The Use of Generative AI for Scientific Literature Searches for Systematic Reviews: ChatGPT and Microsoft Bing AI Performance Evaluation.

Background: A large language model is a type of artificial intelligence (AI) model that opens up great possibilities for health care practice, research, and education, although scholars have emphasized the need to proactively address the issue of unvalidated and inaccurate information regarding its use. One of the best-known large language models is ChatGPT (OpenAI). It is believed to be of great help to medical research, as it facilitates more efficient data set analysis, code generation, and literature review, allowing researchers to focus on experimental design as well as drug discovery and development. Objective: This study aims to explore the potential of ChatGPT as a real-time literature search tool for systematic reviews and clinical decision support systems, to enhance their efficiency and accuracy in health care settings. Methods: The search results of a published systematic review by human experts on the treatment of Peyronie disease were selected as a benchmark, and the literature search formula of the study was applied to ChatGPT and Microsoft Bing AI as a comparison to human researchers. Peyronie disease typically presents with discomfort, curvature, or deformity of the penis in association with palpable plaques and erectile dysfunction. To evaluate the quality of individual studies derived from AI answers, we created a structured rating system based on bibliographic information related to the publications. We classified its answers into 4 grades if the title existed: A, B, C, and F. No grade was given for a fake title or no answer. Results: From ChatGPT, 7 (0.5%) out of 1287 identified studies were directly relevant, whereas Bing AI resulted in 19 (40%) relevant studies out of 48, compared to the human benchmark of 24 studies. In the qualitative evaluation, ChatGPT had 7 grade A, 18 grade B, 167 grade C, and 211 grade F studies, and Bing AI had 19 grade A and 28 grade C studies. Conclusions: This is the first study to compare AI and conventional human systematic review methods as a real-time literature collection tool for evidence-based medicine. The results suggest that the use of ChatGPT as a tool for real-time evidence generation is not yet accurate and feasible. Therefore, researchers should be cautious about using such AI. The limitations of this study using the generative pre-trained transformer model are that the search for research topics was not diverse and that it did not prevent the hallucination of generative AI. However, this study will serve as a standard for future studies by providing an index to verify the reliability and consistency of generative AI from a user's point of view. If the reliability and consistency of AI literature search services are verified, then the use of these technologies will help medical research greatly.

Neoadjuvant Chemotherapy Prior to Radical Cystectomy for Muscle-Invasive Bladder Cancer With Variant Histology: A Systematic Review and Meta-Analysis of Survival Outcomes and Pathological Features.

PURPOSE: To conduct systematic review and meta-analysis to evaluate effects of neoadjuvant chemotherapy (NAC) on survival and histopathological outcomes of variant histology (VH) of urothelial carcinoma (UC) of bladder. METHODS: This systematic review was registered in PROSPERO (CRD42023389115). Literature search was conducted in PubMed/Medline, Embase, and Cochrane Library for studies published up to January 2023. Population, intervention, comparator, outcome, and study design were as follows: bladder cancer patients with VH (population), neoadjuvant chemotherapy (intervention), radical cystectomy only (comparators), oncological survival and pathologic response (outcomes), and retrospective or prospective (study design). RESULTS: Finally, a total of 17 studies were included in the present study (quantitative analysis, n = 17; qualitative analysis, n = 12). Pooled HR was 0.49 (95% CI: 0.31-0.76; P = .002) for OS. Pooled HR was 0.61 (95% CI: 0.38-0.98; P = .04) for CSS. Pooled HR was 0.44 (95% CI: 0.21-0.93; P = .03) in PFS. Pooled OR was 6.61 (95% CI: 4.50-9.73; P < .00001) in complete pathologic response. Pooled OR was 9.59 (95% CI: 3.56-25.85; P < .00001) in any pathologic response. Evidence quality assessments for each 5 comparisons using the GRADE approach were that Certainty was moderate in 1, low in 1, and very low in 3. CONCLUSIONS: Administration of NAC before surgery in bladder cancer patients with VH might confer better survival outcomes and higher pathologic down staging rate than no administration of NAC before surgery.

Comparing effects of alpha-blocker management on acute urinary retention secondary to benign prostatic hyperplasia: A systematic review and network meta-analysis.

Background: To compare the effects of different alpha-blocker regimes on acute urinary retention (AUR) and the success rate of trial without catheter (TWOC) among patients with AUR secondary to benign prostatic hyperplasia (BPH) to determine the most effective regime. Methods: A comprehensive literature search was performed using PubMed/Medline, Embase, and Cochrane Library up to June 2021. Studies that compared successful TWOC rates between each alpha-blocker regime in patients with AUR secondary to BPH were included. The outcome was the odds ratio of successful TWOC after AUR between groups (each regime of alpha blocker or placebo). To indirectly compare the effect of each alpha-blocker regime on the outcome (successful TWOC rate), a network meta-analysis was conducted using a Bayesian hierarchical random effects model for dichotomous outcomes. Results: In total, 13 randomized controlled trials were included in the present study. There were six nodes (five alpha-blocker regimes and placebo) and eight comparisons in the evidence network plot. Compared to placebo, alfuzosin, silodosin, tamsulosin, and alfuzosin plus tamsulosin resulted in significantly higher TWOC success rates, whereas doxazosin did not show a significant difference in TWOC success rate compared to placebo. Alfuzosin plus tamsulosin was ranked first, followed in order by tamsulosin, silodosin, alfuzosin, and doxazosin. There was no significant inconsistency in the results of this analysis. Conclusions: Alpha blockers may increase the success rate of TWOC. This study evaluated the priority of the effect of several alpha-blocker regimens on AUR related to BPH, which is expected to be helpful in selecting the best medication for patients with AUR.

Long-term end-stage renal disease risks after living kidney donation: a systematic review and meta-analysis.

BACKGROUND: Recent studies have shown that donor nephrectomy can induce renal function impairment. However, few meta-analysis studies about this have proceeded. Therefore, the objective of this systematic review and meta-analysis including all data of recent research studies was to determine whether living donor nephrectomy (LDN) could induce renal function impairment. METHODS: By November 2020, comprehensive literature searches were performed on PubMed, Embase, and Cochrane databases. Inclusion criteria were: (1) observational studies with data about overall end-stage renal disease (ESRD) or chronic kidney disease (CKD) of living kidney donors, (2) control group consisted of people without donor nephrectomy, and (3) outcomes of studies included long-term end-stage renal disease risks after living kidney donation. Risk of Bias in Non-randomized Studies of interventions (ROBINS-I) assessment tool was used to evaluate our methodological quality. RESULTS: The qualitative review included 11 studies and the meta-analysis included 5 studies. In the meta-analysis, the integrated overall ESRD risk was 5.57 (95% CI: 2.03-15.30). Regarding the overall risk of bias using ROBINS-I assessment tool, 0 studies was rated as "Low", 7 studies were rated as "moderate", 2 studies were rated as "Serious", and two studies were rated as "Critical". CONCLUSIONS: Our study showed that LDN increased ESRD risk in LDN patients. However, in our meta-analysis, variables in included studies were not uniform and the number of included studies was small. To have a definite conclusion, meta-analyses of well-planned and detailed studies need to be conducted in the future.

Efficacy of pelvic floor muscle exercise or therapy with or without duloxetine: a systematic review and network Meta-analysis.

OBJECTIVES: Postprostatectomy urinary incontinence (PPUI) is a serious complication despite surgical advances. Treatment options for PPUI include conservative care like Pelvic floor muscle exercise (PFME), which is a physiotherapy performed by the patients themselves; Pelvic floor muscle therapy (PFMT), a physiotherapy performed under the guidance of a therapist, and duloxetine treatment; and surgical interventions. In this study, network meta-analysis (NMA) was performed for direct comparison of these treatment options. MATERIALS AND METHODS: The NMA pooled the odds ratios and 95% credible intervals using the number of patients achieving urinary continence and the total number of patients in an intention-to-treat population. The treatments were ranked based on the surface under the cumulative ranking curve (SUCRA) probabilities and the rankograms. RESULTS: The pooled overall ORs of patients achieving urinary continence compared with no treatment was 1.73 (95% CrI: 0.657, 4.71) in PFME, 2.62 (95% CrI: 0.553, 13.5) in PFME plus Duloxetine, and 4.05 (95% CrI: 1.70, 10.2) in PFMT. The SUCRA values of ranking probabilities for each treatment showed high rates of continence in the order of PFMT, PFME plus Duloxetine, and PFME. CONCLUSION: The results suggest that patients with PPUI should undergo PFMT and consider duloxetine as an additional treatment option.

Microbiome in Bladder Cancer: A Systematic Review.

Although many studies on bladder cancer and the microbiome have been conducted so far, useful strains at the species level have not yet been identified. In addition, in the case of urine studies, methodological heterogeneity is too great, and in tissue studies, the species level through shotgun analysis has not been revealed, and studies using stool samples have provided only limited information. In this review, we will review all the microbiome studies related to bladder cancer so far through a systematic review.