Self-controlled Case Series Study for Acute Kidney Injury after Starting Proton Pump Inhibitors or Potassium-Competitive Acid Blocker in Patients with Cancer Using a Large Claims Database.

To investigate the risk of acute kidney injury (AKI) in patients with cancer following the initiation of proton pump inhibitors (PPIs) and potassium-competitive acid blocker (PCAB), considering sex and anti-cancer drug use. We conducted a self-controlled case-series study using the Japan Medical Data Center claims data from 12422 patients with cancer who were prescribed PPIs or PCAB between January 2017 and December 2019. Considering the timing of PPI or PCAB, control period (days -120 to -1), risk period 1 (days 0 to +30), and risk period 2 (days +31 to +365) were defined. To assess the incidence rate ratio (IRR) and 95% confidence interval (CI) as the risk ratio, we adjusted for anti-cancer drugs to assess the risk of AKI. Additionally, we also examined sex differences to identify the risk of AKI. AKI was observed in risk period 1 [2.05 (1.12-3.72), p = 0.0192], but a slight reduction was noted in risk period 2 [0.60 (0.36-1.00), p = 0.0481]. A sex-specific increase in the risk of AKI was observed only in males during risk period 1 [2.18 (1.10-4.32), p = 0.0260], with a reduction in risk period 2 [0.48 (0.26-0.89), p = 0.0200]. We identified an increased risk of AKI in patients with cancer starting PPIs or PCAB particularly in males within 30 d after PPI or PCAB initiation, emphasizing the need for vigilant monitoring and management of AKI in this patient population.

[Development of a Medical Big Data Analysis System Utilizing Artificial Intelligence Analytics in Clinical Pharmacy].

Industrial reforms utilizing artificial intelligence (AI) have been progressing remarkably worldwide in recent years. In medical informatics, medical big-data analytics involving AI are increasingly being promoted, and AI in the medical field is being widely applied in research areas such as protein-structure analysis and diagnostic support. Previously, we developed a unique adverse drug reactions analysis system that incorporates Accord.NET, an open-source machine learning (ML) framework written in the programming language C#, and uses the Japanese Adverse Drug Event Report (JADER) database. The developed system can provide necessary information for exploratory investigation of drug efficacy, side effects, adherence, and so on. To efficiently interpret the calculated data and minimize noise, the developed system features a data visualization tool that can visualize the results of various statistical analyses and machine learning models in real-time three dimensions (3D), making it intuitive to grasp the results. This feature makes the system ideal for individuals in clinical work. We believe that the system will facilitate more efficient drug management and clinical pharmacy research. In this review, we introduce an example of domain-driven design development of this AI analysis system for pharmacists in clinical practice with the aim of further utilizing medical big data and AI analytics.

Identification of the Components of Proton Pump Inhibitors and Potassium-Competitive Acid Blocker That Lead to Cardiovascular Events in Working-Age Individuals: A 12-Month Retrospective Cohort Study Using a Large Claims Database.

This study aimed to identify the components of proton pump inhibitors (PPIs) or potassium-competitive acid blocker (PCAB) that lead to cardiovascular events in individuals of working age. We analyzed large claims data of individuals who were administered PPIs or PCAB. We enrolled working-age individuals administered PPI or PCAB without cardiovascular history with a 12-month screening and 12-month observation period and determined the proportion of cardiovascular events and the predictive factors of cardiovascular events in this population. Among the eligible individuals, 0.5% (456/91098) had cardiovascular events during the 12-month observation period. Predictive factors for cardiovascular events were age for +1 year (p < 0.0001), male sex (p < 0.0001), hypertension (p = 0.0056), and diabetes mellitus (p < 0.0001). The cardiovascular disease risk was higher in working-age individuals administered lansoprazole than in those administered other drugs (vs. rabeprazole; p = 0.0002, vs. omeprazole; p = 0.0046, vs. vonoprazan; p < 0.0001, and vs. esomeprazole; p < 0.0001). We identified the risk for cardiovascular events in individuals being treated with lansoprazole. Lansoprazole is known for its higher CYP2C19 inhibition activity compared with other PPIs or PCAB. A possible mechanism by which lansoprazole may lead to cardiovascular events is inhibiting the generation of epoxyeicosatrienoic acids from arachidonic acids, an intrinsic cardioprotective activator via CYP2C19 inhibition. Thus, we recommend avoiding administering lansoprazole to working-age individuals require PPIs or PCAB.

[Medical Big Data Analysis Using Machine Learning Algorithms in the Field of Clinical Pharmacy].

Industrial reforms utilizing artificial intelligence (AI) have been progressing remarkably around the world in recent years. In medical informatics, the application of medical big data analytics using AI is also being promoted, and it is expected to provide screening methods for predicting potential adverse drug reactions (ADRs) and discovering new effects. Previously, we developed a unique ADRs analysis system that incorporates Accord.NET, an open-source machine learning (ML) framework written in the programming language C#, and uses the Japanese Adverse Drug Event Report (JADER) database. By using this system to analyze ADRs and screening the cause and severity of ADRs, information can be obtained to evaluate efficacy as well as ADRs. Although both statistical methods and ML are commonly used for prediction, a characteristic difference between them is that the former emphasizes causal relationships and the latter emphasizes prediction results. Therefore, it is important to distinguish between cases where decisions must be made with an emphasis on causality and those where decisions must be made by focusing on unknown risks, and statistical methods and ML should be selected and used as appropriate. Against this backdrop, this paper describes a use case and suggests that the proper use of AI tools to analyze medical big data will help clinical pharmacists practice optimal drug management for each patient.

[Potential for Big Data Analysis Using AI in the Field of Clinical Pharmacy].

Industrial reforms utilizing artificial intelligence (AI) have advanced remarkably in recent years. The application of AI to big data analysis in the medical information field has also been advancing and is expected to be used to find drug adverse effects that cannot be predicted by conventional methods. We have developed an adverse drug reactions analysis system that uses machine learning and data from the Japanese Adverse Drug Event Report (JADER) database. The system was developed using the C# programming language and incorporates the open source machine learning library Accord.Net. Potential analytical capabilities of the system include discovering unknown drug adverse effects and evaluating drug-induced adverse events in pharmaceutical management. However, to apply the system to pharmaceutical management, it is important to examine the characteristics and suitability of the level of AI used in the system and to select statistical methods or machine learning when appropriate. If these points are addressed, there is potential for pharmaceutical management to be individualized and optimized in the clinical setting by using the developed system to analyze big data. The system also has the potential to allow individual healthcare facilities such as hospitals and pharmacies to contribute to drug repositioning, including the discovery of new efficacies, interactions, and drug adverse events.