Liver Stiffness Measurement and Risk Prediction of Hepatocellular Carcinoma After HCV Eradication in Veterans With Cirrhosis.

BACKGROUND & AIMS: Patients with cirrhosis secondary to chronic hepatitis C virus (HCV) are at risk for hepatocellular carcinoma (HCC) despite a sustained virological response (SVR). We examined whether post-SVR liver stiffness measurement (LSM) could be used to stratify HCC risk. METHODS: This was a retrospective cohort study of 1850 participants identified from the Veterans Health Administration, with HCV cirrhosis and SVR, followed up over 5099 person-years, from the time of post-SVR elastography until death, HCC, or the end of the study. RESULTS: The risk of HCC increased by 3% with every 1-kPa increase in LSM (adjusted hazard ratio [aHR], 1.03, 95% confidence interval [CI], 1.01-1.04; P < .001) and decreased with the number of years from SVR (aHR, 0.79; 95% CI, 0.70-0.90; P = .0003). The adjusted annual risk of HCC was 2.03% among participants with post-SVR LSM <10 kPa, 2.48% in LSM 10-14.9 kPa (aHR, 1.71; 95% CI, 1.01-2.88; P = .046), 3.22% for LSM 15-19.9 kPa (aHR, 1.59; 95% CI, 0.78-3.20; P = .20), 5.07% among LSM 20-24.9 kPa (aHR, 2.55; 95% CI, 1.30-5.01; P = .01), and 5.44% in LSM ≥25 kPa (aHR, 3.03; 95% CI, 1.74-5.26; P < .0001). The adjusted annual risk of HCC was < 0.4% in participants with LSM <5 kPa and without diabetes mellitus. CONCLUSIONS: LSM predicts rates of HCC in patients with HCV cirrhosis after SVR at multiple cutoff levels and offers a single test to predict portal hypertension-related complications and HCC. Patients with LSM <5 kPa in the absence of diabetes mellitus had a low risk of HCC in which surveillance could be discontinued.

Increased posterior cingulate cortex blood flow in cancer-related fatigue.

Fatigue is a common symptom associated with cancer treatments. Brain mechanisms underlying cancer-related fatigue (CRF) and its progression following therapy are poorly understood. Previous studies have suggested a role of the default mode network (DMN) in fatigue. In this study we used arterial spin labeling (ASL) perfusion functional magnetic resonance imaging (fMRI) and compared resting cerebral blood flow (CBF) differences in the posterior cingulate cortex (PCC), a core hub of the DMN, between 16 patients treated with radiation therapy (RAT) for prostate (9 males) or breast (7 females) cancer and 18 healthy controls (HC). Resting CBF in patients was also measured immediately after the performance of a fatiguing 20-min psychomotor vigilance task (PVT). Twelve of 16 cancer patients were further followed between 3 and 7 months after completion of the RAT (post-RAT). Patients reported elevated fatigue on RAT in comparison to post-RAT, but no change in sleepiness, suggesting that the underlying neural mechanisms of CRF progression are distinct from those regulating sleep drive progression. Compared to HC, patients showed significantly increased resting CBF in the PCC and the elevated PCC CBF persisted during the follow up visit. Post-PVT, but not pre-PVT, resting CBF changes in the PCC correlated with fatigue changes after therapy in patients with CRF, suggesting that PCC CBF following a fatiguing cognitive task may be a biomarker for CRF recovery.

Ursodeoxycholic acid is associated with a reduction in SARS-CoV-2 infection and reduced severity of COVID-19 in patients with cirrhosis.

BACKGROUND AND AIMS: Studies have demonstrated that reducing farnesoid X receptor activity with ursodeoxycholic acid (UDCA) downregulates angiotensin-converting enzyme in human lung, intestinal and cholangiocytes organoids in vitro, in human lungs and livers perfused ex situ, reducing internalization of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) into the host cell. This offers a potential novel target against coronavirus disease 2019 (COVID-19). The objective of our study was to compare the association between UDCA exposure and SARS-CoV-2 infection, as well as varying severities of COVID-19, in a large national cohort of participants with cirrhosis. METHODS: In this retrospective cohort study among participants with cirrhosis in the Veterans Outcomes and Costs Associated with Liver cohort, we compared participants with exposure to UDCA, with a propensity score (PS) matched group of participants without UDCA exposure, matched for clinical characteristics, and vaccination status. The outcomes included SARS-CoV-2 infection, symptomatic, at least moderate, severe, or critical COVID-19, and COVID-19-related death. RESULTS: We compared 1607 participants with cirrhosis who were on UDCA, with 1607 PS-matched controls. On multivariable logistic regression, UDCA exposure was associated with reduced odds of developing SARS-CoV-2 infection (adjusted odds ratio [aOR] 0.54, 95% confidence interval [CI] 0.41-0.71, p < 0.0001). Among patients who developed COVID-19, UDCA use was associated with reduced disease severity, including symptomatic COVID-19 (aOR 0.54, 95% CI 0.39-0.73, p < 0.0001), at least moderate COVID-19 (aOR 0.51, 95% CI 0.32-0.81, p = 0.005), and severe or critical COVID-19 (aOR 0.48, 95% CI 0.25-0.94, p = 0.03). CONCLUSIONS: In participants with cirrhosis, UDCA exposure was associated with both a decrease in SARS-CoV-2 infection, and reduction in symptomatic, at least moderate, and severe/critical COVID-19.

Landscape of Genetic Alterations Underlying Hallmark Signature Changes in Cancer Reveals TP53 Aneuploidy-driven Metabolic Reprogramming.

The hallmark signatures based on gene expression capture core cancer processes. Through a pan-cancer analysis, we describe the overview of hallmark signatures across tumor types/subtypes and reveal significant relationships between these signatures and genetic alterations. TP53 mutation exerts diverse changes, including increased proliferation and glycolysis, which are closely mimicked by widespread copy-number alterations. Hallmark signature and copy-number clustering identify a cluster of squamous tumors and basal-like breast and bladder cancers with elevated proliferation signatures, frequent TP53 mutation, and high aneuploidy. In these basal-like/squamous TP53-mutated tumors, a specific and consistent spectrum of copy-number alterations is preferentially selected prior to whole-genome duplication. Within Trp53-null breast cancer mouse models, these copy-number alterations spontaneously occur and recapitulate the hallmark signature changes observed in the human condition. Together, our analysis reveals intertumor and intratumor heterogeneity of the hallmark signatures, uncovering an oncogenic program induced by TP53 mutation and select aneuploidy events to drive a worsened prognosis. Significance: Our data demonstrate that TP53 mutation and a resultant selected pattern of aneuploidies cause an aggressive transcriptional program including upregulation of glycolysis signature with prognostic implications. Importantly, basal-like breast cancer demonstrates genetic and/or phenotypic changes closely related to squamous tumors including 5q deletion that reveal alterations that could offer therapeutic options across tumor types regardless of tissue of origin.

Design and implementation of an Internet-Based cancer risk assessment tool: Use over 10 years.

BACKGROUND: Prevention and early intervention can improve survival and quality of life across all cancers. Patient understanding of risk factors and associated actionable lifestyle changes and screening programs is not well understood by clinicians METHODS: An Internet-based tool, Reduce My Risk, was created in 2009 and made available on oncolink.org. Users voluntarily completed a survey regarding demographics and cancer risk factors, and received information about their cancer risk RESULTS: Twenty eight thousand and one surveys were completed from 2009 to 2019. Median age was 26 years (18-101); 60% were females, 87% lived in North America, and 37% had at least a bachelor's degree. Users reported on behavioral/ modifiable risk factors: 13% were current smokers, 52% were current consumers of alcohol, and 8% of those had ≥14 drinks/week. Body mass index (BMI) was ≥30 in 19%; 74% of all surveys reported dietary risks and 36% reported infrequent exercise. Excess UV exposure was reported by 19%. Among women, 36% reported performing breast self-examinations monthly, and 50% reported receiving clinician breast examinations at least once every 3 years. Sixty seven percent of men 55-75 years reported screening prostate specific antigen testing, with 50% receiving annual digital rectal examinations. Nonmodifiable risk factors included family cancer history (64%), genetic syndrome (3%), and cancer-predisposing health conditions (26%) CONCLUSIONS: Ninety-seven percent of users reported modifiable risk factors, and 60% reported ≥4 of these risk factors. Understanding detailed characteristics of a large number of respondents has the potential to improve educational interventions to reduce cancer risk through behavioral modification and cancer screening across the general public.

Outcomes following radical prostatectomy or external beam radiation for veterans with Gleason 9 and 10 prostate cancer.

BACKGROUND: The optimal upfront treatment modality for patients with nonmetastatic Gleason Score 9 and 10 prostate cancer (GS 9-10 PCa) is unknown. METHODS: We conducted a retrospective cohort study of patients in the Veterans Health Administration (VHA) with GS 9-10 PCa treated with radical prostatectomy (RP) or external beam radiation therapy with androgen deprivation therapy (EBRT+ADT) from 1/2000 to 12/2010. Outcomes included overall survival (OS), distant metastasis-free survival (DMFS), and salvage/adjuvant therapy-free survival (SAFS), as assessed by Kaplan-Meier analysis. RESULTS: We identified 1220 veterans with GS 9-10 PCa; 335 were treated with RP, and 885 were treated with EBRT+ADT. With a median follow-up of 9.9 years, propensity score-matched analyses demonstrated that RP had superior 10-year OS (70.8% [RP] vs. 61.2% [EBRT+ADT], p < 0.001), 10-year DMFS rates were similar between RP (76.7%) and EBRT+ADT (81.0%), and 10-year SAFS rates were lower for RP vs EBRT + ADT (35.2% [RP] vs. 75.2% [EBRT+ADT], p < 0.001). The receipt of salvage ADT was higher with upfront RP (51.9% vs. 26.1%, p < 0.001), despite receipt of adjuvant/salvage EBRT in 41.8% of RP patients. Among patients treated with RP, there were no differences in outcomes by race. However, higher survival rates were noted among Black patients treated with EBRT+ADT compared with White patients. CONCLUSIONS: This analysis demonstrated higher 10-year OS rates among men treated with upfront RP versus EBRT+ADT, though missing confounders and similar DMFS rates suggest the long-term cause-specific OS rates may be similar. We also highlight real-world outcomes of a diverse patient population in the VHA and improved outcomes for Black patients receiving EBRT+ADT.

Postvaccination COVID-19 infection is associated with reduced mortality in patients with cirrhosis.

BACKGROUND AND AIMS: Patients develop breakthrough COVID-19 infection despite vaccination. The aim of this study was to identify outcomes in patients with cirrhosis who developed postvaccination COVID-19. METHODS: We performed a retrospective cohort study among US veterans with cirrhosis and postvaccination or unvaccinated COVID-19. Patients were considered fully vaccinated if COVID-19 was diagnosed 14 days after the second dose of either the Pfizer BNT162b2, the Moderna 1273-mRNA, or the single-dose Janssen Ad.26.COV2.S vaccines and partially vaccinated if COVID-19 was diagnosed 7 days after the first dose of any vaccine but prior to full vaccination. We investigated the association of postvaccination COVID-19 with mortality. RESULTS: We identified 3242 unvaccinated and 254 postvaccination COVID-19 patients with cirrhosis (82 after full and 172 after partial vaccination). In a multivariable analysis of a 1:2 propensity-matched cohort including vaccinated (n = 254) and unvaccinated (n = 508) participants, postvaccination COVID-19 was associated with reduced risk of death (adjusted HR [aHR], 0.21; 95% CI, 0.11-0.42). The reduction was observed after both full (aHR, 0.22; 95% CI, 0.08-0.63) and partial (aHR, 0.19; 95% CI, 0.07-0.54) vaccination, following the 1273-mRNA (aHR, 0.12; 95% CI 0.04-0.37) and BNT162b2 (aHR, 0.27; 95% CI, 0.10-0.71) vaccines and among patients with compensated (aHR, 0.19; 95% CI, 0.08-0.45) and decompensated (aHR, 0.27; 95% CI, 0.08-0.90) cirrhosis. Findings were consistent in a sensitivity analysis restricted to participants who developed COVID-19 after vaccine availability. CONCLUSIONS: Though patients with cirrhosis can develop breakthrough COVID-19 after full or partial vaccination, these infections are associated with reduced mortality.

Factors Associated With Fatigue in Patients with Breast Cancer Undergoing External Beam Radiation Therapy.

PURPOSE: Cancer-related fatigue (CRF), a prevalent symptom among cancer patients, is a side effect of external beam radiation therapy (EBRT). Even when targeting organs unrelated to caloric intake or the central nervous system, radiation therapy can increase CRF, a poorly understood toxicity resulting from patient-specific, systemic therapy-related, and radiation-specific factors. We sought to determine factors associated with fatigue among patients receiving EBRT for breast cancer. METHODS AND MATERIALS: To determine the variables associated with fatigue among patients with nonmetastatic breast cancer, we retrospectively analyzed prospectively collected toxicity data for a cohort of 1286 adult females with breast cancer who began curative-intent EBRT between April 4, 2010, and October 10, 2017. We hypothesized certain variables are associated with provider-reported Common Terminology Criteria for Adverse Events version 4 fatigue, graded 0 to 3, at baseline and over the course of radiation treatment. RESULTS: All patients were women, with a median age of 57 (range, 24-90). Mean fatigue was low (0.35 [95% confidence interval, 0.32-0.38]) at the start of radiation, increasing weekly and peaking at week 6 (0.85 [0.81-0.90]). Baseline fatigue was associated with higher American Joint Committee on Cancer stage (P < .001), N-stage (P < .001), anxiolytics (P < .001), anticonvulsants (P = .002), antidepressants (P = .006), antihistamines (P < .001), and antipsychotics (P < .001). Chemotherapy was not associated with baseline fatigue. Over the course of treatment, on multivariable analysis, only lower dose per fraction (P < .001) was significantly associated with increasing fatigue. In a subgroup analysis, heart and lung mean, V5, and V20 doses were not found to be associated with increasing fatigue. CONCLUSIONS: This work informs clinicians which factors are associated with CRF at the start of radiation therapy (more advanced disease and prescription of anxiolytics, anticonvulsants, antidepressants, antihistamines, and antipsychotics) and increase CRF over the course of radiation (smaller fraction size). This extensive analysis of factors associated with fatigue provides further evidence that hypofractionated radiation therapy for breast cancer is associated with less acute toxicity than conventionally fractionated treatment.

Combination of CHEK1/2 inhibition and ionizing radiation results in abscopal tumor response through increased micronuclei formation.

We explore a novel strategy of activating immune signaling through increased micronuclei formation utilizing a cell cycle checkpoint inhibitor to drive cell cycle progression following ionizing radiation. The Chk1/2 inhibitor AZD7762 is used to abrogate radiation therapy (RT)-induced G2/M cell cycle arrest in multiple cell lines and, we find that this therapeutic combination promotes increased micronuclei formation in vitro and subsequently drives increased type I interferon signaling and cytotoxic T-cell activation. In vivo studies using B16-F10 melanoma cancer cells implanted in C57/BL6 mice demonstrate improved rates of tumor control at the abscopal (unirradiated) site, located outside of the radiation field, only in the AZD7762 + RT group, with a corresponding reduction in mean tumor volume, increase in the CD8 T-cell population, and immune activated gene signaling. Our results demonstrate that targeted inhibition of cell cycle checkpoint activation following ionizing radiation drives increased production of immunogenic micronuclei, leading to systemic tumor response with potential future clinical benefit.

Machine learning highlights the deficiency of conventional dosimetric constraints for prevention of high-grade radiation esophagitis in non-small cell lung cancer treated with chemoradiation.

BACKGROUND AND PURPOSE: Radiation esophagitis is a clinically important toxicity seen with treatment for locally-advanced non-small cell lung cancer. There is considerable disagreement among prior studies in identifying predictors of radiation esophagitis. We apply machine learning algorithms to identify factors contributing to the development of radiation esophagitis to uncover previously unidentified criteria and more robust dosimetric factors. MATERIALS AND METHODS: We used machine learning approaches to identify predictors of grade ≥ 3 radiation esophagitis in a cohort of 202 consecutive locally-advanced non-small cell lung cancer patients treated with definitive chemoradiation from 2008 to 2016. We evaluated 35 clinical features per patient grouped into risk factors, comorbidities, imaging, stage, histology, radiotherapy, chemotherapy and dosimetry. Univariate and multivariate analyses were performed using a panel of 11 machine learning algorithms combined with predictive power assessments. RESULTS: All patients were treated to a median dose of 66.6 Gy at 1.8 Gy per fraction using photon (89.6%) and proton (10.4%) beam therapy, most often with concurrent chemotherapy (86.6%). 11.4% of patients developed grade ≥ 3 radiation esophagitis. On univariate analysis, no individual feature was found to predict radiation esophagitis (AUC range 0.45-0.55, p ≥ 0.07). In multivariate analysis, all machine learning algorithms exhibited poor predictive performance (AUC range 0.46-0.56, p ≥ 0.07). CONCLUSIONS: Contemporary machine learning algorithms applied to our modern, relatively large institutional cohort could not identify any reliable predictors of grade ≥ 3 radiation esophagitis. Additional patients are needed, and novel patient-specific and treatment characteristics should be investigated to develop clinically meaningful methods to mitigate this survival altering toxicity.

Risk of post-operative, pre-radiotherapy contralateral neck recurrence in patients treated with surgery followed by adjuvant radiotherapy for human papilloma virus-associated tonsil cancer.

OBJECTIVE: One approach to reduce treatment-related morbidity for human papilloma virus (HPV)-associated tonsil cancer is omitting radiotherapy to the contralateral neck. Pathologic risk factors for early contralateral neck disease, however, are poorly understood. We report on the risk contralateral neck failures from the time of pre-operative diagnostic imaging to time of planning for adjuvant radiation in a single institution series of HPV-associated tonsillar cancer patients undergoing surgery followed by radiotherapy (RT). METHODS: Retrospective analysis of 123 patients with T1-T3 HPV-positive tonsillar squamous cell carcinoma treated between 2010 and 2016 with transoral robotic surgery and selective ipsilateral neck dissection followed by adjuvant RT. Contralateral neck recurrence was classified as the detection of a pathologic node in the contralateral neck prior to initiation of adjuvant RT. RESULTS: Seven patients (5.7%) developed contralateral neck disease/failure between the time of pre-operative diagnostic neck imaging and time of planning of adjuvant radiation. Increased ratio of positive/resected nodes [odds ratio (OR) 1.073, p = 0.005] was significantly associated with increased risk of contralateral neck recurrence, with a trend found for close/positive margins (OR 5.355, p = 0.06), tumor size (OR 2.046, p = 0.09), and total number of nodes positive (OR 1.179, p = 0.062). CONCLUSIONS: Patients who develop very early contralateral neck disease, between completion of ipsilateral neck dissection and the initiation of radiotherapy, have a higher ratio of positive nodes to total nodes resected in the ipsilateral neck. These findings suggest that proper selection of patients for omission of treatment of the contralateral, node-negative neck should be made with this in mind, with future studies needed to document the impact on toxicity and disease outcomes from such an approach. ADVANCES IN KNOWLEDGE: Pathologic risk factors in the dissected, ipsilateral neck in patients with tonsil cancer may inform the risk of contralateral neck failure. Patient selection for future, prospective efforts to examine sparing of the contralateral neck need to be based with these risk factors in mind.

Revisiting Bone Marrow Core Biopsy Adequacy Criteria in the Era of Extensive Ancillary Testing.

BACKGROUND: Bone marrow core biopsy is a routine component of comprehensive marrow evaluation, and adequacy criteria have been recommended. However, the effectiveness of these adequacy criteria for diagnostic bone marrow evaluation needs to be reassessed in the current era of extensive ancillary testing. We aimed to determine the impact of core biopsy length and intertrabecular area of evaluable bone marrow on overall adequacy for diagnostic marrow evaluation at our tertiary care institution. METHODS: Five hundred sequential cases of iliac crest bone marrow sampling were identified by retrospective re-view at our tertiary care institution. In this cohort, 470 core biopsies were obtained for histologic evaluation. Data including gross core biopsy length, number of intertrabecular 40x high power fields of evaluable marrow, and other pathologic/clinical parameters were compiled. RESULTS: The mean core biopsy length was 1.2 cm, and only 23% measured the recommended ≥ 1.5 cm. However, 96% of the core biopsies were interpretable and contributed to the comprehensive bone marrow evaluation. Notably, 100% of biopsies with ≥ 5.5 intertrabecular areas were contributory. Ancillary testing including immunophenotypic, cytogenetic, and/or molecular studies were performed in > 99% of cases. CONCLUSIONS: When histology was integrated with ancillary testing, the overall diagnosis was substantially limited in only 0.4% of cases and material deemed entirely insufficient in 0.4%. The number of intertrabecular 40x areas of evaluable marrow is a better predictor of adequacy than core biopsy length, and adequacy criteria should be revised in this era of extensive ancillary testing.

The impact of treatment package time on locoregional control for HPV+ oropharyngeal squamous cell carcinoma treated with surgery and postoperative (chemo)radiation.

BACKGROUND: For patients with head and neck squamous cell carcinoma (SCC) undergoing surgery followed by postoperative radiotherapy (PORT), time from surgery to completion of adjuvant therapy, "package time" impacts locoregional control (LRC). However, the significance of package time in HPV+ oropharyngeal SCC (OPSCC) is unknown. METHODS: We examined patients undergoing TORS resection with PORT for HPV+ OPSCC from January 2010 to December 2015 with ≥18 months follow-up (n = 267). A cutoff of 15 weeks was used to delineate patients into short and long package time groups. LRC loss was defined as any recurrence after surgery. RESULTS: Prolonged package time >15 weeks was associated with inferior LRC in this HPV+ OPSCC cohort, driven primarily by interval from surgery to PORT initiation. Multivariate analysis showed that package time and T classification are both independently associated with LRC. CONCLUSIONS: Among HPV+ OPSCC, prolongation of package time appears to compromise LRC, but not survival.

Four-Year Outcomes From a Prospective Phase II Clinical Trial of Moderately Hypofractionated Proton Therapy for Localized Prostate Cancer.

PURPOSE: Moderately hypofractionated radiation therapy represents an effective treatment for localized prostate cancer (PC). Although large randomized trials have reported the efficacy of photon-based hypofractionated therapy, hypofractionated proton therapy (HFPT) has not been extensively studied. This study was performed to determine the clinical and patient-reported outcomes for patients with PC treated with HFPT. METHODS AND MATERIALS: Between 2010 and 2017, 184 men were enrolled on a trial of 70 Gy in 28 fractions of HFPT for low- to intermediate-risk PC. Acute and late toxicity was evaluated using National Cancer Institute Common Terminology Criteria for Adverse Events version 4.0. Patient-reported outcomes were measured by International Prostate Symptom Score, International Index of Erectile Function Questionnaire, and Expanded Prostate Cancer Index Composite scores. RESULTS: Median follow-up was 49.2 months. Enrolled patients had low-risk (n = 18), favorable intermediate-risk (n = 78), and unfavorable intermediate-risk (n = 88) PC. Four-year rates of biochemical-clinical failure-free survival were 93.5% (95% confidence interval, 89%-98%), 94.4% (89%-100%), 92.5% (86%-100%), and 93.8% (88%-100%) in the overall group and the low-risk, favorable intermediate-risk, and unfavorable intermediate-risk cohorts, respectively (log-rank P > .4). The incidence of acute grade 2 or higher gastrointestinal (GI) and urologic toxicities were 3.8% and 12.5%, respectively. The 4-year incidence of late grade 2 or higher urologic and GI toxicity was 7.6% (4%-13%) and 13.6% (9%-20%), respectively. One late grade 3 GI toxicity was reported. All late toxicities were transient. Patient-reported International Prostate Symptom, International Index of Erectile Function, and Expanded Prostate Cancer Index Composite scores had no significant long-term changes after completion of HFPT (Supplementary Table 1, available at https://doi.org/10.1016/j.ijrobp.2019.05.069). CONCLUSIONS: HFPT is associated with low rates of toxicity and does not appear to negatively affect 4-year patient reported urinary and bowel health. Further comparative analyses are warranted to better understand differences between proton and photon HFRT.

Predicting radiation pneumonitis in locally advanced stage II-III non-small cell lung cancer using machine learning.

BACKGROUND AND PURPOSE: Radiation pneumonitis (RP) is a radiotherapy dose-limiting toxicity for locally advanced non-small cell lung cancer (LA-NSCLC). Prior studies have proposed relevant dosimetric constraints to limit this toxicity. Using machine learning algorithms, we performed analyses of contributing factors in the development of RP to uncover previously unidentified criteria and elucidate the relative importance of individual factors. MATERIALS AND METHODS: We evaluated 32 clinical features per patient in a cohort of 203 stage II-III LA-NSCLC patients treated with definitive chemoradiation to a median dose of 66.6 Gy in 1.8 Gy daily fractions at our institution from 2008 to 2016. Of this cohort, 17.7% of patients developed grade ≥2 RP. Univariate analysis was performed using trained decision stumps to individually analyze statistically significant predictors of RP and perform feature selection. Applying Random Forest, we performed multivariate analysis to assess the combined performance of important predictors of RP. RESULTS: On univariate analysis, lung V20, lung mean, lung V10 and lung V5 were found to be significant RP predictors with the greatest balance of specificity and sensitivity. On multivariate analysis, Random Forest (AUC = 0.66, p = 0.0005) identified esophagus max (20.5%), lung V20 (16.4%), lung mean (15.7%) and pack-year (14.9%) as the most common primary differentiators of RP. CONCLUSIONS: We highlight Random Forest as an accurate machine learning method to identify known and new predictors of symptomatic RP. Furthermore, this analysis confirms the importance of lung V20, lung mean and pack-year as predictors of RP while also introducing esophagus max as an important RP predictor.

Exploratory analysis using machine learning to predict for chest wall pain in patients with stage I non-small-cell lung cancer treated with stereotactic body radiation therapy.

BACKGROUND AND PURPOSE: Chest wall toxicity is observed after stereotactic body radiation therapy (SBRT) for peripherally located lung tumors. We utilize machine learning algorithms to identify toxicity predictors to develop dose-volume constraints. MATERIALS AND METHODS: Twenty-five patient, tumor, and dosimetric features were recorded for 197 consecutive patients with Stage I NSCLC treated with SBRT, 11 of whom (5.6%) developed CTCAEv4 grade ≥2 chest wall pain. Decision tree modeling was used to determine chest wall syndrome (CWS) thresholds for individual features. Significant features were determined using independent multivariate methods. These methods incorporate out-of-bag estimation using Random forests (RF) and bootstrapping (100 iterations) using decision trees. RESULTS: Univariate analysis identified rib dose to 1 cc < 4000 cGy (P = 0.01), chest wall dose to 30 cc < 1900 cGy (P = 0.035), rib Dmax < 5100 cGy (P = 0.05) and lung dose to 1000 cc < 70 cGy (P = 0.039) to be statistically significant thresholds for avoiding CWS. Subsequent multivariate analysis confirmed the importance of rib dose to 1 cc, chest wall dose to 30 cc, and rib Dmax. Using learning-curve experiments, the dataset proved to be self-consistent and provides a realistic model for CWS analysis. CONCLUSIONS: Using machine learning algorithms in this first of its kind study, we identify robust features and cutoffs predictive for the rare clinical event of CWS. Additional data in planned subsequent multicenter studies will help increase the accuracy of multivariate analysis.

Proton therapy for thoracic reirradiation of non-small cell lung cancer.

Lung cancer is a leading cause of cancer death with frequent local failures after initial curative-intent treatment. Locally recurrent non-small cell lung cancer represents a challenging clinical scenario as patients have often received prior radiation as part of a definitive treatment regimen. Proton beam therapy, through its characteristic Bragg peak and lack of exit dose is a potential means of minimizing the toxicity to previously irradiated organs and improving the therapeutic ratio. This article aims to review the rationale for the use of proton beam therapy for treatment of locally recurrent non-small cell lung cancer, highlight the current published experience on the feasibility, efficacy, and limitations of proton beam reirradiation, and discuss future avenues for improved patient selection and treatment delivery.