Accuracy and usability of artificial intelligence chatbot generated chemotherapy protocols.

Background: Medical practitioners are increasingly using artificial intelligence (AI) chatbots for easier and faster access to information. To our knowledge, the accuracy and availability of AI-generated chemotherapy protocols has not yet been studied. Methods: Nine simulated cancer patient cases were designed and AI chatbots, ChatGPT version 3.5 (OpenAI) and Bing (Microsoft), were used to generate chemotherapy protocols for each case. Results: Generated chemotherapy protocols were compared with the original protocols for nine simulated cancer patients. ChatGPT's overall performance was 5 out of 9 on protocol generation, and Bing's was 4 out of 9; this was statistically nonsignificant (p = 1). Conclusion: AI chatbots show both potential and limitations in generating chemotherapy protocols. The overall performance is low, and they should be used carefully in oncological practice.

Comparison of the Efficacy and Safety of 3 Months of CAPOX Followed by 3 Months of Capecitabine and 6 Months of CAPOX/FOLFOX in the Adjuvant Treatment of Low-Risk Stage III Colon Cancer Treated Surgically.

INTRODUCTION: In the adjuvant treatment of low-risk stage III colon cancer treated surgically, 3 months of CAPOX followed by 3 months of capecitabine is not a common clinical practice. Since there are no data on this practice in the literature, we have no idea how often it is used. However, it should be noted that this application is used in some centers due to the cumulative neurotoxicity of oxaliplatin but there are insufficient data in the literature on its efficacy. METHODS: The data of patients with colon cancer treated surgically who were followed up in 12 different oncology centers in Turkey between November 2004 and June 2022 were analyzed retrospectively. RESULTS: The study included 194 patients. The treatment arms were as follows: 3 months of CAPOX followed by 3 months of capecitabine = arm A and CAPOX/FOLFOX (6 months) = arm B. There were 78 patients (40.2%) in arm A and 116 patients (59.8%) in arm B. The median age and sex distribution were similar between the treatment arms. The median follow-up period of all patients was 34.4 months (95% confidence interval, 29.1-39.7). When arm A was compared with arm B, 3-year disease-free survival (DFS) was 75.3% versus 88.4% and 5-year DFS was 75.3% versus 82.8%, respectively. There were similar DFS outcomes between the treatment arms (p = 0.09). Rates of any grade of neuropathy were numerically lower in arm A, but the difference between the treatment arms was not statistically significant (51.3% vs. 56.9%; p = 0.44). The frequency of neutropenia was similar between the treatment arms. CONCLUSION: In this study, the efficacy and safety of the 3 months of CAPOX followed by 3 months of capecitabine chemotherapy regimen in the adjuvant treatment of low-risk stage III colon cancer treated surgically were proven. This result may also support the discontinuation of oxaliplatin at 3 months while continuing fluoropyrimidines, which is a common clinical practice but lacks sufficient data.

Enhancing the Anti-angiogenic Effect of Bevacizumab with ACE Inhibition on mCRC.

INTRODUCTION: Angiotensin 2 has been shown to promote angiogenesis through multiple pathways. Reduction of angiotensin 2 production by angiotensin-converting enzyme inhibitors (ACEi) could enhance the antiangiogenic effect of bevacizumab and lead to improved survival. METHODS: Data from metastatic colorectal cancer (mCRC) patients treated with bevacizumab in our hospital were retrospectively collected. Patients were divided into groups taking ACEi or angiotensin receptor blockers (ARB) or neither. We performed survival analysis and COX proportional hazard modelling and calculated the hazard ratio (HR). Multivariate analyses were performed to measure the impact of factors affecting survival, and subgroup analyses were performed for patients younger than 65 years. RESULTS: We enrolled 133 patients who received bevacizumab therapy. Eighty patients were male, and 53 were female. Twenty-three patients received ACEi treatment, and 34 patients received ARB. The median age was 58 years. Progression-free survival was higher in the ACEi group than in the ARB group or in the group receiving neither (7.66 vs. 5.98 vs. 5.0 months; p < 0.01), corresponding to a HR of 0.44 for the ACEi group (95% CI 0.26-0.74). Overall survival was not significantly longer in the ACEi group than in the ARB group or in the group receiving neither (22.0 vs. 23.5 vs. 19.7 months; p = 0.30), HR 0.66 (95% CI 0.38-1.2). In a subgroup analysis, overall survival was higher in patients younger than 65 years in the ACEi group (45.0 vs. 16.2 months; p = 0.02). CONCLUSION: In the final analysis, ACEi use in patients treated with bevacizumab resulted in prolonged progression-free survival, but this did not affect overall survival. Because our study is the first to look at the enhancement of the effect of bevacizumab by ACEi treatment and ACEi receiving patients are older, it would be useful to confirm our results by randomized trials.

Starting of biological disease modifying antirheumatic drugs may be postponed in rheumatoid arthritis patients with multimorbidity: Single center real life results.

The objective of this study was to assess the frequency of comorbidities and multimorbidities in rheumatoid arthritis (RA) patients under biologic therapy and their effects on biological disease modifying antirheumatic drugs (DMARDs) choice, timing, and response.Hacettepe University Biologic Registry (HUR-BIO) is single center biological DMARD registry. Cardiovascular, infectious, cancer, and other comorbidities were recorded with face to face interviews. Multimorbidity is defined as >1 comorbidity. Disease duration, initial date of biological DMARDs, initial and overall biological DMARD choice were recorded. Disease activity score-28 (DAS-28) responses were compared to comorbidity presence and multimorbidity.Total of 998 RA patients were enrolled into the study. The mean age was 53.1 (12.5) and mean disease duration (standard deviation [SD]) was 11.7 (7.5) years. At least 1 comorbidity was detected in 689 (69.1%) patients, 375 (37.9%) patients had multimorbidity. Patients had mean 1.36 ±â€Š1.32 comorbidity. The median durations of first biological DMARDs prescription were 60 (3-552) months after RA diagnosis. For multimorbidity patients, the median first biological prescription duration was longer than the duration for patients without multimorbidity (72 [3-552] vs 60 [3-396] months, P < .001). The physicians prescribe tumor necrosis factor inhibitor (TNFi) biological drugs less frequently than other biological DMARDs in patients with at least 1 comorbidity (66.2% vs 74.5%, P = .007) or multimorbidity (34.6% vs 43.5%, P = .006). Patients with comorbidities and multimorbidity achieved DAS-28 remission less frequently than patients without comorbidity (31.6% vs 42.6%, P = .012 and 27.2% vs 39.7%, P = .001, respectively).In real life, physicians may postpone to prescribe biological DMARDs and less frequently choose TNFi biological drugs in patients with multimorbidity. Furthermore, comorbidity may have a negative effect on the treatment response.