Abstract
With the increasing amounts of electronic health data being constantly generated in medical examinations and by sensors and mobile applications, data visualization methods can assist medical professionals and researchers in exploring and making sense of the data. Two important challenges faced by data visualization are large data volume and protection of sensitive data. In this paper, we propose a graph-based method that allows the exploration of a patient dataset, while also naturally allowing the summarization of large amounts of data, making it applicable to large datasets and sensitive data. A graph is constructed from the raw data, encoding local similarities among patients, and is visualized on the screen, producing a visual map of the patient distribution. Multidimensional glyphs are put in place of the nodes, revealing the properties that characterize each graph area. The graph construction method is extended to an incremental scheme, allowing federated graph formation. The proposed method is demonstrated in three use cases, regarding frailty in older adults, Sjögren’s Syndrome patients, and a large-size diabetes dataset.
Similar content being viewed by others
References
Beck F, Burch M, Diehl S, Weiskopf D (2017) A taxonomy and survey of dynamic graph visualization. In: Computer graphics forum, vol 36, pp 133–159. Wiley Online Library
Bhavnani SK, Drake J, Divekar R (2014) The role of visual analytics in asthma phenotyping and biomarker discovery
Borgo R, Kehrer J, Chung David HS, Maguire E, Laramee RS, Hauser H, Ward M, Chen M (2013) Glyph-based visualization: Foundations, design guidelines, techniques and applications. In: Eurographics (STARs), pp 39–63
Cao N, Lin Y-R, Gotz D, Du F (2018) Z-glyph: Visualizing outliers in multivariate data. Inf Vis 17(1):22–40
Dix A, Ellis G (1998) Starting simple: adding value to static visualisation through simple interaction. In: Proceedings of the working conference on advanced visual interfaces, pp 124–134
Drosou A, Kalamaras I, Stavros P, Dimitrios T (2016) An enhanced graph analytics platform (gap) providing insight in big network data. J Innov Digit Ecosyst 3(2):83–97
EU H2020 (2018) European project FrailSafe: Sensing and predictive treatment of frailty and associated co-morbidities using advanced personalized patient models and advanced interventions. https://frailsafe-project.eu/
EU H2020 (2020) European project HarmonicSS: Harmonization and integrative analysis of regional, national and international Cohorts on primary Sjögren’s Syndrome (pSS) towards improved stratification, treatment and health policy making. https://www.harmonicss.eu/
Fried LP, Tangen CM, Jeremy W, Newman AB, Hirsch C, Gottdiener J, Seeman T, Tracy R, Kop WJ, Burke G (2001) Frailty in older adults: evidence for a phenotype. J Gerontol A Biol Med Sci 56(3):M146–M157
Fuchs J, Isenberg P, Bezerianos A, Keim D (2016) A systematic review of experimental studies on data glyphs. IEEE Trans Visual Comput Graph 23(7):1863–1879
Hachul S, Jünger M. (2005) Large-graph layout with the fast multipole multilevel method, Spring, V, (December), 1–27
Jeffrey H, Danah B (2005) Vizster: Visualizing online social networks. In: IEEE symposium on information visualization, 2005. INFOVIS 2005., pp 32–39. IEEE
Kalamaras I, Drosou A, Tzovaras D (2014) Multi-objective optimization for multimodal visualization. IEEE Trans Multimed 16(5):1460–1472
Kwon O-H, Muelder C, Kyungwon L, Kwan-Lium M (2016) A study of layout, rendering, and interaction methods for immersive graph visualization. IEEE Trans Visual Comput Graph 22(7):1802–1815
Li L, Wei-Yi C, Glicksberg BS, Gottesman O, Tamler R, Chen R, Bottinger EP, Dudley JT (2015) Sci Transl Med. In: Identification of type 2 diabetes subgroups through topological analysis of patient similarity, vol 7, pp 311ra174–311ra174
Linhares CDG, Travençolo BAN, Paiva JGS, Rocha LEC (2017) Dynetvis: a system for visualization of dynamic networks. In: Proceedings of the symposium on applied computing, pp 187–194
Liu J, Bier E, Wilson A, Guerra-Gomez JA, Honda T, Sricharan K, Gilpin L, Davies D (2016) Graph analysis for detecting fraud, waste, and abuse in healthcare data. AI Mag 37(2):33–46
William JRL (2012) Combing the hairball with biofabric: a new approach for visualization of large networks. BMC Bioinform 13(1):1–16
Jiawei L, Si YW (2020) Clustering-based force-directed algorithms for 3d graph visualization. J Supercomput 76(12):9654–9715
Opach T, Popelka S, Dolezalova J, Ketil JR (2018) Star and polyline glyphs in a grid plot and on a map display: which perform better. Cart Geogr Inf Sci 45(5):400–419
Pai S, Bader GD (2018) Patient similarity networks for precision medicine. J Molec Biol 430(18):2924–2938
Polychronidou E, Kalamaras I, Votis K, Tzovaras D (2018) Towards visualizing primary sjögren’s syndrome data from heterogeneous cohorts. In: Proceedings of the 10th hellenic conference on artificial intelligence, pp 1–4
Polychronidou E, Kalamaras I, Votis K, Tzovaras D (2019) Health vision: An interactive web based platform for healthcare data analysis and visualisation. In: 2019 IEEE Conference on computational intelligence in bioinformatics and computational biology (CIBCB), pp 1–8. IEE
Polychronidou E, Xochelli A, Moschonas P, Papadopoulos S, Hatzidimitriou A, Vlamos P, Stamatopoulos K, Tzovaras D (2017) Chronic lymphocytic leukemia patient clustering based on somatic hypermutation (shm) analysis. In: GeNeDis 2016, pp 127–138. Springer
Ribassin-Majed L, Marguet S, Lee Anne WM, Ng WT, Ma J, Chan Anthony TC, Huang P-Y, Zhu G, Chua DTT, Chen Y et al (2017) What is the best treatment of locally advanced nasopharyngeal carcinoma? an individual patient data network meta-analysis. J Clin Oncol 35(5):498
Ropinski T, Oeltze S, Preim B (2011) Survey of glyph-based visualization techniques for spatial multivariate medical data. Comput Graph 35 (2):392–401
Strack B, DeShazo JP, Gennings C, Olmo JL, Ventura S, Cios KJ, Clore JN (2014) Impact of hba1c measurement on hospital readmission rates: analysis of 70,000 clinical database patient records. BioMed research international 2014
Valdivia P, Buono P, Plaisant C, Dufournaud N, Fekete J-D (2020) Analyzing dynamic hypergraphs with parallel aggregated ordered hypergraph visualization. IEEE transactions on visualization and computer graphics
Ward M (2008) Multivariate data glyphs: Principles and practice. In: Handbook of data visualization, pp 179–198. Springer
Widanagamaachchi W, Livnat Y, Bremer P-T, Duvall S, Pascucci V (2017) Interactive visualization and exploration of patient progression in a hospital setting. In: AMIA annual symposium proceedings, vol 2017, pp 1773. American Medical Informatics Association
Zacharaki EI, Deltouzos K, Kalogiannis S, Kalamaras I, Bianconi L, Degano C, Orselli R, Montesa J, Moustakas K, Votis K et al (2020), An ict platform for unobtrusive sensing of multi-domain frailty for personalized interventions. IEEE Journal of Biomedical and Health Informatics, Frailsafe
Zhou Y, Saad Y (2007) A chebyshev–davidson algorithm for large symmetric eigenproblems. SIAM J Matr Anal Appl 29(3):954–971
Acknowledgements
This work has been supported by the EU H2020 projects FrailSafe (H2020-PHC-21-2015, grant agreement no. 690140) and HarmonicSS (H2020-SC1-2016-RTD, grant agreement no. 731944).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kalamaras, I., Glykos, K., Megalooikonomou, V. et al. Graph-based visualization of sensitive medical data. Multimed Tools Appl 81, 209–236 (2022). https://doi.org/10.1007/s11042-021-10990-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-10990-1