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.

Current updates relating to treatment for interstitial cystitis/bladder pain syndrome: systematic review and network meta-analysis.

BACKGROUND: Despite the publication of several meta-analyses regarding the efficacy of certain therapies in helping individuals with interstitial cystitis (IC) / bladder pain syndrome (BPS), these have not provided a comprehensive review of therapeutic strategies. The study aimed to determine the efficacy of various therapies for IC/BPS and identify potential moderating factors using randomized controlled trials (RCTs). METHODS: We queried the PubMed, Cochrane, and Embase databases to identify prospective RCTs using inclusion criteria: 1) patients diagnosed with IC, 2) interventions included relevant treatments, 3) comparisons were a specified control or placebo, 4) outcomes were mean differences for individual symptoms and structured questionnaires. The pairwise meta-analysis and network meta-analysis (NMA) were performed to compare the treatments used in IC/BPS. Hedges' g standardized mean differences (SMDs) were used for improvement in all outcomes using random-effects models. Efficacy outcomes included individual symptoms such as pain, frequency, urgency, and nocturia, as well as structured questionnaires measuring IC/BPS symptoms. RESULTS: A comprehensive literature search was conducted which identified 70 RCTs with 3,651 patients. The analysis revealed that certain treatments, such as instillation and intravesical injection, showed statistically significant improvements in pain and urgency compared to control or placebo groups in traditional pairwise meta-analysis. However, no specific treatment demonstrated significant improvement in all outcomes measured in the NMA. The results of moderator analyses to explore influential variables indicated that increasing age was associated with increased nocturia, while longer follow-up periods were associated with decreased frequency. CONCLUSION: This systematic review and meta-analysis provide insights into the efficacy of various treatments for IC. Current research suggests that a combination of therapies may have a positive clinical outcome for patients with IC, despite the fact that treatment for this condition is not straightforward. TRIAL REGISTRATION: PROSPERO CRD42022384024.

Effect of cannabidiol on apoptosis and cellular interferon and interferon-stimulated gene responses to the SARS-CoV-2 genes ORF8, ORF10 and M protein.

AIMS: To study effects on cellular innate immune responses to ORF8, ORF10, and Membrane protein (M protein) from the Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that causes COVID-19, in combination with cannabidiol (CBD). MAIN METHODS: HEK293 cells transfected with plasmids expressing control vector, ORF8, ORF10, or M protein were assayed for cell number and markers of apoptosis at 24 h, and interferon and interferon-stimulated gene expression at 14 h, with or without CBD. Cells transfected with polyinosinic:polycytidylic acid (Poly (I:C)) were also studied as a general model of RNA-type viral infection. KEY FINDINGS: Reduced cell number and increased early and late apoptosis were found when expression of viral genes was combined with 1-2 µM CBD treatment, but not in control-transfected cells treated with CBD, or in cells expressing viral genes but treated only with vehicle. In cells expressing viral genes, CBD augmented expression of IFNγ, IFNλ1 and IFNλ2/3, as well as the 2'-5'-oligoadenylate synthetase (OAS) family members OAS1, OAS2, OAS3, and OASL. CBD also augmented expression of these genes in control cells not expressing viral genes, but without enhancing apoptosis. CBD similarly enhanced the cellular anti-viral response to Poly (I:C). SIGNIFICANCE: Our results demonstrate a poor ability of HEK293 cells to respond to SARS-CoV-2 genes alone, but an augmented innate anti-viral response to these genes in the presence of CBD. Thus, CBD may prime components of the innate immune system, increasing readiness to respond to RNA-type viral infection without activating apoptosis, and could be studied for potential in prophylaxis.

Effect of cannabidiol on apoptosis and cellular interferon and interferon-stimulated gene responses to the SARS-CoV-2 genes ORF8, ORF10 and M protein

AimsTo study effects on cellular innate immune responses to novel genes ORF8 and ORF10, and the more conserved Membrane protein (M protein) from the Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that causes COVID-19, either alone, or in combination with cannabidiol (CBD). Main MethodsHEK293 cells were transfected with a control plasmid, or plasmids expressing ORF8, ORF10, or M protein, and assayed for cell number and markers of apoptosis at 24 h, and expression of interferon and interferon-stimulated genes at 14 h. Key findingsA significant reduction in cell number, and increase in early and late apoptosis, was found after 24 h in cells where expression of viral genes was combined with 1-2 M CBD treatment, but not in control-transfected cells treated with CBD, or in cells expressing viral genes but treated only with vehicle. CBD (2 M) augmented expression of IFN{gamma}, IFN{lambda}1 and IFN{lambda}2/3, as well as the 2-5-oligoadenylate synthetase (OAS) family members OAS1, OAS2, OAS3, and OASL, in cells expressing ORF8, ORF10, and M protein. CBD also augmented expression of these genes in control cells not expressing viral genes, without enhancing apoptosis. SignificanceOur results demonstrate a poor ability of HEK293 cells to respond to SARS-CoV-2 genes alone, but suggest an augmented innate anti-viral response to these genes in the presence of CBD. Furthermore, our results indicate that CBD may prime components of the innate immune system, increasing readiness to respond to viral infection without activating apoptosis, and therefore could be studied for potential in prophylaxis.