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.

Radiotherapy is increasingly used to treat oligometastatic patients. We sought to identify prognostic criteria in oligometastatic patients undergoing definitive hypofractionated image-guided radiotherapy (HIGRT). Exclusively extracranial oligometastatic patients treated with HIGRT were pooled. Characteristics including age, sex, primary tumor type, interval to metastatic diagnosis, number of treated metastases and organs, metastatic site, prior systemic therapy for primary tumor treatment, prior definitive metastasis-directed therapy, and systemic therapy for metastasis associated with overall survival (OS), progression-free survival (PFS), and treated metastasis control (TMC) were assessed by the Cox proportional hazards method. Recursive partitioning analysis (RPA) identified prognostic risk strata for OS and PFS based on pretreatment factors. 361 patients were included. Primary tumors included non-small cell lung (17%), colorectal (19%), and breast cancer (16%). Three-year OS was 56%, PFS was 24%, and TMC was 72%. On multivariate analysis, primary tumor, interval to metastases, treated metastases number, and mediastinal/hilar lymph node, liver, or adrenal metastases were associated with OS. Primary tumor site, involved organ number, liver metastasis, and prior primary disease chemotherapy were associated with PFS. OS RPA identified five classes: class 1: all breast, kidney, or prostate cancer patients (BKP) (3-year OS 75%, 95% CI 66–85%); class 2: patients without BKP with disease-free interval of 75+ months (3-year OS 85%, 95% CI 67–100%); class 3: patients without BKP, shorter disease-free interval, ≤ two metastases, and age < 62 (3-year OS 55%, 95% CI 48–64%); class 4: patients without BKP, shorter disease-free interval, ≥ three metastases, and age < 62 (3-year OS 38%, 95% CI 24–60%); class 5: all others (3-year OS 13%, 95% CI 5–35%). Higher biologically effective dose (BED) (p < 0.01) was associated with OS. We identified clinical factors defining oligometastatic patients with favorable outcomes, who we hypothesize are most likely to benefit from metastasis-directed therapy.

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.