Explainable Artificial Intelligence to Identify Dosimetric Predictors of Toxicity in Patients with Locally Advanced Non-Small Cell Lung Cancer: A Secondary Analysis of RTOG 0617.

PURPOSE: Dosimetric predictors of toxicity in patients treated with definitive chemoradiation for locally advanced non-small cell lung cancer are often identified through trial and error. This study used machine learning (ML) and explainable artificial intelligence to empirically characterize dosimetric predictors of toxicity in patients treated as part of a prospective clinical trial. METHODS AND MATERIALS: A secondary analysis of the Radiation Therapy Oncology Group (RTOG) 0617 trial was performed. Multiple ML models were trained to predict grade ≥3 pulmonary, cardiac, and esophageal toxicities using clinical and dosimetric features. Model performance was evaluated using the area under the curve (AUC). The best performing model for each toxicity was explained using the Shapley Additive Explanation (SHAP) framework; SHAP values were used to identify relevant dosimetric thresholds and were converted to odds ratios (ORs) with confidence intervals (CIs) generated using bootstrapping to obtain quantitative measures of risk. Thresholds were validated using logistic regression. RESULTS: The best-performing models for pulmonary, cardiac, and esophageal toxicities, outperforming logistic regression, were extreme gradient boosting (AUC, 0.739), random forest (AUC, 0.706), and naive Bayes (AUC, 0.721), respectively. For pulmonary toxicity, thresholds of a mean dose >18 Gy (OR, 2.467; 95% CI, 1.049-5.800; P = .038) and lung volume receiving ≥20 Gy (V20) > 37% (OR, 2.722; 95% CI, 1.034-7.163; P = .043) were identified. For esophageal toxicity, thresholds of a mean dose >34 Gy (OR, 4.006; 95% CI, 2.183-7.354; P < .001) and V20 > 37% (OR, 3.725; 95% CI, 1.308-10.603; P = .014) were identified. No significant thresholds were identified for cardiac toxicity. CONCLUSIONS: In this data set, ML approaches validated known dosimetric thresholds and outperformed logistic regression at predicting toxicity. Furthermore, using explainable artificial intelligence, clinically useful dosimetric thresholds might be identified and subsequently externally validated.

Modern Radiation for Hematologic Stem Cell Transplantation: Total Marrow and Lymphoid Irradiation or Intensity-Modulated Radiation Therapy Total Body Irradiation.

The development of large-field intensity-modulated radiation therapy (IMRT) has enabled the implementation of total marrow irradiation (TMI), total marrow and lymphoid irradiation (TMLI), and IMRT total body irradiation (TBI). IMRT TBI limits doses to organs at risk, primarily the lungs and in some cases the kidneys and lenses, which may mitigate complications. TMI/TMLI allows for dose escalation above TBI radiation therapy doses to malignant sites while still sparing organs at risk. Although still sparingly used, these techniques have established feasibility and demonstrated promise in reducing the adverse effects of TBI while maintaining and potentially improving survival outcomes.

Long-Term Follow-Up of Bridging Therapies Prior to CAR T-Cell Therapy for Relapsed/Refractory Large B Cell Lymphoma.

BACKGROUND: Bridging therapy (BT) with systemic therapy (ST), radiation therapy (RT), or combined-modality therapy (CMT) is increasingly being utilized prior to chimeric antigen receptor (CAR) T-cell therapy for large B-cell lymphoma (LBCL). We report the long-term outcomes of the patients who received commercial CAR T-cell therapy with or without BT. METHODS: The patients with LBCL who underwent infusion of a commercial CD19 CAR T product were eligible. The radiation was stratified as comprehensive or focal. The efficacy outcomes and toxicity were analyzed. RESULTS: In total, 156 patients were included and, of them, 52.5% of the patients received BT. The median progression-free survival (PFS) was 0.65 years in the BT cohort compared to 1.45 years in the non-BT cohort. The median overall survival (OS) was 3.16 years in the BT cohort and was not reached in the non-BT cohort. The patients who received comprehensive radiation (versus focal) had significantly improved PFS and OS, achieving a 1-year PFS of 100% vs. 9.1% and 1-year OS of 100% vs. 45.5%. There was no difference in the severe toxicity between any of the nonbridging or BT cohorts. CONCLUSIONS: BT did not appear to compromise outcomes with respect to response rates, disease control, survival, and toxicity. The patients with limited disease treated with RT had favorable outcomes.

Stereotactic body radiation therapy to the kidney for metastatic renal cell carcinoma: A narrative review of an emerging concept.

This narrative review provides a historical overview of cytoreductive nephrectomy for metastatic renal cell carcinoma (mRCC) and examines the safety and therapeutic potential of cytoreductive stereotactic body radiation therapy (SBRT) for mRCC in the modern immunotherapy era. In the last five years, the introduction of immune checkpoint inhibitors for the treatment of mRCC has improved outcomes for patients. This has brought forth new exploration of the role of CN in combination with immunotherapy. Early retrospective evidence suggests that there may be a benefit of deferred CN after immunotherapy (IOT) for de novo mRCC patients. However, there has also been concern regarding the feasibility of surgery after IOT due to inflammation. SBRT may be an appropriate alternative in these circumstances. Since 1999, cytoreductive SBRT has been used for inoperable primary RCC. Several prospective and retrospective studies treating the kidney tumor for localized RCC have shown that this technique is safe and produces favorable and durable local control. SBRT has also exhibited similar effectiveness to CN, while providing additional benefits including noninvasiveness and the ability to treat tumors that can't be treated with nephrectomy or ablation due to size or location. Furthermore, SBRT confers immunostimulatory effects, which are hypothesized to work synergistically with immunotherapy. Clinicians should consider SBRT a safe and reliable alternative to CN for RCC patients. Ongoing studies are exploring the utility of SBRT for treatment of the primary tumor in mRCC patients receiving standard of care immunotherapy.

Genomic and Transcriptomic Predictors of Response from Stereotactic Body Radiation Therapy in Patients with Oligoprogressive Renal Cell Carcinoma.

Stereotactic body radiation therapy (SBRT) has been shown to be safe and effective for delaying systemic treatment change among patients with metastatic renal cell carcinoma (mRCC). In this study, we sought to assess the genomic signatures of patients with mRCC who underwent SBRT for oligoprogression. A total of 30 patients with oligoprogressive disease were identified, the majority of whom had clear cell renal cell carcinoma (83.3%) and were receiving first-line treatment (53.3%). Genomic and transcriptomic sequencing were available in 20 and 16 patients, respectively. Duration of systemic treatment (DOT) was categorized as that prior (DOT[P]) and subsequent (DOT[S]) to radiation treatment. The median DOT(P) and DOT(S) were 15.1 and 18.3 mo, respectively, with a median DOT(S)/DOT(P) ratio of 1.4. Patients who had a DOT(S)/DOT(P) ratio of ≥1 had increased expression in pathways related to cell proliferation and development. In contrast, among patients with a ratio of ≤1, the reactive oxygen species pathway was enriched. This study highlights the potential role of genomics and transcriptomics to refine radiation treatment selection in patients with mRCC. PATIENT SUMMARY: In this study, we looked at mutations and genomic expressions among kidney cancer patients who responded better to stereotactic body radiotherapy. We found that enriched expression of certain pathways might play a role in response to radiotherapy.

Long-term follow up of patients with hematological malignancies treated with total body irradiation using intensity modulated radiation therapy.

Background: With the advent of modern radiation treatment technologies such as intensity modulated radiation therapy (IMRT), there has been increasing interest in its use for total body irradiation (TBI) conditioning regimens for hematopoietic cell transplantation (HCT) to achieve lower doses to critical organs such as the lungs and kidneys. Although this has been reported on in early studies, long-term safety and efficacy data is limited. Methods: We performed a single institution matched-pair retrospective analysis of patients treated with IMRT TBI and standard TBI between 2010 and 2020 to provide data on long-term outcomes. Patients with hematologic malignancies, who could not tolerate standing for traditional TBI or who received prior radiation received IMRT TBI. Patients were matched based on age, diagnosis, disease status, and year of transplant, and were matched 2:1 to the standard TBI and IMRT TBI cohorts. Patient and treatment characteristics, toxicity, graft-versus-host disease (GVHD), dosimetry, and outcomes were evaluated for each cohort. Results: A total of 13 patients met inclusion criteria for the IMRT cohort, leading to 26 patients in the standard TBI cohort. There was no significant difference in relevant clinical factors between the cohorts. Reasons for using IMRT over conventional TBI included being unable to stand (n=5), prior radiation (n=5), and pediatric patient requiring anesthesia (n=3). Among living patients, median follow-up for all patients was 5.1 years in the IMRT TBI cohort and 5.5 years in the standard TBI cohort. The 5-yr estimate of OS was 68% in the IMRT TBI cohort and 60% in the standard TBI cohort (p=0.706). The 5-yr estimate of RFS was 54% in the IMRT TBI cohort and 60% in the standard TBI cohort (p=0.529). There was no clinically significant pneumonitis, nephritis, hypothyroidism, or cataracts reported in the IMRT TBI cohort. 41.7% of patients in the IMRT TBI cohort and 79.2% of patients in the standard TBI cohort experienced Grade II-IV acute GVHD (p=0.023). Conclusions: IMRT TBI appears to lead to favorable long-term outcome and dosimetry, and therefore potentially improved long-term toxicity profile compared to conventional TBI. IMRT TBI warrants further investigation as part of larger prospective trials.

Role of radiotherapy in treatment of extramedullary relapse following total marrow and lymphoid irradiation in high-risk and/or relapsed/refractory acute leukemia.

Background: Total Marrow and Lymphoid Irradiation (TMLI) is a promising component of the preparative regimen for hematopoietic cell transplantation in patients with high-risk acute myeloid leukemia (AML) and acute lymphoid leukemia (ALL). Extramedullary (EM) relapse after TMLI is comparable to TBI and non-TBI conditioning regimens. This study evaluates outcomes of patients treated with radiotherapy (RT) with EM relapse previously treated with TMLI. Methods: A retrospective analysis of five prospective TMLI trials was performed. TMLI targeted bones and major lymphoid tissues using image-guided tomotherapy, with total dose ranging from 12 to 20 Gy. EM recurrences were treated at the discretion of the hematologist and radiation oncologist using RT ± chemotherapy. Descriptive statistics and survival analysis were then performed on this cohort. Results: In total, 254 patients with refractory or relapsed AML or ALL were treated with TMLI at our institution. Twenty-one patients were identified as receiving at least one subsequent course of radiation. A total of 67 relapse sites (median=2 sites/patient, range=1-16) were treated. Eleven relapsed patients were initially treated with curative intent. Following the initial course of subsequent RT, 1-year, 3-year and 5-year estimates of OS were 47.6%, 32.7% and 16.3%, respectively. OS was significantly better in patients treated with curative intent, with median OS of 50.7 months vs 1.6 months (p<0.001). 1-year, 3-year and 5-year estimates of PFS were 23.8%, 14.3% and 14.3%, respectively. PFS was significantly better in patients treated with curative intent, with median PFS of 6.6 months vs 1.3 months (p<0.001). Following RT, 86.6% of the sites had durable local control. Conclusions: RT is an effective modality to treat EM relapse in patients with acute leukemia who relapse after HCT achieving high levels of local control. In patients with limited relapse amenable to curative intent, radiation confers favorable long-term survival. Radiation as salvage treatment for EM relapse after HCT warrants further evaluation.

Oligometastatic Breast Cancer Patients Treated with High-Dose Chemotherapy and Targeted Radiation: Long-Term Follow-Up of a Phase II Trial.

BACKGROUND: Patients with oligometastatic breast cancer (oMBC) may benefit from aggressive local therapy. We sought to assess the effects of consolidative radiation therapy (RT) on outcomes in oMBC patients treated on a prospective phase II trial of high-dose chemotherapy (HDCT). METHODS: Between 2005 and 2009, 12 patients with oMBC (≤3 metastatic sites) cancer were treated on protocol. Patients were to receive tandem HDCT supported by hematopoietic cell rescue (HCR). All radiographically identifiable oligometastatic sites received targeted radiation. RESULTS: HDCT was initiated at a median of 6.7 (3.5-12.7) months after diagnosis of oMBC. Hormone receptors (HR) were positive in 91.6% of patients, and HER2 was overexpressed in 25% of patients. Median radiation dose (EQD2) was 41.2 (37.9-48.7) Gy. Median follow-up was 13.1 (6.8-15.1) years for living patients. Ten-year PFS and OS were 33% (95%CI, 10-59%) and 55% (95%CI, 22-79%), respectively. Durable local control of treated lesions was 87.5%. At the last follow up, two patients remained progression free and two more were without evidence of disease following additional salvage treatment. CONCLUSIONS: Although modern systemic therapies have obviated the use of HDC, aggressive local therapy warrants further evaluation and fractionated radiotherapy is a viable alternative if SBRT is not available.

Long-Term Outcomes of Patients on a Phase II Prospective Trial of Oligometastatic Hormone-Sensitive Prostate Cancer Treated With Androgen Deprivation and External Beam Radiation.

PURPOSE: External beam radiation therapy (EBRT) to oligometastases may improve outcomes in patients with oligometastatic hormone-sensitive prostate cancer (oHSPC). Follow-up on this cohort has been limited to <5 years and prospective data on de novo patients with oHSPC are lacking. We reviewed the long-term outcomes of patients with oHSPC treated with EBRT and androgen deprivation therapy on a prospective trial. METHODS AND MATERIALS: From 2006 to 2011, patients with oHSPC with 1 to 5 metastases received 36 weeks of androgen deprivation therapy (luteinizing hormone-releasing hormone agonist + bicalutamide) and up to 53 Gy to all visible metastases. When indicated, the primary tumor or prostate bed was treated with EBRT up to 78 or 66 Gy, respectively. RESULTS: Twenty-nine patients were treated: 15 de novo, 14 oligorecurrent, and 21 patients (72.4%) had bone metastases. Median number of metastases per patient was 1 (range, 1-5). EBRT was administered to 52 lesions (38 bone, 12 pelvic lymph nodes [LNs], 2 nonpelvic LNs) up to 53 Gy (range, 47-66). Median follow-up was 9.9 years (years; range, 0.2-14.4). Median overall survival was 9.7 years (95% confidence interval [CI], 5.8-not reached). Median progression-free survival was 1.9 years (95% CI, 1.6-2.2). Patients who presented with prostate cancer-defined de novo metastases had significantly improved (P = .04) median progression-free survival (2.0 years; 95% CI, 1.3-6.0) compared with oligorecurrent patients (1.8 years; 95% CI, 1.0-2.0). Patients who presented with LN-only metastases had numerically improved (P = .13) median PFS (5.8 years; 95% CI, 1.2-not reached) compared with patients with bony metastases (1.8 years; 95% CI, 1.3-2.0). At last follow-up, 17 patients (58.6%) had local control of all EBRT-treated metastases. The metastases that locally progressed had previously been controlled for median 3.5 years (range, 1.7-10.5). CONCLUSIONS: Our results compare favorably with other reported studies of patients with oHSPC and provide new insights into their long-term outcomes.

Role of Salvage Radiation Treatment of Relapses in Relapsed/Refractory Diffuse Large B Cell Lymphoma Post-Autologous Stem Cell Transplant.

PURPOSE: Approximately 50% of patients with relapsed/refractory diffuse large B cell lymphoma (R/R DLBCL) will relapse post-autologous stem cell transplant (ASCT), and the role of salvage therapy is not well defined. We examined radiation therapy (RT) as salvage treatment in this patient population. MATERIALS AND METHODS: A retrospective review of patients with DLBCL who had an ASCT during 2004 to 2016 and subsequently relapsed was performed. Clinical and pathologic characteristics were collected, including detailed information regarding post-ASCT treatment. Response rates were tabulated and survival analysis was performed, stratified by salvage modality. RESULTS: A total of 165 patients with R/R DLBCL who relapsed after ASCT were identified; 91 of these patients received salvage chemotherapy as their first line of relapse therapy, and 14 received salvage radiation. Median salvage RT dose was 36 Gy (range, 24-50). The objective response rate with salvage chemotherapy and RT was 53.0% and 78.5%, respectively (P = 0.07), and the complete response rate was 31.3% and 57.1%, respectively (P = 0.06). Median follow-up among living patients was 48.9 months (range, 4.8-136.17). Among patients with one site of relapse post-ASCT, median overall survival in patients who received salvage RT was significantly improved (P = 0.008) relative to chemotherapy (not reached [95% confidence interval {CI}, 8.4-not reached] versus 10.0 months [95% CI, 5.3-17.8]). Median progression-free survival in patients who received salvage RT was not significantly different (P = 0.16) relative to chemotherapy (8.4 months [95% CI, 2.5-47.7] versus 3.9 months [95% CI, 2.4-8.5]). CONCLUSIONS: Patients who received RT as first salvage therapy post-ASCT, particularly with localized disease, had favorable oncologic outcomes. Future studies are needed to understand which patients with R/R DLBCL who relapse after ASCT may benefit from early salvage RT versus chemotherapy.