Evaluating ChatGPT Responses on Thyroid Nodules for Patient Education.

Background: ChatGPT, an artificial intelligence (AI) chatbot, is the fastest growing consumer application in history. Given recent trends identifying increasing patient use of Internet sources for self-education, we seek to evaluate the quality of ChatGPT-generated responses for patient education on thyroid nodules. Methods: ChatGPT was queried 4 times with 30 identical questions. Queries differed by initial chatbot prompting: no prompting, patient-friendly prompting, 8th-grade level prompting, and prompting for references. Answers were scored on a hierarchical score: incorrect, partially correct, correct, or correct with references. Proportions of responses at incremental score thresholds were compared by prompt type using chi-squared analysis. Flesch-Kincaid grade level was calculated for each answer. The relationship between prompt type and grade level was assessed using analysis of variance. References provided within ChatGPT answers were totaled and analyzed for veracity. Results: Across all prompts (n = 120 questions), 83 answers (69.2%) were at least correct. Proportions of responses that were at least partially correct (p = 0.795) and correct (p = 0.402) did not differ by prompt; responses that were correct with references did (p < 0.0001). Responses from 8th-grade level prompting were the lowest mean grade level (13.43 ± 2.86) and were significantly lower than no prompting (14.97 ± 2.01, p = 0.01) and prompting for references (16.43 ± 2.05, p < 0.0001). Prompting for references generated 80/80 (100%) of referenced medical publications within answers. Seventy references (87.5%) were legitimate citations, and 58/80 (72.5%) provided accurately reported information from the referenced publication. Conclusion: ChatGPT overall provides appropriate answers to most questions on thyroid nodules regardless of prompting. Despite targeted prompting strategies, ChatGPT reliably generates responses corresponding to grade levels well-above accepted recommendations for presenting medical information to patients. Significant rates of AI hallucination may preclude clinicians from recommending the current version of ChatGPT as an educational tool for patients at this time.

Perioperative opioids and survival outcomes in resectable head and neck cancer: A systematic review.

BACKGROUND: Opioids are a mainstay in pain control for oncologic surgery. The objective of this systematic review is to evaluate the associations of perioperative opioid use with overall survival (OS) and disease-free survival (DFS) in patients with resectable head and neck cancer (HNC). METHODS: A systematic review of PubMed, SCOPUS, and CINAHL between 2000 and 2022 was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies investigating perioperative opioid use for patients with HNC undergoing surgical resection and its association with OS and DFS were included. RESULTS: Three thousand three hundred seventy-eight studies met initial inclusion criteria, and three studies representing 562 patients (intraoperative opioids, n = 463; postoperative opioids, n = 99) met final exclusion criteria. One study identified that high intraoperative opioid requirement in oral cancer surgery was associated with decreased OS (HR = 1.77, 95% CI 0.995-3.149) but was not an independent predictor of decreased DFS. Another study found that increased intraoperative opioid requirements in treating laryngeal cancer was demonstrated to have a weak but statistically significant inverse relationship with DFS (HR = 1.001, p = 0.02) and OS (HR = 1.001, p = 0.02). The last study identified that patients with chronic opioid after resection of oral cavity cancer had decreased DFS (HR = 2.7, 95% CI 1.1-6.6) compared to those who were not chronically using opioids postoperatively. CONCLUSION: An association may exist between perioperative opioid use and OS and DFS in patients with resectable HNC. Additional investigation is required to further delineate this relationship and promote appropriate stewardship of opioid use with adjunctive nonopioid analgesic regimens.

Differences in Functional and Survival Outcomes Between Patients Receiving Primary Surgery vs Chemoradiation Therapy for Treatment of T1-T2 Oropharyngeal Squamous Cell Carcinoma.

Importance: Due to lack of data from high-powered randomized clinical trials, the differences in functional and survival outcomes for patients with oropharyngeal squamous cell carcinoma (OPSCC) undergoing primary transoral robotic surgery (TORS) vs primary radiation therapy and/or chemoradiation therapy (RT/CRT) are unclear. Objectives: To compare 5-year functional (dysphagia, tracheostomy dependence, and gastrostomy tube dependence) and survivorship outcomes in patients with T1-T2 OPSCC receiving primary TORS vs RT/CRT. Design, Setting, and Population: This national multicenter cohort study used data from a global health network (TriNetX) to identify differences in functional and survival outcomes among patients with OPSCC who underwent primary TORS or RT/CRT in 2002 to 2022. After propensity matching, 726 patients with OPSCC met inclusion criteria. In the TORS group, 363 (50%) patients had undergone primary surgery, and in the RT/CRT group, 363 (50%) patients had received primary RT/CRT. Data analyses were performed from December 2022 to January 2023 using the TriNetX platform. Exposure: Primary surgery with TORS or primary treatment with radiation therapy and/or chemoradiation therapy. Main Outcomes and Measures: Propensity score matching was used to balance the 2 groups. Functional outcomes were measured at 6 months, 1 year, 3 years, 5 years, and more than 5 years posttreatment and included dysphagia, gastrostomy tube dependence, and tracheostomy dependence according to standard medical codes. Five-year overall survivorship was compared between patients undergoing primary TORS vs RT/CRT. Results: Propensity score matching allowed a study sample with 2 cohorts comprising statistically similar parameters with 363 (50%) patients in each. Patients in the TORS cohort had a mean (SD) age of 68.5 (9.9) vs 68.8 (9.7) years in RT/CRT cohort; 86% and 88% were White individuals, respectively; 79% of patients were men in both cohorts. Primary TORS was associated with clinically meaningful increased risk of dysphagia at 6 months (OR, 1.37; 95% CI, 1.01-1.84) and 1 year posttreatment (OR, 1.71; 95% CI, 1.22-2.39) compared with primary RT/CRT. Patients receiving surgery were less likely to be gastrostomy tube dependent at 6 months (OR, 0.46; 95% CI, 0.21-1.00) and 5 years posttreatment (risk difference, -0.05; 95% CI, -0.07 to -0.02). Differences in overall rates of tracheostomy dependence (OR, 0.97; 95% CI, 0.51-1.82) between groups were not clinically meaningful. Patients with OPSCC, unmatched for cancer stage or human papillomavirus status, who received RT/CRT had worse 5-year overall survival than those who underwent primary surgery (70.2% vs 58.4%; hazard ratio, 0.56; 95% CI, 0.40-0.79). Conclusions and Relevance: This national multicenter cohort study of patients undergoing primary TORS vs primary RT/CRT for T1-T2 OPSCC found that primary TORS was associated with a clinically meaningful increased risk of short-term dysphagia. Patients treated with primary RT/CRT had an increased risk of short- and long-term gastrostomy tube dependence and worse 5-year overall survival than those who underwent surgery.

Evaluating ChatGPT responses on obstructive sleep apnea for patient education.

STUDY OBJECTIVES: We evaluated the quality of ChatGPT responses to questions on obstructive sleep apnea for patient education and assessed how prompting the chatbot influences correctness, estimated grade level, and references of answers. METHODS: ChatGPT was queried 4 times with 24 identical questions. Queries differed by initial prompting: no prompting, patient-friendly prompting, physician-level prompting, and prompting for statistics/references. Answers were scored on a hierarchical scale: incorrect, partially correct, correct, correct with either statistic or referenced citation ("correct+"), or correct with both a statistic and citation ("perfect"). Flesch-Kincaid grade level and citation publication years were recorded for answers. Proportions of responses at incremental score thresholds were compared by prompt type using chi-squared analysis. The relationship between prompt type and grade level was assessed using analysis of variance. RESULTS: Across all prompts (n = 96 questions), 69 answers (71.9%) were at least correct. Proportions of responses that were at least partially correct (P = .387) or correct (P = .453) did not differ by prompt; responses that were at least correct+ (P < .001) or perfect (P < .001) did. Statistics/references prompting provided 74/77 (96.1%) references. Responses from patient-friendly prompting had a lower mean grade level (12.45 ± 2.32) than no prompting (14.15 ± 1.59), physician-level prompting (14.27 ± 2.09), and statistics/references prompting (15.00 ± 2.26) (P < .0001). CONCLUSIONS: ChatGPT overall provides appropriate answers to most questions on obstructive sleep apnea regardless of prompting. While prompting decreases response grade level, all responses remained above accepted recommendations for presenting medical information to patients. Given ChatGPT's rapid implementation, sleep experts may seek to further scrutinize its medical literacy and utility for patients. CITATION: Campbell DJ, Estephan LE, Mastrolonardo EV, Amin DR, Huntley CT, Boon MS. Evaluating ChatGPT responses on obstructive sleep apnea for patient education. J Clin Sleep Med. 2023;19(12):1989-1995.

Evaluating the impact of hemodynamic support measures on head and neck free tissue transfer outcomes: A population-based analysis.

OBJECTIVES: This study sought to analyze the effects of perioperative blood transfusions and vasopressors on 30-day surgical complications and 1-year mortality after reconstructive surgery in head and neck free tissue transfer (FTT) and to identify predictors of administration of perioperative blood transfusions or vasopressors. MATERIALS AND METHODS: TriNetX (TriNetX LLC, Cambridge, USA), an international population-level electronic health record database, was queried to identify subjects that underwent FTT requiring perioperative (intraoperative to postoperative day 7) vasopressors or blood transfusions. Primary dependent variables were 30-day surgical complications and 1-year mortality. Propensity score matching was used to control for population differences, and covariate analysis was used to identify preoperative comorbidities associated with perioperative vasopressor or transfusion requirements. RESULTS: 7,631 patients met inclusion criteria. Preoperative malnutrition was associated with increased odds of perioperative transfusion (p = 0.002) and vasopressor requirement (p < 0.001). Perioperative blood transfusion (n = 941) was associated with increased odds of any surgical complication (p = 0.041) within 30 days postoperatively and specifically increased odds of wound dehiscence (p = 0.008) and FTT failure (p = 0.002), respectively. Perioperative vasopressor was (n = 197) was not associated with 30-day surgical complications. Vasopressor requirement was associated with increased hazards-ratio of mortality at 1-year (p = 0.0031). CONCLUSION: Perioperative blood transfusion in FTT is associated with increased odds for surgical complications. Judicious use as a hemodynamic support measure should be considered. Perioperative vasopressor use was associated with an increased risk of one-year mortality. Malnutrition is a modifiable risk factor for perioperative transfusion and vasopressor requirement. These data warrant further investigation to assess causation and potential opportunity for practice improvement.