Purpose: This systematic review aims to analyze the literature on the application of AI in predicting patient outcomes and treatment-related toxicity in those undergoing SBRT or SRS across heterogeneous tumor sites. Materials and methods: Our review conformed to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. PubMed, EMBASE and Scopus were systematically searched for English-language human studies evaluating AI for outcome and toxicity prediction in patients undergoing SBRT or SRS for solid tumors. Search terms included (“Stereotactic Body Radiotherapy” OR “SBRT” OR “Stereotactic Radiosurgery” OR “SRS” OR “Stereotactic Ablative Radiotherapy” OR “SABR”) AND (“Artificial Intelligence” OR “AI” OR “Machine Learning” OR “Deep Learning” OR “Radiomics”) AND (“Response Prediction” OR “Response to Treatment” OR “Outcome Prediction”) AND (“Toxicity” OR “Side Effects” OR “Treatment Toxicities” OR “Adverse Events”). Results: The search yielded 29 eligible retrospective studies, published between 2020 and 2025. Eight studies addressed early-stage primary lung cancer, highlighting the potential of AI-based models in predicting radiation-induced pneumonitis, fibrosis and local control. Five studies investigated AI models for predicting hepatobiliary toxicity following SBRT for liver tumors. Sixteen studies involved SRS-treated patients with brain metastases or benign intracranial neoplasms (e.g., arteriovenous malformations, vestibular schwannomas, meningiomas), exploring AI algorithms for predicting treatment response and radiation-induced changes. In the results, AI might have been exploited to both reaffirm already known clinical predictors and to identify novel imaging, dosimetric or biological biomarkers. Examples include predicting radiation pneumonitis in lung cancer, residual liver function in hepatic tumors and local recurrence in brain metastases, thus supporting tailored treatment decisions. Conclusions: Combining AI with SBRT could greatly enhance personalized cancer care by predicting patient-specific outcomes and toxicity. AI models analyze complex datasets, including imaging and clinical data, to identify patterns that traditional methods may miss, thus enabling more accurate risk stratification and reducing variability in treatment planning. With further research and clinical validation, this integration could make radiotherapy safer, more effective and contribute to advancement in precision oncology.

Biochemical recurrences after radical prostatectomy (RP) can be managed with curative purpose through salvage radiation therapy (SRT). RT dose escalation, such as stereotactic RT (SSRT), may improve relapse-free survival in this setting. STARR trial (NCT05455736) is a prospective multicenter study including patients affected by macroscopic recurrence within the prostate bed after RP treated with SSRT. Recurrence was detected with a Choline or PSMA CT-PET. In the current analysis, the early biochemical response (BR) rate and toxicity profile after three months of follow-up were assessed. Twenty-five patients were enrolled, and data about BR and toxicity at three months after treatment were available for 19 cases. Overall, BR was detected after three months in 58% of cases. Four G1–G2 adverse events were recorded; no G ≥ 3 adverse events were detected. SSRT appears feasible and safe, with more than half of patients experiencing BR and an encouraging toxicity profile. The STARR trial is one of the few prospective studies aimed at implementing this promising treatment strategy in this scenario.

Introduction: Orbital lesions are rare, but are likely to become symptomatic and can impact on patients’ quality of life. Local control is often difficult to obtain, because of proximity to critical structures. CyberKnife stereotactic robotic radiotherapy could represent a viable treatment option. Materials and Methods: Data on patients treated for intraorbital lesions from solid malignancies were retrospectively collected. All patients underwent treatment with CyberKnife system. We analyzed local control, response rate, symptoms control, progression-free survival and overall survival, acute and late toxicity. Results: From January 2012 to May 2017, 20 treatments on 19 patients were performed, with dose ranging from 24 to 35 Gy in 1 to 5 fractions, prescribed at an average isodose line of 79.5% (range: 78-81). After a mean follow-up of 14.26 months (range: 0-58), overall response rate was 75%, with 2 and 4 patients presenting a partial and complete response, respectively. Mean time to best measured response was 15.16 months (range: 2-58). Thirteen patients were alive, with a local control rate of 79%. Mean time to local progression was 5 months (range: 3-7). Three patients reported improvement in symptoms after treatment. Mean planning target volume dose coverage was 97.2% (range: 93.5-99.7). Mean maximum dose (D max) to eye globe, optic nerve, optic chiasm, and lens was 2380.8 cGy (range: 290-3921), 1982.82 cGy (range: 777.3-2897.8), 713.14 cGy (range: 219.5-2273), and 867.9 cGy (range: 38-3118.5). Four patients presented acute toxicity. Conclusion: This current retrospective series demonstrated that CyberKnife robotic stereotactic radiotherapy is a feasible and tolerable approach for intraorbital lesions.

Oligoprogression (OPD) is defined as a condition where limited progression (1–3 metastases) is observed in patients undergoing systemic cancer treatment. In this study we investigated the impact of...