Background: The decision to administer palliative radiotherapy (RT) to patients with bone metastases (BMs), as well as the selection of treatment protocols (dose, fractionation), requires an accurate assessment of survival expectancy. In this study, we aimed to develop three predictive models (PMs) to estimate short-, intermediate-, and long-term overall survival (OS) for patients in this clinical setting. Materials and Methods: This study constitutes a sub-analysis of the PRAIS trial, a longitudinal observational study collecting data from patients referred to participating centers to receive palliative RT for cancer-induced bone pain. Our analysis encompassed 567 patients from the PRAIS trial database. The primary objectives were to ascertain the correlation between clinical and laboratory parameters with the OS rates at three distinct time points (short: 3 weeks; intermediate: 24 weeks; prolonged: 52 weeks) and to construct PMs for prognosis. We employed machine learning techniques, comprising the following steps: (i) identification of reliable prognostic variables and training; (ii) validation and testing of the model using the selected variables. The selection of variables was accomplished using the LASSO method (Least Absolute Shrinkage and Selection Operator). The model performance was assessed using receiver operator characteristic curves (ROC) and the area under the curve (AUC). Results: Our analysis demonstrated a significant impact of clinical parameters (primary tumor site, presence of non-bone metastases, steroids and opioid intake, food intake, and body mass index) and laboratory parameters (interleukin 8 [IL-8], chloride levels, C-reactive protein, white blood cell count, and lymphocyte count) on OS. Notably, different factors were associated with the different times for OS with only IL-8 included both in the PMs for short- and long-term OS. The AUC values for ROC curves for 3-week, 24-week, and 52-week OS were 0.901, 0.767, and 0.806, respectively. Conclusions: We successfully developed three PMs for OS based on easily accessible clinical and laboratory parameters for patients referred to palliative RT for painful BMs. While our findings are promising, it is important to recognize that this was an exploratory trial. The implementation of these tools into clinical practice warrants further investigation and confirmation through subsequent studies with separate databases.

Rossi, R., Medici, F., Habberstad, R., Klepstad, P., Cilla, S., Dall'Agata, M., et al. (2024). Development of a predictive model for patients with bone metastases referred to palliative radiotherapy: Secondary analysis of a multicenter study (the PRAIS trial). CANCER MEDICINE, 13(19), 1-12 [10.1002/cam4.70050].

Development of a predictive model for patients with bone metastases referred to palliative radiotherapy: Secondary analysis of a multicenter study (the PRAIS trial)

Rossi, Romina;Medici, Federica
;
Morganti, Alessio Giuseppe;Maltoni, Marco
2024

Abstract

Background: The decision to administer palliative radiotherapy (RT) to patients with bone metastases (BMs), as well as the selection of treatment protocols (dose, fractionation), requires an accurate assessment of survival expectancy. In this study, we aimed to develop three predictive models (PMs) to estimate short-, intermediate-, and long-term overall survival (OS) for patients in this clinical setting. Materials and Methods: This study constitutes a sub-analysis of the PRAIS trial, a longitudinal observational study collecting data from patients referred to participating centers to receive palliative RT for cancer-induced bone pain. Our analysis encompassed 567 patients from the PRAIS trial database. The primary objectives were to ascertain the correlation between clinical and laboratory parameters with the OS rates at three distinct time points (short: 3 weeks; intermediate: 24 weeks; prolonged: 52 weeks) and to construct PMs for prognosis. We employed machine learning techniques, comprising the following steps: (i) identification of reliable prognostic variables and training; (ii) validation and testing of the model using the selected variables. The selection of variables was accomplished using the LASSO method (Least Absolute Shrinkage and Selection Operator). The model performance was assessed using receiver operator characteristic curves (ROC) and the area under the curve (AUC). Results: Our analysis demonstrated a significant impact of clinical parameters (primary tumor site, presence of non-bone metastases, steroids and opioid intake, food intake, and body mass index) and laboratory parameters (interleukin 8 [IL-8], chloride levels, C-reactive protein, white blood cell count, and lymphocyte count) on OS. Notably, different factors were associated with the different times for OS with only IL-8 included both in the PMs for short- and long-term OS. The AUC values for ROC curves for 3-week, 24-week, and 52-week OS were 0.901, 0.767, and 0.806, respectively. Conclusions: We successfully developed three PMs for OS based on easily accessible clinical and laboratory parameters for patients referred to palliative RT for painful BMs. While our findings are promising, it is important to recognize that this was an exploratory trial. The implementation of these tools into clinical practice warrants further investigation and confirmation through subsequent studies with separate databases.
2024
Rossi, R., Medici, F., Habberstad, R., Klepstad, P., Cilla, S., Dall'Agata, M., et al. (2024). Development of a predictive model for patients with bone metastases referred to palliative radiotherapy: Secondary analysis of a multicenter study (the PRAIS trial). CANCER MEDICINE, 13(19), 1-12 [10.1002/cam4.70050].
Rossi, Romina; Medici, Federica; Habberstad, Ragnhild; Klepstad, Pal; Cilla, Savino; Dall'Agata, Monia; Kaasa, Stein; Caraceni, Augusto Tommaso; Morga...espandi
File in questo prodotto:
File Dimensione Formato  
CAM4-13-e70050.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 1.27 MB
Formato Adobe PDF
1.27 MB Adobe PDF Visualizza/Apri
CAM4-13-e70050-s001.docx

accesso aperto

Tipo: File Supplementare
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 14.68 kB
Formato Microsoft Word XML
14.68 kB Microsoft Word XML Visualizza/Apri

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/11585/998528
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact