Radiation Therapy Oncology Group (RTOG) 0617 was a randomized trial that investigated both the impact of radiation dose-escalation and the addition of cetuximab on the treatment of non-small cell lung cancer (NSCLC). The results of RTOG 0617 were surprising, with the dose escalation randomization being closed prematurely due to futility stopping rules, and cetuximab ultimately showing no overall survival benefit. Locally advanced unresectable NSCLC has conventionally been treated with concurrent chemoradiation. Though advances in treatment technology have improved the ability to deliver adequate treatment dose, the foundation for radiotherapy (RT) has remained the same since the 1980s. Since then, progressive studies have sought to establish the safety and efficacy of escalating radiation dose to loco-regional disease. Though RTOG 0617 did not produce the anticipated result, much interest remains in dose escalation and establishing an explanation for the findings of this study. Cetuximab was also not found to provide a survival benefit when applied to an unselected population. However, planned retrospective analysis suggests that those patients with high epidermal growth factor receptor (EGFR) expression may benefit, suggesting that cetuximab should be applied in a targeted fashion. We discuss the results of RTOG 0617 and additional findings from post-hoc analysis that suggest that dose escalation may be limited by normal tissue toxicity. We also present ongoing studies that aim to address potential causes for mortality in the dose escalation arm through adaptive or proton therapy, and are also leveraging additional concurrent systemic agents such as tyrosine kinase inhibitors (TKIs) for EGFR-activating mutations or EML4-ALK rearrangements, and poly (ADP-ribose) polymerase (PARP) inhibitors.

A 65-year-old female presented to radiation oncology for potential treatment options due to metastatic pancreatic cancer and significant abdominal pain. Imaging demonstrated a large pancreatic mass with lymphadenopathy, vascular encasement, and liver metastases. She initiated palliative radiation treatment and developed persistent nausea and vomiting, as well as significant laboratory derangements. She was subsequently admitted and diagnosed with tumor lysis syndrome, though this diagnosis is usually an oncologic emergency seen with hematologic malignancies following chemotherapy. 

Purpose

Patients undergoing radiotherapy (RT) or chemoradiotherapy (CRT) may require emergency department evaluation or hospitalization. Early identification may direct preventative supportive care, improving outcomes and reducing health care costs. We developed and evaluated a machine learning (ML) approach to predict these events.

Methods

A total of 8,134 outpatient courses of RT and CRT from a single institution from 2013 to 2016 were identified. Extensive pretreatment data were programmatically extracted and processed from the electronic health record (EHR). Training and internal validation cohorts were randomly generated (3:1 ratio). Gradient tree boosting (GTB), random forest, support vector machine, and least absolute shrinkage and selection operator logistic regression approaches were trained and internally validated based on area under receiver operating characteristic (AUROC) curve. The most predictive ML approach was also evaluated using only disease- and treatment-related factors to assess predictive gain of extensive EHR data.

Results

All methods had high predictive accuracy, particularly GTB (validation AUROC, 0.798). Extensive EHR data beyond disease and treatment information improved accuracy (delta AUROC, 0.056). A Youden-based cutoff corresponded to validation sensitivity of 81.0% (175 of 216 courses with events) and specificity of 67.3% (1,218 of 1811 courses without events). Interpretability is an important advantage of GTB. Variable importance identified top predictive factors, including treatment (planned RT and systemic therapy), pretreatment encounters (emergency department visits and admissions in the year before treatment), vital signs (weight loss and pain score in the year before treatment), and laboratory values (albumin level at weeks before treatment).

Conclusion

ML predicts emergency visits and hospitalization during cancer therapy. Incorporating predictions into clinical care algorithms may help direct personalized supportive care, improve quality of care, and reduce costs. A prospective trial investigating ML-assisted direction of increased clinical assessments during RT is planned.

Treatment planning is an essential step of the radiotherapy workflow. It has become more sophisticated over the past couple of decades with the help of computer science, enabling planners to design highly complex radiotherapy plans to minimize the normal tissue damage while persevering sufficient tumor control. As a result, treatment planning has become more labor intensive, requiring hours or even days of planner effort to optimize an individual patient case in a trial-and-error fashion. More recently, artificial intelligence has been utilized to automate and improve various aspects of medical science. For radiotherapy treatment planning, many algorithms have been developed to better support planners. These algorithms focus on automating the planning process and/or optimizing dosimetric trade-offs, and they have already made great impact on improving treatment planning efficiency and plan quality consistency. In this review, the smart planning tools in current clinical use are summarized in 3 main categories: automated rule implementation and reasoning, modeling of prior knowledge in clinical practice, and multicriteria optimization. Novel artificial intelligence-based treatment planning applications, such as deep learning-based algorithms and emerging research directions, are also reviewed. Finally, the challenges of artificial intelligence-based treatment planning are discussed for future works.

Objectives

Expert abstraction of acute toxicities is critical in oncology research but is labor-intensive and variable. We assessed the accuracy of a natural language processing (NLP) pipeline to extract symptoms from clinical notes compared to physicians.

Materials and methods

Two independent reviewers identified present and negated National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) v5.0 symptoms from 100 randomly selected notes for on-treatment visits during radiation therapy with adjudication by a third reviewer. A NLP pipeline based on Apache clinical Text Analysis Knowledge Extraction System was developed and used to extract CTCAE terms. Accuracy was assessed by precision, recall, and F1.

Results

The NLP pipeline demonstrated high accuracy for common physician-abstracted symptoms, such as radiation dermatitis (F1 0.88), fatigue (0.85), and nausea (0.88). NLP had poor sensitivity for negated symptoms.

Conclusion

NLP accurately detects a subset of documented present CTCAE symptoms, though is limited for negated symptoms. It may facilitate strategies to more consistently identify toxicities during cancer therapy.

Pancreatic cancer is a formidable malignancy with poor outcomes. The majority of patients are unable to undergo resection, which remains the only potentially curative treatment option. The management of locally advanced (unresectable) pancreatic cancer is controversial; however, treatment with either chemotherapy or chemoradiation is associated with high rates of local tumor progression and metastases development, resulting in low survival rates. An emerging local modality is stereotactic body radiation therapy (SBRT), which uses image-guided, conformal, high-dose radiation. SBRT has demonstrated promising local control rates and resultant quality of life with acceptable rates of toxicity. Over the past decade, increasing clinical experience and data have supported SBRT as a local treatment modality. Nevertheless, additional research is required to further evaluate the role of SBRT and improve upon the persistently poor outcomes associated with pancreatic cancer. This review discusses the existing clinical experience and technical implementation of SBRT for pancreatic cancer and highlights the directions for ongoing and future studies.

The rapid adoption of electronic health records (EHRs) has created extensive repositories of digitized data that can be used to inform improvements in care delivery, processes, and patient outcomes. While the clinical data captured in EHRs are widely used for such efforts, EHRs also capture audit log data that reflect how users interact with the EHR to deliver care. Automatically collected audit log data provide a unique opportunity for new insights into EHR user behavior and decision-making processes. Here, we provide an overview of audit log data and examples that could be used to improve oncology care and outcomes in four domains: diagnostic reasoning and consumption, care team collaboration and communication, patient outcomes and experience, and provider burnout/fatigue. This data source could identify gaps in performance and care, physician uptake of EHR features that enhance decision-making, and integration of data trends for oncology. Ensuring researchers and oncologists are familiar with the data's potential and developing the data engineering capacity to utilize this rich data source, will expand the breadth of research to improve cancer care.