Henry Basil Josephine, Lim Wern Han, Syed Ahmad Sharifah M, Menon Premakumar Chandini, Mohd Tahir Nurul Ain, Mhd Ali Adliah, Seman Zamtira, Ishak Shareena, Mohamed Shah Noraida
Centre for Quality Management of Medicines, Faculty of Pharmacy, Universiti Kebangsaan Malaysia, Kuala Lumpur, Malaysia.
School of Information Technology, Monash University Malaysia, Selangor, Malaysia.
Digit Health. 2024 Oct 18;10:20552076241286434. doi: 10.1177/20552076241286434. eCollection 2024 Jan-Dec.
Neonates' physiological immaturity and complex dosing requirements heighten their susceptibility to medication administration errors (MAEs), with the potential for severe harm and substantial economic impact on healthcare systems. Developing an effective risk prediction model for MAEs is crucial to reduce and prevent harm.
This national-level, multicentre, prospective direct observational study was conducted in neonatal intensive care units (NICUs) of five public hospitals in Malaysia. Randomly selected nurses were directly observed during medication preparation and administration. Each observation was independently assessed for errors. Ten machine learning (ML) algorithms were applied with features derived from systematic reviews, incident reports, and expert consensus. Model performance, prioritising F1-score for MAEs, was evaluated using various measures. Feature importance was determined using the permutation-feature importance for robust comparison across ML algorithms.
A total of 1093 doses were administered to 170 neonates, with mean age and birth weight of 33.43 (SD ± 5.13) weeks and 1.94 (SD ± 0.95) kg, respectively. F1-scores for the ten models ranged from 76.15% to 83.28%. Adaptive boosting (AdaBoost) emerged as the best-performing model (F1-score: 83.28%, accuracy: 77.63%, area under the receiver operating characteristic: 82.95%, precision: 84.72%, sensitivity: 81.88% and negative predictive value: 64.00%). The most influential features in AdaBoost were the intravenous route of administration, working hours, and nursing experience.
This study developed and validated an ML-based model to predict the presence of MAEs among neonates in NICUs. AdaBoost was identified as the best-performing algorithm. Utilising the model's predictions, healthcare providers can potentially reduce MAE occurrence through timely interventions.
新生儿生理上不成熟且给药要求复杂，这增加了他们发生用药错误（MAE）的易感性，可能造成严重伤害并对医疗系统产生重大经济影响。开发一种有效的MAE风险预测模型对于减少和预防伤害至关重要。
这项国家级、多中心、前瞻性直接观察研究在马来西亚五家公立医院的新生儿重症监护病房（NICU）进行。在药物准备和给药过程中直接观察随机挑选的护士。每次观察都独立评估是否存在错误。应用了十种机器学习（ML）算法，其特征源自系统评价、事件报告和专家共识。使用各种指标评估模型性能，优先考虑MAE的F1分数。使用排列特征重要性来确定特征重要性，以便在ML算法之间进行稳健比较。
共对170名新生儿给药1093剂，平均年龄和出生体重分别为33.43（标准差±5.13）周和1.94（标准差±0.95）千克。十个模型的F1分数在76.15%至83.28%之间。自适应增强（AdaBoost）成为表现最佳的模型（F1分数：83.28%，准确率：77.63%，受试者工作特征曲线下面积：82.95%，精确率：84.72%，灵敏度：81.88%，阴性预测值：64.00%）。AdaBoost中最具影响力的特征是静脉给药途径、工作时间和护理经验。
本研究开发并验证了一种基于ML的模型，用于预测NICU中新生儿MAE的存在。AdaBoost被确定为表现最佳的算法。利用该模型的预测结果，医疗服务提供者有可能通过及时干预减少MAE的发生。
