Comparative Analysis of US Guidelines for the Management of Cutaneous Squamous Cell and Basal Cell Carcinoma.

Background: This study presents a comparative analysis of recently published guidelines to manage cutaneous squamous cell carcinoma (cSCC) and cutaneous basal cell carcinoma (cBCC) within the United States (US). Methods: A PubMed database search was performed for the time period between June 1, 2016, and December 1, 2022. A comprehensive comparison was performed in the following clinical interest areas: staging and risk stratification, management of primary tumor and regional nodes with curative intent, and palliative treatment. Results: Guidelines from 3 organizations were analyzed: the American Academy of Dermatology (AAD), the National Comprehensive Cancer Network (NCCN), and the American Society for Radiation Oncology (ASTRO). The guidelines used different methodologies to grade evidence, making comparison difficult. There was agreement that surgery is the preferred treatment for curative cBCC and cSCC. For patients ineligible for surgery, there was a consensus to recommend definitive radiation. AAD and NCCN recommended consideration of other topical modalities in selected low-risk cBCC. Postoperative radiation therapy (PORT) was uniformly recommended in patients with positive margins that could not be cleared with surgery and in patients with nerve invasion. The definition and extent of nerve invasion varied. All guidelines recommended surgery as the primary treatment in patients with lymph node metastases in a curative setting. The criteria used for PORT varied; NCCN and ASTRO used lymph node size, number of nodes, and extracapsular extension for recommending PORT. Both NCCN and ASTRO recommend consideration of systemic treatment along with PORT in patients with extracapsular extension. Conclusion: US guidelines provide contemporary and complementary information on the management of cBCC and cSCC. There are opportunities for research, particularly in the areas of staging, indications for adjuvant treatment in curative settings, extent of nerve invasion and prognosis, and the role of systemic treatments in curative and palliative settings.

Determining risk and predictors of head and neck cancer treatment-related lymphedema: A clinicopathologic and dosimetric data mining approach using interpretable machine learning and ensemble feature selection.

Background and purpose: The ability to determine the risk and predictors of lymphedema is vital in improving the quality of life for head and neck (HN) cancer patients. However, selecting robust features is challenging due to the multicollinearity and high dimensionality of radiotherapy (RT) data. This study aims to overcome these challenges using an ensemble feature selection technique with machine learning (ML). Materials and methods: Thirty organs-at-risk, including bilateral cervical lymph node levels, were contoured, and dose-volume data were extracted from 76 HN treatment plans. Clinicopathologic data was collected. Ensemble feature selection was used to reduce the number of features. Using the reduced features as input to ML and competing risk models, internal and external lymphedema prediction capability was evaluated with the ML models, and time to lymphedema event and risk stratification were estimated using the risk models. Results: Two ML models, XGBoost and random forest, exhibited robust prediction performance. They achieved average F1-scores and AUCs of 84 ± 3.3 % and 79 ± 11.9 % (external lymphedema), and 64 ± 12 % and 78 ± 7.9 % (internal lymphedema). Predictive ML and risk models identified common predictors, including bulky node involvement, high dose to various lymph node levels, and lymph nodes removed during surgery. At 180 days, removing 0-25, 26-50, and > 50 lymph nodes increased external lymphedema risk to 72.1 %, 95.6 %, and 57.7 % respectively (p = 0.01). Conclusion: Our approach, involving the reduction of HN RT data dimensionality, resulted in effective ML models for HN lymphedema prediction. Predictive dosimetric features emerged from both predictive and competing risk models. Consistency with clinicopathologic features from other studies supports our methodology.

Quality of Large Language Model Responses to Radiation Oncology Patient Care Questions.

Importance: Artificial intelligence (AI) large language models (LLMs) demonstrate potential in simulating human-like dialogue. Their efficacy in accurate patient-clinician communication within radiation oncology has yet to be explored. Objective: To determine an LLM's quality of responses to radiation oncology patient care questions using both domain-specific expertise and domain-agnostic metrics. Design, Setting, and Participants: This cross-sectional study retrieved questions and answers from websites (accessed February 1 to March 20, 2023) affiliated with the National Cancer Institute and the Radiological Society of North America. These questions were used as queries for an AI LLM, ChatGPT version 3.5 (accessed February 20 to April 20, 2023), to prompt LLM-generated responses. Three radiation oncologists and 3 radiation physicists ranked the LLM-generated responses for relative factual correctness, relative completeness, and relative conciseness compared with online expert answers. Statistical analysis was performed from July to October 2023. Main Outcomes and Measures: The LLM's responses were ranked by experts using domain-specific metrics such as relative correctness, conciseness, completeness, and potential harm compared with online expert answers on a 5-point Likert scale. Domain-agnostic metrics encompassing cosine similarity scores, readability scores, word count, lexicon, and syllable counts were computed as independent quality checks for LLM-generated responses. Results: Of the 115 radiation oncology questions retrieved from 4 professional society websites, the LLM performed the same or better in 108 responses (94%) for relative correctness, 89 responses (77%) for completeness, and 105 responses (91%) for conciseness compared with expert answers. Only 2 LLM responses were ranked as having potential harm. The mean (SD) readability consensus score for expert answers was 10.63 (3.17) vs 13.64 (2.22) for LLM answers (P < .001), indicating 10th grade and college reading levels, respectively. The mean (SD) number of syllables was 327.35 (277.15) for expert vs 376.21 (107.89) for LLM answers (P = .07), the mean (SD) word count was 226.33 (191.92) for expert vs 246.26 (69.36) for LLM answers (P = .27), and the mean (SD) lexicon score was 200.15 (171.28) for expert vs 219.10 (61.59) for LLM answers (P = .24). Conclusions and Relevance: In this cross-sectional study, the LLM generated accurate, comprehensive, and concise responses with minimal risk of harm, using language similar to human experts but at a higher reading level. These findings suggest the LLM's potential, with some retraining, as a valuable resource for patient queries in radiation oncology and other medical fields.