Development and Optimization of a Machine-Learning Prediction Model for Acute Desquamation After Breast Radiation Therapy in the Multicenter REQUITE Cohort

Aldraimli, Mahmoud; Osman, Sarah; Grishchuck, Diana; Ingram, Samuel; Lyon, Robert; Mistry, A; Oliveira, Jorge; Samuel, Robert; Shelley, Leila E.A.; Soria, Daniele; Dwek, Miriam; Aguado-Barrera, Miguel E.; Azria, D.; Chang‐Claude, Jenny; Dunning, Alison M.; Giraldo, Alexandra; Green, Sheryl; Gutiérrez-Enríquez, S.; Herskind, Carsten; Hulle, Hans Van; Lambrecht, Maarten; Lozza, Laura; Rancati, T.; Reyes, Victoria; Rosenstein, Barry S.; Ruysscher, Dirk De; Santis, Maria Carmen De; Seibold, Petra; Sperk, E.; Symonds, R. Paul; Stobart, Hilary; Taboada-Valadares, Begoña; Talbot, Christopher J.; Vakaet, Vincent; Vega, Ana; Veldeman, Liv; Veldwijk, Marlon R.; Webb, Adam; Weltens, Caroline; West, Catharine; Chaussalet, Thierry J.; Rattay, Tim

doi:10.1016/j.adro.2021.100890

Cited by 9 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, previous investigations have revealed limited performance of statistical and radiobiological based models, i.e., normal tissue complication probability (NTCP) models, in predicting individual patients' skin toxicity [ 13 , 14 ]. Nevertheless, by extracting spatial information from dose distribution using dosiomics, i.e., a texture analysis (TA) approach, prediction capability can be significantly improved [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

“…Recent studies have highlighted the effectiveness of machine learning (ML) to construct predictive models for skin toxicities by incorporating patient and treatment-related features either individually [ 13 ], or in combination with quantitative thermal imaging biomarkers (i.e., thermoradiomics) [ 18 ], spectrophotometric markers [ 19 ], and planning CT image [ 20 ]. Nonetheless, the utilization of additional imaging devices in these studies has some limitations, including high implementation and maintenance costs, which indirectly affect patient expenses.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Saadatmand,

Mahdavi,

Nikoofar

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

Background Radiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals. Methods Dosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 − (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 − and AST 2 + groups and cutoff value calculations. Results Results showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71–0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models. Conclusions This study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Saadatmand,

Mahdavi,

Nikoofar

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

show abstract

“…The thermal markers at the fifth treatment fraction were found predictive of acute skin toxicity with a prediction accuracy of 0.87. Recently, Aldraimli et al (14) developed several clinical prediction models for acute breast desquamation after whole breast external beam radiation therapy in the prospective multicenter REQUITE cohort study. After optimization, the random forest algorithm was found the best model, able to classify patients with acceptable performance in the validation cohort (AUC = 0.77).…”

Section: Introductionmentioning

confidence: 99%

Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry

et al. 2023

View full text Add to dashboard Cite

PurposeRadiation-induced skin toxicity is a common and distressing side effect of breast radiation therapy (RT). We investigated the use of quantitative spectrophotometric markers as input parameters in supervised machine learning models to develop a predictive model for acute radiation toxicity.Methods and materialsOne hundred twenty-nine patients treated for adjuvant whole-breast radiotherapy were evaluated. Two spectrophotometer variables, i.e. the melanin (IM) and erythema (IE) indices, were used to quantitatively assess the skin physical changes. Measurements were performed at 4-time intervals: before RT, at the end of RT and 1 and 6 months after the end of RT. Together with clinical covariates, melanin and erythema indices were correlated with skin toxicity, evaluated using the Radiation Therapy Oncology Group (RTOG) guidelines. Binary group classes were labeled according to a RTOG cut-off score of ≥ 2. The patient’s dataset was randomly split into a training and testing set used for model development/validation and testing (75%/25% split). A 5-times repeated holdout cross-validation was performed. Three supervised machine learning models, including support vector machine (SVM), classification and regression tree analysis (CART) and logistic regression (LR), were employed for modeling and skin toxicity prediction purposes.ResultsThirty-four (26.4%) patients presented with adverse skin effects (RTOG ≥2) at the end of treatment. The two spectrophotometric variables at the beginning of RT (IM,T0 and IE,T0), together with the volumes of breast (PTV2) and boost surgical cavity (PTV1), the body mass index (BMI) and the dose fractionation scheme (FRAC) were found significantly associated with the RTOG score groups (p<0.05) in univariate analysis. The diagnostic performances measured by the area-under-curve (AUC) were 0.816, 0.734, 0.714, 0.691 and 0.664 for IM, IE, PTV2, PTV1 and BMI, respectively. Classification performances reported precision, recall and F1-values greater than 0.8 for all models. The SVM classifier using the RBF kernel had the best performance, with accuracy, precision, recall and F-score equal to 89.8%, 88.7%, 98.6% and 93.3%, respectively. CART analysis classified patients with IM,T0 ≥ 99 to be associated with RTOG ≥ 2 toxicity; subsequently, PTV1 and PTV2 played a significant role in increasing the classification rate. The CART model provided a very high diagnostic performance of AUC=0.959.ConclusionsSpectrophotometry is an objective and reliable tool able to assess radiation induced skin tissue injury. Using a machine learning approach, we were able to predict grade RTOG ≥2 skin toxicity in patients undergoing breast RT. This approach may prove useful for treatment management aiming to improve patient quality of life.

show abstract

“…[12][13][14][15] In addition to various investigations in imaging applications, the ML technique has been of interest to medical physicists for the prediction of radiation treatment side effects or patients who would benefit from adaptive radiotherapy. [16][17][18] However, the lack of sufficiently sizeable datasets for data mining restricts the application of ML techniques. If publicly open, such data resources would also enable research by scientists without access to particular experimental equipment.…”

Section: Introductionmentioning

confidence: 99%

“…Other possible applications for ML include the prediction of electron inelastic mean free paths, band gaps in semiconductors, stopping power predictions, and machine learning on neutron and x‐ray scattering and spectroscopies 12–15 . In addition to various investigations in imaging applications, the ML technique has been of interest to medical physicists for the prediction of radiation treatment side effects or patients who would benefit from adaptive radiotherapy 16–18 . However, the lack of sufficiently sizeable datasets for data mining restricts the application of ML techniques.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive open‐access database of electron backscattering coefficients for energies ranging from 0.1 keV to 15 MeV

Akbari

2023

Medical Physics

View full text Add to dashboard Cite

PurposeThe characterization of electron backscattering is essential in medical physics for accurately assessing dose deposited around inhomogeneities where backscattering alters the spatial energy distribution pattern and for determining Monte‐Carlo code's ability to effectively describe electron scattering and does calculation in a target volume. Recent machine learning advances have provided physicists with powerful tools for effectively extracting information and trends from extensive experiment observations if sufficiently sizeable datasets are available for data mining. We report on the development of a publicly accessible database on electron backscattering coefficients for solid targets.Acquisition and validation methodsThe first database on electron‐solid interactions was assembled in 1995. Data for bulk materials, limited to normal incidence and energies up to 100 keV, were primarily focusing on electron microscopy. To accommodate broad high‐energy applications and include the most recent publications we have created a comprehensive database of electron backscattering coefficients, listed as a function of target atomic number and thickness, electron energy, and incidence angle. These additions resulted in a database of 3566 data points, compared to the previous database of 1430. The data collection includes only published experimental observations (no calculations or results fitting) with no attempt to judge their accuracy or quality. A limited number of data points were compared to recently published Monte‐Carlo results.Data format and usage notesThe presented database provides values of electron backscattering coefficients for 50 elements and 19 compounds at electron energies ranging from 0.1 keV to 15 MeV, presented in ASCII files. Each file contains the electron energy and backscattering coefficient with target thickness or electron incidence angle included where available, and the reference number shown in the last column. Additionally, the presented data were shown in the graphs for better visualization. The online database can be accessed from the website https://doi.org/10.5281/zenodo.7810951.Potential applicationsThe database provides the most up‐to‐date source of experimentally obtained electron backscattering coefficients that can be used in theoretical and MC calculations and modeling validations. The data availability is still very limited for many solids and almost non‐existent for compounds. Novel machine learning methods should be well adapted to predict these unknown values for various targets, thicknesses, energies, and incident angles utilizing the presented cleaned dataset.

show abstract

Development and Optimization of a Machine-Learning Prediction Model for Acute Desquamation After Breast Radiation Therapy in the Multicenter REQUITE Cohort

Abstract: REQUITE consortium, Development and optimisation of a machine-learning prediction model for acute desquamation following breast radiotherapy in the multi-centre REQUITE cohort, Advances in Radiation Oncology (2022), doi:

Cited by 9 publications

References 37 publications

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry

A comprehensive open‐access database of electron backscattering coefficients for energies ranging from 0.1 keV to 15 MeV

Contact Info

Product

Resources

About