文献速递临床试验与 GCP医学人工智能与信息学

个体化抗抑郁治疗决策支持系统:一项随机临床试验

A Decision-Support System to Personalize Antidepressant Treatment in Major Depressive Disorder: A Randomized Clinical Trial.
PubMed 文献 · JAMA · 2026-01-01

这项多中心随机临床试验纳入540例18-74岁重性抑郁障碍患者,评估基于网络的PETRUSHKA工具与常规护理相比的疗效。24周时PETRUSHKA组抑郁和焦虑症状改善更显著,但缺乏双盲设计和大量缺失数据限制结果有效性。

要点

  • PETRUSHKA决策支持工具可降低8周抗抑郁药停药率(17%vs27%)。
  • 工具组24周PHQ-9和GAD-7评分改善优于常规护理。
  • 开放标签设计和缺失数据限制结果解释,需谨慎推广。

核心结论

  • 与常规护理相比,PETRUSHKA工具增加8周时仍在服用抗抑郁药的患者数量,并改善24周抑郁和焦虑症状。
  • 缺乏双盲设计和大量缺失数据限制结果有效性。

研究设计与样本

  • 多中心随机临床试验,在巴西、加拿大和英国47个中心开展。
  • 纳入18-74岁重性抑郁障碍患者540例,1:1随机分为PETRUSHKA工具组(n=271)和常规护理组(n=269)。
  • 主要分析纳入493例,中位年龄35岁(IQR 25-48),女性58%,PHQ-9平均16.6(SD 5.1),GAD-7平均11.5(SD 4.1)。

临床怎么用

  • 对于重性抑郁障碍患者,可考虑使用PETRUSHKA决策支持工具辅助抗抑郁药选择,以提高早期治疗保留率。
  • 工具辅助决策可能有助于24周时抑郁和焦虑症状的进一步改善。

局限性

  • 缺乏双盲设计。
  • 大量缺失数据限制结果有效性。

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

IMPORTANCE: Antidepressants for moderate to severe major depressive disorder may be discontinued prematurely because the prescribed antidepressant is not always the most appropriate medication for an individual. Guidelines have recommended more precise targeting of antidepressant treatment. OBJECTIVE: To evaluate the efficacy of a web-based tool to personalize antidepressant treatment. DESIGN, SETTING, AND PARTICIPANTS: This multicenter, randomized clinical trial included persons between the ages of 18 and 74 years with major depressive disorder. The trial was conducted at 47 sites in 3 countries (Brazil, Canada, and the UK). The first participant was screened on November 29, 2022, and the last follow-up visit occurred on January 15, 2025. INTERVENTION: A total of 540 participants were randomized (1:1) to an evidence-based clinical decision-support system (PETRUSHKA tool; n = 271) or usual care (n = 269). MAIN OUTCOMES AND MEASURES: The primary outcome was treatment discontinuation due to any cause at 8 weeks. The secondary outcomes included treatment discontinuation up to 24 weeks due to adverse events and changes in depressive symptoms (measured with the 9-item Patient Health Questionnaire [PHQ-9]; range, 0-27; higher scores indicate more severe depression) and anxiety symptoms (measured with the 7-item Generalized Anxiety Disorder [GAD-7] questionnaire; range, 0-21; higher scores indicate more severe symptoms). RESULTS: Of the 520 eligible participants, 493 were included in the primary analysis (median age, 35 [IQR, 25 to 48] years; 58% female; PHQ-9 mean score, 16.6 [SD, 5.1]; GAD-7 mean score, 11.5 [SD, 4.1]). At 8 weeks, 41 of 241 participants (17%) in the PETRUSHKA group discontinued the prescribed antidepressant due to any cause vs 69 of 252 (27%) in the usual care group (adjusted relative risk, 0.62 [95% CI, 0.44 to 0.88]; P = .007). At 8 weeks, 22 of 241 participants (9%) in the PETRUSHKA group discontinued the prescribed antidepressant due to adverse events vs 39 of 252 (16%) in the usual care group (adjusted relative risk, 0.59 [95% CI, 0.36 to 0.97]; P = .04). For the assessment of depressive symptoms at 24 weeks, the mean PHQ-9 score was 7.1 (SD, 5.4) in the PETRUSHKA group vs 9.2 (SD, 6.5) in the usual care group (n = 129 in each group; adjusted between-group mean difference, -1.92 [95% CI, -3.06 to -0.78]; P < .001). For the assessment of anxiety symptoms at 24 weeks, the mean GAD-7 score was 4.6 (SD, 4.1) in the PETRUSHKA group (n = 133) vs 5.8 (SD, 4.9) in the usual care group (n = 126) (adjusted between-group mean difference, -1.39 [95% CI, -2.26 to -0.52]; P = .002). CONCLUSIONS AND RELEVANCE: Compared with usual care, use of the PETRUSHKA tool increased the number of patients still taking their antidepressant at 8 weeks and improved depressive and anxiety symptoms at 24 weeks. However, lack of a double-blind design and the large amount of missing data limit the validity of these results. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT05608330.

来源:JAMA,查看原文。版权归原作者所有。

引用

  1. Cipriani A, Fernandes KBP, Mulsant BH, et al. A Decision-Support System to Personalize Antidepressant Treatment in Major Depressive Disorder: A Randomized Clinical Trial. JAMA. 2026. PMID: 41779422. doi:10.1001/jama.2026.1327

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。