Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy

Dean, Jamie; Wong, Kee H.; Welsh, Liam; Jones, Ann-Britt; Schick, Ulricke; Oh, Jung Hun; Apte, Aditya; Newbold, Kate; Bhide, Shreerang A.; Harrington, Kevin; Deasy, Joseph O.; Nutting, Christopher M.; Gulliford, S.

doi:10.1016/j.ctro.2017.11.009

Cited by 34 publications

(32 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, our data represent the first application of ML to assessing emergency evaluation or hospitalization risk in patients undergoing outpatient cancer therapy. Prior ML models in oncology have focused on RT-associated toxicities on the basis of normal tissue doses [37][38][39][40][41][42] or clinical decline of admitted patients with hematologic malignancies. 43 Non-ML models of acute events during cancer therapy have been developed for chemotherapy toxicity.…”

Section: Discussionmentioning

confidence: 99%

Predicting Emergency Visits and Hospital Admissions During Radiation and Chemoradiation: An Internally Validated Pretreatment Machine Learning Algorithm

Hong

Niedzwiecki

Palta

et al. 2018

JCO Clinical Cancer Informatics

View full text Add to dashboard Cite

Purpose Patients undergoing radiotherapy (RT) or chemoradiotherapy (CRT) may require emergency department evaluation or hospitalization. Early identification may direct preventative supportive care, improving outcomes and reducing health care costs. We developed and evaluated a machine learning (ML) approach to predict these events. Methods A total of 8,134 outpatient courses of RT and CRT from a single institution from 2013 to 2016 were identified. Extensive pretreatment data were programmatically extracted and processed from the electronic health record (EHR). Training and internal validation cohorts were randomly generated (3:1 ratio). Gradient tree boosting (GTB), random forest, support vector machine, and least absolute shrinkage and selection operator logistic regression approaches were trained and internally validated based on area under receiver operating characteristic (AUROC) curve. The most predictive ML approach was also evaluated using only disease- and treatment-related factors to assess predictive gain of extensive EHR data. Results All methods had high predictive accuracy, particularly GTB (validation AUROC, 0.798). Extensive EHR data beyond disease and treatment information improved accuracy (delta AUROC, 0.056). A Youden-based cutoff corresponded to validation sensitivity of 81.0% (175 of 216 courses with events) and specificity of 67.3% (1,218 of 1811 courses without events). Interpretability is an important advantage of GTB. Variable importance identified top predictive factors, including treatment (planned RT and systemic therapy), pretreatment encounters (emergency department visits and admissions in the year before treatment), vital signs (weight loss and pain score in the year before treatment), and laboratory values (albumin level at weeks before treatment). Conclusion ML predicts emergency visits and hospitalization during cancer therapy. Incorporating predictions into clinical care algorithms may help direct personalized supportive care, improve quality of care, and reduce costs. A prospective trial investigating ML-assisted direction of increased clinical assessments during RT is planned.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting Emergency Visits and Hospital Admissions During Radiation and Chemoradiation: An Internally Validated Pretreatment Machine Learning Algorithm

Hong

Niedzwiecki

Palta

et al. 2018

JCO Clinical Cancer Informatics

View full text Add to dashboard Cite

show abstract

“…Incorporation of 3D dose information within dose-response models can be performed with 3D moment invariants. This has been used for the parotid glands (xerostomia) 28 , oral mucosa (mucositis) 29,30 and pharyngeal mucosa (dysphagia) 31 . This technique parameterises the centre of mass, skewness and spread of the dose distribution within an organ, which enables toxicities in both parallel and serial structures to be investigated.…”

Section: Discussionmentioning

confidence: 99%

Image-based Data Mining to Probe Dosimetric Correlates of Radiation-induced Trismus

Beasley

Thor

McWilliam

et al. 2018

International Journal of Radiation Oncology*Biology*Physics

View full text Add to dashboard Cite

IBDM bypasses the common assumption that dose patterns within structures are unimportant. Our novel IBDM approach for continuous outcome variables successfully identified a cluster of voxels that are highly associated with trismus, overlapping partially with the ipsilateral masseter. Tests on an external validation cohort showed an even stronger correlation with trismus. These results support use of the region in HNRT treatment planning to potentially reduce trismus.

show abstract

“…Dean et al (22) developed a model to predict severe acute dysphagia in H&N cancer patients treated with RT. Penalized LR (PLR), SVM, and RF models were trained using dosimetric and clinical data and then internally and externally validated on 173 and 90 patients, respectively.…”

Section: Head and Neckmentioning

confidence: 99%

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

et al. 2020

View full text Add to dashboard Cite

In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.

show abstract

Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy

Cited by 34 publications

References 66 publications

Predicting Emergency Visits and Hospital Admissions During Radiation and Chemoradiation: An Internally Validated Pretreatment Machine Learning Algorithm

Predicting Emergency Visits and Hospital Admissions During Radiation and Chemoradiation: An Internally Validated Pretreatment Machine Learning Algorithm

Image-based Data Mining to Probe Dosimetric Correlates of Radiation-induced Trismus

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

Contact Info

Product

Resources

About