McInnes Aaron N, Olsen Sarah T, Sullivan Christi R P, Cooper Dawson C, Wilson Saydra, Sonmez Ayse Irem, Albott C Sophia, Olson Stephen C, Peterson Carol B, Rittberg Barry R, Herman Alexander, Bajzer Matej, Nahas Ziad, Widge Alik S
Department of Psychiatry and Behavioral Science, University of Minnesota Twin Cities, Minneapolis, MN, USA.
Pers Med Psychiatry. 2024 Nov-Dec;47-48. doi: 10.1016/j.pmip.2024.100135. Epub 2024 Aug 22.
Repetitive transcranial magnetic stimulation (rTMS) therapy could be improved by more accurate and earlier prediction of response. Latent class mixture (LCMM) and non-linear mixed effects (NLME) modeling have been applied to model the trajectories of antidepressant response (or non-response) to TMS, but it is not known whether such models are useful in predicting clinically meaningful change in symptom severity, i.e. categorical (non)response as opposed to continuous scores.
We compared LCMM and NLME approaches to model the antidepressant response to TMS in a naturalistic sample of 238 patients receiving rTMS for treatment resistant depression, across multiple coils and protocols. We then compared the predictive power of those models.
LCMM trajectories were influenced largely by baseline symptom severity, but baseline symptoms provided little predictive power for later antidepressant response. Rather, the optimal LCMM model was a nonlinear two-class model that accounted for baseline symptoms. This model accurately predicted patient response at 4 weeks of treatment (AUC = 0.70, 95% CI = [0.52 - 0.87]), but not before. NLME offered slightly improved predictive performance at 4 weeks of treatment (AUC = 0.76, 95% CI = [0.58 - 0.94], but likewise, not before.
In showing the predictive validity of these approaches to model response trajectories to rTMS, we provided preliminary evidence that trajectory modeling could be used to guide future treatment decisions.
重复经颅磁刺激（rTMS）疗法可通过更准确和更早地预测反应来改进。潜在类别混合（LCMM）和非线性混合效应（NLME）建模已被用于模拟TMS抗抑郁反应（或无反应）的轨迹，但尚不清楚此类模型是否有助于预测症状严重程度的临床有意义变化，即分类（无）反应而非连续分数。
我们比较了LCMM和NLME方法，以模拟238例接受rTMS治疗难治性抑郁症的患者在自然样本中的TMS抗抑郁反应，涉及多个线圈和方案。然后我们比较了这些模型的预测能力。
LCMM轨迹在很大程度上受基线症状严重程度影响，但基线症状对后期抗抑郁反应的预测能力很小。相反，最佳的LCMM模型是一个考虑基线症状的非线性两类模型。该模型准确预测了治疗4周时的患者反应（AUC = 0.70，95% CI = [0.52 - 0.87]），但在此之前不行。NLME在治疗4周时的预测性能略有提高（AUC = 0.76，95% CI = [0.58 - 0.94]），但同样在此之前不行。
通过展示这些方法对rTMS反应轨迹建模的预测有效性，我们提供了初步证据，表明轨迹建模可用于指导未来的治疗决策。
