Radiomics and predictive models applied to head and neck radiotherapy: an overview of ongoing trials Radiomica e modelli predittivi applicati alla radioterapia dei tumori testa-collo: una overview degli studi ongoing Aims: In radiation oncology practice, comprehensive information on tumor genomic profile and tumor characteristics extractable by imaging can improve treatment planning and clinical response evaluation. Current studies on radiomics and predictive models of radiation-induced side effects (RISE) and/or tumor response will provide more informative results. In this paper we report a short overview of current modeling studies in patients subjected to radiotherapy (RT) for head and neck cancers (HNC) with the main scope to provide a preliminary explorative analysis on these topics. Methods: In April 2019 we performed an advanced search on clinicaltrials.gov website using the following keywords and strategy: “Head and Neck Radiotherapy” AND “Predictive models OR Mathematical models OR Radiomic features”. Studies in the following recruitment status: Suspended, Withdrawn and Unknown Status, as well as trials enrolling pediatric patients, were excluded. Both studies assessing RISE and tumor response have been selected and analyzed. We extracted data regarding study type, patients’ number, recruitment status, model assessment, inclusion criteria, primary and secondary outcome measures. Results: Our search provided 3 studies (Table 1). All trials were recruiting at the time of our search. A total of 2460 patients were expected. No definitive results were available. The NCT03294122 and NCT02489084 studies are assessing models to predict RISE in HNC, regardless of the primary tumor site. In this setting, we observed an emerging interest on the role of the microenvironment (e.g. microbiota, inflammatory markers), as well as on tissue features extracted by radiomic analyses and DNA profiles. Another study (NCT03656133) is specifically assessing tumor response of p16+ or HPV+ squamous cell oropharynx carcinoma by determining whether a mathematical model based on the individual patient “proliferation saturation index” is able to predict rapid tumor response and support the decision of personalized RT fractionation. Conclusion: Comprehensive database of clinical, genetic, biological, imaging, dosimetric data are needed to match the collected information. The management of big data to aid the decision-making in clinical practice requires a multidisciplinary approach and experts’ support. Tolerance and effectiveness of RT for HNC could be improved by using these innovative approaches. Definitive results and further validations of the proposed models are necessary.

Radiomics and predictive models applied to head and neck radiotherapy: an over-view of ongoing trials

R. Carbonara;A. Sardaro
2019-01-01

Abstract

Radiomics and predictive models applied to head and neck radiotherapy: an overview of ongoing trials Radiomica e modelli predittivi applicati alla radioterapia dei tumori testa-collo: una overview degli studi ongoing Aims: In radiation oncology practice, comprehensive information on tumor genomic profile and tumor characteristics extractable by imaging can improve treatment planning and clinical response evaluation. Current studies on radiomics and predictive models of radiation-induced side effects (RISE) and/or tumor response will provide more informative results. In this paper we report a short overview of current modeling studies in patients subjected to radiotherapy (RT) for head and neck cancers (HNC) with the main scope to provide a preliminary explorative analysis on these topics. Methods: In April 2019 we performed an advanced search on clinicaltrials.gov website using the following keywords and strategy: “Head and Neck Radiotherapy” AND “Predictive models OR Mathematical models OR Radiomic features”. Studies in the following recruitment status: Suspended, Withdrawn and Unknown Status, as well as trials enrolling pediatric patients, were excluded. Both studies assessing RISE and tumor response have been selected and analyzed. We extracted data regarding study type, patients’ number, recruitment status, model assessment, inclusion criteria, primary and secondary outcome measures. Results: Our search provided 3 studies (Table 1). All trials were recruiting at the time of our search. A total of 2460 patients were expected. No definitive results were available. The NCT03294122 and NCT02489084 studies are assessing models to predict RISE in HNC, regardless of the primary tumor site. In this setting, we observed an emerging interest on the role of the microenvironment (e.g. microbiota, inflammatory markers), as well as on tissue features extracted by radiomic analyses and DNA profiles. Another study (NCT03656133) is specifically assessing tumor response of p16+ or HPV+ squamous cell oropharynx carcinoma by determining whether a mathematical model based on the individual patient “proliferation saturation index” is able to predict rapid tumor response and support the decision of personalized RT fractionation. Conclusion: Comprehensive database of clinical, genetic, biological, imaging, dosimetric data are needed to match the collected information. The management of big data to aid the decision-making in clinical practice requires a multidisciplinary approach and experts’ support. Tolerance and effectiveness of RT for HNC could be improved by using these innovative approaches. Definitive results and further validations of the proposed models are necessary.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/288109
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact