Nonsteroidal anti-inflammatory drugs use in patients with chronic kidney disease are often prescribed from different clinicians than those who diagnosed them

Data-Driven Clinical Pharmacy Research: Utilizing Machine Learning and Medical Big Data

To conduct clinical pharmacy research, we often face the limitations of conventional statistical methods and single-center observational study. To overcome these issues, we have conducted data-driven research using machine learning methods and medical big data. Decision tree analysis, one of the typical machine learning methods, has a flowchart-like structure that allows users to easily and quantitatively evaluate the occurrence percentage of events due to the combination of multiple factors by answering related questions with Yes or No. Using this feature, we first developed a risk prediction model for acute kidney injury caused by vancomycin, a condition we frequently encounter in clinical practice. Additionally, by replacing the prediction target from a binary variable (i.e., presence or absence of adverse drug reactions) to a continuous variable (i.e., drug dosage), we built a model to estimate the initial dose of vancomycin required to reach the optimal blood level recommended by guidelines. We found its accuracy to be better than that of conventional dose-setting algorithms. Moreover, employing Japanese medical big data such as the claims database helped us overcome the major limitations of conventional clinical pharmacy research such as institutional bias caused by single-center studies. We demonstrated that the combined use of machine learning and medical big data could generate high-quality evidence leveraging the strengths of each approach. Data-driven clinical pharmacy research using machine learning and medical big data has enabled researchers to surpass the limitations of conventional research and produce clinically valuable findings.

Investigation of the Real-World Situation and Risk Factors Associated with Olanzapine Prescribed to Diabetes Patients by Using a Japanese Claims Database

Olanzapine is effective for schizophrenia management; however, it is contraindicated in diabetes patients. In addition, olanzapine is useful for treating nausea and vomiting, such as in the case of chemotherapy-induced nausea and vomiting (CINV). Therefore, we hypothesized that the contraindicated prescription of olanzapine likely occurs among cancer patients with diabetes, especially by non-psychiatric physicians. Hence, we conducted a nationwide survey to elucidate the situation of such contraindicated prescriptions and the associated risk factors. We extracted the data of patients who were newly prescribed olanzapine between April 2015 and March 2017 from the health insurance claims database developed by JMDC, Inc., Tokyo. The patients who were prescribed contraindicated olanzapine were defined as those who were prescribed olanzapine after a diagnosis of diabetes and diabetes drug prescription. In all, the data of 7181 patients were analyzed. We evaluated the proportion of diabetes patients who were prescribed contraindicated olanzapine from among those who were prescribed olanzapine. Furthermore, we investigated the background of patients who were prescribed olanzapine for information such as olanzapine prescribers and history of cancer chemotherapy. In all, 100 diabetes patients (1.39%) were prescribed olanzapine. In these patients, the frequency of olanzapine prescription was higher by non-psychiatry/neurology physicians than by psychiatry/neurology physicians (3.25 and 0.85%, respectively). Additionally, all olanzapine prescriptions in cancer chemotherapy-treated diabetes patients were issued by non-psychiatry/neurology physicians. Thus, our study revealed there were diabetes patients who were prescribed olanzapine. Additionally, olanzapine for CINV management was more likely to be a contraindicated prescription.