在成年患者中预测牛炭胺诱导的低血症:使用现实世界CDM数据的多中心机器学习分析
Gucheol Jung1, JaeHyeok Lee1, Sung-Min Gho1
1Medical R&D Center, Deepnoid, Inc., Seoul, Republic of Korea.
Seizure
|October 30, 2025
概括
机器学习模型准确地预测了使用牛炭胺 (OXC) 的严重低血风险. 关键的风险因素包括同时服用的药物和病史,使患者的个性化监测成为可能.
科学领域:
- 药物监督 药物监督 药物监督
- 临床信息学 临床信息学
- 机器学习在医学中的应用
背景情况:
- 牛炭bazepine (OXC) 是一种常见的抗发作药物 (ASM).
- 氧化使用与低血症的显著风险有关,这可能是严重的不良影响.
- 现实世界的数据和先进的分析对于理解和减轻药物诱导的副作用至关重要.
研究的目的:
- 评估由牛炭bazepine (OXC) 诱导的严重低血的患病率和确定危险因素.
- 开发和验证机器学习 (ML) 模型,用于预测OXC诱导的严重低血症.
- 为了利用多中心的现实世界数据,在观察医学结果伙伴关系-共同数据模型 (OMOP-CDM) 中标准化,进行可靠的分析.
主要方法:
- 一项回顾性队列研究,利用来自韩国两家三级医院的OMOP-CDM数据.
- 包括处方OXC的成年患者,严重的低血症定义为血清≤128 mmol/L.
- 使用单机构和多中心培训方法开发和比较ML模型 (XGBoost,随机森林,SVM,后勤回归,原始贝叶斯),使用SHAP值进行解释.
主要成果:
- 在2253名患者中,严重低血的患病率为8.4%.
- 在多中心数据上训练的XGBoost模型实现了最高的预测性能 (AUROC 0.83,F1-score 0.41).
- 通过SHAP分析确定的关键预测因素包括同时使用酸或利尿剂,高OXC剂量,年龄较大,中风病史以及其他联合使用的药物,如β-阻断剂,通道阻断剂,催眠药和其他ASM.
结论:
- 机器学习,特别是XGBoost,有效地预测使用多中心真实世界的数据与牛炭胺相关的严重低血风险.
- SHAP分析为风险因素提供了临床相关的见解,促进了个性化的监测策略.
- 这些发现支持将预测分析纳入常规治疗,以提高患者的安全性.
更多相关视频
09:32Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
Published on: December 18, 2016
12.8K
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.5K
相关概念视频
Antiepileptic Drugs: Potassium Channel Activators
620
Ezocgabine or retigabine, an antiepileptic drug of remarkable efficacy, has revolutionized the management of seizures. It is a potassium channel activator, explicitly targeting the family of Q subtype potassium channels. It enhances the transmembrane potassium currents, regulating neuronal excitability. This action stabilizes the resting membrane potential, a pivotal factor in mitigating the hyperexcitability that characterizes epilepsy.
Ezogabine has gained approval as an adjunctive treatment...
Ezogabine has gained approval as an adjunctive treatment...
620
Epilepsy and Seizures: Overview
1.1K
Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
1.1K
Seizures: Classification
1.3K
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
1.3K
