言语即可预测:初始可卡因戒断期的言语是长期药物使用行为的生物标志物证据
研究采集88例初始戒断的可卡因使用障碍患者(iCUDs)5分钟言语样本,其中57例纳入分析,每3个月随访至1年,评估戒断、渴求、戒断天数及近期可卡因使用。短期预测中结合基线药物使用指标的非自然语言处理模型预测力最强;长期预测中言语样本单独即达统计学显著(Spearman r ≥ 0.46,预测戒断准确率80%)。作者认为言语指标可能优于常用结局指标,但需在更大独立样本中重复。
要点
- 57例iCUDs随访至1年,言语样本对长期戒断预测Spearman r ≥ 0.46、准确率80%。
- 短期预测以结合基线药物使用指标的非NLP模型预测力最强。
- 作者认为言语指标可能优于常用结局指标,但需更大独立样本重复。
核心结论
- 与临床试验常用结局指标相比,基于言语的指标可能作为初始戒断iCUDs长期药物使用结局的更好预测因素。
- 言语样本可能比传统指标更有效地捕捉较长时间间隔内的非线性动态。
- 作者认为言语指标可能可推广至其他可卡因成瘾亚组及其他物质使用障碍和相关共病。
研究设计与样本
- 基线时88例初始戒断的可卡因使用障碍患者(iCUDs)提供5分钟言语样本,描述戒除药物的积极后果和使用药物的消极后果。
- 结局包括戒断、渴求、戒断天数和近期可卡因使用,每3个月评估一次,随访至1年,57例iCUDs纳入分析。
- 预测建模比较自然语言处理(NLP)技术(以句子嵌入与既定量表为目标)与利用标准人口学和基线心理测量变量的模型。
主要发现
- 在较短时间间隔,结合基线时所获相同药物使用指标(作为结局)的非NLP模型获得最大预测力,可能反映其变化速度慢、可用线性函数估计。
- 在较长时期预测中,言语样本单独即显示统计学显著结果,预测戒断的Spearman r ≥ 0.46、准确率80%。
- 因此,言语样本可能比传统指标更有效地捕捉较长时间间隔内的非线性动态。
关键数值与推荐
- 预测戒断的Spearman r ≥ 0.46,准确率80%。
临床怎么用
- 原文未据此给出推荐。
局限性
- 这些结果需要在更大且独立的样本中重复。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Valid scalable biomarkers for predicting longitudinal clinical outcomes in psychiatric research are crucial for optimizing intervention and prevention efforts. Here, we recorded spontaneous speech from initially abstinent individuals with cocaine use disorder (iCUDs) for use in predicting drug use outcomes. METHODS: At baseline, 88 iCUDs provided 5-minute speech samples describing the positive consequences of quitting drug use and negative consequences of using drugs. Outcomes, including withdrawal, craving, abstinence days, and recent cocaine use, were assessed at 3-month intervals for up to 1 year (57 iCUDs were included in the analyses). Predictive modeling compared natural language processing (NLP) techniques, specifically sentence embeddings with established inventories as targets, with models utilizing standard demographic and baseline psychometric variables. RESULTS: At short time intervals, maximal predictive power was obtained with non-NLP models that also incorporated the same drug use measures (as the outcomes) obtained at baseline, potentially reflecting their slow rate of change, which could be estimated by linear functions. However, for longer-term predictions, speech samples alone demonstrated statistically significant results, with Spearman r ≥ 0.46 and 80% accuracy for predicting abstinence. Therefore, speech samples may capture nonlinear dynamics over extended intervals more effectively than traditional measures. These results need to be replicated in larger and independent samples. CONCLUSIONS: Compared with the common outcome measures used in clinical trials, speech-based measures could be leveraged as better predictors of longitudinal drug use outcomes in initially abstinent iCUDs, as potentially generalizable to other subgroups with cocaine addiction, and to additional substance use disorders and related comorbidity.
引用
- Agurto C, Cecchi GA, King S, et al. Speak and You Shall Predict: Evidence That Speech at Initial Cocaine Abstinence Is a Biomarker of Long-Term Drug Use Behavior. Biol Psychiatry. 2025. PMID: 39842704. doi:10.1016/j.biopsych.2025.01.009
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。