Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry
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.Met...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.1044358/full |
| _version_ | 1797959727962914816 |
|---|---|
| author | Savino Cilla Carmela Romano Gabriella Macchia Mariangela Boccardi Donato Pezzulla Milly Buwenge Augusto Di Castelnuovo Francesca Bracone Amalia De Curtis Chiara Cerletti Licia Iacoviello Licia Iacoviello Maria Benedetta Donati Francesco Deodato Francesco Deodato Alessio Giuseppe Morganti Alessio Giuseppe Morganti |
| author_facet | Savino Cilla Carmela Romano Gabriella Macchia Mariangela Boccardi Donato Pezzulla Milly Buwenge Augusto Di Castelnuovo Francesca Bracone Amalia De Curtis Chiara Cerletti Licia Iacoviello Licia Iacoviello Maria Benedetta Donati Francesco Deodato Francesco Deodato Alessio Giuseppe Morganti Alessio Giuseppe Morganti |
| author_sort | Savino Cilla |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T00:35:49Z |
| format | Article |
| id | doaj.art-5031313034da4f60ad2ab7c4306000e0 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-11T00:35:49Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-5031313034da4f60ad2ab7c4306000e02023-01-06T17:58:48ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-01-011210.3389/fonc.2022.10443581044358Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometrySavino Cilla0Carmela Romano1Gabriella Macchia2Mariangela Boccardi3Donato Pezzulla4Milly Buwenge5Augusto Di Castelnuovo6Francesca Bracone7Amalia De Curtis8Chiara Cerletti9Licia Iacoviello10Licia Iacoviello11Maria Benedetta Donati12Francesco Deodato13Francesco Deodato14Alessio Giuseppe Morganti15Alessio Giuseppe Morganti16Medical Physics Unit, Gemelli Molise Hospital, Campobasso, ItalyMedical Physics Unit, Gemelli Molise Hospital, Campobasso, ItalyRadiation Oncology Unit, Gemelli Molise Hospital, Campobasso, ItalyRadiation Oncology Unit, Gemelli Molise Hospital, Campobasso, ItalyRadiation Oncology Unit, Gemelli Molise Hospital, Campobasso, ItalyRadiation Oncology, Istituti di Ricovero e Cura a Carattere Scientifico (IRCCS) Azienda Ospedaliero-Universitaria di Bologna, Bologna, ItalyMediterranea Cardiocentro, Napoli, ItalyDepartment of Epidemiology and Prevention, IRCCS Neuromed, Pozzilli, ItalyDepartment of Epidemiology and Prevention, IRCCS Neuromed, Pozzilli, ItalyDepartment of Epidemiology and Prevention, IRCCS Neuromed, Pozzilli, ItalyDepartment of Epidemiology and Prevention, IRCCS Neuromed, Pozzilli, ItalyDepartment of Medicine and Surgery, Research Center in Epidemiology and Preventive Medicine (EPIMED), University of Insubria, Varese, ItalyDepartment of Epidemiology and Prevention, IRCCS Neuromed, Pozzilli, ItalyRadiation Oncology Unit, Gemelli Molise Hospital, Campobasso, ItalyIstituto di Radiologia, Universitá Cattolica del Sacro Cuore, Rome, ItalyRadiation Oncology, Istituti di Ricovero e Cura a Carattere Scientifico (IRCCS) Azienda Ospedaliero-Universitaria di Bologna, Bologna, ItalyDepartment of Experimental, Diagnostic, and Specialty Medicine - DIMES, Alma Mater Studiorum Bologna University, Bologna, ItalyPurposeRadiation-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.https://www.frontiersin.org/articles/10.3389/fonc.2022.1044358/fullmachine learningradiation oncologybreasttoxicityspectrophotometry |
| spellingShingle | Savino Cilla Carmela Romano Gabriella Macchia Mariangela Boccardi Donato Pezzulla Milly Buwenge Augusto Di Castelnuovo Francesca Bracone Amalia De Curtis Chiara Cerletti Licia Iacoviello Licia Iacoviello Maria Benedetta Donati Francesco Deodato Francesco Deodato Alessio Giuseppe Morganti Alessio Giuseppe Morganti Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry Frontiers in Oncology machine learning radiation oncology breast toxicity spectrophotometry |
| title | Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| title_full | Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| title_fullStr | Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| title_full_unstemmed | Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| title_short | Machine-learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| title_sort | machine learning prediction model for acute skin toxicity after breast radiation therapy using spectrophotometry |
| topic | machine learning radiation oncology breast toxicity spectrophotometry |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.1044358/full |
| work_keys_str_mv | AT savinocilla machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT carmelaromano machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT gabriellamacchia machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT mariangelaboccardi machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT donatopezzulla machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT millybuwenge machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT augustodicastelnuovo machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT francescabracone machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT amaliadecurtis machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT chiaracerletti machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT liciaiacoviello machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT liciaiacoviello machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT mariabenedettadonati machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT francescodeodato machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT francescodeodato machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT alessiogiuseppemorganti machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry AT alessiogiuseppemorganti machinelearningpredictionmodelforacuteskintoxicityafterbreastradiationtherapyusingspectrophotometry |