Explainable artificial intelligence analysis of brachytherapy boost receipt in cervical cancer during the COVID-19 era.

PURPOSE: Brachytherapy is a critical component of the standard-of-care curative radiotherapy regimen for women with locally advanced cervical cancer (LACC). However, existing literature suggests that many patients will not receive the brachytherapy boost. We used machine learning (ML) and explainable artificial intelligence to characterize this disparity. MATERIALS AND METHODS: Patients with LACC diagnosed from 2004 to 2020 who received definitive radiation were identified in the National Cancer Database. Five ML models were trained to predict if a patient received a brachytherapy boost. The best-performing model was explained using SHapley Additive exPlanation (SHAP) values. To identify trends that may be attributable to the coronavirus disease 2019 (COVID-19) pandemic, the previous analysis was repeated and limited to 2019 to 2020. RESULTS: A total of 37,564 patients with LACC were identified; 5799 were diagnosed from 2019 to 2020 (COVID cohort). Of these patients, 59.3% received a brachytherapy boost, with 76.4% of patients diagnosed in 2019 to 2020 receiving a boost. The random forest model achieved the best performance for both the overall and COVID cohorts. In the overall cohort, the most important predictive features were the year of diagnosis, stage, age, and insurance status. In the COVID cohort, the most important predictive features were FIGO stage, age, insurance status, and hospital type. Of the 26 patients who tested positive for COVID-19 during their course of radiotherapy, 19 (73.1%) received a brachytherapy boost. CONCLUSIONS: A gradual increase in brachytherapy boost utilization has been noted, which did not seem to be significantly impacted by the onset of the COVID-19 pandemic. ML could be considered to identify patient populations where brachytherapy is underutilized, which can provide actionable feedback for improving access.

Omission of adjuvant radiotherapy in low-risk elderly males with breast cancer.

PURPOSE: Randomized clinical trials demonstrate that lumpectomy + hormone therapy (HT) without radiation therapy (RT) yields equivalent survival and acceptable local-regional outcomes in elderly women with early-stage, node-negative, hormone-receptor positive (HR +) breast cancer. Whether these data apply to men with the same inclusion criteria remains unknown. METHODS: The National Cancer Database was queried for male patients ≥ 65 years with pathologic T1-2N0 (≤ 3 cm) HR + breast cancer treated with breast-conserving surgery with negative margins from 2004 to 2019. Adjuvant treatment was classified as HT alone, RT alone, or HT + RT. Male patients were matched with female patients for OS comparison. Survival analysis was performed using Cox regression and Kaplan - Meier method. Inverse probability of treatment weighting (IPTW) was applied to adjust for confounding. RESULTS: A total of 523 patients met the inclusion criteria, with 24.4% receiving HT, 16.3% receiving RT, and 59.2% receiving HT + RT. The median follow-up was 6.9 years (IQR: 5.0-9.4 years). IPTW-adjusted 5-yr OS rates in the HT, RT, and HT + RT cohorts were 84.0% (95% CI 77.1-91.5%), 81.1% (95% CI 71.1-92.5%), and 93.0% (95% CI 90.0-96.2%), respectively. On IPTW-adjusted MVA, relative to HT, receipt of HT + RT was associated with improvements in OS (HR: 0.641; p = 0.042). RT alone was not associated with improved OS (HR: 1.264; p = 0.420). CONCLUSION: Among men ≥ 65 years old with T1-2N0 HR + breast cancer, RT alone did not confer an OS benefit over HT alone. Combination of RT + HT demonstrated significant improvements in OS. De-escalation of treatment through omission of either RT or HT at this point should be done with caution.

Vulvar Cancer, Version 3.2024, NCCN Clinical Practice Guidelines in Oncology.

Vulvar cancer is annually diagnosed in an estimated 6,470 individuals and the vast majority are histologically squamous cell carcinomas. Vulvar cancer accounts for 5% to 8% of gynecologic malignancies. Known risk factors for vulvar cancer include increasing age, infection with human papillomavirus, cigarette smoking, inflammatory conditions affecting the vulva, and immunodeficiency. Most vulvar neoplasias are diagnosed at early stages. Rarer histologies exist and include melanoma, extramammary Paget's disease, Bartholin gland adenocarcinoma, verrucous carcinoma, basal cell carcinoma, and sarcoma. This manuscript discusses recommendations outlined in the NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for treatments, surveillance, systemic therapy options, and gynecologic survivorship.

Current Status and Future Directions of Image-Guided Adaptive Brachytherapy for Locally Advanced Cervical Cancer.

PURPOSE: The standard of care for patients with locally advanced cervical cancer is definitive chemoradiation followed by a brachytherapy boost. This review describes the current status and future directions of image-guided adaptive brachytherapy for locally advanced cervical cancer. METHODS: A systematic search of the PubMed and Clinicaltrials.gov databases was performed, focusing on studies published within the last 10 years. The search queried "cervical cancer [AND] image-guided brachytherapy [OR] magnetic resonance imaging (MRI) [OR] adaptive brachytherapy". DISCUSSION: The retroEMBRACE and EMBRACE-I trials have established the use of MRI as the standard imaging modality for brachytherapy application and planning. Quantitative imaging and radiomics have the potential to improve outcomes, with three ongoing prospective studies examining the use of radiomics to further risk-stratify patients and personalize brachytherapy. Another active area of investigation includes utilizing the superior soft tissue contrast provided by MRI to increase the dose per fraction and decrease the number of fractions needed for brachytherapy, with several retrospective studies demonstrating the safety and feasibility of three-fraction courses. For developing countries with limited access to MRI, trans-rectal ultrasound (TRUS) appears to be an effective alternative, with several retrospective studies demonstrating improved target delineation with the use of TRUS in conjunction with CT guidance. CONCLUSIONS: Further investigation is needed to continue improving outcomes for patients with locally advanced cervical cancer treated with image-guided brachytherapy.

NCCN Guidelines® Insights: Cervical Cancer, Version 1.2024.

The NCCN Guidelines for Cervical Cancer provide recommendations for all aspects of management for cervical cancer, including the diagnostic workup, staging, pathology, and treatment. The guidelines also include details on histopathologic classification of cervical cancer regarding diagnostic features, molecular profiles, and clinical outcomes. The treatment landscape of advanced cervical cancer is evolving constantly. These NCCN Guidelines Insights provide a summary of recent updates regarding the systemic therapy recommendations for recurrent or metastatic disease.

The American Brachytherapy Society and Indian Brachytherapy Society consensus statement for the establishment of high-dose-rate brachytherapy programs for gynecological malignancies in low- and middle-income countries.

PURPOSE: The global cervical cancer burden is disproportionately high in low- and middle-income countries (LMICs), and outcomes can be governed by the accessibility of appropriate screening and treatment. High-dose-rate (HDR) brachytherapy plays a central role in cervical cancer treatment, improving local control and overall survival. The American Brachytherapy Society (ABS) and Indian Brachytherapy Society (IBS) collaborated to provide this succinct consensus statement guiding the establishment of brachytherapy programs for gynecological malignancies in resource-limited settings. METHODS AND MATERIALS: ABS and IBS members with expertise in brachytherapy formulated this consensus statement based on their collective clinical experience in LMICs with varying levels of resources. RESULTS: The ABS and IBS strongly encourage the establishment of HDR brachytherapy programs for the treatment of gynecological malignancies. With the consideration of resource variability in LMICs, we present 15 minimum component requirements for the establishment of such programs. Guidance on these components, including discussion of what is considered to be essential and what is considered to be optimal, is provided. CONCLUSIONS: This ABS/IBS consensus statement can guide the successful and safe establishment of HDR brachytherapy programs for gynecological malignancies in LMICs with varying levels of resources.

Discovery and characterization of prolactin neutralizing monoclonal antibodies for the treatment of female-prevalent pain disorders.

Prolactin (PRL) has recently been demonstrated to elicit female-selective nociceptor sensitization and increase pain-like behaviors in female animals. Here we report the discovery and characterization of first-in-class, humanized PRL neutralizing monoclonal antibodies (PRL mAbs). We obtained two potent and selective PRL mAbs, PL 200,031 and PL 200,039. PL 200,031 was engineered as human IgG1 whereas PL 200,039 was reformatted as human IgG4. Both mAbs have sub-nanomolar affinity for human PRL (hPRL) and produce concentration-dependent and complete inhibition of hPRL signaling at the hPRL receptor (hPRLR). These two PRL mAbs are selective for hPRL as they do not inhibit other hPRLR agonists such as human growth hormone or placental lactogen. They also cross-react with non-human primate PRL but not with rodent PRL. Further, both mAbs show long clearance half-lives after intravenous administration in FcRn-humanized mice. Consistent with their isotypes, these mAbs only differ in binding affinities to Fcγ receptors, as expected by design. Finally, PL 200,019, the murine parental mAb of PL 200,031 and PL 200,039, fully blocked stress-induced and PRL-dependent pain behaviors in female PRL-humanized mice, thereby providing in vivo preclinical proof-of-efficacy for PRL mAbs in mechanisms relevant to pain in females.

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.

A practical guide to hybrid interstitial/intracavitary brachytherapy for locally-advanced cervical cancer.

PURPOSE: In select cases of locally advanced cervical cancer, a hybrid brachytherapy (HBT) approach consisting of a combined intracavitary (IC)/insterstitial (IS) implant can yield improved target coverage and/or decreased organ at risk dose compared to IC techniques while limiting invasiveness compared to IS techniques. METHODS AND MATERIALS: The technique involves placement of transvaginal and/or perineal needles in addition to the tandem and ring/ovoids using either a specialized applicator or free-hand placement. Following applicator and needle placement, brachytherapy may then be planned using principles similar to IC or IS techniques. During treatment planning, it can be helpful to obtain both MRI and CT imaging, as plastic MRI-compatible needles do not show up well on MRI. RESULTS: In patients where acceptable target coverage cannot be achieved using IC alone or doses to nearby OAR are too high, HBT should be evaluated. HBT can improve both dose to target and OAR while sparing patients the morbidity of perineal template-based interstitial brachytherapy. Specific scenarios where HBT may be preferred include bulky residual primary tumor especially with poor response to EBRT, extension into the lateral parametrium, vaginal extension of tumor, and an asymmetric target. Use of HBT can typically permit extension of dose coverage by an additional 1-2 cm beyond what can be achieved with an IC alone technique. CONCLUSION: HBT allows for improved therapeutic ratio by improving target volume coverage and/or lowering doses to OARs. Brachytherapists should be trained on the practical aspects of administering HBT to be able to offer a less invasive and impactful treatment option when appropriate.

Implications of updated staging system for p16+ oropharyngeal squamous cell carcinoma: Is valuable prognostic information being omitted?

BACKGROUND: This study characterized whether the updated AJCC 8th edition nodal staging system for p16+ oropharyngeal squamous cell carcinoma (OPSCC) resulted in the loss of prognostic value. METHODS: The NCDB was queried for patients with node-positive p16+ OPSCC. The prognostic impact of nodal size, nodal quantity, nodal laterality, and extracapsular extension (ECE) on overall survival (OS) was assessed. RESULTS: In the clinical cohort, inferior 5-year OS was observed in patients with more than one positive lymph node (p < 0.001; 82% vs. 86%), ECE (p < 0.001; 82% vs. 75%), or nodal size >6 cm (p < 0.001; 66% vs. 82%). In the pathologic cohort, inferior 5-year OS was observed in patients with > four positive lymph nodes (p < 0.001; 76% vs. 90%), ECE (p < 0.001; 83% vs. 92%), or largest nodal size >6 cm (p < 0.001; 81% vs. 89%). CONCLUSIONS: Simplifications in the current p16+ OPSCC staging system led to loss of prognostic information in nodal staging.

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.

Patterns of Care for Patients With Locally Advanced Rectal Cancer Treated with Total Neoadjuvant Therapy at Predominately Academic Centers between 2016-2020: An NCDB Analysis.

Total neoadjuvant therapy (TNT) has emerged as the preferred approach for locally advanced rectal cancer (LARC), defined as T3/4 or any T with N+ disease. Our objective was to (1) determine the proportion of patients with LARC receiving TNT over time, (2) determine the most common method in which TNT is being delivered, and (3) determine what factors are associated with a greater likelihood of receiving TNT in the United States. Retrospective data was obtained from the National Cancer Database (NCDB) for patients diagnosed with rectal cancer between 2016 and 2020. Patients were excluded if they had M1 disease, T1-2 N0 disease, incomplete staging information, nonadenocarcinoma histology, received RT to a nonrectum site, or received a nondefinitive RT dose. Data were analyzed using linear regression, χ2 test, and binary logistic regression. Of the 26,375 patients included, most patients were treated at an academic facility (94.6%). Five thousand three (19.0%) patients received TNT, and 21,372 (81.0%) patients did not receive TNT. The proportion of patients receiving TNT increased significantly over time, from 6.1% in 2016 to 34.6% in 2020 (slope = 7.36, 95% CI 4.58-10.15, R2 = 0.96, P = .040). The most common TNT regimen was multiagent chemotherapy followed by long-course chemoradiation (73.2% of cases from 2016-2020). There was a significant increase in utilization of short-course RT as part of TNT from 2.8% in 2016 to 13.7% in 2020 (slope = 2.74, 95% CI 0.37-5.11, R2 = 0.82, P = .035). Factors associated with a lower likelihood of TNT usage included age >65, female gender, Black race, and T3 N0 disease. TNT use in the United States has increased significantly from 2016-2020, with approximately 34.6% of patients with LARC receiving TNT in 2020. The observed trend appears to be in line with the recent National Comprehensive Cancer Network guidelines recommending TNT as the preferred approach.

Prognostic Role of Biologically Active Volume of Disease in Patients With Metastatic Lung Adenocarcinoma.

BACKGROUND: Number of metastatic sites can identify patient populations with non-small cell lung cancer (NSCLC) that benefit from aggressive therapy. Total volume of disease is also relevant. We evaluated the prognostic impact of biologically active volume of disease (BaVD) on patients with metastatic lung adenocarcinoma. MATERIALS AND METHODS: Positron emission tomography/computerized tomography (PET/CT) scans from patients with newly diagnosed lung adenocarcinoma prior to starting any therapy were identified. SUV thresholds of 3 and 4 were used to auto-contour all FDG avid areas. Kaplan-Meier analysis and Cox regression were performed to examine influence on OS. RESULTS: One hundred forty-eight patients were included in the analysis. The median BaVD when using an SUV threshold of 3 was 122.8 mL. The median BaVD when using an SUV threshold of 4 was 46.2 mL When stratified by median BaVD using an SUV of 3, median OS was higher for patients with <=122.8 mL (2.12 years) compared to patients with >122.8 mL (1.46 years) (log-rank P = .001). Similarly, when stratified by median BaVD using an SUV of 4, median OS was higher for patients with <=46.2 mL (1.91 years; 95% CI: 1.65-3.22 years) compared to patients with >46.2 mL (1.48 years; 95% CI: 1.07-1.80 years) (log-rank P = .007). On multivariable analysis, BaVD was significantly associated with OS when using an SUV threshold of 3 (HR: 20.169, P < .001) and 4 (HR: 4.117, P < .001). CONCLUSION: BaVD is an important prognostic factor in metastatic lung adenocarcinoma and may aid identification of patients with limited disease who may be candidates for more aggressive therapies.

Thoracic Radiation in Limited Stage Small Cell Lung Cancer: Trends in Radiation Fractionation.

INTRODUCTION: Thoracic radiotherapy (TRT) is standard of care for limited-stage small cell lung cancer (LS-SCLC). Although initial data supported the use of twice-daily (BID) radiation to a dose of 45 Gy, recent trials have suggested similar efficacy with daily fractionation (QD) to a dose of 60 to 70 Gy. This study evaluates trends in treatment regimen in patients treated with TRT for LS-SCLC. MATERIALS AND METHODS: The National Cancer Database (NCDB) was queried for patients with LS-SCLC treated with TRT between 2004 to 2017 grouped by RT fractionation QD vs. BID. Exclusion criteria were unknown stage, and unknown RT dose. Multivariable (MVA) analyses using logistic regression were performed to investigate factors associated with receipt of a specific fractionation schedule. RESULTS: A total of 17,453 patients met inclusion criteria, with 4,996 receiving BID treatment and 12,457 receiving QD treatment. The most common QD dose was 60 Gy (48.9%). Overall, QD fractionation has increased (1.3%/year). In 2004, 45 Gy BID treatment (41.4%) was the dominant fractionation. By 2017, 60 Gy QD (45.2%) increased (1.9%/y) to be the dominant fractionation, while 45 Gy BID (24.8%) decreased (-1.4%/y) to be the second most common fractionation. On MVA, factors that affect 1 treatment over the other were further stratified. CONCLUSION: Since 2004, QD fractionation has been the preferred TRT regimen for patients with LS-SCLC compared to BID fractionation, with the proportion of patients getting QD treatment continuing to increase. The choice of treatment regimen appears to be influenced by both patient and facility characteristics.

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative review.

Background and Objective: Machine learning (ML) models are increasingly being utilized in oncology research for use in the clinic. However, while more complicated models may provide improvements in predictive or prognostic power, a hurdle to their adoption are limits of model interpretability, wherein the inner workings can be perceived as a "black box". Explainable artificial intelligence (XAI) frameworks including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) are novel, model-agnostic approaches that aim to provide insight into the inner workings of the "black box" by producing quantitative visualizations of how model predictions are calculated. In doing so, XAI can transform complicated ML models into easily understandable charts and interpretable sets of rules, which can give providers with an intuitive understanding of the knowledge generated, thus facilitating the deployment of such models in routine clinical workflows. Methods: We performed a comprehensive, non-systematic review of the latest literature to define use cases of model-agnostic XAI frameworks in oncologic research. The examined database was PubMed/MEDLINE. The last search was run on May 1, 2022. Key Content and Findings: In this review, we identified several fields in oncology research where ML models and XAI were utilized to improve interpretability, including prognostication, diagnosis, radiomics, pathology, treatment selection, radiation treatment workflows, and epidemiology. Within these fields, XAI facilitates determination of feature importance in the overall model, visualization of relationships and/or interactions, evaluation of how individual predictions are produced, feature selection, identification of prognostic and/or predictive thresholds, and overall confidence in the models, among other benefits. These examples provide a basis for future work to expand on, which can facilitate adoption in the clinic when the complexity of such modeling would otherwise be prohibitive. Conclusions: Model-agnostic XAI frameworks offer an intuitive and effective means of describing oncology ML models, with applications including prognostication and determination of optimal treatment regimens. Using such frameworks presents an opportunity to improve understanding of ML models, which is a critical step to their adoption in the clinic.

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.

Machine learning to refine prognostic and predictive nodal burden thresholds for post-operative radiotherapy in completely resected stage III-N2 non-small cell lung cancer.

BACKGROUND: The role of post-operative radiotherapy (PORT) for completely resected N2 non-small-cell lung cancer (NSCLC) is controversial in light of recent randomized data. We sought to utilize machine learning to identify a subset of patients who may still benefit from PORT based on extent of nodal involvement. MATERIALS/METHODS: Patients with completely resected N2 NSCLC were identified in the National Cancer Database. We trained a machine-learning based model of overall survival (OS). SHapley Additive exPlanation (SHAP) values were used to identify prognostic and predictive thresholds of number of positive lymph nodes (LNs) involved and lymph node ratio (LNR). Cox proportional hazards regression was used for confirmatory analysis. RESULTS: A total of 16,789 patients with completely resected N2 NSCLC were identified. Using the SHAP values, we identified thresholds of 3+ positive LNs and a LNR of 0.34+. On multivariate analysis, PORT was not significantly associated with OS (p = 0.111). However, on subset analysis of patients with 3+ positive LNs, PORT improved OS (HR: 0.91; 95% CI: 0.86-0.97; p = 0.002). On a separate subset analysis in patients with a LNR of 0.34+, PORT improved OS (HR: 0.90; 95% CI: 0.85-0.96; p = 0.001). Patients with 3+ positive lymph nodes had a 5-year OS of 38% with PORT compared to 31% without PORT. Patient with positive lymph node ratio 0.34+ had a 5-year OS of 38% with PORT compared to 29% without PORT. CONCLUSIONS: Patients with a high lymph node burden or lymph node ratio may present a subpopulation of patients who could benefit from PORT. To our knowledge, this is the first study to use machine learning algorithms to address this question with a large national dataset. These findings address an important question in the field of thoracic oncology and warrant further investigation in prospective studies.

Evaluation of Radiation Oncologist and Trainee Opinions on Residency Expansion, Possible Actions, and Training Program Accreditation Changes in the United States.

PURPOSE: The objective of this study was to sample the opinions of radiation oncologists and trainees in the United States regarding residency expansion, what action(s) should be taken to limit residency supply, if any, and the proposed Accreditation Council for Graduate Medical Education (ACGME) changes. METHODS AND MATERIALS: An online survey was distributed to 1048 attending radiation oncologists by e-mail and approximately 800 residents through their program coordinators. The survey asked respondents to rank how strongly they agreed with certain statements regarding residency supply, possible solutions to address any perceived oversupply, and the proposed ACGME changes on a 1-to-10 disagreement-to-agreement scale. The 16% response rate yielded 294 responses for analysis. RESULTS: Of the respondents, 90 (30%) were residents, and 204 (70%) were attendings, of whom 117 (57%) were academic and 87 (43%) were nonacademic. Eighty-six percent agreed that there is a residency oversupply issue, and 91% agreed that actions should be taken to limit residency expansion. On χ2 test, residents and attendings were similarly likely to agree that there is a residency oversupply issue (93% and 89%, P = .27), although residents were more likely to agree that this oversupply should be acted upon compared with attendings (100% and 88%, P < .01). Regarding possible solutions, respondents were most likely to agree that further expansion should be limited (90%), program requirements should be made more stringent (76%), and the use of the Supplemental Offer and Acceptance Program should be limited (69%). Proposed ACGME changes that respondents were most likely to agree with included requiring that programs have modern image guidance, stereotactic radiation therapy, and brachytherapy techniques (98%) and have 4+ faculty members and maintain a faculty-to-resident ratio of >1.5:1 (86%). Case log minimums most supported to be increased were 4 uterus (65%) and 11 postmastectomy breast (61%) simulations. CONCLUSIONS: The majority of respondents agree that there is a residency oversupply issue and that actions should be taken to limit residency expansion and make program requirements more stringent.

Characterizing impact of positive lymph node number in endometrial cancer using machine-learning: A better prognostic indicator than FIGO staging?

BACKGROUND: Number of involved lymph nodes (LNs) is a crucial stratification factor in staging of numerous disease sites, but has not been incorporated for endometrial cancer. We evaluated whether number of involved LNs provide improved prognostic value. PATIENTS AND METHODS: Patients diagnosed with node-positive endometrial adenocarcinoma without distant metastasis were identified in the National Cancer Database. We trained a machine-learning based model of overall survival. Shapley additive explanation values (SHAP) based on the model were used to identify cutoffs of number of LNs involved. Results were validated using a Cox proportional hazards regression model. RESULTS: We identified 11,381 patients with endometrial cancer meeting the inclusion criteria. Using the SHAP values, we selected the following thresholds: 1-3 LNs, 4-5 LNs, and 6+ LNs. The 3-year OS was 82.0% for 1-3 LNs, 74.3% for 4-5 LNs (hazard ratio [HR] 1.38; p < 0.001), and 59.9% for 6+ LNs (HR 2.23; p < 0.001). On univariate Cox regression, PA nodal involvement was a significant predictor of OS (HR 1.20; p < 0.001) but was not significant on multivariate analysis when number of LNs was included (HR 1.05; p = 0.273). Additionally, we identified an interaction between adjuvant therapy and number of involved LNs. Patients with 1-3 involved LNs had 3-year OS of 85.2%, 78.7% and 74.2% with chemoradiation (CRT), chemotherapy, and radiation, respectively. Patients with 6+ involved LNs had 3-yr OS of 67.8%, 49.6%, and 48.9% with CRT, chemotherapy, and radiation, respectively (p < 0.001). CONCLUSION: Number of involved LNs is a stronger prognostic and predictive factor compared to PA node involvement.