Determine the therapeutic role of radiotherapy in administrative data: a data mining approach

BMC Medical Research Methodology

Greg Salomons²  Jina Zhang-Salomons¹ 

[1] Department of Public Health Sciences, Queen’s University, Kingston, ON, Canada;Kingston General Hospital, Kingston, ON, Canada

关键词: Decision tree;    Classification;    Data quality;    Missing data;    Administrative data;    Palliation;    Treatment intent;    Role of radiotherapy;   

Others  :  1122938
DOI  :  10.1186/1471-2288-15-11

 received in 2014-06-03, accepted in 2015-01-21,  发布年份 2015

【 摘 要 】

Background

Clinical data gathered for administrative purposes often lack sufficient information to separate the records of radiotherapy given for palliation from those given for cure. An absence, incompleteness, or inaccuracy of such information could hinder or bias the study of the utilization and outcome of radiotherapy. This study has three specific purposes: 1) develop a method to determine the therapeutic role of radiotherapy (TRR); 2) assess the accuracy of the method; 3) report the quality of the information on treatment “intent” recorded in the clinical data in Ontario, Canada. A general purpose is to use this study as a prototype to demonstrate and test a method to assess the quality of administrative data.

Methods

This is a population based retrospective study. A random sample was drawn from the treatment records with “intent” assigned in treating hospitals. A decision tree is grown using treatment parameters as predictors and “intent” as outcome variable to classify the treatments into curative or palliative. The tree classifier was applied to the entire dataset, and the classification results were compared with those identified by “intent”. A manual audit was conducted to assess the accuracy of the classification.

Results

The following parameters predicted the TRR, from the strongest to the weakest: radiation dose per fraction, treated body-region, disease site, and time of treatment. When applied to the records of treatments given between 1990 and 2008 in Ontario, Canada, the classification rules correctly classified 96.1% of the records. The quality of the “intent” variable was as follows: 77.5% correctly classified, 3.7% misclassified, and 18.8% did not have an “intent” assigned.

Conclusions

The classification rules derived in this study can be used to determine the TRR when such information is unavailable, incomplete, or inaccurate in administrative data. The study demonstrates that data mining approach can be used to effectively assess and improve the quality of large administrative datasets.

【 授权许可】

   
2015 Zhang-Salomons and Salomons; licensee BioMed Central.

【 图 表 】

Figure 1.

Figure 2.

【 参考文献 】

• [1]Kirkbride P: The role of radiation therapy in palliative care. J Palliat Care 1995, 11(1):19-26.
• [2]Huang J, Zhou S, Groome P, Tyldesley S, Zhang-Salomons J, Mackillop WJ: Factors affecting the use of palliative radiotherapy in Ontario. J Clin Oncol 2001, 19(1):137-44.
• [3]Johnston GM, Boyd CJ, Joseph P, MacIntyre M: Variation in delivery of palliative radiotherapy to persons dying of cancer in Nova Scotia, 1994 to 1998. J Clin Oncol 2001, 19(14):3323-32.
• [4]Danielson B, Winget M, Gaon Z, Murray B, Pearcey R: Palliative radiotherapy for women with breast cancer. Clin Oncol 2008, 20:506-12.
• [5]Nieder C, Norum J, Spanne O, Gilberg I, Vagstad G, Dalhaug A: Does distance to treatment centre influence the rate of palliative radiotherapy in adult cancer patients? Anticancer Res 2009, 29(7):2641-4.
• [6]Wu JSY, Kerba M, Wong R, Mckimmon E, Eiql B, Hagen NA: Patterns of practice in palliative radiotherapy for painful bone metastases: impact of a regional rapid access clinic on access to care. Int J Radiat Oncol Biol Phys 2010, 78(2):533-8.
• [7]Kong W, Zhang-Salomons J, Hanna T, Mackillop WJ: A population-based study of the fractionation of palliative radiotherapy for bone metastasis in Ontario. Int J Radiat Oncol Biol Phys 2010, 69:1209-17.
• [8]Johnston GM, Gibbons L, Burge FI, Dewar RA, Cummings I, Levy IG: Identifying potential need for cancer palliation in Nova Scotia. CMAJ 1998, 158(13):1691-8.
• [9]Cancer Care Ontario: CCO Data Book Archive. 2010. https://www.cancercare.on.ca/ext/databook/dbarchive/DataBookArchive.htm webcite
• [10]Kass GV: An exploratory technique for investigating large quantities of categorical data. Appl Stat 1980, 29(2):119-27.
• [11]Peabody JW, Luch F, Jain S, Bertenthal D, Glassman P: Assessing the accuracy of administrative data in health information systems. Med Care 2044, 42(11):1066-72.
• [12]Gao J, Johnston GM, Lavergne MR, McIntyre P: Identifying population groups with low palliative care program enrolment using classification and egression tree analysis. J Palliat Care 2011, 27(2):98-106.
• [13]Hall EJ: Radiobiology for the Radiologist. 5th edition. Philadelphia (PA): Lippincott Williams & Wilkins; 2000.
• [14]Ritter M, Forman J, Kupelian P, Lawton C, Petereit D: Hypofractionation for prostate cancer. Cancer J 2009, 15(1):1-6.