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.

In recent years, the GS1 data bar has been displayed on all ethical drugs to prevent medical accidents caused by dispensing errors. However, performing drug collation for oral drugs remains a challenge because the GS1 data bar is sometimes defective during the dispensing process. Our results showed that only 14.7％ of the drugs adopted by Kyushu University Hospital displayed a single GS1 data bar per tablet or slit, and measures were not taken to prevent GS1 data bar defects for most of the drugs. In addition, incidences of prescriptions containing less than one sheet of the press through package for counting dispensing, grinding, and one-dose package by hand were 54.5％, 71.6％, and 54.4％, respectively, suggesting that lack of the GS1 data bar occurred frequently in clinical settings. To promote the utilization of the GS1 data bar for oral drugs, pharmaceutical companies should address the GS1 data bar de ciency challenge and improve its design.