Artificial Intelligence-suggested Predictive Model of Survival in Patients Treated With Stereotactic Radiotherapy for Early Lung Cancer.

BACKGROUND/AIM: Overall survival (OS)-predictive models to clinically stratify patients with stage I Non-Small Cell Lung Cancer (NSCLC) undergoing stereotactic body radiation therapy (SBRT) are still unavailable. The aim of this work was to build a predictive model of OS in this setting. PATIENTS AND METHODS: Clinical variables of patients treated in three Institutions with SBRT for stage I NSCLC were retrospectively collected into a reference cohort A (107 patients) and 2 comparative cohorts B1 (32 patients) and B2 (38 patients). A predictive model was built using Cox regression (CR) and artificial neural networks (ANN) on reference cohort A and then tested on comparative cohorts. RESULTS: Cohort B1 patients were older and with worse chronic obstructive pulmonary disease (COPD) than cohort A. Cohort B2 patients were heavier smokers but had lower Charlson Comorbidity Index (CCI). At CR analysis for cohort A, only ECOG Performance Status 0-1 and absence of previous neoplasms correlated with better OS. The model was enhanced combining ANN and CR findings. The reference cohort was divided into prognostic Group 1 (0-2 score) and Group 2 (3-9 score) to assess model's predictions on OS: grouping was close to statistical significance (p=0.081). One and 2-year OS resulted higher for Group 1, lower for Group 2. In comparative cohorts, the model successfully predicted two groups of patients with divergent OS trends: higher for Group 1 and lower for Group 2. CONCLUSION: The produced model is a relevant tool to clinically stratify SBRT candidates into prognostic groups, even when applied to different cohorts. ANN are a valuable resource, providing useful data to build a prognostic model that deserves to be validated prospectively.

Diverse Imaging Methods May Influence Long-Term Oncologic Outcomes in Oligorecurrent Prostate Cancer Patients Treated with Metastasis-Directed Therapy (the PRECISE-MDT Study).

Metastasis-directed therapy (MDT) has been tested in clinical trials as a treatment option for oligorecurrent prostate cancer (PCa). However, there is an ongoing debate regarding the impact of using different imaging techniques interchangeably for defining lesions and guiding MDT within clinical trials. Methods: We retrospectively identified oligorecurrent PCa patients who had 5 or fewer nodal, bone, or visceral metastases detected by choline or prostate-specific membrane antigen (PSMA) PET/CT and who underwent MDT stereotactic body radiotherapy with or without systemic therapy in 8 tertiary-level cancer centers. Imaging-guided MDT was assessed as progression-free survival (PFS), time to systemic treatment change due to polymetastatic conversion (PFS2), and overall survival predictor. Propensity score matching was performed to account for clinical differences between groups. Results: Of 402 patients, 232 (57.7%) and 170 (42.3%) underwent MDT guided by [18F]fluorocholine and PSMA PET/CT, respectively. After propensity score matching, patients treated with PSMA PET/CT-guided MDT demonstrated longer PFS (hazard ratio [HR], 0.49 [95% CI, 0.36-0.67]; P < 0.0001), PFS2 (HR, 0.42 [95% CI, 0.28-0.63]; P < 0.0001), and overall survival (HR, 0.39 [95% CI, 0.15-0.99]; P < 0.05) than those treated with choline PET/CT-guided MDT. Additionally, we matched patients who underwent [68Ga]Ga-PSMA-11 versus [18F]F-PSMA-1007 PET/CT, observing longer PFS and PFS2 in the former subgroup (PFS: HR, 0.51 [95% CI, 0.26-1.00]; P < 0.05; PFS2: HR, 0.24 [95% CI, 0.09-0.60]; P < 0.05). Conclusion: Diverse imaging methods may influence outcomes in oligorecurrent PCa patients undergoing MDT. However, prospective, head-to-head studies, ideally incorporating a randomized design, are necessary to provide definitive evidence and facilitate the practical application of these findings.

Stereotactic prostate radiotherapy with or without androgen deprivation therapy, study protocol for a phase III, multi-institutional randomized-controlled trial.

Objective: The therapeutic landscape for localized prostate cancer (PC) is evolving. Stereotactic radiotherapy (SRT) has been reported to be at least not inferior to standard radiotherapy, but the effect of androgen deprivation therapy (ADT) in this setting is still unknown and its use is left to clinical judgment. There is therefore the need to clarify the role of ADT in association with SRT, which is the aim of the present study. Methods: We present a study protocol for a randomized, multi-institutional, Phase III clinical trial, designed to study SRT in unfavorable intermediate and a subclass of high-risk localized PC. Patients (pts) will be randomized 1:1 to SRT + ADT or SRT alone. SRT will consists in 36.25 Gy in 5 fractions, ADT will be a single administration of Triptorelin 22.5 mg concurrent to SRT. Primary end point will be biochemical disease-free survival. Secondary end points will be disease-free survival, freedom from local recurrence, freedom from regional recurrence, freedom from distant metastasis and overall survival (OS); quality of life QoL and patient reported outcomes will be an exploratory end point and will be scored with EPIC-26, EORTC PR 25, IPSS, IIEF questionnaires in SRT + ADT and SRT alone arms. Moreover, clinician reported acute and late toxicity, assessed with CTCAE v. 5.0 scales will be safety end points. Results: Sample size is estimated of 310 pts. For acute toxicity and quality of life results are awaited after 6 months since last patient in, whereas, for efficacy end points and late toxicity mature results will be available 3-5 years after last patient in. Conclusion: Evidence is insufficient to guide decision making concerning ADT administration in the new scenario of prostate ultra-hypofractionation. Hence, the need to investigate the ADT role in SRT specific setting. Advances in knowledge: The stereotactic prostate radiotherapy with or without ADT trial (SPA Trial) has been designed to establish a new standard of care for SRT in localized unfavorable intermediate and a subclass of localized high risk PC.