一个计算效率高的生物医学文本处理框架用于药物监测:集成低级适应和可解释的AI用于药物不良反应检测
Zahra Rezaei1, Sara Safi Samghabadi1, Mohammad Amin Amini1
1School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA.
Medical & biological engineering & computing
|November 28, 2025
概括
这项研究引入了一种有效的框架,用于使用AI检测药物不良反应 (ADR). 它显著降低了计算成本,同时保持了高准确度,并为患者安全提供了可解释的见解.
科学领域:
- 计算型药物监督系统的使用.
- 医疗保健中的人工智能
- 对于药物安全性的自然语言处理.
背景情况:
- 药物不良反应 (ADRs) 的早期检测对于患者的安全至关重要,但由于传统药物监测中的报告不足和数据延迟而受到阻碍.
- 社交媒体平台为ADR检测提供了潜在的数据来源,但需要有效处理杂的非正式文本.
- 现有的方法往往缺乏计算效率和可解释性,限制了实时应用.
研究的目的:
- 开发一个使用变压器模型进行ADR检测的计算效率高和可解释的框架.
- 整合低级适应 (LoRA) 和夏普利添加式解释 (SHAP) 来从社交媒体数据中增强ADR检测.
- 在准确性,成本降低和可解释性方面评估框架的性能.
主要方法:
- 使用的基于编码器的变压器模型 (BERT,DistilBERT,RoBERTa) 通过低级调整 (LoRA) 进行微调.
- 为了模型的可解释性,采用了SHapley添加式解释 (SHAP),分析了ADR预测的特征重要性.
- 在与药物安全相关的3900多条注释推特数据集上训练和评估框架.
主要成果:
- 在三个疾病类别中,LoRA降低了可训练的参数和培训成本高达50%,同时保持了高分类准确性 (98%以上).
- SHAP分析证实,模型依赖临床相关术语 (药物名称,症状) 来准确预测ADR.
- 拟议的框架在处理非正式社交媒体数据方面表现强,优于传统的微调方法.
结论:
- 集成的LoRA和SHAP框架提供了一个计算效率高,可解释和准确的解决方案,用于从社交媒体实时检测ADR.
- 这种方法是可扩展的,适合资源有限的医疗保健机构,使积极的药物监督成为可能.
- 该框架支持将人工智能驱动的药物监测集成到临床决策支持系统中,以提高患者安全.
关键词:
药物不良反应 药物不良反应计算型药物监督系统的使用.只有编码器的变压器医疗保健信息系统 医疗保健信息系统低级别的适应 (LoRA)QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRA QLoRa QLRA QLoRa QLRA QLRA QLRA QLRA QLRA QLRA QLRA QLRA QLRAQR沙普利的添加剂解释 (SHAP)
相关概念视频
01:19Pharmacovigilance
1.6K
Post-marketing surveillance is a critical component of pharmaceutical regulation, often uncovering unanticipated adverse drug reactions (ADRs) once a drug is widely used over an extended period.
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
1.6K
01:28Structure-Activity Relationships and Drug Design
1.7K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.7K
01:30Quantitative Aspects of Drug-Receptor Interaction
1.7K
The receptor occupancy theory connects a drug's response to the number of occupied receptors. With higher drug concentrations, more receptors are occupied, leading to increased responses. The formation of drug-receptor complexes involves association and dissociation rates, which reach equilibrium when the forward and backward reactions are equal. The equilibrium association constant (Ka) and its inverse, the equilibrium dissociation constant (Kd), indicate drug affinity. Higher Ka and lower...
1.7K
00:59Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
297
Noncompartmental analyses offer an alternative method for describing drug pharmacokinetics without relying on a specific compartmental model. In this approach, the drug's pharmacokinetics are assumed to be linear, with the terminal phase log-linear. This assumption allows for simplified analysis and interpretation of the drug's behavior in the body.
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
297
01:12Analysis of Population Pharmacokinetic Data
657
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
657
01:16Drug Biotransformation: Overview
3.5K
Pharmaceutical substances known as xenobiotics are predominantly lipophilic and nonionized. This enables them to permeate lipid bilayers, such as cell membranes, and interact with intracellular target receptors. Lipophilic drugs have an advantage in crossing biological barriers and reaching their intended sites of action. However, lipophilic drugs often have a restricted capacity for renal expulsion or elimination from the body. When these drugs enter the kidneys and undergo glomerular...
3.5K