Cascella Marco, Simonini Alessandro, Coluccia Sergio, Bignami Elena Giovanna, Fiore Gilberto, Petrucci Emiliano, Vergallo Alessandro, Sollecchia Giacomo, Marinangeli Franco, Pedone Roberto, Vittori Alessandro
Unit of Anesthesiology, Intensive Care Medicine, and Pain Medicine, Department of Medicine, Surgery, and Dentistry, University of Salerno, Baronissi, Salerno, 84082, Italy.
Pediatric Anesthesia and Intensive Care Unit, Salesi Children's Hospital, 60121, Ancona, Italy.
J Anesth Analg Crit Care. 2025 Jul 1;5(1):40. doi: 10.1186/s44158-025-00255-w.
Burnout (BO) is a serious issue affecting professionals across various sectors, leading to adverse psychological and occupational consequences, even in anesthesiologists. Machine learning, particularly neural networks, can offer effective data-driven approaches to identifying BO risk more accurately. This study aims to develop and evaluate different artificial dense neural network (DNN)-based models to predict BO based on occupational, psychological, and behavioral factors.
A dataset (300 Italian anesthesiologists) comprising workplace stressors, psychological well-being indicators, and demographic variables was used to train DNN models. Model performance was measured using standard evaluation metrics, including accuracy, precision, recall, and F1 score. Statistical tests were adopted to assess differences in prediction across the DNNs.
The best neural architecture achieved a predictive accuracy of 0.68, with key contributors to BO including workload, emotional exhaustion, job dissatisfaction, and lack of work-life balance. Despite substantial differences among the six implemented algorithms, no significant variation in prediction performance was observed.
Psychological distress scores are significantly higher in the high-risk BO group, suggesting greater anxiety, depression, and overall distress in this category. While challenges remain, continued advancements in artificial intelligence and data science promise more effective and personalized mental health care solutions.
Not applicable.
职业倦怠（BO）是一个严重问题，影响着各个领域的专业人员，会导致不良的心理和职业后果，麻醉医生也不例外。机器学习，尤其是神经网络，可以提供有效的数据驱动方法，更准确地识别职业倦怠风险。本研究旨在开发和评估基于不同人工密集神经网络（DNN）的模型，以根据职业、心理和行为因素预测职业倦怠。
使用一个数据集（300名意大利麻醉医生）训练DNN模型，该数据集包括工作场所压力源、心理健康指标和人口统计学变量。使用标准评估指标（包括准确率、精确率、召回率和F1分数）来衡量模型性能。采用统计检验来评估不同DNN在预测方面的差异。
最佳神经架构的预测准确率达到0.68，导致职业倦怠的关键因素包括工作量、情感耗竭、工作不满意以及缺乏工作与生活的平衡。尽管所实施的六种算法之间存在显著差异，但在预测性能方面未观察到显著变化。
高风险职业倦怠组的心理困扰得分显著更高，表明该类别中焦虑、抑郁和总体困扰程度更大。虽然挑战依然存在，但人工智能和数据科学的持续进步有望带来更有效和个性化的心理健康护理解决方案。
不适用。
