重性精神障碍跨诊断前驱期的纵向演变:基于自然语言处理与电子健康档案的动态时间网络分析
这项回顾性2年队列研究纳入南伦敦与莫兹利NHS基金会信托6462例重性精神障碍患者(单相心境障碍2066例、双相心境障碍740例、精神病性障碍3656例),用自然语言处理每3个月提取61个前驱特征,构建广义向量自回归面板时间网络。网络显示强自相关(0.04≤z≤0.10)、以正性连接为主,攻击性(出中心性=0.103)与流泪(入中心性=0.134)为中心性最高的特征;三个亚网络差异极小,社区分析识别出阳性精神病性社区与两个行为社区。
要点
- 重性精神障碍前驱特征时间网络以正性连接为主,攻击性出中心性=0.103、流泪入中心性=0.134为最中心特征。
- 单相心境障碍、双相心境障碍与精神病性障碍亚网络差异极小:单相与精神病性障碍间3.5%的边不同,单相与双相0.8%,双相与精神病性0.4%。
- 社区分析识别出阳性精神病性社区(妄想思维-幻觉-偏执)及两个行为社区(攻击-大麻使用-可卡因使用-敌意、攻击-激越-敌意)为最常见。
核心结论
- 本研究是迄今对重性精神障碍前驱特征纵向相互作用规模最大的时间网络分析,结果进一步支持跨诊断早期识别服务、细化风险评估并识别中心特征作为潜在干预靶点。
研究设计与样本
- 回顾性2年队列研究,纳入南伦敦与莫兹利NHS基金会信托电子健康档案中6462例重性精神障碍患者(单相心境障碍2066例、双相心境障碍740例、精神病性障碍3656例)。
- 用经验证的自然语言处理算法在重性精神障碍发病前2年至6个月间每3个月提取61个前驱特征的发生情况。
- 采用广义向量自回归面板分析构建前驱特征时间网络并校正协变量,以偏定向相关系数z报告边权重;用置换分析比较三个亚网络,用Spinglass进行社区分析。
主要发现
- 重性精神障碍网络显示强自相关(0.04≤z≤0.10),以正性连接为主,攻击性出中心性=0.103、流泪入中心性=0.134为最中心特征。
- 单相心境障碍与精神病性障碍亚网络间3.5%的边不同,单相与双相心境障碍间0.8%,双相与精神病性障碍间0.4%。
- 社区分析识别出一个阳性精神病性社区(妄想思维-幻觉-偏执)和两个行为社区(攻击-大麻使用-可卡因使用-敌意、攻击-激越-敌意)为最常见。
关键数值与推荐
- 前驱特征提取时间窗为发病前2年至6个月,每3个月评估一次,共61个前驱特征。
- 边权重用偏定向相关系数z表示,自相关范围为0.04≤z≤0.10。
- 中心性以离开(出中心性)或进入(入中心性)节点的非自回归连接之和计算。
临床怎么用
- 作者认为研究结果进一步支持跨诊断早期识别服务、细化评估以识别高风险个体,并将中心特征作为潜在干预靶点。
局限性
- 原文未报告局限性。
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
Modelling the prodrome to severe mental disorders (SMD), including unipolar mood disorders (UMD), bipolar mood disorders (BMD) and psychotic disorders (PSY), should consider both the evolution and interactions of symptoms and substance use (prodromal features) over time. Temporal network analysis can detect causal dependence between and within prodromal features by representing prodromal features as nodes, with their connections (edges) indicating the likelihood of one feature preceding the other. In SMD, node centrality could reveal insights into important prodromal features and potential intervention targets. Community analysis can identify commonly occurring feature groups to define SMD at-risk states. This retrospective (2-year) cohort study aimed to develop a global transdiagnostic SMD network of the temporal relationships between prodromal features and to examine within-group differences with sub-networks specific to UMD, BMD and PSY. Electronic health records (EHRs) from South London and Maudsley (SLaM) NHS Foundation Trust were included from 6462 individuals with SMD diagnoses (UMD:2066; BMD:740; PSY:3656). Validated natural language processing algorithms extracted the occurrence of 61 prodromal features every three months from two years to six months before SMD onset. Temporal networks of prodromal features were constructed using generalised vector autoregression panel analysis, adjusting for covariates. Edge weights (partial directed correlation coefficients, z) were reported in autocorrelative, unidirectional and bidirectional relationships. Centrality was calculated as the sum of (non-autoregressive) connections leaving (out-centrality, cout) or entering (in-centrality, cin) a node. The three sub-networks (UMD, BMD, PSY) were compared using permutation analysis, and community analysis was performed using Spinglass. The SMD network revealed strong autocorrelations (0.04 ≤ z ≤ 0.10), predominantly positive connections, and identified aggression (cout = 0.103) and tearfulness (cin = 0.134) as the most central features. Sub-networks for UMD, BMD, and PSY showed minimal differences, with 3.5% of edges differing between UMD and PSY, 0.8% between UMD and BMD, and 0.4% between BMD and PSY. Community analysis identified one positive psychotic community (delusional thinking-hallucinations-paranoia) and two behavioural communities (aggression-cannabis use-cocaine use-hostility, aggression-agitation-hostility) as the most common. This study represents the most extensive temporal network analysis conducted on the longitudinal interplay of SMD prodromal features. The findings provide further evidence to support transdiagnostic early detection services across SMD, refine assessments to detect individuals at risk and identify central features as potential intervention targets.
引用
- Arribas M, Barnby JM, Patel R, et al. Longitudinal evolution of the transdiagnostic prodrome to severe mental disorders: a dynamic temporal network analysis informed by natural language processing and electronic health records. Mol Psychiatry. 2025. PMID: 39843546. doi:10.1038/s41380-025-02896-3
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。