Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jun:12721:491-496.
doi: 10.1007/978-3-030-77211-6_58. Epub 2021 Jun 8.

Identifying Symptom Clusters Through Association Rule Mining

Mikayla Biggs  1 , Carla Floricel  2 , Lisanne Van Dijk  3 , Abdallah S R Mohamed  3 , C David Fuller  3 , G Elisabeta Marai  2 , Xinhua Zhang  2 , Guadalupe Canahuate  1
Affiliations

Identifying Symptom Clusters Through Association Rule Mining

Mikayla Biggs et al. Artif Intell Med Conf Artif Intell Med (2005-). 2021 Jun.

Abstract

Cancer patients experience many symptoms throughout their cancer treatment and sometimes suffer from lasting effects post-treatment. Patient-Reported Outcome (PRO) surveys provide a means for monitoring the patient's symptoms during and after treatment. Symptom cluster (SC) research seeks to understand these symptoms and their relationships to define new treatment and disease management methods to improve patient's quality of life. This paper introduces association rule mining (ARM) as a novel alternative for identifying symptom clusters. We compare the results to prior research and find that while some of the SCs are similar, ARM uncovers more nuanced relationships between symptoms such as anchor symptoms that serve as connections between interference and cancer-specific symptoms.

Keywords: Association rule mining; PRO; Symptom clusters.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.. Symptom Severity in the (a) acute and (b) late stages.
Acute: > half of patients experience low severity symptoms, while a sizable 20% experience severe symptoms. Late: patients experience mostly low rated symptoms with highest prevalence in fatigue, drymouth, swallow, and taste.
Fig. 2.
Fig. 2.. Symptoms Association Rule Graph.
The graph encoding shows the top 20 association rules for (a) acute and (b) late symptoms. In the acute state there is a large cluster of severe symptoms. In the late stage, drowsy and fatigue appear to be anchor symptoms connecting a cluster of interference symptoms with a cluster of cancer symptoms.
See this image and copyright information in PMC

References

    1. Christopherson KM, et al.for the MD Anderson Head and Neck Cancer Symptom Working Group; Spatial-Non-spatial Multi-Dimensional Analysis of Radiotherapy Treatment/Toxicity Team (SMART3). Chronic radiation-associated dysphagia in oropharyngeal cancer survivors: Towards age-adjusted dose constraints for deglutitive muscles. Clin Transl Radiat Oncol 2019June15;18:16–22. doi: 10.1016/j.ctro.2019.06.005. - DOI - PMC - PubMed
    1. Wentzel A, Hanula P, van Dijk LV, Elgohari B, Mohamed ASR, Cardenas CE, Fuller CD, Vock DM, Canahuate G, Marai GE. Precision toxicity correlates of tumor spatial proximity to organs at risk in cancer patients receiving intensity-modulated radiotherapy. Radiother Oncol 2020July;148245–251. doi: 10.1016/j.radonc.2020.05.023. Epub 2020 May 16. - DOI - PMC - PubMed
    1. Wentzel A, Hanula P, Luciani T, Elgohari B, Elhalawani H, Canahuate G, Vock D, Fuller CD, Marai GE. Cohort-based T-SSIM Visual Computing for Radiation Therapy Prediction and Exploration. IEEE Trans Vis Comput Graph 2020January;26(1):949–959. doi: 10.1109/TVCG.2019.2934546. Epub 2019 Aug 22. - DOI - PMC - PubMed
    1. Marai GE, Ma C, Burks AT, Pellolio F, Canahuate G, Vock DM, Mohamed ASR, Fuller CD. Precision Risk Analysis of Cancer Therapy with Interactive Nomograms and Survival Plots. IEEE Trans Vis Comput Graph 2019April;25(4):1732–1745. doi: 10.1109/TVCG.2018.2817557. Epub 2018 Mar 20. - DOI - PMC - PubMed
    1. 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 Rep 2017March9;7:43928. doi: 10.1038/srep43928. - DOI - PMC - PubMed

LinkOut - more resources