High alert drugs screening using gradient boosting classifier

Abstract

Prescription errors in high alert drugs (HAD), a group of drugs that have a high risk of complications and potential negative consequences, are a major and serious problem in medicine. Standardized hospital interventions, protocols, or guidelines were implemented to reduce the errors but were not found to be highly effective. Machine learning driven clinical decision support systems (CDSS) show a potential solution to address this problem. We developed a HAD screening protocol with a machine learning model using Gradient Boosting Classifier and screening parameters to identify the events of HAD prescription errors from the drug prescriptions of out and inpatients at Maharaj Nakhon Chiang Mai hospital in 2018. The machine learning algorithm was able to screen drug prescription events with a risk of HAD inappropriate use and identify over 98% of actual HAD mismatches in the test set and 99% in the evaluation set. This study demonstrates that machine learning plays an important role and has potential benefit to screen and reduce errors in HAD prescriptions.

Using machine learning or deep learning models in a hospital setting to detect inappropriate prescriptions: a systematic review

“…Finally, one article26 described an algorithm capable of screening high alert drug errors from prescriptions.…”

“…Eight publications14 15 17–19 23 24 26 used supervised ML models (online supplemental table 1); unsupervised ML algorithms (online supplemental tale 2) were used in three publications 16 20 25…”

“…Eight articles14 15 17–19 23 24 26 described the use of supervised ML (online supplemental table 1). Five ML models were tested: DT,17–19 24 SVM,18 bagging,17 18 24 boosting14 17 18 23 24 26 and neural network 15 17 23. Three articles14 15 26 compared distinct ML techniques.…”

“…Five ML models were tested: DT,17–19 24 SVM,18 bagging,17 18 24 boosting14 17 18 23 24 26 and neural network 15 17 23. Three articles14 15 26 compared distinct ML techniques. Lewin-Epstein et al 23 combined multiple techniques to enhance the results.…”

Application of random forest based on semi-automatic parameter adjustment for optimization of anti-breast cancer drugs

“…Z Xiong, D Wang, X Liu, et al (12) used a new graph neural network structure (Attentive FP), which uses a graph attention mechanism to achieve learning from relevant drugs in a data set, and experimental results showed that At tent ive FP achieve d st ate -of-the-art prediction performance in various datasets. P Wongyikul, N Thongyot, P Tantrakoolcharoen, et al (13) developed an had screening protocol using Gradient Boosting Classifier machine learning model and screening parameters to identify HAD prescription error events from drug prescriptions. The experimental results show that machine learning plays an important role in screening and reducing HAD prescription errors and has potential benefits.…”