Purpose
Clinical data collection and development of outcome prediction models by machine learning
can form the foundation for a learning health system offering precision radiation
therapy. However, changes in clinical practice over time can affect the measures and
patient outcomes and, hence, the collected data. We hypothesize that regular prediction
model updates and continuous prospective data collection are important to prevent
the degradation of a model's predication accuracy.
Methods and Materials
Clinical and dosimetric data from head and neck patients receiving intensity modulated
radiation therapy from 2008 to 2015 were prospectively collected as a routine clinical
workflow and anonymized for this analysis. Prediction models for grade ≥2 xerostomia
at 3 to 6 months of follow-up were developed by bivariate logistic regression using
the dose-volume histogram of parotid and submandibular glands. A baseline prediction
model was developed with a training data set from 2008 to 2009. The selected predictor
variables and coefficients were updated by 4 different model updating methods. (A)
The prediction model was updated by using only recent 2-year data and applied to patients
in the following test year. (B) The model was updated by increasing the training data
set yearly. (C) The model was updated by increasing the training data set on the condition
that the area under the curve (AUC) of the recent test year was less than 0.6. (D)
The model was not updated. The AUC of the test data set was compared among the 4 model
updating methods.
Results
Dose to parotid and submandibular glands and grade of xerostomia showed decreasing
trends over the years (2008-2015, 297 patients; P < .001). The AUC of predicting grade ≥2 xerostomia for the initial training data
set (2008-2009, 41 patients) was 0.6196. The AUC for the test data set (2010-2015,
256 patients) decreased to 0.5284 when the initial model was not updated (D). However,
the AUC was significantly improved by model updates (A: 0.6164; B: 0.6084; P < .05). When the model was conditionally updated, the AUC was 0.6072 (C).
Conclusions
Our preliminary results demonstrate that updating prediction models with prospective
data collection is effective for maintaining the performance of xerostomia prediction.
This suggests that a machine learning framework can handle the dynamic changes in
a radiation oncology clinical practice and may be an important component for the construction
of a learning health system.
To read this article in full you will need to make a payment
ASTRO Member Login
ASTRO Members, full access to the journal is a member benefit. Use your society credentials to access all journal content and features.
One-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Purchase one-time access:
Already a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- The Learning Health Care System: Workshop Summary.Washington DC. National Academies Press, 2007
- The science of learning health systems: Foundations for a new journal.Learning Health Systems. 2017; 1: e10020
- Rapid-learning system for cancer care.J Clin Oncol. 2010; 28: 4268-4274
- Needs and challenges for big data in radiation oncology.Int J Radiat Oncol Biol Phys. 2016; 95: 909-915
- Using Big Data Analytics to Advance Precision Radiation Oncology.Int J Radiat Oncol Biol Phys. 2018; 101: 285-291
- ‘Rapid Learning health care in oncology’ - An approach toward decision support systems enabling customised radiotherapy.Radiother Oncol. 2013; 109: 159-164
- Big data in radiation therapy: Challenges and opportunities.Br J Radiol. 2017; 90 (20160689)
- Machine learning applications in cancer prognosis and prediction.Comput Struct Biotechnol J. 2014; 13: 8-17
- A framework for effective management of change in clinical practice: Dissemination and implementation of clinical practice guidelines.Qual Health Care. 1999; 8: 177-183
- Parotid-sparing intensity modulated versus conventional radiotherapy in head and neck cancer (PARSPORT): A phase 3 multicentre randomised controlled trial.Lancet Oncol. 2011; 12: 127-136
- Xerostomia: An update for clinicians.Aust Dent J. 2010; 55: 238-244
- Xerostomia and salivary hypofunction in vulnerable elders: Prevalence and etiology.Oral Surg Oral Med Oral Pathol Oral Radiol. 2012; 114: 52-60
- Subjective reports of oral dryness in an older adult population.Community Dent Oral Epidemiol. 1993; 21: 165-168
- Issues in the epidemiological investigation of dry mouth.Gerodontology. 2005; 22: 65-76
- The impact of dose on parotid salivary recovery in head and neck cancer patients treated with radiation therapy.Int J Radiat Oncol Biol Phys. 2007; 67: 660-669
- A data-mining framework for large scale analysis of dose-outcome relationships in a database of irradiated head and neck cancer patients.Med Phys. 2015; 42: 4329-4337
- Radiomic analysis of salivary glands and its role for predicting xerostomia in irradiated head and neck cancer patients.Int J Radiat Oncol Biol Phys. 2016; 96: S217
- A risk prediction model for head and neck radiation toxicities: Novel insights to reduce the risk of head and neck radiation-induced xerostomia.Int J Radiat Oncol Biol Phys. 2016; 96: E686
- OncoSpace: A new paradigm for clinical research and decision support in radiation oncology.in: Proc XVIth Int Conf on the Use of Computers in Radiotherapy, Amsterdam. 2010
- Oncospace consortium: A shared radiation oncology database system designed for personalized medicine and research.Int J Radiat Oncol Biol Phys. 2015; 93: E385
- Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiotherapy.Advances in Radiation Oncology. 2017; 3: 346-355
- Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): Explanation and elaboration.Ann Intern Med. 2015; 162: W1-W73
- Assessing the performance of prediction models: A framework for some traditional and novel measures.Epidemiology. 2010; 21: 128-138
- Online learning and online convex optimization. Foundations and Trends in Machine Learning.4. Now Publishers Inc, Hanover, MA2012: 107-194
Article Info
Publication History
Published online: October 06, 2018
Accepted:
October 6,
2018
Received:
August 11,
2018
Footnotes
Conflict of interest: Funding for this research was provided by Canon Medical Systems Corporation .
Identification
Copyright
© 2018 Elsevier Inc. All rights reserved.
