
12. Zhang W, Yue X, Tang G, Wu W, Huang F, Zhang X. SFPEL-LPI: Sequence-based feature projection ensemble learning for predicting LncRNAprotein interactions. PLoS computational biology. 2018 Dec 11;14(12):e1006616.
13. Xia E, Sun W, Mei J, Xu E, Wang K, Qin Y. Mining disease-symptom relation from massive biomedical literature and its application in severe disease diagnosis. InAMIA Annual Symposium Proceedings 2018 Dec 5 (Vol. 2018, p. 1118).
14. Zhou X, Menche J, Barabási AL, Sharma A. Human symptoms–disease network. Nature communications. 2014 Jun 26;5(1):4212.
15. Bojer CS, Meldgaard JP. Kaggle forecasting competitions: An overlooked learning opportunity. International Journal of Forecasting. 2021 Apr 1;37(2):587-603.
  16. Pavlopoulos GA, Kontou PI, Pavlopoulou A, Bouyioukos C, Markou E, Bagos PG. Bipartite graphs in systems biology and medicine: a survey of methods and applications. GigaScience. 2018 Apr;7(4):giy014.
17. Rustamaji HC, Kusuma WA, Nurdiati S, Batubara I. Community detection with greedy modularity disassembly strategy. Scientific Reports. 2024 Feb 26;14(1):4694.
18. Zahiri M, Mohammadzadeh J, Harifi S. An improved Girvan-Newman community detection algorithm using trust-based centrality. Journal of Ambient Intelligence and Humanized Computing. 2023 Apr;14(4):3755-66.
19. Zhang J, Wang S, Wang Y, Zhuang J, Hang L, Wu Y, Xu D, Huang C. Symptom clusters and network analysis in patients with gynecologic cancer undergoing chemotherapy: A cross-sectional study. Asia-Pacific Journal of Oncology Nursing. 2024 Dec 1;11(12):100612.
20. Rha SY, Lee J. Stable symptom clusters and evolving symptom networks in relation to chemotherapy cycles. Journal of pain and symptom management. 2021 Mar 1;61(3):544-54.
21. Luo R, Chen H, Liu Y, Sun H, Tang S, Chen Y. Symptom clusters among breast cancer patients in relation to chemotherapy cycles: a longitudinal study. Supportive Care in Cancer. 2023 Oct;31(10):573.
22. Kim HJ, McGuire DB, Tulman L, Barsevick AM. Symptom clusters: concept analysis and clinical implications for cancer nursing. Cancer nursing. 2005 Jul 1;28(4):270-82.
23. Qi Y, Li H, Chan DN, Ma X, Wong CL. Effects of yoga interventions on the fatigue-pain-sleep disturbance symptom cluster in breast cancer patients: a systematic review. European Journal of Oncology Nursing. 2024 Jun 1;70:102594.