Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Roses Have Thorns: Understanding the Downside of Oncological Care Delivery Through Visual Analytics and Sequential Rule Mining (2308.07895v2)

Published 15 Aug 2023 in cs.HC

Abstract: Personalized head and neck cancer therapeutics have greatly improved survival rates for patients, but are often leading to understudied long-lasting symptoms which affect quality of life. Sequential rule mining (SRM) is a promising unsupervised machine learning method for predicting longitudinal patterns in temporal data which, however, can output many repetitive patterns that are difficult to interpret without the assistance of visual analytics. We present a data-driven, human-machine analysis visual system developed in collaboration with SRM model builders in cancer symptom research, which facilitates mechanistic knowledge discovery in large scale, multivariate cohort symptom data. Our system supports multivariate predictive modeling of post-treatment symptoms based on during-treatment symptoms. It supports this goal through an SRM, clustering, and aggregation back end, and a custom front end to help develop and tune the predictive models. The system also explains the resulting predictions in the context of therapeutic decisions typical in personalized care delivery. We evaluate the resulting models and system with an interdisciplinary group of modelers and head and neck oncology researchers. The results demonstrate that our system effectively supports clinical and symptom research.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (82)
  1. R. Agrawal and R. Srikant. Fast Algorithms for Mining Association Rules in Large Databases. In Proc. 20th Int. Conf. Very Large Data Bases (VLDB), p. 487–499. Morgan Kaufmann Publishers Inc., 1994.
  2. Symptom Clusters: Myth or Reality? Palliative Med., 24(4):373–385, 2010. doi: 10 . 1177/0269216310367842
  3. D. Antweiler and G. Fuchs. Visualizing Rule-based Classifiers for Clinical Risk Prognosis. In 2022 IEEE Vis. and Visual Anal. (VIS), pp. 55–59. IEEE, 2022. doi: 10 . 1109/tkde . 2008 . 131
  4. In Search of Patient Zero: Visual Analytics of Pathogen Transmission Pathways in Hospitals. IEEE Trans. Vis. Comp. Graph., 27(2):711–721, 2021. doi: 10 . 1109/tvcg . 2020 . 3030437
  5. A visual-interactive system for prostate cancer stratifications. In Proc. IEEE VIS Workshop Visualizing Electronic Health Record Data, 2014. doi: 10 . 1109/mcg . 2015 . 49
  6. Identifying Symptom Clusters from Patient Reported Outcomes through Association Rule Mining. 19th Int. Conf. Artif. Intel. in Med. (AIME), 2021. doi: 10 . 1007/978-3-030-77211-6_58
  7. L. Brasseur. Florence Nightingale’s Visual Rhetoric in the Rose Diagrams. Tech. Comm. Quarterly, 14(2):161–182, 2005.
  8. D. Bruzzese and C. Davino. Visual Mining of Association Rules. In Visual Data Mining, p. 103–122. Springer, 2008. doi: 10 . 1007/978-3-540-71080-6_8
  9. Visual Analytics for Evaluating Clinical Pathways. In 2017 IEEE Workshop on Visual Anal. in Healthcare (VAHC), pp. 39–46. IEEE, 2017. doi: 10 . 1109/VAHC . 2017 . 8387499
  10. Spatially-aware Clustering Improves AJCC-8 Risk Stratification Performance in Oropharyngeal Carcinomas. Oral Oncology, 144:106460, 2023. doi: 10 . 1016/j . oraloncology . 2023 . 106460
  11. B. C. Cappers and J. J. van Wijk. Exploring Multivariate Event Sequences Using Rules, Aggregations, and Selections. IEEE Trans. Vis. Comp. Graph., 24(1):532–541, 2017. doi: 10 . 1109/tvcg . 2017 . 2745278
  12. Chronic radiation-associated dysphagia in oropharyngeal cancer survivors: Towards age-adjusted dose constraints for deglutitive muscles. Clin. & Trans. Rad. Onco., 18:16–22, 2019.
  13. Visual Analytics for Epidemiologists: Understanding the Interactions Between Age, Time, and Disease with Multi-Panel Graphs. PLoS one, 6(2):1–8, 2011. doi: 10 . 1371/journal . pone . 0014683
  14. Assessing symptom distress in cancer patients: The M.D. Anderson Symptom Inventory. Cancer, 89:1634–46, 11 2000. doi: 10 . 1046/j . 1533-2500 . 2001 . 01023-30 . x
  15. D. Defays. An Efficient Algorithm for a Complete Link Method. The Comp. Journ., 20(4):364–366, 1977. doi: 10 . 1093/comjnl/20 . 4 . 364
  16. J. Deogun and L. Jiang. Prediction Mining–an Approach to Mining Association Rules for Prediction. In Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing: 10th International Conference, RSFDGrC 2005, Proceedings, Part II 10, pp. 98–108. Springer, 2005. doi: 10 . 1007/11548706_11
  17. Sequence Braiding: Visual Overviews of Temporal Event Sequences and Attributes. IEEE Trans. Vis. Comp. Graph., 27(2):1353–1363, 2020. doi: 10 . 31219/osf . io/mq2wt
  18. Symptom Clusters in Advanced Cancer Patients: An Empirical Comparison of Statistical Methods and the Impact on Quality of Life. Pain and Symptom Manag., 51(1):88–98, 2016. doi: 10 . 1016/j . jpainsymman . 2015 . 07 . 013
  19. EventAction: Visual Analytics for Temporal Event Sequence Recommendation. In 2016 IEEE Conf. on Vis. Anal. Sci. and Tech. (VAST), pp. 61–70. IEEE, 2016. doi: 10 . 1109/vast . 2016 . 7883512
  20. Creative Visualisation Opportunities Workshops: A Case Study in Population Health. In 2022 IEEE Eval. and Beyond-Methodological Approaches for Vis. (BELIV), pp. 11–19. IEEE, 2022. doi: 10 . 1109/beliv57783 . 2022 . 00006
  21. Long-term patient Reported Outcomes Following Radiation Therapy for Oropharyngeal Cancer. Rad. Onco., 12(1):150, 2017.
  22. Symptom Clusters in Cancer Patients: A Review of the Literature. Curr. Onco., 14(5):173–179, 2007. doi: 10 . 3747/co . 2007 . 145
  23. Opening Access to Visual Exploration of Audiovisual Digital Biomarkers: an OpenDBM Analytics Tool. arXiv preprint arXiv:2210.01618, 2022.
  24. Thalis: Human-Machine Analysis of Longitudinal Symptoms in Cancer Therapy. IEEE Trans. Vis. Comp. Graph., 28(1):151–161, 2021. doi: 10 . 1109/tvcg . 2021 . 3114810
  25. CMRules: Mining Sequential Rules Common to Several Sequences. Knowledge-Based Systems, 25(1):63–76, 2012. doi: 10 . 1016/j . knosys . 2011 . 07 . 005
  26. SPMF: a Java Open-source Pattern Mining Library. J. Mach. Learn. Res., 15(1):3389–3393, 2014.
  27. D. Gotz and H. Stavropoulos. DecisionFlow: Visual Analytics for High-Dimensional Temporal Event Sequence Data. IEEE Trans. Vis. Comp. Graph., 20(12):1783–1792, 2014. doi: 10 . 1109/tvcg . 2014 . 2346682
  28. Visualizing Uncertainty and Alternatives in Event Sequence Predictions. In Proc. CHI Conf. Human Factors in Comput. Sys., p. 1–12, 2019. doi: 10 . 1145/3290605 . 3300803
  29. Eventthread: Visual Summarization and Stage Analysis of Event Sequence Data. IEEE Trans. Vis. Comp. Graph., 24(1):56–65, 2017. doi: 10 . 1109/tvcg . 2017 . 2745320
  30. Exploring the Differential Experience of Breast Cancer Treatment-Related Symptoms: a Cluster Analytic Approach. Support. Care in Cancer, 16(8):925–933, 2008. doi: 10 . 1007/s00520-007-0364-2
  31. A Richly Interactive Exploratory Data Analysis and Visualization Tool Using Electronic Medical Records. BMC Med. Infor. and Dec. Making, 15:92, 2015. doi: 10 . 1186/s12911-015-0218-7
  32. Crystalclear: Active Visualization of Association Rules. In Int. Workshop on Act. Min., AM2002, 2002.
  33. Association Between pro- and anti-Inflammatory Cytokine Genes and a Symptom Cluster of Pain, Fatigue, Sleep Disturbance, and Depression. Cytokine, 58(3):437–447, 2012. doi: 10 . 1016/j . cyto . 2012 . 02 . 015
  34. P. Jaccard. The distribution of the flora in the alpine zone. 1. New phytologist, 11(2):37–50, 1912. doi: 10 . 1111/j . 1469-8137 . 1912 . tb05611 . x
  35. W. Jentner and D. A. Keim. Visualization and Visual Analytic Techniques for Patterns. Springer, 2019. doi: 10 . 1007/978-3-030-04921-8_12
  36. CarePre: An Intelligent Clinical Decision Assistance System. ACM Trans. Comput. Healthcare, 1(1), 2020. doi: 10 . 1145/3344258
  37. Analytical Methods and Issues for Symptom Cluster Research in Oncology. Curr. Opi. in Supp. and Pall. Care, 7(1):45–53, 2013. doi: 10 . 1097/spc . 0b013e32835bf28b
  38. Interactive Visual Analysis of Image-Centric Cohort Study Data. IEEE Trans. Vis. Comp. Graph., 20(12):1673–1682, 2014. doi: 10 . 1109/tvcg . 2014 . 2346591
  39. Interpretable Decision Sets: A Joint Framework for Description and Prediction. In Proc. 22nd ACM SIGKDD Int. Conf. Know. Disc. and Data Min., p. 1675–1684. ACM, New York, NY, USA, 2016. doi: 10 . 1145/2939672 . 2939874
  40. Interpretable Classifiers Using Rules and Bayesian Analysis: Building a Better Stroke Prediction Model. The Annals of App. Stat., 9(3):1350 – 1371, 2015. doi: 10 . 1214/15-AOAS848
  41. Details-first, show context, overview last: supporting exploration of viscous fingers in large-scale ensemble simulations. IEEE Trans. Vis. Comp. Graph., 25(1):1225–1235, 2018.
  42. A spatial neighborhood methodology for computing and analyzing lymph node carcinoma similarity in precision medicine. Jour. of Bio. Info., 112:100067, 2020. doi: 10 . 1016/j . yjbinx . 2020 . 100067
  43. Cohort Comparison of Event Sequences with Balanced Integration of Visual Analytics and Statistics. In Proc. 20th Int. Conf. Intel. UI (IUI), p. 38–49. ACM, 2015. doi: 10 . 1145/2678025 . 2701407
  44. G. E. Marai. Visual Scaffolding in Integrated Spatial and Nonspatial Analysis. In EuroVis Workshop Visual Analytics (EuroVA). The Eurographics Association, 2015.
  45. G. E. Marai. Activity-Centered Domain Characterization for Problem-Driven Scientific Visualization. IEEE Trans. Vis. Comp. Graph., 24(1):913–922, 2018. doi: 10 . 1109/tvcg . 2017 . 2744459
  46. Precision Risk Analysis of Cancer Therapy with Interactive Nomograms and Survival Plots. IEEE Trans. Vis. Comp. Graph., 25(4):1732–1745, 2019. doi: 10 . 1109/tvcg . 2018 . 2817557
  47. Ten simple rules to create biological network figures for communication, 2019.
  48. GRACE: A Visual Comparison Framework for Integrated Spatial and Non-Spatial Geriatric Data. IEEE Trans. Vis. Comp. Graph., 19(12):2916–2925, 2013. doi: 10 . 1109/tvcg . 2013 . 161
  49. Decompositional Rule Extraction From Support Vector Machines by Active Learning. IEEE Trans. Knowl. Data Eng, 21(2):178–191, 2008. doi: 10 . 1109/tkde . 2008 . 131
  50. T. Metsalu and J. Vilo. ClustVis: A Web Tool for Visualizing Clustering of Multivariate Data Using Principal Component Analysis and Heatmap. Nucleic Acids Research, 43(W1):W566–W570, 2015. doi: 10 . 1093/nar/gkv468
  51. GUCCI-Guided Cardiac Cohort Investigation of Blood Flow Data. IEEE Trans. Vis. Comp. Graph., 2021. doi: 10 . 1109/tvcg . 2021 . 3134083
  52. Rulematrix: Visualizing and Understanding Classifiers with Rules. IEEE Trans. Vis. Comp. Graph., 25(1):342–352, 2018. doi: 10 . 1109/tvcg . 2018 . 2864812
  53. Temporal Event Sequence Simplification. IEEE Trans. Vis. Comp. Graph., 19(12):2227–2236, 2013. doi: 10 . 1109/tvcg . 2013 . 200
  54. Multidisciplinary Larynx Cancer Working Group. Conditional Survival Analysis of Patients With Locally Advanced Laryngeal Cancer: Construction of a Dynamic Risk Model and Clinical Nomogram. Sci. Reports, 7(1):43928, 2017.
  55. LTARM: A Novel Temporal Association Rule Mining Method to Understand Toxicities in a Routine Cancer Treatment. Knowledge-Based Systems, 161:313–328, 2018. doi: 10 . 1016/j . knosys . 2018 . 07 . 031
  56. Development and Validation of a Staging System for HPV-Related Oropharyngeal Cancer by the International Collaboration on Oropharyngeal Cancer Network for Staging (ICON-S): a Multicentre Cohort Study. The Lancet Onco., 17(4):440–451, 2016. doi: 10 . 1016/S1470-2045(15)00560-4
  57. G. Peake and J. Wang. Explanation mining: Post hoc interpretability of latent factor models for recommendation systems. In Proc. 24th ACM SIGKDD Int. Conf. on Knowl. Disc. & Data Min., pp. 2060–2069, 2018. doi: 10 . 1145/3219819 . 3220072
  58. LifeLines: Visualizing Personal Histories. In Proc. SIGCHI Conf. Hu. Fact. in Comp. Sys., p. 221–227, 1996. doi: 10 . 1145/257089 . 257391
  59. Visual Analytics for the Exploration of Tumor Tissue Characterization. In Comp. Graph. Forum, vol. 34, pp. 11–20. Wiley Online Library, 2015. doi: 10 . 1111/cgf . 12613
  60. Measuring Head and Neck Cancer Symptom Burden: the Development and Validation of the MD Anderson Symptom Inventory, Head and Neck Module. Head & Neck: J. for the Sci. and Spec. of the Head and Neck, 29(10):923–931, 2007. doi: 10 . 1002/hed . 20602
  61. Multivariate Methods to Identify Cancer-related Symptom Clusters. Res. in Nursing & Health, 32(3):345–360, 2009. doi: 10 . 1002/nur . 20323
  62. Discovering Symptom Patterns of COVID-19 Patients Using Association Rule Mining. Comp. in Bio. and Med., 131:104249, 2021. doi: 10 . 1016/j . compbiomed . 2021 . 104249
  63. Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad. J Med Internet Res, 24(4):e29455, Apr 2022. doi: 10 . 2196/29455
  64. Clustering of largely right-censored oropharyngeal head and neck cancer patients for discriminative groupings to improve outcome prediction. Scientific reports, 10(1):1–14, 2020.
  65. The impact of induction and/or concurrent chemoradiotherapy on acute and late patient-reported symptoms in oropharyngeal cancer: application of a mixed-model analysis of a prospective observational cohort registry. Cancer, 127(14):2453–2464, 2021.
  66. Head and neck cancer predictive risk estimator to determine control and therapeutic outcomes of radiotherapy (HNC-PREDICTOR): development, international multi-institutional validation, and web implementation of clinic-ready model-based risk stratification for head and neck cancer. European Journal of Cancer, 178:150–161, 2023. doi: 10 . 1016/j . ejca . 2022 . 10 . 011
  67. Threadstates: State-based Visual Analysis of Disease Progression. IEEE Trans. Vis. Comp. Graph., 28(1):238–247, 2021. doi: 10 . 31219/osf . io/vcskm
  68. Temporal summaries: Supporting temporal categorical searching, aggregation and comparison. IEEE Trans. Vis. Comp. Graph., 15(6):1049–1056, 2009. doi: 10 . 1109/tvcg . 2009 . 187
  69. Predicting Late Symptoms of Head and Neck Cancer Treatment Using LSTM and Patient Reported Outcomes. In Proc. of the 25th Int. Database Eng. & Apps. Symposium, IDEAS ’21. Assoc. for Comp. Mach., 2021. doi: 10 . 1145/3472163 . 3472177
  70. Mosbie: a tool for comparison and analysis of rule-based biochemical models. BMC Bioinformatics, 15(1):316, Sep 2014. doi: 10 . 1186/1471-2105-15-316
  71. Explainable Spatial Clustering: Leveraging Spatial Data in Radiation Oncology. In IEEE Vis. Comp. Graph., p. 281–285, 2020. doi: 10 . 1109/vis47514 . 2020 . 00063
  72. DASS Good: Explainable Data Mining of Spatial Cohort Data. Comp. Graph. Forum, 2023. doi: 10 . 1111/cgf . 14830
  73. Cohort-based T-SSIM Visual Computing for Radiation Therapy Prediction and Exploration. IEEE Trans. Vis. Comp. Graph., 26(1):949–959, 2020. doi: 10 . 1109/tvcg . 2019 . 2934546
  74. Precision toxicity correlates of tumor spatial proximity to organs at risk in cancer patients receiving intensity-modulated radiotherapy. Radiother. & Onco., 148:245–251, 2020.
  75. Precision association of lymphatic disease spread with radiation-associated toxicity in oropharyngeal squamous carcinomas. Rad. and Onco., 161:152–158, 2021. doi: 10 . 1016/j . radonc . 2021 . 06 . 016
  76. K. Wongsuphasawat and D. Gotz. Outflow: Visualizing Patient Flow by Symptoms and Outcome. In IEEE VisWeek Workshop Vis. Anal. in Health., p. 25–28. American Medical Informatics Association, 2011.
  77. LifeFlow: Visualizing an Overview of Event Sequences. In Proc. SIGCHI Conf. Hu. Fact. in Comp. Sys., p. 1747–1756, 2011. doi: 10 . 1145/1979742 . 1979557
  78. Scalable Bayesian Rule Lists. In Int. Conf. on ML, pp. 3921–3930. PMLR, 2017.
  79. An exploration and validation of visual factors in understanding classification rule sets. In IEEE Trans. Vis. Comp. Graph., pp. 6–10. IEEE, 2021. doi: 10 . 1109/vis49827 . 2021 . 9623303
  80. Evaluating the effect of right-censored end point transformation for radiomic feature selection of data from patients with oropharyngeal cancer. JCO Clin. Cancer Informatics, 2:1–19, 2018.
  81. Iterative cohort analysis and exploration. Info. Vis., 14(4):289–307, 2015. doi: 10 . 1177/1473871614526077
  82. Iforest: Interpreting Random Forests via Visual Analytics. IEEE Trans. Vis. Comp. Graph., 25(1):407–416, 2018. doi: 10 . 1109/tvcg . 2018 . 2864475
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now