Evaluation of artificial intelligence-generated drug therapy communication skill competencies in medical education.

AIMS: This study compared three artificial intelligence (AI) platforms' potential to identify drug therapy communication competencies expected of a graduating medical doctor. METHODS: We presented three AI platforms, namely, Poe Assistant©, ChatGPT© and Google Bard©, with structured queries to generate communication skill competencies and case scenarios appropriate for graduating medical doctors. These case scenarios comprised 15 prototypical medical conditions that required drug prescriptions. Two authors independently evaluated the AI-enhanced clinical encounters, which integrated a diverse range of information to create patient-centred care plans. Through a consensus-based approach using a checklist, the communication components generated for each scenario were assessed. The instructions and warnings provided for each case scenario were evaluated by referencing the British National Formulary. RESULTS: AI platforms demonstrated overlap in competency domains generated, albeit with variations in wording. The domains of knowledge (basic and clinical pharmacology, prescribing, communication and drug safety) were unanimously recognized by all platforms. A broad consensus among Poe Assistant© and ChatGPT© on drug therapy-related communication issues specific to each case scenario was evident. The consensus primarily encompassed salutation, generic drug prescribed, treatment goals and follow-up schedules. Differences were observed in patient instruction clarity, listed side effects, warnings and patient empowerment. Google Bard did not provide guidance on patient communication issues. CONCLUSIONS: AI platforms recognized competencies with variations in how these were stated. Poe Assistant© and ChatGPT© exhibited alignment of communication issues. However, significant discrepancies were observed in specific skill components, indicating the necessity of human intervention to critically evaluate AI-generated outputs.

Risk of limb amputation and bone fractures with sodium glucose cotransporter-2 inhibitors: a network meta-analysis and meta-regression.

BACKGROUND: Sodium glucose cotransporter-2 inhibitors (SGLT2is) have gained immense attention for a variety of indications. Limb amputations (LA) and fractures were reported in clinical trials. This network meta-analysis and meta-regression were carried out to quantify the risks of these events. RESEARCH DESIGN AND METHODS: Randomized clinical trials evaluating SGLT2is and reporting patients developing LA/fracture were included. Odds ratios (OR) with 95% confidence intervals (95% CI) were the effect estimates. Sub-group analyses and meta-regression analysis were carried out. RESULTS: Ninety articles were included (LA: 36 studies; 96522 participants and fracture: 66 studies; 102,862 participants). An increased risk of LA (OR: 1.2; 95% CI: 1.1, 1.3) was observed. Amongst SGLT2is, canagliflozin was associated with increased risk of LA (OR: 1.6, 95% CI: 1.1, 2.4) while dapagliflozin with fracture (OR: 1.1, 95% CI: 1, 1.2). Sub-group analysis revealed increased risk of LA with an OR of 1.3 among those in the age group of > 40 to < 65, body-mass index of > 30 kg/m2, HbA1c category of > 7%, duration of diabetes of > 10 years, type 2 diabetes, and an OR of 1.2 for SGLT2is administration of > 6 months. CONCLUSIONS: SGLT2is were observed with an increased risk of LA. High- risk categories were identified for which precautions should be recommended in the standard treatment guidelines. PROTOCOL REGISTRATION: Open Science Framework (https://osf.io/5fwyk).

Enhancing readability of USFDA patient communications through large language models: a proof-of-concept study.

BACKGROUND: The US Food and Drug Administration (USFDA) communicates new drug safety concerns through drug safety communications (DSCs) and medication guides (MGs), which often challenge patients with average reading abilities due to their complexity. This study assesses whether large language models (LLMs) can enhance the readability of these materials. METHODS: We analyzed the latest DSCs and MGs, using ChatGPT 4.0© and Gemini© to simplify them to a sixth-grade reading level. Outputs were evaluated for readability, technical accuracy, and content inclusiveness. RESULTS: Original materials were difficult to read (DSCs grade level 13, MGs 22). LLMs significantly improved readability, reducing the grade levels to more accessible readings (Single prompt - DSCs: ChatGPT 4.0© 10.1, Gemini© 8; MGs: ChatGPT 4.0© 7.1, Gemini© 6.5. Multiple prompts - DSCs: ChatGPT 4.0© 10.3, Gemini© 7.5; MGs: ChatGPT 4.0© 8, Gemini© 6.8). LLM outputs retained technical accuracy and key messages. CONCLUSION: LLMs can significantly simplify complex health-related information, making it more accessible to patients. Future research should extend these findings to other languages and patient groups in real-world settings.

Retrospective Tertiary Care-Based Cohort Study on Clinical Characteristics and Outcomes of Ceftazidime-Avibactam-Resistant Carbapenem-Resistant Klebsiella pneumoniae Infections.

Introduction: The advent of ceftazidime-avibactam (CAZ-AVI)-resistant carbapenem-resistant Klebsiella pneumoniae (CRKP) isolates has been steadily documented in recent years. We aimed to identify risk factors of CAZ-AVI-resistant CRKP infection and assess clinical outcomes of patients. Methods: The study retrospectively examined the clinical and microbiological data of patients with ceftazidime avibactam susceptible and ceftazidime avibactam-resistant Klebsiella pneumonia carbapenem-resistant enterobacteriaceae infection to identify risk factors, clinical features, and outcomes using multivariate logistic regression analysis. Results: A total of 152 patients with CRKP infection were enrolled in this study. Patients with CAZ-AVI-resistant CRKP isolates (20/34 = 58.8%) had prior exposure to carbapenems (p=0.003) and had more tracheostomies (16/34 = 47.1%) (p=0.001). Only 8/28 (28.6%) patients with CAZ-AVI susceptible CRKP isolates died amongst those administered ceftazidime-avibactam compared to 49/90 (54.4%) who did not receive the same (p=0.016). 1/9 (11.1%) patients with CAZ-AVI-resistant CRKP isolates who received colistin died compared to 13/25 (52%) who did not receive colistin (p=0.03). There was no association between presence of CAZ-AVI-resistant CRKP isolates and overall mortality (odds ratio: 0.7; 95% CI: 0.3, 1.6), and no independent predictors of risk factors to overall mortality in the group with CAZ-AVI-resistant CRKP isolates were noted. Conclusion: Early advent of CAZ-AVI resistance in CRE isolates highlights the dynamic necessity of routine CAZ-AVI resistance laboratory testing and antimicrobial stewardship programmes focusing on the utilization of all antibiotics. Consolidating the hospital infection control of tracheostomies may help to prevent CAZ resistance in CRKP. Colistin may aid in decreasing of mortality rates among patients with CAZ-AVI CRKP isolates.

Assessing the Decision-Making Capabilities of Artificial Intelligence Platforms as Institutional Review Board Members.

Background: Institutional review boards (IRBs) face delays in reviewing research proposals, underscoring the need for optimized standard operating procedures (SOPs). This study assesses the abilities of three artificial intelligence (AI) platforms to address IRB challenges and draft essential SOPs. Methods: An observational study was conducted using three AI platforms in 10 case studies reflecting IRB functions, focusing on creating SOPs. The accuracy of the AI outputs was assessed against good clinical practice (GCP) guidelines. Results: The AI tools identified GCP issues, offered guidance on GCP violations, detected conflicts of interest and SOP deficiencies, recognized vulnerable populations, and suggested expedited review criteria. They also drafted SOPs with some differences. Conclusion: AI platforms could aid IRB decision-making and improve review efficiency. However, human oversight remains critical for ensuring the accuracy of AI-generated solutions.

Genito-urinary infectious adverse events related to sodium glucose cotransporter-2 inhibitors: a network meta-analysis and meta-regression.

INTRODUCTION: Sodium glucose cotransporter-2 inhibitors (SGLT2is) are an emerging class of drugs with wide indications. Controversial evidence exists regarding the risk of urinary tract infection (UTI) and genital infections (GI) with SGLT2is paving way for undertaking this network meta-analysis and meta-regression study. METHODS: Data from randomized trials evaluating SGLT2is reporting the number of patients with UTI and GI were included. Odds ratios (OR) with 95% confidence intervals (95% CI) were the effect estimates. Meta-regression analysis identified risk factors. Number needed to harm (NNH) was estimated. RESULTS: Two hundred and sixty-four articles were included [UTI (213 studies; 150,140 participants) and GI (188 studies; 121,275 participants)]. An increased risk of UTI (OR: 1.11; 95% CI: 1.06, 1.16) and GI (OR: 3.5, 95% CI: 3.1, 3.9) was observed. Men showed a lower risk of UTI (OR: 0.2; 95% CI: 0.2, 0.3) and GI (OR: 0.4; 95% CI: 0.4, 0.5). Meta-regression analyses revealed BMI ≥ 30 kg/m2 and duration of SGLT2i treatment for ≥6 months as risk factors. NNH was 16 for UTI and 25 for GI. CONCLUSION: SGLT2is increase the risk of UTI and GI that needs to be incorporated in the treatment guidelines with precautions in high-risk patients. PROSPECTIVE PROTOCOL REGISTRATION: https://osf.io/5fwyk.

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study.

BACKGROUND: Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process. METHODS: In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students. RESULTS: Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom's taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner's stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner's stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined. CONCLUSIONS: AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners' stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Intraclass comparison of inhaled corticosteroids for the risk of pneumonia in chronic obstructive pulmonary airway disorder: a network meta-analysis and meta-regression.

BACKGROUND: Inhalational corticosteroids (ICS) were observed to increase the pneumonia risk in chronic obstructive pulmonary airway disorder (COPD). However, it is unknown whether any differences exist between the drugs within the ICS class. AIM: This study aimed to evaluate the risk of pneumonia associated with different ICS and identify factors that predict pneumonia in patients with moderate-to-severe COPD using a network meta-analysis. METHOD: Electronic databases (Medline, Cochrane CENTRAL and Google Scholar) were searched for trials comparing ICS in COPD patients. The outcomes were pneumonia and serious pneumonia. Odds ratios (OR) with 95% confidence interval (95% CI) were estimated. Meta-regression was used to identify the predictors. The strength of evidence was graded using the Grading of Recommendations, Assessment, Development, and Evaluations approach. RESULTS: Sixty-six studies (103,347 participants) were included. Fluticasone (OR: 1.46; 95% CI: 1.26, 1.7), mometasone (OR: 2.2; 95% CI: 1.05, 4.6), and beclometasone (OR: 1.7; 95% CI: 1.1, 2.6) were observed with an increased pneumonia risk compared to placebo. Fluticasone (OR: 1.5; 95% CI: 1.3, 1.7) was observed with an increased risk of serious pneumonia. High doses (OR: 1.2; 95% CI: 1.03, 1.4), BMI ≥ 25 kg/m2 (OR: 1.6; 95% CI: 1.1, 2.2), and history of exacerbations in the preceding year predicted the pneumonia risk. Evidence strength was moderate. CONCLUSION: ICS class differences in pneumonia risk were observed in terms of pooled effect estimates but it is unlikely that any clinically relevant differences exist. Risk-benefit analysis supports ICS use in moderate-severe COPD.

Correlations between serum kidney injury molecule-1, cystatin C and immunosuppressants: A cross-sectional study of renal transplant patients in Bahrain.

Renal transplant patients receive several immunosuppressive drug regimens that are potentially nephrotoxic for treatment. Serum creatinine is the standard for monitoring kidney function; however, cystatin C (Cys C) and kidney injury molecule-1 (KIM-1) have been found to indicate kidney injury earlier than serum creatinine and provide a better reflection of kidney function. Here, we assessed Cys C and KIM-1 serum levels in renal transplant patients receiving mycophenolate mofetil, tacrolimus, sirolimus, everolimus, or cyclosporine to evaluate kidney function. We used both the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) 2021 equation, which is based on creatinine and combined creatinine with Cys C, and the CKD-EPI 2012 equation, which is based on Cys C alone, to estimate glomerular filtration rate (GFR). Then, we assessed the association between serum KIM-1 and GFR < 90 mL per minute per 1.73 m 2. We observed significantly higher serum Cys C levels in patients with the elevated serum creatinine, compared with those with normal serum creatinine. The estimated GFRs based on creatinine were significantly higher than those based on the other equations, while a significant positive correlation was observed among all equations. Serum KIM-1 levels were negatively correlated with the estimated GFRs by the CKD-EPI Cys C and the combined creatinine with Cys C equations. A serum KIM-1 level above 0.71 ng/mL is likely to indicate GFR < 90 mL per minute per 1.73 m 2. We observed a significant correlation between serum creatinine and Cys C in our renal transplant patients. Therefore, serum KIM-1 may be used to monitor renal function when using potentially nephrotoxic drugs in renal transplants.

Comparative Analysis of Machine Learning Algorithms Evaluating the Single Nucleotide Polymorphisms of Metabolizing Enzymes with Clinical Outcomes Following Intravenous Paracetamol in Preterm Neonates with Patent Ductus Arteriosus.

AIMS: Pharmacogenomics has been identified to play a crucial role in determining drug response. The present study aimed to identify significant genetic predictor variables influencing the therapeutic effect of paracetamol for new indications in preterm neonates. BACKGROUND: Paracetamol has recently been preferred as a first-line drug for managing Patent Ductus Arteriosus (PDA) in preterm neonates. Single Nucleotide Polymorphisms (SNPs) in CYP1A2, CYP2A6, CYP2D6, CYP2E1, and CYP3A4 have been observed to influence the therapeutic concentrations of paracetamol. OBJECTIVES: The purpose of this study was to evaluate various Machine Learning Algorithms (MLAs) and bioinformatics tools for identifying the key genotype predictor of therapeutic outcomes following paracetamol administration in neonates with PDA. METHODS: Preterm neonates with hemodynamically significant PDA were recruited in this prospective, observational study. The following SNPs were evaluated: CYP2E1*5B, CYP2E1*2, CYP3A4*1B, CYP3A4*2, CYP3A4*3, CYP3A5*3, CYP3A5*7, CYP3A5*11, CYP1A2*1C, CYP1A2*1K, CYP1A2*3, CYP1A2*4, CYP1A2*6, and CYP2D6*10. Amongst the MLAs, Artificial Neural Network (ANN), C5.0 algorithm, Classification and Regression Tree analysis (CART), discriminant analysis, and logistic regression were evaluated for successful closure of PDA. Generalized linear regression, ANN, CART, and linear regression were used to evaluate maximum serum acetaminophen concentrations. A two-step cluster analysis was carried out for both outcomes. Area Under the Curve (AUC) and Relative Error (RE) were used as the accuracy estimates. Stability analysis was carried out using in silico tools, and Molecular Docking Studies (MDS) were carried out for the above-mentioned enzymes. RESULTS: Two-step cluster analyses have revealed CYP2D6*10 and CYP1A2*1C to be the key predictors of the successful closure of PDA and the maximum serum paracetamol concentrations in neonates. The ANN was observed with the maximum accuracy (AUC = 0.53) for predicting the successful closure of PDA with CYP2D6*10 as the most important predictor. Similarly, ANN was observed with the least RE (1.08) in predicting maximum serum paracetamol concentrations, with CYP2D6*10 as the most important predictor. Further MDS confirmed the conformational changes for P34A and P34S compared to the wildtype structure of CYP2D6 protein for stability, flexibility, compactness, hydrogen bond analysis, and the binding affinity when interacting with paracetamol, respectively. The alterations in enzyme activity of the mutant CYP2D6 were computed from the molecular simulation results. CONCLUSION: We have identified CYP2D6*10 and CYP1A2*1C polymorphisms to significantly predict the therapeutic outcomes following the administration of paracetamol in preterm neonates with PDA. Prospective studies are required for confirmation of the findings in the vulnerable population.

Unraveling the Role of COMT Polymorphism in Dopamine-Mediated Vasopressor Effects: An Observational Cross-Sectional Study.

AIMS: To evaluate the association between rs4680 polymorphism in the COMT gene and the vasoconstrictive effects of commonly used vasopressors. BACKGROUND: Dopamine is a medication that is given intravenously to critically ill patients to help increase blood pressure. Catechol O-Methyl Transferase (COMT) breaks down dopamine and other catecholamines. There is a genetic variation in the COMT gene called rs4680 that can affect how well the enzyme works. Studies have shown that people with this genetic variation may have different blood pressure levels. However, no one has looked at how this genetic variation affects the way dopamine works to increase blood pressure. OBJECTIVES: To investigate the impact of the rs4680 polymorphism in the COMT gene on the pharmacodynamic response to dopamine. METHODS: Critically ill patients administered dopamine were included following the consent of their legally acceptable representatives. Details on their demographic characteristics, diagnosis, drug-related details, changes in the heart rate, blood pressure, and urinary output were obtained. The presence of rs4680 polymorphism in the COMT gene was evaluated using a validated method. RESULTS: One hundred and seventeen patients were recruited, and we observed a prevalence of rs4680 polymorphism in 57.3% of our critically ill patients. Those with mutant genotypes were observed with an increase in the median rate of change in mean arterial pressure (mm Hg/hour) [wild: 8.9 (-22.6 to 49.1); heterozygous mutant: 5.9 (-34.1 to 61.6); and homozygous mutant: 19.5 (-2.5 to 129.2)] and lowered urine output (ml/day) [wild: 1080 (21.4 to 5900); heterozygous mutant: 380 (23.7 to 15800); and homozygous mutant: 316.7 (5.8 to 2308.3)]. CONCLUSION: V158M (rs4680) polymorphism is widely prevalent in the population and was significantly associated with altered effects as observed clinically. This finding suggests valuable insights into the molecular basis of COMT function and its potential impact on neurotransmitter metabolism and related disorders. Large-scale studies delineating the effect of these polymorphisms on various vasopressors are the need of the hour.

Risk of Diabetic Ketoacidosis Associated with Sodium Glucose Cotransporter-2 Inhibitors: A Network Meta-Analysis and Meta-Regression.

Background: Sodium glucose cotransporter-2 inhibitors (SGLT2is) represent an emerging class of drugs with diverse indications. Despite their therapeutic potential, concerns regarding safety, particularly diabetic ketoacidosis (DKA), remain contentious, with uncertainty regarding differences among various SGLT2is. This study aimed to conduct a network meta-analysis and meta-regression to evaluate the risk of SGLT2i-induced DKA and associated factors. Methods: We systematically searched electronic databases for randomized clinical trials assessing SGLT2is across indications, reporting incidences of DKA. Mixed treatment comparison pooled estimates (MTCPEs) were calculated, and odds ratios (OR) with 95% confidence intervals (95% CI) served as effect estimates. We analyzed differences across dose categories (low, medium, and high) and conducted a meta-regression analysis to identify risk factors. The strength of evidence for key comparisons was determined. Results: Our analysis included 73 articles encompassing 85,997 participants assessing the risk of DKA. SGLT2is were associated with a heightened risk of DKA compared to placebo/control interventions (OR: 1.83; 95% CI: 1.35, 2.46), a finding confirmed by bootstrap analysis. Among SGLT2is, dapagliflozin (OR: 1.9; 95% CI: 1.17, 3.08), sotagliflozin (OR: 1.93; 95% CI: 1.14, 3.25), canagliflozin (OR: 1.11; 95% CI: 1.11, 12.45), and ertugliflozin (OR: 3.92; 95% CI: 1.04, 14.77) exhibited increased DKA risk. No significant differences were observed among specific SGLT2is. Sub-group analyses revealed a high risk of DKA with low (OR: 1.98; 95% CI: 1.3, 2.95) and high doses (OR: 2.4; 95% CI: 1.7, 3.3), type 1 diabetes (OR: 3.6; 95% CI: 1.6, 8.1), type 2 diabetes (OR: 1.6; 95% CI: 1.3, 2.4), as well as a diabetes duration exceeding 10 years (OR: 3.4; 95% CI: 1.1, 10.8). The evidence of certainty for most comparisons was moderate. Conclusions: SGLT2 inhibitors (SGLT2is) have been found to elevate the risk of DKA. The key factors that significantly predict the likelihood of DKA include the presence of diabetes (whether T1D or T2D) and the duration of diabetes. Based on these findings, standard treatment guidelines should advise taking specific precautions against DKA in patients identified as high-risk.

Assessment of drug utilization and potentially inappropriate medications in hemodialysis patients with end-stage renal dysfunction: A study in a tertiary care hospital in Bahrain.

BACKGROUND: Patients undergoing dialysis pose therapeutic challenges in terms of polypharmacy, administration of potentially inappropriate drugs, and drugs with the potential risk of toxicity. OBJECTIVE: This study evaluated the use of drugs, potentially inappropriate medicines (PIM), drugs with risk of Torsades de Pointes (TdP), and the complexity of the prescribed regimen using the medication regimen complexity index scale in patients undergoing hemodialysis. METHODS: A retrospective cohort study was carried out amongst patients receiving hemodialysis. Drugs were classified into one of four classes: (i) drugs used in managing renal complications, (ii) cardiovascular drugs, (iii) anti-diabetic drugs, (iv) drugs for symptomatic management, and (v) others. Drugs were considered as PIM according to the Can-SOLVE CKD working group from a network of Canadian nephrology health professionals. The study adhered to the CredibleMeds classification of drugs with known, possible, and conditional risk of TdP and the complexity of prescribed medicines was evaluated based on the pre-validated medication regimen complexity index scale based on form/route, frequency of dosing, and requirement of special instructions. RESULTS: Sixty-three participants were included in the study (49 males and 14 females) with the median (range) age of 45 (21-66) years. Cardiovascular drugs followed by drugs used for managing renal complications were the most common classes administered. Notably, 12 (19.1%) patients received one of the non-steroidal anti-inflammatory drugs, 21 (33.3%) received a proton pump inhibitor, three (4.8%) received pregabalin, two (3.2%) received opioid drugs, and one (1.6%) was administered celecoxib. Atorvastatin, furosemide, omeprazole, and allopurinol were the most common PIM drugs administered to the study participants followed by others. Drugs used for symptomatic management had significantly more PIM compared to other classes (p < 0.0001). Six (9.5%) patients received drugs with known TdP risk, one with possible TdP risk, and 61 with conditional risk. Median (range) medical regimen complexity index score was 26.5 (2-62.5). CONCLUSION: A huge burden of drug therapy was observed in the hemodialysis patients in terms of higher proportions of PIM, complex medical regimen, and prescription of drugs with risk of TdP. Implementation of clinical decision support tools enhancing rational prescription and identification of drugs with TdP risk, introducing antimicrobial stewardship, and stepwise deprescription of the drugs with the least benefit-risk ratio are warranted.

Leveraging artificial intelligence to detect ethical concerns in medical research: a case study.

BACKGROUND: Institutional review boards (IRBs) have been criticised for delays in approvals for research proposals due to inadequate or inexperienced IRB staff. Artificial intelligence (AI), particularly large language models (LLMs), has significant potential to assist IRB members in a prompt and efficient reviewing process. METHODS: Four LLMs were evaluated on whether they could identify potential ethical issues in seven validated case studies. The LLMs were prompted with queries related to the proposed eligibility criteria of the study participants, vulnerability issues, information to be disclosed in the informed consent document (ICD), risk-benefit assessment and justification of the use of a placebo. Another query was issued to the LLMs to generate ICDs for these case scenarios. RESULTS: All four LLMs were able to provide answers to the queries related to all seven cases. In general, the responses were homogeneous with respect to most elements. LLMs performed suboptimally in identifying the suitability of the placebo arm, risk mitigation strategies and potential risks to study participants in certain case studies with a single prompt. However, multiple prompts led to better outputs in all of these domains. Each of the LLMs included all of the fundamental elements of the ICD for all case scenarios. Use of jargon, understatement of benefits and failure to state potential risks were the key observations in the AI-generated ICD. CONCLUSION: It is likely that LLMs can enhance the identification of potential ethical issues in clinical research, and they can be used as an adjunct tool to prescreen research proposals and enhance the efficiency of an IRB.

Prognostic variables predict clinical outcome after decompressive craniectomy: A single institute experience; A retrospective study.

Decompressive craniectomy (DC) is a well-established neurosurgical intervention in patients with high intracranial pressure who fail to respond to medical treatment. Data on predictive factors for functional outcomes in patients with DC who have malignant middle cerebral artery (MCA) infarction as opposed to intracranial hemorrhage (ICH) are scarce. Eighty-four patients who underwent DC treatment for ICH and malignant MCA infarction were examined. All patients underwent surgery in the Bahrain Salmaniya Medical Complex Neurosurgery Unit between January 2017 and June 2021. To determine whether any of these demonstrated a link to the functional outcome, radiographic factors were compared with clinical data. The postsurgical midline shift (MLS) (ICH group) showed the strongest correlation (ρ = 0.434; P = .006), as in the MCA infarction group as well (ρ = 0.46; P = .005). Further analyses using binary logistic regression with postsurgical basal cistern status and ∆ MLS, and it was observed to be statistically significant (odds ratios: 0.067, 95% CI: 0.007, 0.67; P = .021). The initial Glasgow coma scale, postsurgical MLS, basal cistern status, and ∆ are Measurable variables that can be used to predict outcomes in the groups with ICH and MCA infarction.

Evaluation of Supervised Machine Learning Algorithms and Computational Structural Validation of Single Nucleotide Polymorphisms Related to Acute Liver Injury with Paracetamol.

AIMS: To identify single nucleotide polymorphisms (SNPs) of paracetamol-metabolizing enzymes that can predict acute liver injury. BACKGROUND: Paracetamol is a commonly administered analgesic/antipyretic in critically ill and chronic renal failure patients and several SNPs influence the therapeutic and toxic effects. OBJECTIVE: To evaluate the role of machine learning algorithms (MLAs) and bioinformatics tools to delineate the predictor SNPs as well as to understand their molecular dynamics. METHODS: A cross-sectional study was undertaken by recruiting critically ill patients with chronic renal failure and administering intravenous paracetamol as a standard of care. Serum concentrations of paracetamol and the principal metabolites were estimated. Following SNPs were evaluated: CYP2E1*2, CYP2E1_-1295G>C, CYP2D6*10, CYP3A4*1B, CYP3A4*2, CYP1A2*1K, CYP1A2*6, CYP3A4*3, and CYP3A5*7. MLAs were used to identify the predictor genetic variable for acute liver failure. Bioinformatics tools such as Predict SNP2 and molecular docking (MD) were undertaken to evaluate the impact of the above SNPs with binding affinity to paracetamol. RESULTS: CYP2E1*2 and CYP1A2*1C genotypes were identified by MLAs to significantly predict hepatotoxicity. The predictSNP2 revealed that CYP1A2*3 was highly deleterious in all the tools. MD revealed binding energy of -5.5 Kcal/mol, -6.9 Kcal/mol, and -6.8 Kcal/mol for CYP1A2, CYP1A2*3, and CYP1A2*6 against paracetamol. MD simulations revealed that CYP1A2*3 and CYP1A2*6 missense variants in CYP1A2 affect the binding ability with paracetamol. In-silico techniques found that CYP1A2*2 and CYP1A2*6 are highly harmful. MD simulations revealed CYP3A4*2 (A>G) had decreased binding energy with paracetamol than CYP3A4, and CYP3A4*2(A>T) and CYP3A4*3 both have greater binding energy with paracetamol. CONCLUSION: Polymorphisms in CYP2E1, CYP1A2, CYP3A4, and CYP3A5 significantly influence paracetamol's clinical outcomes or binding affinity. Robust clinical studies are needed to identify these polymorphisms' clinical impact on the pharmacokinetics or pharmacodynamics of paracetamol.

Indications, success, and adverse event rates of pediatric endoscopic retrograde cholangiopancreatography (ERCP): a systematic review and meta-analysis.

BACKGROUND: To improve knowledge on endoscopic retrograde cholangiopancreatography (ERCP) in children, we aimed to study the proportion of indications, success rate and complication of ERCP. METHODS: We performed a systematic search of all articles published up to December 2022 in the following databases: Cochrane Library, PubMed (MEDLINE) and Scopus. The meta-analysis was performed using a random-effects model. Heterogeneity was determined by the I2 statistics and the Cochrane Q test. The included data were analyzed to identify the proportion of indications, success rate and complications of ERCP in children. RESULTS: Based on data from 52 studies with a total of 5624 participants, the most common indications for ERCP in children were biliary [48% (95% CI: 0.40 - 0.57; I2 = 98.17%, P < 0.001)] and both biliary and pancreatic [41% (95% CI: 0.33 - 0.49; I2 = 98.27%, P < 0.001)]. The success rate of ERCP was 95% (95% CI: 0.94 - 0.96; I2 = 82.53%, P < 0.001) with the overall complication rate of 7% (95% CI: 0.05 - 0.09; I2 = 82.06%, P < 0.001). The pooled estimate for the incidence of post ERCP pancreatitis was 4% (95% CI: 0.03 - 0.06; I2 = 85.46%, P < 0.001) and the bleeding was 0% (95% CI: 0.0 - 0.0; I2 = 28.21%, P = 0.03). CONCLUSIONS: ERCP appears to be performed safely in children with a similar success rate as in the adult population.

Gentamicin in Neonates with Hemodynamically Significant Patent Ductus Arteriosus.

Background: Gentamicin has been shown to cause vasodilation in preclinical studies. Hemodynamically significant patent ductus arteriosus (hsPDA) is a commonly observed congenital heart disorder in preterm neonates. Concomitant gentamicin theoretically shall delay the closure/result in nonclosure of ductus arteriosus (DA). Similarly, hsPDA can alter the pharmacokinetics of gentamicin and so trough gentamicin concentrations. We carried out the present study to evaluate the association between gentamicin use and closure of hsPDA (treated with acetaminophen) as well as the effect of hsPDA on trough concentrations. Methods: This study was a prospective, observational study that included 60 neonates diagnosed with hsPDA by echocardiography and 102 neonates without hsPDA. Demographic details, size of DA as per echocardiography at the end of treatment with acetaminophen, gentamicin-dosing regimen, and trough concentrations were collected. Standard definitions were adhered in classifying the gestational age, birth weights, and size of DA. The numerical values are reported in median (range). Results: Neonates with hsPDA had significantly lower daily doses of gentamicin [4.5 (2.5-10), 7 (3.2-13) mg; P < 0.001] but longer duration of therapy [8 (3-14), 5 (3-7) days; P < 0.001] than those without hsPDA in very preterm neonates. No significant differences were observed in the trough concentrations of gentamicin between the groups. No association was observed between gentamicin use and closure of DA. However, those with successful closure of DA received gentamicin for a longer duration [6 (3-10), 4 (3-14) days; P < 0.05] that was independent of acetaminophen duration and had received higher cumulative doses of gentamicin. Conclusion: In conclusion, we observed a significantly longer duration of gentamicin therapy in neonates with hsPDA compared to those without hsPDA. No significant differences were observed in the rates of closure of DA with concomitant gentamicin administration and gentamicin trough concentrations.

Computational Structural Validation of CYP2C9 Mutations and Evaluation of Machine Learning Algorithms in Predicting the Therapeutic Outcomes of Warfarin.

AIM: The study aimed to identify the key pharmacogenetic variable influencing the therapeutic outcomes of warfarin using machine learning algorithms and bioinformatics tools. BACKGROUND: Warfarin, a commonly used anticoagulant drug, is influenced by cytochrome P450 (CYP) enzymes, particularly CYP2C9. MLAs have been identified to have great potential in personalized therapy. OBJECTIVE: The purpose of the study was to evaluate MLAs in predicting the critical outcomes of warfarin therapy and validate the key predictor genotyping variable using bioinformatics tools. METHODS: An observational study was conducted on adults receiving warfarin. Allele discrimination method was used for estimating the single nucleotide polymorphisms (SNPs) in CYP2C9, VKORC1, and CYP4F2. MLAs were used for identifying the significant genetic and clinical variables in predicting the poor anticoagulation status (ACS) and stable warfarin dose. Advanced computational methods (SNPs' deleteriousness and impact on protein destabilization, molecular dockings, and 200 ns molecular dynamics simulations) were employed for examining the influence of CYP2C9 SNPs on structure and function. RESULTS: Machine learning algorithms revealed CYP2C9 to be the most important predictor for both outcomes compared to the classical methods. Computational validation confirmed the altered structural activity, stability, and impaired functions of protein products of CYP2C9 SNPs. Molecular docking and dynamics simulations revealed significant conformational changes with mutations R144C and I359L in CYP2C9. CONCLUSION: We evaluated various MLAs in predicting the critical outcome measures associated with warfarin and observed CYP2C9 as the most critical predictor variable. The results of our study provide insight into the molecular basis of warfarin and the CYP2C9 gene. A prospective study validating the MLAs is urgently needed.