No abstract

Overdose prescription errors sometimes cause serious life-threatening adverse drug events, while underdose errors lead to diminished therapeutic effects. Therefore, it is important to detect and prevent these errors. In the present study, we used the one-class support vector machine (OCSVM), one of the most common unsupervised machine learning algorithms for anomaly detection, to identify overdose and underdose prescriptions. We extracted prescription data from electronic health records in Kyushu University Hospital between January 1, 2014 and December 31, 2019. We constructed an OCSVM model for each of the 21 candidate drugs using three features: age, weight, and dose. Clinical overdose and underdose prescriptions, which were identified and rectified by pharmacists before administration, were collected. Synthetic overdose and underdose prescriptions were created using the maximum and minimum doses, defined by drug labels or the UpToDate database. We applied these prescription data to the OCSVM model and evaluated its detection performance. We also performed comparative analysis with other unsupervised outlier detection algorithms (local outlier factor, isolation forest, and robust covariance). Twenty-seven out of 31 clinical overdose and underdose prescriptions (87.1%) were detected as abnormal by the model. The constructed OCSVM models showed high performance for detecting synthetic overdose prescriptions (precision 0.986, recall 0.964, and F-measure 0.973) and synthetic underdose prescriptions (precision 0.980, recall 0.794, and F-measure 0.839). In comparative analysis, OCSVM showed the best performance. Our models detected the majority of clinical overdose and underdose prescriptions and demonstrated high performance in synthetic data analysis. OCSVM models, constructed using features such as age, weight, and dose, are useful for detecting overdose and underdose prescriptions.

ObjectiveThis study aimed to evaluate the safety and tolerability of OP-724, a CREB-binding protein/β-catenin inhibitor, in patients with advanced primary biliary cholangitis (PBC).DesignAn open-label, non-randomised, phase 1 trial was conducted at two hospitals in Japan. Patients with advanced PBC classified as stage III or higher according to the Scheuer classification by liver biopsy between 4 September 2019 and 21 September 2021 were enrolled. Seven patients received intravenous OP-724 infusions at escalating dosages of 280 and 380 mg/m2/4 hours two times weekly for 12 weeks. The primary endpoint was the incidence of serious adverse events (SAEs). The secondary endpoints were the incidence of AEs and the improvement in the modified Histological Activity Index (mHAI) score.ResultsSeven patients (median age, 68 years) were enrolled. Of these seven patients, five completed twelve cycles of treatment, one discontinued prematurely for personal reasons in the 280 mg/m2/4 hours cohort, and one in the 380 mg/m2/4 hours cohort was withdrawn from the study due to drug-induced liver injury (grade 2). Consequently, the recommended dosage was determined to be 280 mg/m2/4 hours. SAEs did not occur. The most common AEs were abdominal discomfort (29%) and abnormal hepatic function (43%). OP-724 treatment was associated with histological improvements in the fibrosis stage (2/5 (40%)) and mHAI score (3/5 (60%)) on histological analysis.ConclusionAdministration of intravenous OP-724 infusion at a dosage of 280 mg/m2/4 hours two times weekly for 12 weeks was well tolerated by patients with advanced PBC. However, further evaluation of antifibrotic effects in patients with PBC is warranted.Trial registration numberNCT04047160.

No abstract