Search

PURPOSE: The estimation of prognosis and life expectancy is critical in the care of patients with advanced cancer. To aid clinical decision making, we build a prognostic strategy combining a machine learning (ML) model with explainable artificial intelligence to predict 1-year survival after palliative radiotherapy (RT) for bone metastasis. MATERIALS AND METHODS: Data collected in the multicentric PRAIS trial were extracted for 574 eligible adults diagnosed with metastatic cancer. The primary end point was the overall survival (OS) at 1 year (1-year OS) after the start of RT. Candidate covariate predictors consisted of 13 clinical and tumor-related pre-RT patient characteristics, seven dosimetric and treatment-related variables, and 45 pre-RT laboratory variables. ML models were developed and internally validated using the Python package. The effectiveness of each model was evaluated in terms of discrimination. A Shapley Additive Explanations (SHAP) explainability analysis to infer the global and local feature importance and to understand the reasons for correct and misclassified predictions was performed. RESULTS: The best-performing model for the classification of 1-year OS was the extreme gradient boosting algorithm, with AUC and F1-score values equal to 0.805 and 0.802, respectively. The SHAP technique revealed that higher chance of 1-year survival is associated with low values of interleukin-8, higher values of hemoglobin and lymphocyte count, and the nonuse of steroids. CONCLUSION: An explainable ML approach can provide a reliable prediction of 1-year survival after RT in patients with advanced cancer. The implementation of SHAP analysis provides an intelligible explanation of individualized risk prediction, enabling oncologists to identify the best strategy for patient stratification and treatment selection. The estimation of prognosis and life expectancy is critical in the care of patients with advanced cancer. To aid clinical decision making, we build a prognostic strategy combining a machine learning model with explainable artificial intelligence to predict one-year survival after palliative radiotherapy (RT) for bone metastasis. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer patients frequently experience pain, impacting their quality of life. Unfortunately, pain management in those referred for radiotherapy (RT) is often insufficient, with limited research in this area. This study aimed to assess the adequacy and effectiveness of pain management and identify factors affecting them in cancer patients referred for RT. We observed 1042 cancer outpatients and found that 42.9% did not receive adequate pain management. Specifically, 72% of patients referred for palliative RT and 75% of those referred for curative RT experienced inadequate or ineffective analgesic therapy. Patients undergoing palliative RT, those with poorer general health, those with cancer-related pain, and those treated in Northern Italy had higher odds of receiving adequate pain management. Our findings highlight the need for educational and organizational strategies to address this issue and suggest that early palliative RT referral can improve pain management and treatment outcomes for cancer patients. Background: Pain is a prevalent symptom among cancer patients, and its management is crucial for improving their quality of life. However, pain management in cancer patients referred to radiotherapy (RT) departments is often inadequate, and limited research has been conducted on this specific population. This study aimed to assess the adequacy and effectiveness of pain management when patients are referred for RT. Moreover, we explored potential predictors of adequate pain management. Methods: This observational, prospective, multicenter cohort study included cancer patients aged 18 years or older who were referred to RT departments. A pain management assessment was conducted using the Pain Management Index (PMI), calculated by subtracting the pain score from the analgesic score (PMI < 0 indicated inadequate pain management). Univariate and multivariate analyses were performed to identify predictors of adequate pain management. Results: A total of 1042 cancer outpatients were included in the study. The analysis revealed that 42.9% of patients with pain did not receive adequate pain management based on PMI values. Among patients with pain or taking analgesics and referred to palliative or curative RT, 72% and 75% had inadequate or ineffective analgesic therapy, respectively. The odds of receiving adequate pain management (PMI ≥ 0) were higher in patients undergoing palliative RT (OR 2.52; p < 0.001), with worse ECOG-PS scores of 2, 3 and 4 (OR 1.63, 2.23, 5.31, respectively; p: 0.017, 0.002, 0.009, respectively) compared to a score of 1 for those with cancer-related pain (OR 0.38; p < 0.001), and treated in northern Italy compared to central and southern of Italy (OR 0.25, 0.42, respectively; p < 0.001). Conclusions: In this study, a substantial proportion of cancer patients referred to RT departments did not receive adequate pain management. Educational and organizational strategies are necessary to address the inadequate pain management observed in this population. Moreover, increasing the attention paid to non-cancer pain and an earlier referral of patients for palliative RT in the course of the disease may improve pain response and treatment outcomes. [ABSTRACT FROM AUTHOR]

Oligometastatic breast cancer patients can today could benefit from a multimodal approach, combining systemic therapy with metastasis-directed treatment using stereotactic body radiotherapy (SBRT). However, the possibility to synchronously treat multiple lesions is still challenging, needing the ability to generate complex dose distributions with steep dose gradients outside the lesions and major sparing of surrounding organs at risk and accurately track and reproduce the patient's position before and during radiation therapy. We report the case of an oligometastatic patient from left breast cancer, which occurred after a full course of whole breast radiotherapy, treated using the potential of modern technology including single-isocenter setup, plan automation, breath-hold technique and surface guided tracking and reproducibility of patient's position before and during radiation therapy. A 44-year-old female patient with a history of left breast cancer, specifically a luminal-B-like invasive ductal carcinoma with Her2 overexpression, was admitted to our department. The patient previously underwent a left mastectomy (pT2N0M0), 4 cycles of adjuvant chemotherapy, adjuvant radiotherapy on the chest wall and lymph nodes drainage, and 5 years of hormonal therapy. A chest wall ultrasound and positron emission tomography revealed the presence of new lesions in the area of the surgical scar from the previous mastectomy, internal mammary, axillary and retropectoral levels. The 3 lesions were simultaneously treated with a mono-isocentric VMAT plan using SBRT technique with a total dose of 30 Gy delivered in 5 fractions. Due to the technical challenges, this treatment was supported by the use of planning automation, breath-hold technique and surface-guided radiation therapy to improve the accuracy of the dose delivery. Two different plans were generated and compared to pursue the best dosimetric result, including a summed plan obtained from 3 individual SBRT plans for each lesion with a separate isocenter placed in each of them (MIP), and a single-isocenter SBRT plan able to treat multiple lesions synchronously (SIP). Because of the advantages in terms of dosimetry and dose delivery efficiency, the patient was successfully treated with the SIP plan. The treatment time was reduced to about 4.5 minutes, allowing the comfortably use of breath-hold technique. After treatment, the condition of the patient was normal, and no toxicities have been observed in follow-up. SBRT with mono isocentric VMAT planning represents the recommended approach to simultaneously treat multiple lesions in close proximity in the thoracic district., Competing Interests: Conflict of interest statement The authors declare no conflict of interest., (Copyright © 2024 American Association of Medical Dosimetrists. Published by Elsevier Inc. All rights reserved.)

Purpose: Bone metastases frequently occur during malignant disease. Palliative radiation therapy (PRT) is a crucial part of palliative care because it can relieve pain and improve patients' quality of life. Often, a clinician's survival estimation is too optimistic. Prognostic scores (PSs) can help clinicians tailor PRT indications to avoid over- or undertreatment. Although the PS is supposed to aid radiation oncologists (ROs) in palliative-care scenarios, it is unclear what type of support, and to what extent, could impact daily clinical practice., Methods and Materials: A national-based investigation of the prescriptive decisions on simulated clinical cases was performed in Italy. Nine clinical cases from real-world clinical practice were selected for this study. Each case description contained complete information regarding the parameters defining the prognosis class according to the PS (in particular, the Mizumoto Prognostic Score, a validated PS available in literature and already applied in some clinical trials). Each case description contained complete information regarding the parameters defining the prognosis class according to the PS. ROs were interviewed through questionnaires, each comprising the same 3 questions per clinical case, asking (1) the prescription after detailing the clinical case features but not the PS prognostic class definition; (2) whether the RO wanted to change the prescription once the PS prognostic class definition was revealed; and (3) in case of a change of the prescription, a new prescriptive option. Three RO categories were defined: dedicated to PRT (RO-d), nondedicated to PRT (RO-nd), and resident in training (IT). Interviewed ROs were distributed among different regions of the country., Results: Conversion rates, agreements, and prescription trends were investigated. The PS determined a statistically significant 11.12% of prescription conversion among ROs. The conversion was higher for the residents and significantly higher for worse prognostic scenario subgroups, respectively. The PS improved prescriptive agreement among ROs (particularly for worse-prognostic-scenario subgroups). Moreover, PS significantly increased standard prescriptive approaches (particularly for worse-clinical-case presentations)., Conclusions: To the best of our knowledge, the PROPHET study is the first to directly evaluate the potential clinical consequences of the regular application of any PS. According to the Prophet study, a prognostic score should be integrated into the clinical practice of palliative radiation therapy for bone metastasis and training programs in radiation oncology., (© 2022 The Author(s).)