Intricacies of Human-AI Interaction in Dynamic Decision-Making for Precision Oncology: A Case Study in Response-Adaptive Radiotherapy.

Background: Adaptive treatment strategies that can dynamically react to individual cancer progression can provide effective personalized care. Longitudinal multi-omics information, paired with an artificially intelligent clinical decision support system (AI-CDSS) can assist clinicians in determining optimal therapeutic options and treatment adaptations. However, AI-CDSS is not perfectly accurate, as such, clinicians' over/under reliance on AI may lead to unintended consequences, ultimately failing to develop optimal strategies. To investigate such collaborative decision-making process, we conducted a Human-AI interaction case study on response-adaptive radiotherapy (RT). Methods: We designed and conducted a two-phase study for two disease sites and two treatment modalities-adaptive RT for non-small cell lung cancer (NSCLC) and adaptive stereotactic body RT for hepatocellular carcinoma (HCC)-in which clinicians were asked to consider mid-treatment modification of the dose per fraction for a number of retrospective cancer patients without AI-support (Unassisted Phase) and with AI-assistance (AI-assisted Phase). The AI-CDSS graphically presented trade-offs in tumor control and the likelihood of toxicity to organs at risk, provided an optimal recommendation, and associated model uncertainties. In addition, we asked for clinicians' decision confidence level and trust level in individual AI recommendations and encouraged them to provide written remarks. We enrolled 13 evaluators (radiation oncology physicians and residents) from two medical institutions located in two different states, out of which, 4 evaluators volunteered in both NSCLC and HCC studies, resulting in a total of 17 completed evaluations (9 NSCLC, and 8 HCC). To limit the evaluation time to under an hour, we selected 8 treated patients for NSCLC and 9 for HCC, resulting in a total of 144 sets of evaluations (72 from NSCLC and 72 from HCC). Evaluation for each patient consisted of 8 required inputs and 2 optional remarks, resulting in up to a total of 1440 data points. Results: AI-assistance did not homogeneously influence all experts and clinical decisions. From NSCLC cohort, 41 (57%) decisions and from HCC cohort, 34 (47%) decisions were adjusted after AI assistance. Two evaluations (12%) from the NSCLC cohort had zero decision adjustments, while the remaining 15 (88%) evaluations resulted in at least two decision adjustments. Decision adjustment level positively correlated with dissimilarity in decision-making with AI [NSCLC: ρ = 0.53 ( p < 0.001); HCC: ρ = 0.60 ( p < 0.001)] indicating that evaluators adjusted their decision closer towards AI recommendation. Agreement with AI-recommendation positively correlated with AI Trust Level [NSCLC: ρ = 0.59 ( p < 0.001); HCC: ρ = 0.7 ( p < 0.001)] indicating that evaluators followed AI's recommendation if they agreed with that recommendation. The correlation between decision confidence changes and decision adjustment level showed an opposite trend [NSCLC: ρ = -0.24 ( p = 0.045), HCC: ρ = 0.28 ( p = 0.017)] reflecting the difference in behavior due to underlying differences in disease type and treatment modality. Decision confidence positively correlated with the closeness of decisions to the standard of care (NSCLC: 2 Gy/fx; HCC: 10 Gy/fx) indicating that evaluators were generally more confident in prescribing dose fractionations more similar to those used in standard clinical practice. Inter-evaluator agreement increased with AI-assistance indicating that AI-assistance can decrease inter-physician variability. The majority of decisions were adjusted to achieve higher tumor control in NSCLC and lower normal tissue complications in HCC. Analysis of evaluators' remarks indicated concerns for organs at risk and RT outcome estimates as important decision-making factors. Conclusions: Human-AI interaction depends on the complex interrelationship between expert's prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. The collaborative decision-making process can be summarized as follows: (i) some clinicians may not believe in an AI system, completely disregarding its recommendation, (ii) some clinicians may believe in the AI system but will critically analyze its recommendations on a case-by-case basis; (iii) when a clinician finds that the AI recommendation indicates the possibility for better outcomes they will adjust their decisions accordingly; and (iv) When a clinician finds that the AI recommendation indicate a worse possible outcome they will disregard it and seek their own alternative approach.

Mesothelioma: Pleural, Version 1.2024.

Mesothelioma is a rare cancer that originates from the mesothelial surfaces of the pleura and other sites, and is estimated to occur in approximately 3,500 people in the United States annually. Pleural mesothelioma is the most common type and represents approximately 85% of these cases. The NCCN Guidelines for Mesothelioma: Pleural provide recommendations for the diagnosis, evaluation, treatment, and follow-up for patients with pleural mesothelioma. These NCCN Guidelines Insights highlight significant updates to the NCCN Guidelines for Mesothelioma: Pleural, including revised guidance on disease classification and systemic therapy options.

Consolidation Osimertinib Versus Durvalumab Versus Observation After Concurrent Chemoradiation in Unresectable EGFR-Mutant NSCLC: A Multicenter Retrospective Cohort Study.

INTRODUCTION: Durvalumab improves survival when used as consolidation therapy after chemoradiation (CRT) in patients with stage III NSCLC. The optimal consolidation therapy for patients with EGFR-mutant (EGFRmut) stage III NSCLC remains unknown. METHODS: In this multi-institutional, international retrospective analysis across 24 institutions, we evaluated outcomes in patients with stage III EGFRmut NSCLC treated with concurrent CRT followed by consolidation therapy with osimertinib, durvalumab, or observation between 2015 and 2022. Kaplan-Meier method was used to estimate real-world progression-free survival (rwPFS, primary end point) and overall survival (secondary end point). Treatment-related adverse events (trAEs) during consolidation treatment were defined using Common Terminology Criteria for Adverse Events version 5.0. Multivariable Cox regression analysis was used. RESULTS: Of 136 patients with stage III EGFRmut NSCLC treated with definitive concurrent CRT, 56 received consolidation durvalumab, 33 received consolidation osimertinib, and 47 was on observation alone. Baseline characteristics were similar across the three cohorts. With a median follow-up of 46 months for the entire cohort, the median duration of treatment was not reached (NR) for osimertinib (interquartile range: NR-NR) and was 5.5 (interquartile range: 2.4-10.8) months with durvalumab. After adjusting for nodal status, stage III A/B/C, and age, patients treated with consolidation osimertinib had significantly longer 24-month rwPFS compared to those treated with durvalumab or in the observation cohorts (osimertinib: 86%, durvalumab: 30%, observation: 27%, p < 0.001 for both comparisons). There was no difference in rwPFS between the durvalumab and the observation cohorts. No significant difference in overall survival across the three cohorts was detected, likely due to the limited follow-up. Any-grade trAE occurred in 52% (2 [6.1%] grade ≥3) and 48% (10 [18%] grade ≥3) of patients treated with osimertinib and durvalumab, respectively. Of 45 patients who progressed on consolidation durvalumab, 37 (82%) subsequently received EGFR tyrosine kinase inhibitors. Of these, 14 (38%) patients developed trAEs including five patients with pneumonitis (14%; 2 [5.4%] grade ≥3) and five patients with diarrhea (14%; 1 [2.7%] grade ≥3). CONCLUSIONS: This study suggests that among patients with stage III unresectable NSCLC with a sensitizing EGFR mutation, consolidation osimertinib was associated with a significantly longer rwPFS compared to durvalumab or observation. No unanticipated safety signals were observed with consolidation osimertinib.

Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy.

PURPOSE: Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control. METHODS AND MATERIALS: A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points. RESULTS: The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51). CONCLUSIONS: Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.

Mesothelioma: Peritoneal, Version 2.2023, NCCN Clinical Practice Guidelines in Oncology.

Mesothelioma is a rare cancer originating in mesothelial surfaces of the peritoneum, pleura, and other sites. These NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) focus on peritoneal mesothelioma (PeM). The NCCN Guidelines for PeM provide recommendations for workup, diagnosis, and treatment of primary as well as previously treated PeM. The diagnosis of PeM may be delayed because PeM mimics other diseases and conditions and because the disease is so rare. The pathology section was recently updated to include new information about markers used to identify mesothelioma, which is difficult to diagnose. The term "malignant" is no longer used to classify mesotheliomas, because all mesotheliomas are now defined as malignant.

Magnetic Resonance-Guided Stereotactic Body Radiation Therapy/Hypofractionated Radiation therapy for Metastatic and Primary Central and Ultracentral Lung Lesions.

Introduction: The recent results from the Nordic-HILUS study indicate stereotactic body radiation therapy (SBRT) is associated with high-grade toxicity for ultracentral (UC) tumors. We hypothesized that magnetic resonance-guided SBRT (MRgSBRT) or hypofractionated radiation therapy (MRgHRT) enables the safe delivery of high-dose radiation to central and UC lung lesions. Methods: Patients with UC or central lesions were treated with MRgSBRT/MRgHRT with real-time gating or adaptation. Central lesions were defined as per the Radiation Therapy Oncology Group and UC as per the HILUS study definitions: (1) group A or tumors less than 1 cm from the trachea and/or mainstem bronchi; or (2) group B or tumors less than 1 cm from the lobar bronchi. The Kaplan-Meier estimate and log-rank test were used to estimate survival. Associations between toxicities and other patient factors were tested using the Mann-Whitney U test and Fisher's exact test. Results: A total of 47 patients were included with a median follow-up of 22.9 months (95% confidence interval: 16.4-29.4). Most (53%) had metastatic disease. All patients had central lesions and 55.3% (n = 26) had UC group A. The median distance from the proximal bronchial tree was 6.0 mm (range: 0.0-19.0 mm). The median biologically equivalent dose (α/ß = 10) was 105 Gy (range: 75-151.2). The most common radiation schedule was 60 Gy in eight fractions (40.4%). Most (55%) had previous systemic therapy, 32% had immunotherapy and 23.4% had previous thoracic radiation therapy. There were 16 patients who underwent daily adaptation. The 1-year overall survival was 82% (median = not reached), local control 87% (median = not reached), and progression-free survival 54% (median = 15.1 mo, 95% confidence interval: 5.1-25.1). Acute toxicity included grade 1 (26%) and grade 2 (21%) with only two patients experiencing grade 3 (4.3%) in the long term. No grade 4 or 5 toxicities were seen. Conclusions: Previous studies noted high rates of toxicity after SBRT to central and UC lung lesions, with reports of grade 5 toxicities. In our cohort, the use of MRgSBRT/MRgHRT with high biologically effective doses was well tolerated, with two grade 3 toxicities and no grade 4/5.

NCCN Guidelines® Insights: Non-Small Cell Lung Cancer, Version 2.2023.

The NCCN Guidelines for Non-Small Cell Lung Cancer (NSCLC) provide recommendations for management of disease in patients with NSCLC. These NCCN Guidelines Insights focus on neoadjuvant and adjuvant (also known as perioperative) systemic therapy options for eligible patients with resectable NSCLC.

Dose-Limiting Pulmonary Toxicity in a Phase 1/2 Study of Radiation and Chemotherapy with Ipilimumab Followed by Nivolumab for Patients With Stage 3 Unresectable Non-Small Cell Lung Cancer.

PURPOSE: We hypothesized that concurrent ipilimumab with chemoradiationtherapy (chemoRT) followed by maintenance nivolumab would be safe for patients with unresectable stage III non-small cell lung cancer (NSCLC). We aimed to assess the safety (phase 1) and the 12-month progression-free survival (PFS) (phase 2) in a multi-institution prospective trial. METHODS AND MATERIALS: Eligible patients had unresectable stage III NSCLC. The treatment included platinum doublet chemotherapy with concurrent thoracic radiation therapy to 60 Gy in 30 fractions and ipilimumab (1 mg/kg) delivered during weeks 1 and 4. After chemoRT, maintenance nivolumab (480 mg) was given every 4 weeks for up to 12 cycles. Adverse events (AEs) were assessed according to the Common Terminology Criteria for Adverse Events, version 5.0. Survival analyses were performed with Kaplan Meier (KM) methods and log-rank tests. RESULTS: The trial was discontinued early after enrolling 19 patients without proceeding to the phase 2 component because of unacceptable toxicity. Sixteen patients (84%) had grade ≥3 (G3+) possible treatment-related toxicity, most commonly pulmonary AEs (n = 8, 42%). Fourteen patients (74%) discontinued study therapy early because of AEs (n = 12, 63%) or patient choice (n = 2, 11%). Eleven patients (58%) experienced G2+ pulmonary toxicity with median time to onset 4.1 months (95% CI 2.6-not reached [NR]), and 12-month freedom from G2+ pulmonary toxicity 37% (95% CI, 16-59). Five patients had G5 AEs, including 3 with G5 pulmonary AEs (1 respiratory failure with pneumonitis and pulmonary embolism, 1 pneumonia/chronic obstructive pulmonary disease exacerbation, 1 pulmonary fibrosis). Despite toxicities, the median PFS was 19.2 months (95% CI 6.1-NR) and the median overall survival was NR (95% CI 6.1-NR) with median follow-up of 30.1 months by the reverse KM method. CONCLUSIONS: Concurrent ipilimumab with chemoRT for unresectable stage III NSCLC is associated with pulmonary toxicity that may limit opportunities for improved outcomes. Future studies aiming to incorporate ipilimumab or other anti-CTLA4 therapies into management of unresectable stage III NSCLC should consider careful measures to minimize toxicity risk.

Early-Stage Primary Lung Neuroendocrine Tumors Treated With Stereotactic Body Radiation Therapy: A Multi-Institution Experience.

PURPOSE: Current guidelines recommend surgery as standard of care for primary lung neuroendocrine tumor (LNET). Given that LNET is a rare clinical entity, there is a lack of literature regarding treatment of LNET with stereotactic body radiation therapy (SBRT). We hypothesized that SBRT could lead to effective locoregional tumor control and long-term outcomes. METHODS AND MATERIALS: We retrospectively reviewed 48 tumors in 46 patients from 11 institutions with a histologically confirmed diagnosis of LNET, treated with primary radiation therapy. Data were collected for patients treated nonoperatively with primary radiation therapy between 2006 and 2020. Patient records were reviewed for lesion characteristics and clinical risk factors. Kaplan-Meier analysis, log-rank tests, and Cox multivariate models were used to compare outcomes. RESULTS: Median age at treatment was 71 years and mean tumor size was 2 cm. Thirty-two lesions were typical carcinoid histology, 7 were atypical, and 9 were indeterminate. The most common SBRT fractionation schedule was 50 to 60 Gy in 5 daily fractions. Overall survival at 3, 6, and 9 years was 64%, 43%, and 26%, respectively. Progression-free survival at 3, 6, and 9 years was 88%, 78%, and 78%, respectively. Local control at 3, 6, and 9 years was 97%, 91%, and 91%, respectively. There was 1 regional recurrence in a paraesophageal lymph node. No grade 3 or higher toxicity was identified. CONCLUSIONS: This is the largest series evaluating outcomes in patients with LNET treated with SBRT. This treatment is well tolerated, provides excellent locoregional control, and should be offered as an alternative to surgical resection for patients with early-stage LNET, particularly those who may not be ideal surgical candidates.

Artificial Intelligence for Outcome Modeling in Radiotherapy.

Outcome modeling plays an important role in personalizing radiotherapy and finds applications in specialized areas such as adaptive radiotherapy. Conventional outcome models that are based on a simplified understanding of radiobiological effects or empirical fitting often only consider dosimetric information. However, it is recognized that response to radiotherapy is multi-factorial and involves a complex interaction of radiation therapy, patient and treatment factors, and the tumor microenvironment. Recently, large pools of patient-specific biological and imaging data have become available with the development of advanced biotechnology and multi-modality imaging techniques. Given this complexity, artificial intelligence (AI) and machine learning (ML) are valuable to make sense of such a plethora of heterogeneous data and to aid clinicians in their decision-making process. The role of AI/ML has been demonstrated in many retrospective studies and more recently prospective evidence has been emerging as well to support AI/ML for personalized and precision radiotherapy.

Non-Small Cell Lung Cancer, Version 3.2022, NCCN Clinical Practice Guidelines in Oncology.

NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Non-Small Cell Lung Cancer (NSCLC) provide recommended management for patients with NSCLC, including diagnosis, primary treatment, surveillance for relapse, and subsequent treatment. Patients with metastatic lung cancer who are eligible for targeted therapies or immunotherapies are now surviving longer. This selection from the NCCN Guidelines for NSCLC focuses on targeted therapies for patients with metastatic NSCLC and actionable mutations.

Longitudinal patient-reported outcomes and survival among early-stage non-small cell lung cancer patients receiving stereotactic body radiotherapy.

BACKGROUND AND PURPOSE: The study objective was to determine whether longitudinal changes in patient-reported outcomes (PROs) were associated with survival among early-stage, non-small cell lung cancer (NSCLC) patients undergoing stereotactic body radiation therapy (SBRT). MATERIALS AND METHODS: Data were obtained from January 2015 through March 2020. We ran a joint probability model to assess the relationship between time-to-death, and longitudinal PRO measurements. PROs were measured through the Edmonton Symptom Assessment Scale (ESAS). We controlled for other covariates likely to affect symptom burden and survival including stage, tumor diameter, comorbidities, gender, race/ethnicity, relationship status, age, and smoking status. RESULTS: The sample included 510 early-stage NSCLC patients undergoing SBRT. The median age was 73.8 (range: 46.3-94.6). The survival component of the joint model demonstrates that longitudinal changes in ESAS scores are significantly associated with worse survival (HR: 1.04; 95% CI: 1.02-1.05). This finding suggests a one-unit increase in ESAS score increased probability of death by 4%. Other factors significantly associated with worse survival included older age (HR: 1.04; 95% CI: 1.03-1.05), larger tumor diameter (HR: 1.21; 95% CI: 1.01-1.46), male gender (HR: 1.87; 95% CI: 1.36-2.57), and current smoking status (HR: 2.39; 95% CI: 1.25-4.56). CONCLUSION: PROs are increasingly being collected as a part of routine care delivery to improve symptom management. Healthcare systems can integrate these data with other real-world data to predict patient outcomes, such as survival. Capturing longitudinal PROs-in addition to PROs at diagnosis-may add prognostic value for estimating survival among early-stage NSCLC patients undergoing SBRT.

Artificial Intelligence Applications to Improve the Treatment of Locally Advanced Non-Small Cell Lung Cancers.

Locally advanced non-small cell lung cancer patients represent around one third of newly diagnosed lung cancer patients. There remains a large unmet need to find treatment strategies that can improve the survival of these patients while minimizing therapeutical side effects. Increasing the availability of patients' data (imaging, electronic health records, patients' reported outcomes, and genomics) will enable the application of AI algorithms to improve therapy selections. In this review, we discuss how artificial intelligence (AI) can be integral to improving clinical decision support systems. To realize this, a roadmap for AI must be defined. We define six milestones involving a broad spectrum of stakeholders, from physicians to patients, that we feel are necessary for an optimal transition of AI into the clinic.

NCCN Guidelines Insights: Non-Small Cell Lung Cancer, Version 2.2021.

The NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Non-Small Cell Lung Cancer (NSCLC) address all aspects of management for NSCLC. These NCCN Guidelines Insights focus on recent updates to the NCCN Guidelines regarding targeted therapies, immunotherapies, and their respective biomarkers.

Prospective Single-Arm Phase 1 and 2 Study: Ipilimumab and Nivolumab With Thoracic Radiation Therapy After Platinum Chemotherapy in Extensive-Stage Small Cell Lung Cancer.

PURPOSE: Consolidative thoracic radiation therapy (TRT) has been shown to improve outcomes for patients with extensive stage small cell lung cancer. We hypothesized that the addition of ipilimumab (IPI) and nivolumab (NIVO) after TRT would improve outcomes for patients with extensive stage small cell lung cancer. METHODS AND MATERIALS: Eligibility required stable disease or better after platinum doublet chemotherapy. Study therapy included consolidative TRT to 30 Gy in 10 fractions, targeting residual primary tumor and initially involved regional lymph nodes. Two weeks after TRT, patients received concurrent IPI (3 mg/kg) and NIVO (1 mg/kg) every 3 weeks for 4 doses followed by NIVO monotherapy (480 mg) every 4 weeks until progression or up to 1 year. RESULTS: The study enrolled 21 patients, with 6-month progression-free survival (PFS) of 24% (90% confidence interval [CI], 11%-40%) and a median PFS of 4.5 months (95% CI, 2.7%-4.6%). The 12-month overall survival (OS) was 48% (95% CI, 29%-64%) with a median OS of 11.7 months (95% CI, 4.7%-16.0%). Fifty-two percent of patients had ≥1 possibly related grade 3 to 4 immune-related adverse event. Grade 3 pulmonary and gastrointestinal immune-related adverse events were recorded in 19% and 24% of patients, respectively. Exploratory analysis showed increased cytotoxic T cell (CD3+CD8+) tumor infiltration was associated with favorable PFS (P = .01) and OS (P = .02). Reduction in peripheral blood CD3+CD8+ from baseline to after first dose of IPI/NIVO was associated with improved PFS (P = .02) and OS (P = .02). CONCLUSIONS: Consolidative IPI and NIVO after platinum-based chemotherapy and TRT demonstrated a toxicity profile consistent with the known adverse events attributable to IPI and NIVO. Although the study regimen did not significantly improve PFS, the OS was higher than historic expectations. CD3+CD8+ tumor infiltration and migration may identify patients most likely to have improved outcomes in small cell lung cancer.

Personalizing Radiotherapy Prescription Dose Using Genomic Markers of Radiosensitivity and Normal Tissue Toxicity in NSCLC.

INTRODUCTION: Cancer sequencing efforts have revealed that cancer is the most complex and heterogeneous disease that affects humans. However, radiation therapy (RT), one of the most common cancer treatments, is prescribed on the basis of an empirical one-size-fits-all approach. We propose that the field of radiation oncology is operating under an outdated null hypothesis: that all patients are biologically similar and should uniformly respond to the same dose of radiation. METHODS: We have previously developed the genomic-adjusted radiation dose, a method that accounts for biological heterogeneity and can be used to predict optimal RT dose for an individual patient. In this article, we use genomic-adjusted radiation dose to characterize the biological imprecision of one-size-fits-all RT dosing schemes that result in both over- and under-dosing for most patients treated with RT. To elucidate this inefficiency, and therefore the opportunity for improvement using a personalized dosing scheme, we develop a patient-specific competing hazards style mathematical model combining the canonical equations for tumor control probability and normal tissue complication probability. This model simultaneously optimizes tumor control and toxicity by personalizing RT dose using patient-specific genomics. RESULTS: Using data from two prospectively collected cohorts of patients with NSCLC, we validate the competing hazards model by revealing that it predicts the results of RTOG 0617. We report how the failure of RTOG 0617 can be explained by the biological imprecision of empirical uniform dose escalation which results in 80% of patients being overexposed to normal tissue toxicity without potential tumor control benefit. CONCLUSIONS: Our data reveal a tapestry of radiosensitivity heterogeneity, provide a biological framework that explains the failure of empirical RT dose escalation, and quantify the opportunity to improve clinical outcomes in lung cancer by incorporating genomics into RT.

Artificial Intelligence Research: The Utility and Design of a Relational Database System.

Although many researchers talk about a "patient database," they typically are not referring to a database at all, but instead to a spreadsheet of curated facts about a cohort of patients. This article describes relational database systems and how they differ from spreadsheets. At their core, spreadsheets are only capable of describing one-to-one (1:1) relationships. However, this article demonstrates that clinical medical data encapsulate numerous one-to-many relationships. Consequently, spreadsheets are very inefficient relative to relational database systems, which gracefully manage such data. Databases provide other advantages, in that the data fields are "typed" (that is, they contain specific kinds of data). This prevents users from entering spurious data during data import. Because each record contains a "key," it becomes impossible to add duplicate information (ie, add the same patient twice). Databases store data in very efficient ways, minimizing space and memory requirements on the host system. Likewise, databases can be queried or manipulated using a highly complex language called SQL. Consequently, it becomes trivial to cull large amounts of data from a vast number of data fields on very precise subsets of patients. Databases can be quite large (terabytes or more in size), yet still are highly efficient to query. Consequently, with the explosion of data available in electronic health records and other data sources, databases become increasingly important to contain or order these data. Ultimately, this will enable the clinical researcher to perform artificial intelligence analyses across vast amounts of clinical data in a way heretofore impossible. This article provides initial guidance in terms of creating a relational database system.

Novel MR-Guided Radiotherapy Elective Rotation for Radiation Oncology Trainees.

MR-guided adaptive radiation therapy (RT) is emerging as an integral treatment modality for certain applications and is poised to become an exciting opportunity for greater treatment precision and personalization. However, this is still a relatively nascent technology and only a few institutions and programs have access to this technology for clinical use and trainee education. To increase the diversity of elective offerings and improve the understanding of an MR-guided radiotherapy program, we initiated a unique MR-guided radiotherapy elective rotation for radiation oncology residents. During a representative four-week rotation, 21 simulations were completed by the resident on service. A plurality of simulations were for pancreas stereotactic body radiation therapy (SBRT; 48%) and a majority (71%) of simulations were for adaptive treatments. Additionally, 74 adaptive fractions were completed during this month, of which a significant majority (74%) were for pancreas SBRT. Of the non-adaptive fractions, the majority were for prostate SBRT and intensity-modulated radiation therapy (IMRT). Although many programs may offer training in some aspects of MR-guided radiotherapy as trainees rotate through certain disease sites, we hope this may serve as a blueprint to encourage programs with this technology to fully embrace training in essential competencies related to MR-guided radiotherapy. MR-guided radiotherapy has unique challenges that trainees need to understand to deliver treatment safely: geometric uncertainty, MRI to RT isocenter, and uncertainties with voxel size/tracking.

NCCN Guidelines Insights: Non-Small Cell Lung Cancer, Version 1.2020.

The NCCN Guidelines for Non-Small Cell Lung Cancer (NSCLC) address all aspects of management for NSCLC. These NCCN Guidelines Insights focus on recent updates in immunotherapy. For the 2020 update, all of the systemic therapy regimens have been categorized using a new preference stratification system; certain regimens are now recommended as "preferred interventions," whereas others are categorized as either "other recommended interventions" or "useful under certain circumstances."

Analysis of Relapse Events After Definitive Chemoradiotherapy in Locally Advanced Non-Small-Cell Lung Cancer Patients.

BACKGROUND: The appropriate follow-up frequency after definitive chemoradiotherapy (CRT) for locally advanced non-small-cell lung cancer patients is unknown. Although surveillance guidelines have been proposed, very few data support current recommendations. Here we analyze relapse events after CRT and investigate whether symptomatic relapses versus those detected by surveillance imaging influences outcomes. PATIENTS AND METHODS: Stage III non-small-cell lung cancer patients treated with CRT at our institution between 2005 and 2014 were retrospectively analyzed. Relapse events were grouped into posttreatment intervals and analyzed with cumulative tables. Time to relapse and overall survival (OS) were compared between patients with relapse detection via symptomatic presentation versus surveillance imaging. RESULTS: A total of 211 patients were identified for analysis. The median follow-up was 43 months for patients alive at the time of analysis. The median age was 63 years, and equal proportions had IIIA or IIIB disease. A total of 135 patients (64%) experienced disease relapse, and of these, 74% did so within 12 months. In those who did not experience relapse at ≤ 12 months, 16%, 6%, and < 5% experienced relapse during 12 to 24, 24 to 36, and > 36 months of follow-up, respectively. In patients with relapse, 56% presented symptomatically, which led to inferior median OS compared to those identified by surveillance imaging (23 vs. 36 months; P = .013). CONCLUSION: This study identified that most relapses occur within 1 year of completing CRT, and approximately half of these occur within 6 months. A symptomatic relapse led to inferior OS. More aggressive surveillance imaging may therefore identify asymptomatic relapses that are amenable to earlier salvage therapy.