Npj mental health research. 2025 May 15;4(1):18. doi: 10.1038/s44184-025-00129-7 0.02025

Subtyping first-episode psychosis based on longitudinal symptom trajectories using machine learning

基于纵向症状轨迹利用机器学习对首发精神病进行亚型划分翻译改进

Yanan Liu¹, Sara Jalali², Ridha Joober^{2 3}, Martin Lepage^{2 3}, Srividya Iyer^{2 3}, Jai Shah^{2 3}, David Benrimoh^{4 5}

作者单位 +展开

作者单位

¹ Montreal Neurological Institute, McGill University, Montreal, QC, Canada.

² Douglas Research Centre, Montreal, QC, Canada.

³ Department of Psychiatry, McGill University, Montreal, QC, Canada.

⁴ Douglas Research Centre, Montreal, QC, Canada. david.benrimoh@mcgill.ca.

⁵ Department of Psychiatry, McGill University, Montreal, QC, Canada. david.benrimoh@mcgill.ca.

DOI: 10.1038/s44184-025-00129-7 PMID: 40374762

摘要中英对照阅读

Clinical course after first episode psychosis (FEP) is heterogeneous. Subgrouping and predicting longitudinal symptom trajectories after FEP may help develop personalized treatment approaches. We utilized k-means clustering to identify clusters of 411 FEP patients based on longitudinal positive and negative symptoms. Three clusters were identified. Cluster 1 exhibits lower positive and negative symptoms (LS), lower antipsychotic dose, and relatively higher affective psychosis; Cluster 2 shows lower positive symptoms, persistent negative symptoms (LPPN), and intermediate antipsychotic doses; Cluster 3 presents persistently high levels of both positive and negative symptoms (PPNS), and higher antipsychotic doses. We predicted cluster membership (AUC of 0.74) using ridge logistic regression on baseline data. Key predictors included lower levels of apathy, affective flattening, and anhedonia/asociality in the LS cluster, compared to the LPPN cluster. Hallucination severity, positive thought disorder and manic hostility predicted PPNS. These results help parse the FEP trajectory heterogeneity and may facilitate the development of personalized treatments.

Keywords：first-episode psychosis; machine learning

首次精神病发作（FEP）后的临床过程是异质性的。对FEP后纵向症状轨迹进行亚组划分和预测，可能有助于开发个性化的治疗方案。我们利用k-均值聚类方法基于纵向的阳性症状和阴性症状将411名FEP患者划分为三个簇。第一簇表现出较低的阳性和阴性症状（LS）、较低的抗精神病药物剂量以及相对较高的情感型精神病；第二簇显示低水平的阳性症状，持续存在的阴性症状（LPPN），中等水平的抗精神病药物剂量；第三簇呈现高水平且持久的阳性和阴性症状（PPNS）和较高水平的抗精神病药物剂量。我们使用岭逻辑回归在基线数据上预测聚类成员身份（AUC为0.74）。关键预测因素包括LS组与LPPN组相比，较低的淡漠、情感迟钝以及快感缺失/社会退缩水平。幻觉严重程度、阳性思维障碍和躁狂敌意预示着PPNS。这些结果有助于解析FEP轨迹的异质性，并可能促进个性化治疗方案的发展。

关键词：首次精神病发作; 纵向症状轨迹; 机器学习

翻译效果不满意？用Ai改进或寻求AI助手帮助，对摘要进行重点提炼

相关内容

期刊名：Npj mental health research

缩写：

ISSN：

e-ISSN：2731-4251

IF/分区：0.0/

文章目录更多期刊信息

全文链接

官方链接

PMC全文

引文链接

复制

已复制！

格式：

Subtyping first-episode psychosis based on longitudinal symptom trajectories using machine learning

基于纵向症状轨迹利用机器学习对首发精神病进行亚型划分翻译改进

Development and Validation of a Machine Learning-Based Model of Mortality Risk in First-Episode Psychosis

首次精神病发作患者死亡风险的机器学习模型的研发与验证

Correction: Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach

首次精神病发作患者4周和52周治疗结局的多中心预测：机器学习方法的研究（纠错）

Using Machine Learning and Structural Neuroimaging to Detect First Episode Psychosis: Reconsidering the Evidence

运用机器学习和结构神经影像检测首发精神分裂症：重新审视证据

Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach

机器学习方法预测首发精神病患者治疗4周和52周的转归：多中心研究

A New Machine Learning Framework for Understanding the Link Between Cannabis Use and First-Episode Psychosis

一种新的机器学习框架用于理解大麻使用与首次出现的精神病之间的联系

Predicting one-year outcome in first episode psychosis using machine learning

用机器学习预测首发精神病一年内的转归

Identifying clinical clusters with distinct trajectories in first-episode psychosis through an unsupervised machine learning technique

通过无监督机器学习技术识别首发精神病具有不同病程的临床亚群

Development and validation of multivariable prediction models of remission, recovery, and quality of life outcomes in people with first episode psychosis: a machine learning approach

首次精神病发作患者缓解、康复和生活质量结果的多变量预测模型的发展与验证：一种机器学习方法

Classification of First-Episode Psychosis with EEG Signals: ciSSA and Machine Learning Approach

利用EEG信号对首次精神病进行分类：ciSSA和机器学习的方法

Subtyping first-episode psychosis based on longitudinal symptom trajectories using machine learning

基于纵向症状轨迹利用机器学习对首发精神病进行亚型划分 翻译改进

Development and Validation of a Machine Learning-Based Model of Mortality Risk in First-Episode Psychosis

首次精神病发作患者死亡风险的机器学习模型的研发与验证

Correction: Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach

首次精神病发作患者4周和52周治疗结局的多中心预测：机器学习方法的研究（纠错）

Using Machine Learning and Structural Neuroimaging to Detect First Episode Psychosis: Reconsidering the Evidence

运用机器学习和结构神经影像检测首发精神分裂症：重新审视证据

Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach

机器学习方法预测首发精神病患者治疗4周和52周的转归：多中心研究

A New Machine Learning Framework for Understanding the Link Between Cannabis Use and First-Episode Psychosis

一种新的机器学习框架 用于理解大麻使用与首次出现的精神病之间的联系

Predicting one-year outcome in first episode psychosis using machine learning

用机器学习预测首发精神病一年内的转归

Identifying clinical clusters with distinct trajectories in first-episode psychosis through an unsupervised machine learning technique

通过无监督机器学习技术识别首发精神病具有不同病程的临床亚群

Development and validation of multivariable prediction models of remission, recovery, and quality of life outcomes in people with first episode psychosis: a machine learning approach

首次精神病发作患者缓解、康复和生活质量结果的多变量预测模型的发展与验证：一种机器学习方法

Classification of First-Episode Psychosis with EEG Signals: ciSSA and Machine Learning Approach

利用EEG信号对首次精神病进行分类：ciSSA和机器学习的方法

基于纵向症状轨迹利用机器学习对首发精神病进行亚型划分翻译改进

一种新的机器学习框架用于理解大麻使用与首次出现的精神病之间的联系