The Potential of GPT-4 as a Support Tool for Pharmacists: Analytical Study Using the Japanese National Examination for Pharmacists.

BACKGROUND: The advancement of artificial intelligence (AI), as well as machine learning, has led to its application in various industries, including health care. AI chatbots, such as GPT-4, developed by OpenAI, have demonstrated potential in supporting health care professionals by providing medical information, answering examination questions, and assisting in medical education. However, the applicability of GPT-4 in the field of pharmacy remains unexplored. OBJECTIVE: This study aimed to evaluate GPT-4's ability to answer questions from the Japanese National Examination for Pharmacists (JNEP) and assess its potential as a support tool for pharmacists in their daily practice. METHODS: The question texts and answer choices from the 107th and 108th JNEP, held in February 2022 and February 2023, were input into GPT-4. As GPT-4 cannot process diagrams, questions that included diagram interpretation were not analyzed and were initially given a score of 0. The correct answer rates were calculated and compared with the passing criteria of each examination to evaluate GPT-4's performance. RESULTS: For the 107th and 108th JNEP, GPT-4 achieved an accuracy rate of 64.5% (222/344) and 62.9% (217/345), respectively, for all questions. When considering only the questions that GPT-4 could answer, the accuracy rates increased to 78.2% (222/284) and 75.3% (217/287), respectively. The accuracy rates tended to be lower for physics, chemistry, and calculation questions. CONCLUSIONS: Although GPT-4 demonstrated the potential to answer questions from the JNEP and support pharmacists' capabilities, it also showed limitations in handling highly specialized questions, calculation questions, and questions requiring diagram recognition. Further evaluation is necessary to explore its applicability in real-world clinical settings, considering the complexities of patient scenarios and collaboration with health care professionals. By addressing these limitations, GPT-4 could become a more reliable tool for pharmacists in their daily practice.

Time until onset of acute kidney injury by combination therapy with "Triple Whammy" drugs obtained from Japanese Adverse Drug Event Report database.

Acute kidney injury (AKI) associated with "Triple Whammy" drug therapy consisting of renin-angiotensin system inhibitors, diuretics, and nonsteroidal anti-inflammatory drugs (NSAIDs) has been reported. There have been no reports investigating "Triple Whammy" drug therapy and the time to AKI onset using adverse drug events report databases. The aim of this study was to determine the relationship between the time to AKI onset and treatment with "Triple Whammy" drug therapy. We analyzed AKI cases registered in the Japanese Adverse Drug Event Report database. The data were analyzed using the Kaplan-Meier approach, generalized Wilcoxon tests, and Weibull distribution. AKI was reported in 18,415 cases, of which 7,466 cases used Triple Whammy drugs. All combinations of Triple Whammy drugs were associated with significantly higher odds ratios for reporting AKI. In Weibull analysis, AKI onset was early for most combination patterns of Triple Whammy drugs. The Kaplan-Meier approach showed that the treatment duration to AKI onset was much shorter in cases using NSAIDs; median onsets, 8 days for triple combination, 7 days for NSAIDs added to renin-angiotensin system inhibitors, 9 days for NSAIDs added to diuretics, 6 days for diuretics added to NSAIDs, and 9 days for NSAIDs alone. AKI associated with Triple Whammy drugs is likely to occur in the early stages of treatment, especially with concomitant NSAIDs. Patients should be monitored for the occurrence of AKI within the first 2 weeks.

High incidence of major bleeding with off-label use of edoxaban.

In clinical practice, edoxaban is sometimes prescribed for off-label use based on the hypothesis that it is as safe and effective as warfarin. However, there is limited safety information on off-label use due to lack of clinical trial. We aimed to analyze the tolerability of off-label use of edoxaban and to identify patient characteristics associated with major bleeding as adverse effects. Patients under edoxaban treatment between January 2017 and December 2017 were enrolled in this retrospective cohort study. The incidence of major bleeding with off-label use compared with on-label use was analyzed using by log-rank test. Univariate and multivariate regression analysis were undertaken to detect independent variables with significant odds ratio that associated with major bleeding. After the exclusion criteria were applied, the patients were divided into two groups: off-label group (n = 30) and on-label group (n = 161). Incidence of major bleeding was found to be higher in the off-label group (13.3%) than in the on-label group (3.7%) (p<0.05). Multivariate adjustment showed that the off-label use or portal vein thrombosis and patients with history of major bleeding has significantly higher incidence of major bleeding. We demonstrated that off-label use of edoxaban may be a significant risk factor for major bleeding.

[Chronic Effects on Kidney Function by "Triple Whammy" (Combination of Renin and Angiotensin Type Inhibitor, Diuretic Drug and Nonsteroidal Anti-inflammatory Drug)].

Recently, there have been reports that the combination of renin angiotensin inhibitors, diuretics, and non-steroidal anti-inflammatory drugs increases the risk of acute kidney injury (AKI). This combination has been dubbed the "Triple Whammy". However, there have been no reports about its chronic effects on the kidney. In this study, we investigated the chronic effects of the "Triple Whammy" on kidney function. There were 203 outpatients who were prescribed this combination in our hospital for 5 years. We excluded patients who could also confirm the combination in the previous year and patients for whom laboratory data were unavailable, thus, leaving a target patient group of 95 patients. The average estimated glomerular filtration rate (eGFR) decreased significantly from 62.6 to 58.9 mL/min/1.73 m2 immediately after administering the combination (p<0.01). Although no patients were diagnosed with AKI within 90 days after being administered the combination, 7.4% of patients exhibited a ≥25% reduction in eGFR compared with that before commencing the combination. Correlation analysis of gender, age, past renal function, and renal function change demonstrated that eGFR before administration of the combination negatively correlated with changes in eGFR (p<0.01). Considering the effects of individual differences, eGFR changes before and after administering the combination were compared using a case-crossover design and eGFR after administering the combination was found to be significantly reduced (p<0.01). Therefore, it appears that the "Triple Whammy" may cause not only AKI but also chronic renal degeneration.