Physician Assessment of ChatGPT and Bing Answers to American Cancer Society's Questions to Ask About Your Cancer.

OBJECTIVES: Artificial intelligence (AI) chatbots are a new, publicly available tool for patients to access health care-related information with unknown reliability related to cancer-related questions. This study assesses the quality of responses to common questions for patients with cancer. METHODS: From February to March 2023, we queried chat generative pretrained transformer (ChatGPT) from OpenAI and Bing AI from Microsoft questions from the American Cancer Society's recommended "Questions to Ask About Your Cancer" customized for all stages of breast, colon, lung, and prostate cancer. Questions were, in addition, grouped by type (prognosis, treatment, or miscellaneous). The quality of AI chatbot responses was assessed by an expert panel using the validated DISCERN criteria. RESULTS: Of the 117 questions presented to ChatGPT and Bing, the average score for all questions were 3.9 and 3.2, respectively ( P < 0.001) and the overall DISCERN scores were 4.1 and 4.4, respectively. By disease site, the average score for ChatGPT and Bing, respectively, were 3.9 and 3.6 for prostate cancer ( P = 0.02), 3.7 and 3.3 for lung cancer ( P < 0.001), 4.1 and 2.9 for breast cancer ( P < 0.001), and 3.8 and 3.0 for colorectal cancer ( P < 0.001). By type of question, the average score for ChatGPT and Bing, respectively, were 3.6 and 3.4 for prognostic questions ( P = 0.12), 3.9 and 3.1 for treatment questions ( P < 0.001), and 4.2 and 3.3 for miscellaneous questions ( P = 0.001). For 3 responses (3%) by ChatGPT and 18 responses (15%) by Bing, at least one panelist rated them as having serious or extensive shortcomings. CONCLUSIONS: AI chatbots provide multiple opportunities for innovating health care. This analysis suggests a critical need, particularly around cancer prognostication, for continual refinement to limit misleading counseling, confusion, and emotional distress to patients and families.

Disparities in time to prostate cancer treatment initiation before and after the Affordable Care Act.

BACKGROUND: Delayed access to care may contribute to disparities in prostate cancer (PCa). The Affordable Care Act (ACA) aimed at increasing access and reducing healthcare disparities, but its impact on timely treatment initiation for PCa men is unknown. METHODS: Men with intermediate- and high-risk PCa diagnosed 2010-2016 and treated with curative surgery or radiotherapy were identified in the National Cancer Database. Multivariable logistic regression modeled the effect of race and insurance type on treatment delay >180 days after diagnosis. Cochran-Armitage test measured annual trends in delays, and joinpoint regression assessed if 2014, the year the ACA became fully operationalized, was significant for inflection in crude rates of major delays. RESULTS: Of 422,506 eligible men, 18,720 (4.4%) experienced >180-day delay in treatment initiation. Compared to White patients, Black (OR 1.79, 95% CI 1.72-1.87, p < 0.001) and Hispanic (OR 1.37, 95% CI 1.28-1.48, p < 0.001) patients had higher odds of delay. Compared to uninsured, those with Medicaid had no difference in odds of delay (OR 0.94, 95% CI 0.84-1.06, p = 0.31), while those with private insurance (OR 0.57, 95% CI 0.52-0.63, p < 0.001) or Medicare (OR 0.64, 95% CI 0.58-0.70, p < 0.001) had lower odds of delay. Mean time to treatment significantly increased from 2010 to 2016 across all racial/ethnic groups (trend p < 0.001); 2014 was associated with a significant inflection for increase in rates of major delays. CONCLUSIONS: Non-White and Medicaid-insured men with localized PCa are at risk of treatment delays in the United States. Treatment delays have been consistently rising, particularly after implementation of the ACA.

Cost-Effectiveness of Surveillance for Distant Recurrence in Extremity Soft Tissue Sarcoma.

BACKGROUND: Optimal distant recurrence (DR) surveillance strategies for extremity soft tissue sarcoma (STS) are unknown. We performed a cost-effectiveness analysis of different imaging modalities performed at guideline-specified intervals. METHODS: We developed a Markov model simulating lifetime outcomes for 54-year-old patients after definitive treatment for American Joint Committee on Cancer stage II-III extremity STS using four surveillance strategies: watchful waiting (WW), chest X-ray (CXR), chest computed tomography (CCT), and positron emission tomography-computed tomography (PET/CT). Probabilities, utilities, and costs were extracted from the literature and Medicare claims to determine incremental cost-effectiveness ratios (ICER). RESULTS: CCT was the most effective and most costly strategy with CXR the most cost-effective strategy at a societal willing-to-pay (WTP) of $100,000/quality-adjusted life year (QALY). The ICER was $12,113/QALY for CXR versus $104,366/QALY for CCT while PET/CT was never cost-effective. Sensitivity analyses demonstrated CCT becomes the preferred imaging modality as the lifetime risk of DR increases beyond 33% or as the WTP increases beyond $120,000/QALY. CONCLUSIONS: Optimal DR surveillance imaging for stage II-III extremity STS should be individualized based on patients' risks for DR. These results suggest CXR, or CCT performed at more protracted intervals, may be preferred for lower-risk patients (i.e., DR risk <33%), whereas CCT may be preferred for higher-risk patients (i.e., DR risk >33%). Further study of optimal strategies is needed. In the interim, these findings may help to refine guidelines to reduce resource overutilization during routine surveillance of lower-risk sarcoma patients.

Histologic Appearance After Preoperative Radiation Therapy for Soft Tissue Sarcoma: Assessment of the European Organization for Research and Treatment of Cancer-Soft Tissue and Bone Sarcoma Group Response Score.

PURPOSE: To critically assess the prognostic value of the European Organization for Research and Treatment of Cancer-Soft Tissue and Bone Sarcoma Group (EORTC-STBSG) response score and define histologic appearance after preoperative radiation therapy (RT) for soft tissue sarcoma (STS). METHODS AND MATERIALS: For a cohort of 100 patients with STS of the extremity/trunk treated at our institution with preoperative RT followed by resection, 2 expert sarcoma pathologists evaluated the resected specimens for percent residual viable cells, necrosis, hyalinization/fibrosis, and infarction. The EORTC response score and other predictors of recurrence-free survival (RFS) and overall survival (OS) were assessed by Kaplan-Meier and proportional hazard models. RESULTS: Median tumor size was 7.5 cm; 92% were intermediate or high grade. Most common histologies were unclassified sarcoma (34%) and myxofibrosarcoma (25%). Median follow-up was 60 months. The 5-year local recurrence rate was 5%, 5-year RFS was 68%, and 5-year OS was 75%. Distribution of cases according to EORTC response score tiers was as follows: no residual viable tumor for 9 cases (9% pathologic complete response); <1% viable tumor for 0, ≥1% to <10% for 9, ≥10% to <50% for 44, and ≥50% for 38. There was no association between EORTC-STBSG response score and RFS or OS. Conversely, hyalinization/fibrosis was a significant independent favorable predictor for RFS (hazard ratio 0.49, P=.007) and OS (hazard ratio 0.36, P=.02). CONCLUSION: Histologic evaluation after preoperative RT for STS showed a 9% pathologic complete response rate. The EORTC-STBSG response score and percent viable cells were not prognostic. Hyalinization/fibrosis was associated with favorable outcome, and if validated, may become a valid endpoint for neoadjuvant trials.