三分之一的酒精使用障碍诊断错过了ICD编码
Laura Mercurio1, Augusto Garcia2, Stephanie Ruest1,3
1Departments of Emergency Medicine & Pediatrics, Alpert Medical School of Brown University, Providence, RI, USA.
一个新的语言模型在临床笔记中准确地识别了酒精使用障碍 (AUD),超过了传统的ICD编码,并揭示了临床医生大量的不足文档.
科学领域:
- 在医疗保健中的自然语言处理.
- 临床信息学 临床信息学
- 计算语言学 计算语言学
背景情况:
- 酒精使用障碍 (AUD) 具有显著的发病率和死亡率.
- 对临床医生和研究人员来说,准确识别AUD是一个复杂的挑战.
- 现有的诊断方法,如ICD编码,可能无法完全捕捉AUD流行率.
研究的目的:
- 在临床叙述中开发和完善用于检测AUD的语言模型.
- 在MIMIC-III数据库中识别当前ICD-9编码实践遗漏的AUD病例.
主要方法:
- 应用临床BERT患者出院摘要用于AUD分类和检测.
- 使用基于AUD ICD诊断的分层患者组训练并验证了模型.
- 医生对600个样本进行判断,以确认AUD与DSM-V标准相匹配.
主要成果:
- 该模型实现了高性能指标:精度 (0.9),回忆 (0.65),F-1 (0.75),AUC (0.97) 和AU-PRC (0.86).
- 据估计,在整个研究群体中,AUD的记录不足率约为4%.
- 在ICD-9编码识别的患者中,不足文档增加到30%,因为对模型的信心增加了.
结论:
- 开发的模型增强了符合AUD标准的患者的识别能力,超过了ICD代码.
- 差异表明临床医生缺乏文件,而不是对AUD的认可不足.
- 未来的研究应该涉及更广泛的患者群体,以改进模型的灵敏度.
更多相关视频
05:40The Motivation for Alcohol Reward: Predictors of Progressive-Ratio Intravenous Alcohol Self-Administration in Humans
Published on: April 28, 2022
08:05A Prediction Error-driven Retrieval Procedure for Destabilizing and Rewriting Maladaptive Reward Memories in Hazardous Drinkers
Published on: January 5, 2018
相关概念视频
Diagnostic and Statistical Manual of Mental Disorders (DSM)
Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
Substance Use Disorders Affecting Sleep
Understanding the concepts of physical dependence,...
CNS Depressants: Alcohol and Nicotine
Intellectual Disability
Formulating and Validating Nursing Diagnosis II
Risk nursing diagnoses represent clinical judgments of an individual, family, or community more vulnerable to developing the health problem than others...
