Della Valle Andrea, De Carlo Sara, Sonsini Gregorio, Pilati Sebastiano, Perali Andrea, Ubaldi Massimo, Ciccocioppo Roberto
School of Pharmacy, Center of Neuroscience, University of Camerino, Via Madonna delle Carceri, 62032, Camerino, MC, Italy.
School of Pharmacy, Physics Unit, Pharmacology Unit, University of Camerino, Camerino, Italy.
Sci Rep. 2025 Jul 1;15(1):22314. doi: 10.1038/s41598-025-05712-8.
The Forced Swim Test (FST) is a widely used preclinical model for assessing antidepressant efficacy, studying stress response, and evaluating depressive-like behaviours in rodents. Over the last 10 years, more than 5500 scientific articles reporting the use of the FST have been published. Despite its widespread use, the FST behaviours are still manually scored, resulting in a labor-intensive and time-consuming process that is prone to human bias and variability. Despite eliminating some biases, existing automated systems are costly and typically only able to distinguish between immobility and active behaviours. Therefore, they are often unable to accurately differentiate the major subtypes of movement patterns, such as swimming and climbing. To address these limitations, we propose a novel approach based on machine learning (ML) using a three-dimensional residual convolutional neural network (3D RCNN) that processes video pixels directly, capturing the spatiotemporal dynamics of rodent behaviour. Our ML model was validated against manual scoring in rats treated with fluoxetine and desipramine, two antidepressants known to induce distinct behavioural patterns. The ML model successfully differentiated among swimming, climbing, and immobility behaviours, demonstrating its potential as a standardized and unbiased tool for automatized behavioural analysis in the FST. Subsequently, we successfully validated our model by testing its ability to distinguish between drugs that predominantly evoke climbing (i.e., amitriptyline), those that preferentially facilitate swimming (i.e., paroxetine), and those that evoke both in a more balanced manner (i.e., venlafaxine). This approach represents a significant advancement in preclinical research, providing a more accurate and efficient method to analyze forced swimming data in rodents. We anticipate that in addition to the FST, our model and approach could be extended for application to various behavioural tests in laboratory animals, by training with specific datasets.
强迫游泳试验（FST）是一种广泛应用的临床前模型，用于评估抗抑郁药疗效、研究应激反应以及评估啮齿动物的抑郁样行为。在过去10年里，已发表了5500多篇报告使用FST的科学文章。尽管FST被广泛应用，但其行为仍需人工评分，这导致了一个劳动强度大、耗时且容易出现人为偏差和变异性的过程。尽管现有自动化系统消除了一些偏差，但成本高昂，通常只能区分不动行为和主动行为。因此，它们往往无法准确区分运动模式的主要亚型，如游泳和攀爬。为了解决这些局限性，我们提出了一种基于机器学习（ML）的新方法，使用三维残差卷积神经网络（3D RCNN）直接处理视频像素，捕捉啮齿动物行为的时空动态。我们的ML模型在接受氟西汀和地昔帕明治疗的大鼠中与人工评分进行了验证，这两种抗抑郁药已知会诱导不同的行为模式。该ML模型成功区分了游泳、攀爬和不动行为，证明了其作为FST中自动化行为分析的标准化且无偏差工具的潜力。随后，我们通过测试其区分主要诱发攀爬的药物（即阿米替林）、优先促进游泳的药物（即帕罗西汀）以及以更平衡方式诱发两者的药物（即文拉法辛）的能力，成功验证了我们的模型。这种方法代表了临床前研究的重大进展，为分析啮齿动物的强迫游泳数据提供了一种更准确、高效的方法。我们预计，除了FST之外，通过使用特定数据集进行训练，我们的模型和方法可以扩展应用于实验动物的各种行为测试。
