首发双相障碍复发风险预测:机器学习模型的开发、外部验证与药物治疗关联
研究基于瑞典(n=30,402)和芬兰(n=13,790)全国登记数据开发并验证机器学习模型预测首发双相障碍复发,内部验证AUROC为0.71,外部验证为0.68。模型纳入七个可获取预测因子,高危患者中长效针剂抗精神病药与精神科再住院风险降低相关(HR=0.44),低危组仅喹硫平联合丙戊酸盐或拉莫三嗪与风险降低相关。
要点
- 机器学习模型仅用七个可获取预测因子即可预测首发双相障碍复发风险。
- 高危患者中长效针剂抗精神病药与精神科再住院风险降低相关(HR=0.44)。
- 低危组仅喹硫平联合丙戊酸盐或拉莫三嗪与再住院风险降低相关。
核心结论
- 开发的机器学习模型在瑞典队列内部验证AUROC为0.71,在芬兰队列外部验证AUROC为0.68,可用于识别首发双相障碍复发高危个体。
- 高危患者中长效针剂抗精神病药与精神科再住院风险降低相关,低危患者中仅特定联合用药与风险降低相关,提示药物治疗效果可能随预测风险分层而异。
研究设计与样本
- 基于瑞典全国登记数据(n=30,402,随访2006-2021)和芬兰全国登记数据(n=13,790,随访1996-2018)开发并验证机器学习模型。
主要发现
- 模型在瑞典队列内部验证AUROC为0.71(95%CI=0.69-0.72),对精神病性躁狂所致复发AUROC最高为0.85(95%CI=0.80-0.89)。
- 模型在芬兰队列外部验证AUROC为0.68(95%CI=0.66-0.69),对非精神病性躁狂AUROC最高为0.74(95%CI=0.69-0.78)。
- 模型仅纳入七个可获取预测因子,包括首发后30天内药物治疗(锂盐、联合治疗、抗精神病药)、首发后30天内门诊随访、首发初始住院时间延长、既往精神科住院史和病假天数。
- 高危患者(N=10,119,31.77%)中长效针剂抗精神病药与精神科再住院风险降低相关(HR=0.44,95%CI 0.29-0.67)。
- 低危组(n=21,736,68.23%)中仅喹硫平联合丙戊酸盐(HR=0.79,95%CI=0.65-0.95)或联合拉莫三嗪(HR=0.86,95%CI=0.74-0.99)与再住院风险降低相关。
关键数值与推荐
- 高危组定义为模型预测风险最高的患者(N=10,119,占31.77%),该组长效针剂抗精神病药与再住院风险降低相关(HR=0.44,95%CI 0.29-0.67)。
- 低危组定义为其余患者(n=21,736,占68.23%),该组仅喹硫平联合丙戊酸盐(HR=0.79,95%CI=0.65-0.95)或联合拉莫三嗪(HR=0.86,95%CI=0.74-0.99)与再住院风险降低相关。
临床怎么用
- 该模型已在线开放供研究使用,可辅助识别首发双相障碍复发高危个体,支持早期启动长效针剂抗精神病药的个体化决策。
- 对预测低危的患者,可考虑喹硫平联合丙戊酸盐或拉莫三嗪的药物治疗方案,但需结合临床判断。
局限性
- 研究基于瑞典和芬兰登记数据,外部验证AUROC为0.68,模型在其他人群中的表现尚需进一步验证。
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
There are no established prognostic tools for predicting relapse risk in first-episode bipolar disorder (FEBD), limiting the use of personalized treatment approaches. We aimed to develop and validate a machine learning (ML) model to predict relapse in FEBD patients and assess whether pharmacotherapy effectiveness varies across predicted risk strata. We used nationwide registry data from Sweden (n = 30,402; follow-up = 2006-2021) and Finland (n = 13,790; follow-up = 1996-2018). The developed ML model achieved an area under the receiver operating characteristic curve (AUROC) of 0.71 (95% CI = 0.69-0.72, highest for relapse due to psychotic mania [AUROC = 0.85, 95% CI = 0.80-0.89]) in the Swedish cohort (internal validation) and 0.68 (95% CI = 0.66-0.69, highest for nonpsychotic mania [AUROC = 0.74, 95% CI = 0.69-0.78]) in the Finnish cohort (external validation). The model incorporated only seven accessible predictors, including pharmacotherapies during the first 30 days post-FEBD (lithium, combination treatments, and antipsychotics), outpatient follow-up within 30 days post-FEBD, prolonged initial hospitalization for FEBD, history of prior psychiatric hospitalizations, and sickness absence days. Among high-risk patients (N = 10,119, 31.77%), long-acting injectable (LAI) antipsychotics were associated with the greatest reduction in psychiatric rehospitalization risk (HR = 0.44, 95% CI 0.29-0.67). In the low-risk group (n = 21,736, 68.23%), only combinations of quetiapine with valproate (HR = 0.79, 95% CI = 0.65-0.95) or lamotrigine (HR = 0.86, 95% CI = 0.74-0.99) were associated with reduced rehospitalization risk. Available online for research purposes, our internally and externally validated prognostic model may inform clinical decision-making by identifying high-risk individuals who could benefit from early initiation of LAI antipsychotics, promoting a shift toward proactive, risk-guided treatment in FEBD patients.
引用
- Lieslehto J, Tiihonen J, Lähteenvuo M, et al. Relapse risk prediction in patients with first-episode bipolar disorder: development, external validation, and pharmacotherapy associations of a machine learning model. Mol Psychiatry. 2025. PMID: 41131281. doi:10.1038/s41380-025-03316-2
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。