Fig. 1. Decision Curve Analysis (DCA) for neuroimaging models predictive of responsiveness to transcranial magnetic stimulation (TMS). The threshold probability (Pt) represents the point at which positive treatment response to TMS is valued equally to avoiding unnecessary treatment. Net benefit is defined as the percentage of individuals who receive TMS and achieve response minus a weighted percentage of treated individuals who do not respond. The dotted lines represent potential treatment strategies based on functional MRI-defined biotypes of depression from Drysdale et al. [7] When compared with alternative strategies of “treat all” or “treat none” (solid lines), the neuroimaging based strategies provide greater net benefit over a wide range of Pt values above 0.14. Psychiatry has been waiting for a neuroimaging test that can provide practical information to guide treatment decisions [1]. Despite decades of using magnetic resonance imaging to characterize psychiatric neurobiology, no imaging tests have been translated into clinical practice. Challenges to this goal include costs, relevant applications, reproducibility, and the absence of a simple method to evaluate a test’s clinical utility. The traditional statistical metrics reported in neuroimaging studies, such as sensitivity, specificity, and area under the curve, do not provide direct information about whether a test would change a clinical decision. To this end, we introduce the approach of decision curve analysis (DCA) to evaluate predictive neuroimaging models and demonstrate how DCA could be applied to the prediction of treatment response to transcranial magnetic stimulation (TMS) for major depression. DCA provides a framework to evaluate predictive models that incorporates the balancing of risks and benefits of treatment across a range of clinician and patient preferences [2]. DCA has been used to evaluate the clinical utility of predictive tests in oncology, cardiology, and other areas of medicine [3e5], but has yet to be adopted in psychiatry. The core componentofDCA is the conceptof “thresholdprobability” (Pt), or the probability at which an individual values the benefits of treatment equally to avoiding unnecessary treatment. If the probability of a condition being presentwere above the threshold probability, individuals would opt for treatment. Conversely, if this probability were below their threshold, individuals would avoid treatment. DCA calculates the net benefit of predictive models over a range of threshold probabilities and therefore a precise estimate of threshold probability is not required. The unit of net benefit in DCA is equal to the percentage of individuals appropriately treated (“true positives”) minus a weighted percentage of those inappropriately treated (“false positives”) given by a ratio of the threshold probability over its complement (as shown in Equation (1)). Therefore, at low threshold probabilities, the potential harm of false positives is considered low compared to the benefit of treatment. But, if the cost or risk of false positives were high, threshold probability increases and treatment would be reserved to individuals with a higher probability of the condition. The net benefit is then calculated over a range of threshold probabilities and is compared to “treat all” and “treat none” models. The strategy with the highest net benefit over a range of reasonable threshold probabilities is considered superior.

中文翻译：

---

抑郁症和经颅磁刺激的影像定义生物型的临床效用：决策曲线分析

图 1. 预测经颅磁刺激 (TMS) 反应性的神经影像模型的决策曲线分析 (DCA)。阈值概率 (Pt) 表示对 TMS 的积极治疗反应被同等重视以避免不必要的治疗的点。净收益定义为接受 TMS 并达到反应的个体百分比减去未反应的治疗个体的加权百分比。虚线代表基于功能性 MRI 定义的抑郁症生物型的潜在治疗策略，来自 Drysdale 等人。[7] 与“全部治疗”或“不治疗”（实线）的替代策略相比，基于神经影像学的策略在 0.14 以上的广泛 Pt 值范围内提供更大的净收益。精神病学一直在等待能够提供实用信息来指导治疗决策的神经影像学检查 [1]。尽管数十年来使用磁共振成像来表征精神病学神经生物学，但还没有成像测试转化为临床实践。实现这一目标的挑战包括成本、相关应用、可重复性以及缺乏一种简单的方法来评估测试的临床效用。神经影像学研究中报告的传统统计指标，例如敏感性、特异性和曲线下面积，并未提供有关测试是否会改变临床决策的直接信息。为此，我们介绍了决策曲线分析 (DCA) 方法来评估预测性神经影像学模型，并展示 DCA 如何应用于预测重度抑郁症对经颅磁刺激 (TMS) 的治疗反应。DCA 提供了一个评估预测模型的框架，该模型结合了一系列临床医生和患者偏好的治疗风险和收益的平衡[2]。DCA 已被用于评估预测测试在肿瘤学、心脏病学和其他医学领域的临床效用 [3e5]，但尚未在精神病学中采用。DCA 的核心组成部分是“阈值概率”(Pt) 的概念，即个体同等重视治疗益处与避免不必要治疗的概率。如果出现某种状况的概率高于阈值概率，则个人会选择治疗。相反，如果这个概率低于他们的阈值，个人将避免治疗。DCA 计算预测模型在一系列阈值概率上的净收益，因此不需要对阈值概率进行精确估计。DCA 中的净收益单位等于适当治疗的个体百分比（“真阳性”）减去根据阈值概率与其互补值的比率得出的不适当治疗（“假阳性”）的加权百分比（如图所示）在等式 (1)) 中。因此，在低阈值概率下，与治疗的益处相比，误报的潜在危害被认为是低的。但，如果误报的成本或风险很高，阈值概率会增加，并且治疗将保留给具有较高条件概率的个体。然后在一系列阈值概率上计算净收益，并将其与“全部治疗”和“不治疗”模型进行比较。在合理的阈值概率范围内具有最高净收益的策略被认为是优越的。