沉浸式翻译

A Review of the Application of Artificial Intelligence in Psychiatric Diagnosis and Treatment
人工智能在精神病学诊疗中的应用综述

Abstract: This paper comprehensively reviews the application of artificial intelligence (AI) in psychiatric diagnosis and treatment, covering multiple aspects such as basic theories, clinical practices, technological advancements, epidemiological studies, controversies and challenges, as well as future prospects. With the progress of science and technology, AI has demonstrated enormous potential in the field of psychiatry. Its applications, ranging from auxiliary diagnosis to personalized treatment, all indicate that its scope is continuously expanding. However, AI also faces numerous challenges in terms of ethics, accuracy, and even legal regulation. Through a systematic review of relevant literature, this paper aims to conduct an in-depth analysis of the current application status and future development directions of AI in psychiatry, providing references for further promoting research and practice in this field.
摘要：本文全面综述了人工智能（AI）在精神病学诊疗中的应用，涵盖基础理论、临床实践、技术进展、流行病学研究、争议与挑战以及未来展望等多个方面。随着科学技术的进步，人工智能在精神病学领域显示出巨大的潜力。其应用范围从辅助诊断到个性化治疗，都表明其应用范围不断扩大。然而，AI 在道德、准确性甚至法律法规方面也面临许多挑战。本文旨在通过对相关文献的系统梳理，深入分析人工智能在精神病学中的应用现状和未来发展方向，为进一步推动该领域的研究和实践提供参考。

Basic theories of artificial intelligence in psychiatric diagnosis and treatment
人工智能在精神病诊断和治疗中的基础理论

The development history of artificial intelligence technology in psychiatry
人工智能技术在精神病学领域的发展历史

The application of artificial intelligence (AI) in psychiatry is deepening, particularly in areas such as tremor monitoring, optimization of deep brain stimulation (DBS), EEG diagnosis of epilepsy, and surgical prediction, where it has shown significant potential. By integrating machine learning and deep learning technologies, AI can enhance the accuracy and efficiency of epilepsy monitoring, automate EEG analysis, and facilitate the development of personalized treatment strategies, thereby addressing the complexities of epilepsy management (AbuAlrob et al., 2025). Furthermore, the use of AI in neuroimaging is expanding, especially in early diagnosis, where enhanced image analysis capabilities significantly improve diagnostic accuracy and the precision of treatment planning (Dalboni da Rocha et al., 2025).In the management of epilepsy, the application of AI extends beyond diagnosis to include the prediction of seizures and the development of personalized treatment plans. Advances in machine learning and deep learning have significantly enhanced the automation of epilepsy monitoring and treatment. Despite ongoing challenges in model accuracy, interpretability, and applicability, these issues are being progressively addressed through interdisciplinary collaboration (Chen et al., 2025). In neuroimaging, AI has shown significant potential by improving image quality, reducing scan times, and enhancing diagnostic precision, particularly in the neuroimaging of pediatric cancers (Dalboni da Rocha et al., 2025)
人工智能（AI）在精神病学中的应用正在加深，特别是在震颤监测、深部脑刺激优化（DBS）、癫痫脑电图诊断和手术预测等领域，在这些领域显示出巨大的潜力。通过整合机器学习和深度学习技术，人工智能可以提高癫痫监测的准确性和效率，自动化脑电图分析，并促进个性化治疗策略的制定，从而解决癫痫管理的复杂性（AbuAlrob et al.， 2025）。此外，人工智能在神经影像学中的应用正在扩大，尤其是在早期诊断中，增强的图像分析能力显着提高了诊断准确性和治疗计划的精度（Dalboni da Rocha 等人，2025 年）。在癫痫管理中，AI 的应用超越了诊断，包括预测癫痫发作和制定个性化治疗计划。机器学习和深度学习的进步显着增强了癫痫监测和治疗的自动化。尽管在模型准确性、可解释性和适用性方面存在持续挑战，但这些问题正在通过跨学科合作逐步得到解决（Chen et al.， 2025）。在神经影像学中，人工智能通过提高图像质量、减少扫描时间和提高诊断精度，特别是在儿科癌症的神经影像学方面显示出巨大的潜力（Dalboni da Rocha 等人，2025 年）.

The application of AI in psychiatry extends beyond epilepsy and neuroimaging to include the early diagnosis and personalized treatment of neurodegenerative diseases, such as Alzheimer's disease. By integrating AI-enhanced neuroimaging techniques with MRI, PET, and CT scans, AI can accurately detect biomarkers of Alzheimer's disease and use machine learning models to analyze these images, identifying patterns of early cognitive decline(Kale et al., 2024). Furthermore, the role of AI in drug discovery and personalized treatment is expanding, accelerating the identification of effective treatments through predictive models and dynamically adjusting treatments based on individual responses (Kale et al., 2024)
人工智能在精神病学中的应用不仅限于癫痫和神经影像学，还包括神经退行性疾病（如阿尔茨海默病）的早期诊断和个性化治疗。通过将 AI 增强的神经成像技术与 MRI、PET 和 CT 扫描相结合，AI 可以准确检测阿尔茨海默病的生物标志物，并使用机器学习模型分析这些图像，识别早期认知能力下降的模式（Kale et al.， 2024）。此外，人工智能在药物发现和个性化治疗中的作用正在扩大，通过预测模型和根据个体反应动态调整治疗来加速确定有效治疗方法（Kale 等人，2024 年）.

Despite the promising prospects of AI in psychiatry, challenges such as data privacy, ethical considerations, and the seamless integration of AI tools into clinical workflows still need to be addressed. Future research should focus on establishing a comprehensive legal framework and regulatory mechanisms to ensure that the application of AI in psychiatry can enhance diagnostic accuracy and personalized treatment while protecting patient privacy and rights (Yin & Li, 2025). Through these efforts, AI is expected to play a more significant role in psychiatry, improving patients' quality of life
尽管 AI 在精神病学中的前景广阔，但仍需要解决数据隐私、道德考虑以及 AI 工具与临床工作流程的无缝集成等挑战。未来的研究应侧重于建立全面的法律框架和监管机制，以确保人工智能在精神病学中的应用可以提高诊断准确性和个性化治疗，同时保护患者的隐私和权利（Yin & Li，2025。通过这些努力，人工智能有望在精神病学中发挥更重要的作用，提高患者的生活质量.

The combination of the pathological mechanisms of mental illnesses and artificial intelligence
精神疾病的病理机制与人工智能的结合

Artificial intelligence and machine learning technologies have shown significant potential in the diagnosis and treatment of disorders of consciousness. By analyzing neuroimaging and electroencephalogram (EEG) data, these technologies can effectively differentiate between vegetative state and minimally conscious state (MCS) and predict patient recovery and treatment responses.
人工智能和机器学习技术在诊断和治疗意识障碍方面显示出巨大的潜力。通过分析神经影像学和脑电图（EEG）数据，这些技术可以有效区分植物人状态和最低意识状态（MCS），并预测患者的恢复和治疗反应。

First, AI and ML technologies have made significant progress in distinguishing VS/UWS from MCS. Research indicates that a dual-layer and dual-modal graph learning model, which combines functional magnetic resonance imaging and diffusion tensor imaging, can significantly enhance the accuracy of consciousness state classification(Qi et al., 2024) . Furthermore, the deep learning framework, based on EEG, has significantly improved the accuracy of DoC diagnosis by extracting time-frequency features and microstates, and integrating these with patients' clinical characteristics (Zhao et al., 2024)
首先，AI 和 ML 技术在区分 VS/UWS 和 MCS 方面取得了重大进展。研究表明，结合功能磁共振成像和扩散张量成像的双层和双模态图学习模型可以显著提高意识状态分类的准确性（Qi et al.， 2024）。此外，基于脑电图的深度学习框架通过提取时频特征和微观状态，并将其与患者的临床特征相结合，显著提高了 DoC 诊断的准确性（Zhao et al.， 2024）.

In terms of prediction, EEG-derived markers have been used to improve the assessment of DoC patients' outcomes. Using machine learning models, researchers can identify the most promising EEG features to predict the likelihood of patients recovering from DoC (Toppi et al., 2024). Furthermore, nonlinear dynamic analysis combined with machine learning algorithms has shown significant potential in enhancing DoC diagnosis, especially when auditory stimulation is used (Qu et al., 2024).AI and ML technologies also play a crucial role in predicting treatment responses. For instance, studies have shown that EEG-based machine learning models can predict patients' responses to zolpidem, a drug that significantly enhances brain activity in some VS/UWS patients (Machado et al., 2018). Additionally, tDCS (transcranial direct current stimulation) is considered a promising technique for improving consciousness. By measuring the changes in cortical excitability induced by tDCS, researchers can find electrophysiological evidence supporting its therapeutic effects (Bai et al., 2017)
在预测方面，EEG 衍生的标志物已被用于改进对 DoC 患者预后的评估。使用机器学习模型，研究人员可以确定最有前途的脑电图特征，以预测患者从 DoC 中恢复的可能性（Toppi 等人，2024 年）。此外，非线性动态分析与机器学习算法相结合在增强 DoC 诊断方面显示出巨大潜力，尤其是在使用听觉刺激时（Qu et al.， 2024）。AI 和 ML 技术在预测治疗反应方面也发挥着至关重要的作用。例如，研究表明，基于脑电图的机器学习模型可以预测患者对唑吡坦的反应，唑吡坦是一种可显着增强一些 VS/UWS 患者大脑活动的药物（Machado 等人，2018 年）。此外，tDCS（经颅直流电刺激）被认为是一种很有前途的提高意识的技术。通过测量 tDCS 诱导的皮层兴奋性的变化，研究人员可以找到支持其治疗效果的电生理学证据（Bai et al.， 2017）.

In summary, AI and ML technologies have shown broad application prospects in the diagnosis, prognosis, and prediction of treatment responses for DoC. These technologies not only enhance diagnostic accuracy but also provide a scientific basis for personalized treatment plans. Future research should continue to explore the clinical applications of these technologies to further improve the treatment and rehabilitation outcomes for DoC patients.
综上所述，AI 和 ML 技术在 DoC 的诊断、预后和治疗反应预测方面显示出广阔的应用前景。这些技术不仅提高了诊断准确性，还为个性化治疗计划提供了科学依据。未来的研究应继续探索这些技术的临床应用，以进一步改善 DoC 患者的治疗和康复结果。

The theoretical basis of artificial intelligence in the diagnosis of mental illnesses
人工智能在精神疾病诊断中的理论基础

Artificial Intelligence Clinical Practice in Psychiatric Diagnosis and Treatment
人工智能在精神病学诊断和治疗中的临床实践

Application cases of artificial intelligence in the diagnosis of mental illnesses
人工智能在精神疾病诊断中的应用案例

Artificial intelligence (AI) has demonstrated significant advances in psychiatric diagnosis, particularly in enhancing diagnostic accuracy, with systematic reviews reporting performance reaching 85%(Rony et al., 2025). Nevertheless, the clinical translation of AI in mental healthcare confronts critical barriers.A primary constraint is the limited clinical applicability of neuroimaging-based AI models. The feasibility and reporting quality of many such models remain inadequately assessed, with most exhibiting a high risk of bias—especially within analytical domains—severely restricting their clinical utility (Chen et al., 2023)
人工智能（AI）在精神病学诊断方面取得了重大进展，特别是在提高诊断准确性方面，系统评价报告的性能达到 85%（Rony et al.， 2025）。然而，人工智能在心理健康领域的临床转化面临着关键障碍。一个主要限制是基于神经影像学的 AI 模型的临床适用性有限。许多此类模型的可行性和报告质量仍未得到充分评估，大多数模型表现出高偏倚风险——尤其是在分析领域——严重限制了它们的临床效用（Chen 等人，2023 年）.

Equally critical are insufficient sample sizes and data heterogeneity. The inherent complexity and diversity of psychiatric disorders necessitate large, diverse datasets for robust model training and validation. Current studies are often hampered by limited samples, impairing generalizability, while data heterogeneity further complicates model development and deployment (Ostojic et al., 2024)
同样关键的是样本量不足和数据异质性。精神疾病固有的复杂性和多样性需要大型、多样化的数据集来进行强大的模型训练和验证。目前的研究经常受到样本有限的阻碍，损害了普遍性，而数据异质性进一步使模型开发和部署复杂化（Ostojic et al.， 2024）.

Finally, the 'black box' nature of AI decision-making impedes clinical interpretability, creating a significant barrier for practitioners and patients. Concurrently, substantial ethical concerns—including data privacy, algorithmic bias, and accountability- demand rigorous attention throughout the AI lifecycle (Fisher, 2025). In summary, despite its transformative potential for psychiatric diagnosis, AI's clinical integration requires overcoming challenges in model applicability, data robustness, interpretability, and ethical governance. Future efforts should prioritize these areas to realize AI's promise in mental health.
最后，AI 决策的“黑匣子”性质阻碍了临床可解释性，给从业者和患者造成了重大障碍。同时，包括数据隐私、算法偏见和问责制在内的重大道德问题需要在整个 AI 生命周期中得到严格关注（Fisher，2025 年）。总之，尽管 AI 在精神病学诊断方面具有变革性潜力，但其临床集成需要克服模型适用性、数据稳健性、可解释性和道德治理方面的挑战。未来的工作应优先考虑这些领域，以实现 AI 在心理健康方面的承诺。

Artificial intelligence-assisted technologies in the treatment of mental illnesses
人工智能辅助技术治疗精神疾病

The application of artificial intelligence (AI) in the field of psychiatry is expanding, particularly in the realm of auxiliary treatment. Chatbots, as a form of AI technology, can enhance psychological therapy by analyzing conversations. This technology not only provides immediate psychological support but also uses natural language processing to identify and understand patients' emotional states, thereby improving treatment strategies (Ng et al., 2025; Sedlakova & Trachsel, 2023)
人工智能（AI）在精神病学领域的应用正在扩大，尤其是在辅助治疗领域。聊天机器人作为人工智能技术的一种形式，可以通过分析对话来增强心理治疗。这项技术不仅提供即时的心理支持，还使用自然语言处理来识别和理解患者的情绪状态，从而改进治疗策略（Ng et al.， 2025;Sedlakova & Trachsel， 2023）.

In addition, AI has shown great potential in the analysis of genetic data. By analyzing patients' genetic data, AI can help doctors develop more accurate medication plans. This precision-based medication strategy can effectively reduce drug side effects and improve treatment outcomes(Sedlakova & Trachsel, 2023; Srivastav et al., 2025).In terms of behavioral data monitoring, AI also plays an important role. By continuously monitoring patients' behavioral data, AI can help customize personalized rehabilitation training programs. This approach not only improves the effectiveness of rehabilitation training but also helps patients better adapt to the treatment process(Ben Berners-Lee, 2024; Washington et al., 2020)
此外，人工智能在基因数据分析方面显示出巨大的潜力。通过分析患者的基因数据，AI 可以帮助医生制定更准确的用药计划。这种基于精准的用药策略可以有效减少药物副作用并改善治疗结果（Sedlakova & Trachsel，2023;Srivastav et al.， 2025）。在行为数据监测方面，AI 也发挥着重要作用。通过持续监控患者的行为数据，AI 可以帮助定制个性化的康复训练计划。这种方法不仅提高了康复训练的有效性，还帮助患者更好地适应治疗过程（Ben Berners-Lee，2024 年;Washington et al.， 2020）.

Finally, artificial intelligence has shown significant potential in enhancing the effectiveness of social therapy for adolescents. By interacting with teenagers, AI can help them improve their social skills and reduce social anxiety, thereby improving overall treatment outcomes(Kim et al., 2025; Rządeczka et al., 2025). These applications highlight the diverse potential of AI in the field of psychiatry, offering new ideas and tools for future treatments.
最后，人工智能在提高青少年社会治疗的有效性方面显示出巨大的潜力。通过与青少年互动，人工智能可以帮助他们提高社交技能并减少社交焦虑，从而改善整体治疗结果（Kim 等人，2025 年;Rządeczka et al.， 2025）的这些应用程序突出了 AI 在精神病学领域的多种潜力，为未来的治疗提供了新的想法和工具。

Artificial intelligence in clinical decision support in psychiatry
人工智能在精神病学临床决策支持中的应用

The application of artificial intelligence (AI) in the field of mental health offers new possibilities for improving decision-making efficiency and accuracy. However, the widespread use of this technology also faces many challenges, including trust issues, data security, and algorithmic bias.
人工智能（AI）在心理健康领域的应用为提高决策效率和准确性提供了新的可能性。然而，这项技术的广泛使用也面临着许多挑战，包括信任问题、数据安全和算法偏见。

First, the application of AI in mental health services has demonstrated its potential in improving diagnostic accuracy and treatment options. By analyzing vast amounts of health data, AI can help identify early signs of mental health issues and support personalized treatment plans(Auf et al., 2025; Balli et al., 2024). However, despite its strong performance in these areas, trust remains a significant barrier to its widespread adoption. The level of trust that healthcare providers and patients have in AI systems directly influences their acceptance and effectiveness in clinical settings(Higgins & Wilson, 2025)
首先，人工智能在心理健康服务中的应用已证明其在提高诊断准确性和治疗方案方面的潜力。通过分析大量健康数据，人工智能可以帮助识别心理健康问题的早期迹象并支持个性化的治疗计划（Auf et al.， 2025;Balli et al.， 2024）。然而，尽管信任在这些领域表现强劲，但信任仍然是其广泛采用的重大障碍。医疗保健提供者和患者对 AI 系统的信任程度直接影响他们在临床环境中的接受度和有效性（Higgins & Wilson， 2025）.

Second, data security is another significant challenge in the application of AI in mental health. Given the sensitivity of mental health data, ensuring its privacy and security is essential. AI systems need to process vast amounts of patient data, which necessitates stringent security measures during data storage and transmission to prevent data breaches and unauthorized access.
其次，数据安全是人工智能在心理健康领域的应用面临的另一个重大挑战。鉴于心理健康数据的敏感性，确保其隐私和安全至关重要。AI 系统需要处理大量患者数据，因此在数据存储和传输过程中需要采取严格的安全措施，以防止数据泄露和未经授权的访问。

Finally, algorithm bias is another critical issue that AI must address in the context of mental health applications. The decision-making capabilities of AI systems depend on the quality and diversity of their training data. If the training data is biased, AI systems may reflect these biases in their decisions, thereby affecting the fairness and accuracy of diagnoses and treatments. Therefore, developers need to implement measures during the algorithm design and data selection processes to minimize the impact of bias .
最后，算法偏差是 AI 在心理健康应用环境中必须解决的另一个关键问题。AI 系统的决策能力取决于其训练数据的质量和多样性。如果训练数据存在偏差，AI 系统可能会在其决策中反映这些偏差，从而影响诊断和治疗的公平性和准确性。因此，开发人员需要在算法设计和数据选择过程中实施措施，以最大限度地减少偏差的影响。

To sum up, although AI has great potential to improve the efficiency and accuracy of mental health decision-making, its wide application still needs to overcome challenges such as trust, data security and algorithm bias. Through continuous technical improvement and ethical norms improvement, AI is expected to play a greater role in future mental health services.
综上所述，尽管人工智能在提高心理健康决策的效率和准确性方面具有巨大潜力，但其广泛应用仍需克服信任、数据安全和算法偏差等挑战。通过持续的技术改进和道德规范的改进，人工智能有望在未来的心理健康服务中发挥更大的作用。

Artificial Intelligence Progress in Psychiatric Diagnosis and Treatment Technologies
人工智能在精神病学诊疗技术中的研究进展

Emerging technologies of artificial intelligence in the treatment of mental illnesses
人工智能治疗精神疾病的新兴技术

The application of artificial intelligence (AI) and virtual reality (VR) technologies in art therapy offers new possibilities for personalized interventions for mental illness. These technologies can not only enhance the effectiveness of treatment but also provide patients with richer means of expression. However, ethical and safety concerns cannot be ignored when applying these technologies.
人工智能（AI）和虚拟现实（VR）技术在艺术治疗中的应用为精神疾病的个性化干预提供了新的可能性。这些技术不仅可以提高治疗效果，还可以为患者提供更丰富的表达方式。然而，在应用这些技术时，道德和安全问题不容忽视。

First, the emergence of artificial intelligence-assisted therapy (AIATs) marks an innovative integration of digital technology with creative art therapy. Research indicates that AIATs can significantly enhance the therapeutic experience by offering new creative outlets and enhancing existing methods. However, this approach also presents potential drawbacks and ethical challenges. Therefore, when applying AIATs in mental health treatment, it is essential to strike a balance between innovation and ethical responsibility(Cao et al., 2025; Luo et al., 2024)
首先，人工智能辅助疗法（AIAT）的出现标志着数字技术与创意艺术疗法的创新整合。研究表明，AIAT 可以通过提供新的创意渠道和改进现有方法来显着增强治疗体验。然而，这种方法也存在潜在的缺点和道德挑战。因此，在将 AIAT 应用于心理健康治疗时，必须在创新和道德责任之间取得平衡（Cao et al.， 2025;Luo 等人，2024 年）.

Furthermore, integrating artificial intelligence and virtual reality into art and health programs can significantly enhance the cognitive functions and mental health of elderly individuals with mild cognitive impairment. Research indicates that participants in the AI and VR groups scored higher in cognitive function and mental health compared to the control group, particularly showing significant improvements in attention, expression, orientation, and memory(Cao et al., 2025)
此外，将人工智能和虚拟现实整合到艺术和健康计划中可以显着增强患有轻度认知障碍的老年人的认知功能和心理健康。研究表明，与对照组相比，AI 和 VR 组的参与者在认知功能和心理健康方面的得分更高，特别是在注意力、表情、定向和记忆力方面表现出显着改善（Cao et al.， 2025） .

To sum up, although the application of AI and VR technology in art therapy has great potential, ethical and safety issues must be fully considered in the implementation process to ensure that these technologies can be applied in a responsible way in clinical practice
综上所述，虽然人工智能和虚拟实境技术在艺术治疗中的应用潜力巨大，但在实施过程中必须充分考虑伦理和安全问题，以确保这些技术能以负责任的方式应用于临床实践中.

Integration and Optimization of Artificial Intelligence Technologies in Psychiatry
人工智能技术在精神病学中的整合和优化

In the field of psychiatry, integrating multi-source data, optimizing explainable models, and enhancing interdisciplinary collaboration are key strategies to improve the effectiveness of artificial intelligence (AI) applications. By integrating data from various sources, AI models can gain a more comprehensive understanding, thereby improving the accuracy and reliability of predictions. However, the 'black box' nature of AI models often leads to a lack of transparency in their decision-making processes, which can undermine user trust. Therefore, developing explainable AI models is crucial.
在精神病学领域，整合多源数据、优化可解释模型和加强跨学科合作是提高人工智能（AI）应用有效性的关键策略。通过整合来自各种来源的数据，AI 模型可以获得更全面的理解，从而提高预测的准确性和可靠性。然而，AI 模型的“黑匣子”性质通常会导致其决策过程缺乏透明度，这可能会破坏用户的信任。因此，开发可解释的 AI 模型至关重要。

In environmental assessments, similar challenges have been addressed to some extent. For instance, researchers have enhanced the effectiveness of AI in environmental assessments by utilizing multi-source big data and explainable high-precision models(Xu et al., 2024)
在环境评估中，类似的挑战已在一定程度上得到解决。例如，研究人员通过利用多源大数据和可解释的高精度模型提高了人工智能在环境评估中的有效性（Xu et al.， 2024）.

This approach not only improves the accuracy of the models but also enhances their interpretability through tools like saliency maps, making the contributions of each indicator to the model's predictions more transparent. Similarly, this method can be applied to psychiatry, where introducing explainable tools can help clinicians better understand the decision-making processes of AI models, thereby increasing their value in clinical practice.
这种方法不仅提高了模型的准确性，还通过显著性图等工具增强了模型的可解释性，使每个指标对模型预测的贡献更加透明。同样，这种方法可以应用于精神病学，引入可解释的工具可以帮助临床医生更好地理解 AI 模型的决策过程，从而提高它们在临床实践中的价值。

Furthermore, interdisciplinary collaboration is a crucial factor in enhancing the effectiveness of AI applications. In environmental science, the development and application of AI models require integrating knowledge from multiple disciplines, including computer science, statistics, and environmental science(Xu et al., 2024) . Similarly, in psychiatry, the effective use of AI necessitates close collaboration among psychiatry, data science, and ethics. Through interdisciplinary collaboration, potential issues in AI applications can be better identified and addressed, thereby improving the effectiveness and credibility of AI in psychiatry.
此外，跨学科合作是提高 AI 应用有效性的关键因素。在环境科学中，AI 模型的开发和应用需要整合来自计算机科学、统计学和环境科学等多个学科的知识（Xu et al.， 2024）。同样，在精神病学中，人工智能的有效使用需要精神病学、数据科学和伦理学之间的密切合作。通过跨学科合作，可以更好地识别和解决 AI 应用中的潜在问题，从而提高 AI 在精神病学中的有效性和可信度。

Epidemiological studies of artificial intelligence in psychiatry
人工智能在精神病学中的流行病学研究

Artificial intelligence analysis of epidemiological data on mental illnesses
人工智能分析精神疾病流行病学数据

Artificial intelligence has shown great potential in analyzing social media and public health data, particularly in the early warning of mental health issues and the evaluation of telemedicine outcomes. However, to fully leverage these technologies, challenges related to privacy and bias must be addressed. In recent years, with the outbreak of COVID-19, more research has focused on using social media data to predict users&039; mental health status. This approach not only aids in early intervention but also has the potential to significantly impact clinical practice and public health policies(Owen et al., 2024)
人工智能在分析社交媒体和公共卫生数据方面显示出巨大潜力，特别是在心理健康问题的早期预警和远程医疗结果的评估方面。然而，要充分利用这些技术，必须解决与隐私和偏见相关的挑战。近年来，随着 COVID-19 的爆发，更多的研究集中在使用社交媒体数据来预测用户&039;心理健康状况。这种方法不仅有助于早期干预，而且还有可能对临床实践和公共卫生政策产生重大影响（Owen 等人，2024 年）.

In this field, AI-driven methods, particularly natural language processing (NLP), have been widely applied to analyze large volumes of text data. However, a major challenge researchers face is the lack of high-quality public datasets, which are essential for benchmarking these methods. Additionally, researchers must adopt ethical and privacy frameworks to address the stigma faced by individuals with mental health conditions (Owen et al., 2024)
在该领域，AI 驱动的方法，尤其是自然语言处理（NLP），已被广泛应用于分析大量文本数据。然而，研究人员面临的一个主要挑战是缺乏高质量的公共数据集，而这些数据集对于对这些方法进行基准测试至关重要。此外，研究人员必须采用道德和隐私框架来解决患有心理健康问题的人面临的耻辱感（Owen 等人，2024 年）.

To support the development of mental health prediction methods, especially in severe conditions like schizophrenia, larger datasets are needed, including precise dates of participants&039 ' diagnoses. Inviting users to donate their social media data for research purposes could help address widespread ethical and privacy concerns. Multimodal approaches, which integrate social media data from voice, images, and videos for predictions, may offer advancements that text analysis alone cannot achieve(Owen et al., 2024)
为了支持心理健康预测方法的发展，尤其是在精神分裂症等严重情况下，需要更大的数据集，包括参与者的准确日期&039 ' 诊断。邀请用户出于研究目的捐赠他们的社交媒体数据有助于解决广泛的道德和隐私问题。多模态方法整合来自语音、图像和视频的社交媒体数据进行预测，可能会提供仅靠文本分析无法实现的进步（Owen 等人，2024 年）.

In the future, to be adopted in healthcare, medical support, or consumer products, multi-modal approaches for predicting mental health status need further development. These methods may gain more public trust in their effectiveness compared to text-based approaches alone. To achieve this, it is necessary to provide more high-quality social media datasets and formally address the privacy concerns associated with using these data. Social media platforms could be considered a feature that invites users to share data when they post content, as a potential solution(Owen et al., 2024)
未来，要用于医疗保健、医疗支持或消费品，预测心理健康状况的多模态方法需要进一步发展。与单独基于文本的方法相比，这些方法可能会获得公众对其有效性的更多信任。为了实现这一目标，有必要提供更高质量的社交媒体数据集，并正式解决与使用这些数据相关的隐私问题。社交媒体平台可以被视为一种功能，它邀请用户在发布内容时分享数据，作为一种潜在的解决方案（Owen 等人，2024 年）.

The application of artificial intelligence in the prevention of mental illnesses
人工智能在预防精神疾病中的应用

Artificial intelligence (AI) has shown great potential in predicting mental illness risk and customizing personalized prevention programs. However, to ensure the effectiveness and fairness of these technologies in clinical practice, data quality and algorithmic fairness are key factors that must be addressed.
人工智能（AI）在预测精神疾病风险和定制个性化预防计划方面显示出巨大潜力。然而，为了确保这些技术在临床实践中的有效性和公平性，数据质量和算法公平性是必须解决的关键因素。

First, the quality of data directly impacts the accuracy and reliability of predictive models. High-quality data must cover a broad range of biomarkers and behavioral data, ensuring both completeness and accuracy. For instance, biometric data collected by wearable devices, such as sleep patterns, activity levels, and heart rates, can provide crucial information for the early prediction of mental health issues (Saito et al., 2022). The accuracy and continuity of this data are essential for the effectiveness of predictive models.
首先，数据的质量直接影响预测模型的准确性和可靠性。高质量的数据必须涵盖广泛的生物标志物和行为数据，确保完整性和准确性。例如，可穿戴设备收集的生物特征数据，例如睡眠模式、活动水平和心率，可以为心理健康问题的早期预测提供重要信息（Saito 等人，2022 年）。这些数据的准确性和连续性对于预测模型的有效性至关重要。

Secondly, the fairness of algorithms is another critical consideration. When predicting mental health risks, algorithms should not exhibit unfair biases against specific population groups. For instance, in high-risk populations for mental illness, prediction models might show systematic biases due to differences in educational levels, thereby affecting the fairness of the predictions (Şahin et al., 2024). Therefore, when developing and applying these predictive models, it is essential to conduct fairness assessments to prevent exacerbating existing health inequalities.
其次，算法的公平性是另一个关键考虑因素。在预测心理健康风险时，算法不应对特定人群表现出不公平的偏见。例如，在精神疾病的高危人群中，由于教育水平的差异，预测模型可能会显示出系统性偏差，从而影响预测的公平性（Şahin et al.， 2024）。因此，在开发和应用这些预测模型时，必须进行公平性评估以防止加剧现有的健康不平等。

Overall, the application of AI in predicting mental health risks and developing personalized prevention programs holds great promise. However, it is essential to ensure data quality and algorithm fairness to maximize its benefits in clinical practice. This not only enhances the accuracy and reliability of predictions but also ensures that all patients can benefit equitably from these advanced technologies.
总体而言，人工智能在预测心理健康风险和开发个性化预防计划方面的应用前景广阔。然而，必须确保数据质量和算法公平性，以在临床实践中最大限度地发挥其优势。这不仅提高了预测的准确性和可靠性，还确保所有患者都能公平地从这些先进技术中受益。

Artificial intelligence prediction of the prevalent trends of mental illnesses
人工智能预测精神疾病的流行趋势

Artificial Intelligence (AI) has shown significant potential in predicting trends of mental health disorders, particularly in the context of the pandemic. By analyzing big data, AI can assist public health departments in optimizing resource allocation and developing more effective intervention strategies. For instance, during the COVID-19 pandemic, AI was used to forecast the public&039; s mental health needs, providing crucial insights for health policymakers (Othman et al., 2024)
人工智能（AI）在预测心理健康障碍的趋势方面显示出巨大的潜力，尤其是在大流行的背景下。通过分析大数据，AI 可以帮助公共卫生部门优化资源分配并制定更有效的干预策略。例如，在 COVID-19 大流行期间，人工智能被用于预测公众的心理健康需求&039;，为卫生政策制定者提供重要见解（Othman 等人，2024 年）.

The application of AI technology in the mental health field extends beyond predicting trends to include early detection of mental illnesses and the development of personalized treatment plans. Research indicates that AI can enhance the accuracy of diagnosing mental disorders by analyzing a variety of data sources, including electronic health records, mood rating scales, and brain imaging data(Graham et al., 2019). Furthermore, AI can predict and categorize mental health issues, such as depression and suicidal thoughts, using data from social media platforms(Graham et al., 2019)
人工智能技术在心理健康领域的应用不仅限于预测趋势，还包括精神疾病的早期发现和个性化治疗计划的制定。研究表明，人工智能可以通过分析各种数据源来提高诊断精神障碍的准确性，包括电子健康记录、情绪评定量表和脑成像数据（Graham et al.， 2019）。此外，人工智能可以使用来自社交媒体平台的数据预测和分类心理健康问题，例如抑郁症和自杀念头（Graham et al.， 2019）.

During the pandemic, mental health issues have significantly increased globally, making the application of AI particularly important. Systematic reviews and meta-analyses show that the global prevalence of mental health issues such as depression, anxiety, and stress has risen significantly during the pandemic (Nochaiwong et al., 2021). AI models can help predict these trends, thereby supporting public health interventions.
在大流行期间，全球心理健康问题显着增加，这使得 AI 的应用尤为重要。系统评价和荟萃分析表明，在大流行期间，抑郁、焦虑和压力等心理健康问题的全球患病率显着上升（Nochaiwong 等人，2021 年）。AI 模型可以帮助预测这些趋势，从而支持公共卫生干预。

However, despite the promising prospects of AI in mental health, the reliability and accuracy of its models still require continuous improvement. Research indicates that the gap between AI technology and mental health research and clinical care needs to be bridged to ensure its practical effectiveness (Graham et al., 2019). Moreover, the application of AI in mental health prediction faces ethical and privacy challenges, which must be thoroughly addressed during the technological development process(Graham et al., 2019) .
然而，尽管人工智能在心理健康方面的前景广阔，但其模型的可靠性和准确性仍需要不断改进。研究表明，需要弥合人工智能技术与心理健康研究和临床护理之间的差距，以确保其实际效果（Graham et al.， 2019）。此外，人工智能在心理健康预测中的应用面临道德和隐私挑战，必须在技术发展过程中彻底解决（Graham et al.， 2019）。

In epidemic control, the integration of AI models like the SEIR model with AI has proven effective in predicting epidemic trends. These models not only help predict the peak and scale of an epidemic but also provide a scientific basis for government control measures(Feng et al., 2021). Therefore, continuously improving the reliability and accuracy of AI models is crucial for enhancing the efficiency of public health resource utilization and preparing for future health crises.
在疫情控制方面，SEIR 模型与 AI 等 AI 模型的集成已被证明可以有效预测疫情趋势。这些模型不仅有助于预测疫情的高峰和规模，还为政府的控制措施提供了科学依据（Feng et al.， 2021）。因此，不断提高 AI 模型的可靠性和准确性对于提高公共卫生资源利用效率和为未来的健康危机做好准备至关重要。

Controversies and Challenges of Artificial Intelligence in Psychiatric Diagnosis and Treatment
人工智能在精神病诊断和治疗中的争议和挑战

Ethical issues of artificial intelligence in psychiatry
人工智能在精神病学中的伦理问题

The application of artificial intelligence (AI) has shown great potential in many fields, but it also brings numerous ethical challenges. First, data privacy is a critical ethical concern in AI applications. AI systems typically need to process vast amounts of personal data, and the collection, storage, and use of this data must adhere to strict privacy protection measures to prevent data breaches and misuse(Taddese et al., 2025). Additionally, algorithmic bias is another key issue that needs addressing. The decisions made by AI systems can be influenced by inherent biases in the training data, leading to unfair outcomes. Therefore, developers must take steps during the algorithm design and data selection processes to minimize the impact of these biases(Arriagada-Bruneau et al., 2024; Hanna et al., 2024)
人工智能（AI）的应用在许多领域都显示出巨大的潜力，但它也带来了许多道德挑战。首先，数据隐私是 AI 应用程序中的一个关键道德问题。AI 系统通常需要处理大量个人数据，并且这些数据的收集、存储和使用必须遵守严格的隐私保护措施，以防止数据泄露和滥用（Taddese et al.， 2025）。此外，算法偏见是另一个需要解决的关键问题。AI 系统做出的决策可能会受到训练数据中固有偏见的影响，从而导致不公平的结果。因此，开发人员必须在算法设计和数据选择过程中采取措施，以尽量减少这些偏差的影响（Arriagada-Bruneau 等人，2024 年;Hanna et al.， 2024）.

In terms of responsibility attribution, the automated decision-making capabilities of AI systems complicate the delineation of responsibilities. This is particularly true in critical sectors like healthcare, where clearly defining the boundaries between AI and human users is essential to ensure accountability and corrective actions when issues arise(Mohsin Khan et al., 2024; Willem et al., 2024). To address these challenges, it is crucial to establish a comprehensive ethical framework. This framework should encompass principles such as transparency, explainability, fairness, and accountability, guiding the development and application of AI(Heuser et al., 2025; Kowald et al., 2024)
在责任归属方面，AI 系统的自动化决策能力使责任划分复杂化。在医疗保健等关键领域尤其如此，在这些领域，明确定义人工智能和人类用户之间的界限对于确保在出现问题时问责制和采取纠正措施至关重要（Mohsin Khan 等人，2024 年;Willem et al.， 2024）。为了应对这些挑战，建立一个全面的道德框架至关重要。该框架应包含透明度、可解释性、公平性和问责制等原则，指导人工智能的开发和应用（Heuser 等人，2025 年;Kowald 等人，2024 年）.

Furthermore, interdisciplinary collaboration and ongoing research are crucial for addressing AI ethics. By integrating perspectives from technology, law, and social sciences, we can gain a more comprehensive understanding of the ethical challenges posed by AI. This collaboration not only aids in formulating more effective policies and standards but also promotes the responsible use of AI technology, ensuring its sustainable development in society(Achuthan et al., 2024)
此外，跨学科合作和正在进行的研究对于解决 AI 伦理问题至关重要。通过整合技术、法律和社会科学的观点，我们可以更全面地了解 AI 带来的道德挑战。这种合作不仅有助于制定更有效的政策和标准，还促进了人工智能技术的负责任使用，确保其在社会中的可持续发展（Achuthan et al.， 2024）.

Accuracy and reliability of artificial intelligence in the diagnosis and treatment of mental illnesses
人工智能在精神疾病诊断和治疗中的准确性和可靠性

The application of artificial intelligence (AI) in medical diagnosis has shown significant potential, but the accuracy of AI diagnoses varies. For instance, in some cases, the accuracy of AI diagnoses can reach 85%, but this does not mean it will maintain the same level in all scenarios. The generalization capability of AI systems, which is their ability to perform effectively across different clinical settings and patient populations, still requires further validation and optimization(Zhang et al., 2022) .
人工智能（AI）在医学诊断中的应用显示出巨大的潜力，但 AI 诊断的准确性各不相同。例如，在某些情况下，AI 诊断的准确率可以达到 85%，但这并不意味着在所有场景下都会保持相同的水平。人工智能系统的泛化能力，即它们在不同的临床环境和患者群体中有效执行的能力，仍然需要进一步的验证和优化（Zhang et al.， 2022）。

To enhance the accuracy and generalization of AI in diagnosis and treatment, researchers are exploring various methods. For instance, integrating deep learning technology with the expertise of clinical doctors can significantly improve diagnostic accuracy. Although AI models may not match the expertise of experienced clinicians, combining AI diagnoses with human assessments can boost overall diagnostic accuracy(Li et al., 2021)
为了提高人工智能在诊断和治疗中的准确性和泛化性，研究人员正在探索各种方法。例如，将深度学习技术与临床医生的专业知识相结合可以显著提高诊断准确性。尽管 AI 模型可能无法与经验丰富的临床医生的专业知识相匹配，但将 AI 诊断与人工评估相结合可以提高整体诊断准确性（Li et al.， 2021）.

Moreover, AI has shown potential in the early diagnosis of mental disorders. By analyzing speech patterns, behaviors, and physiological data, AI can identify early signs of mental illnesses such as bipolar disorder, schizophrenia, autism spectrum disorder, depression, suicidal tendencies, and dementia. This early detection capability is crucial for timely intervention and effective treatment (Baran & Cetin, 2025)
此外，人工智能在精神障碍的早期诊断中显示出潜力。通过分析语音模式、行为和生理数据，AI 可以识别精神疾病的早期迹象，例如双相情感障碍、精神分裂症、自闭症谱系障碍、抑郁症、自杀倾向和痴呆。这种早期发现能力对于及时干预和有效治疗至关重要（Baran & Cetin，2025）.

However, the application of AI in the medical field still requires long-term clinical validation and optimization to ensure its efficacy and safety. By continuously optimizing models, improving data preprocessing techniques, and fine-tuning hyperparameters, the performance of AI systems can be significantly enhanced, thereby better supporting clinical decision-making and personalized treatment strategies(Baran & Cetin, 2025)
然而，人工智能在医疗领域的应用仍需要长期的临床验证和优化，以确保其有效性和安全性。通过不断优化模型，改进数据预处理技术和微调超参数，可以显著提高 AI 系统的性能，从而更好地支持临床决策和个性化治疗策略（Baran & Cetin， 2025）.

Legal and regulatory challenges of artificial intelligence in psychiatry
人工智能在精神病学中的法律和监管挑战

The application of artificial intelligence (AI) in the medical field has brought many opportunities, but it also faces challenges such as ambiguous responsibility definitions, outdated laws, and data compliance issues. Firstly, as AI technology continues to develop, its autonomy gradually increases, making it more difficult to determine responsibility when problems arise. Traditional legal frameworks struggle to adapt to the dynamic learning characteristics of AI, which differ from static products, leading to complexities in defining product defects and attributing responsibility(Bottomley & Thaldar, 2023). Moreover, data compliance is also one of the significant challenges faced by AI in the medical field. When processing sensitive health data, AI must adhere to strict data protection regulations to ensure that patients' rights and privacy are not violated. To fully leverage the advantages of AI while protecting patients' rights, it is essential to follow relevant legal frameworks(Haftenberger & Dierks, 2023). Therefore, improving the regulatory framework to address these challenges is particularly important. By reassessing and adjusting existing legal concepts or exploring new legal avenues, such as risk-based liability determination methods, clearer legal guidance can be provided for the application of AI. Additionally, establishing appropriate regulatory sandbox environments to facilitate the safe testing and application of AI technology will also contribute to the healthy development of AI in the medical field(Bottomley & Thaldar, 2023)
人工智能（AI）在医疗领域的应用带来了许多机遇，但也面临着责任定义模糊、法律过时和数据合规问题等挑战。首先，随着 AI 技术的不断发展，其自主性逐渐增强，使得出现问题时更难确定责任。传统的法律框架难以适应 AI 的动态学习特性，这与静态产品不同，导致定义产品缺陷和归属责任的复杂性（Bottomley & Thaldar，2023）。此外，数据合规性也是人工智能在医疗领域面临的重大挑战之一。在处理敏感的健康数据时，AI 必须遵守严格的数据保护法规，以确保患者的权利和隐私不受侵犯。为了充分利用 AI 的优势同时保护患者的权利，必须遵循相关的法律框架（Haftenberger & Dierks， 2023）。因此，改进监管框架以应对这些挑战尤为重要。通过重新评估和调整现有的法律概念或探索新的法律途径，例如基于风险的责任确定方法，可以为人工智能的应用提供更清晰的法律指导。此外，建立适当的监管沙盒环境以促进 AI 技术的安全测试和应用也将有助于 AI 在医疗领域的健康发展（Bottomley & Thaldar），2023）.

Future Prospects of Artificial Intelligence-Assisted Psychiatry
人工智能辅助精神病学的未来展望

Development trends of artificial intelligence technology in psychiatric diagnosis and treatment
人工智能技术在精神病学诊疗中的发展趋势

In the future, artificial intelligence (AI) is expected to integrate with virtual reality (VR) and brain-computer interface (BCI) technologies to optimize interpretable models, thereby providing more precise services throughout the entire process of mental health treatment. Through this integration, AI can use the controllable environment provided by VR to manipulate sensory inputs and monitor and adjust neural activities in real time through BCI. This combination not only stimulates specific brain regions, triggering neurochemical changes, but also influences cognitive functions such as memory, perception, and motor skills (Haftenberger & Dierks, 2023)
未来，人工智能（AI）有望与虚拟现实（VR）和脑机接口（BCI）技术相结合，以优化可解释模型，从而在心理健康治疗的整个过程中提供更精准的服务。通过这种集成，AI 可以使用 VR 提供的可控环境来纵感官输入，并通过 BCI 实时监控和调整神经活动。这种组合不仅刺激特定的大脑区域，触发神经化学变化，而且还影响认知功能，如记忆、感知和运动技能（Haftenberger & Dierks，2023 年）.

Research indicates that VR and BCI interventions have significant potential in rehabilitation, the treatment of phobias and anxiety disorders, and cognitive enhancement. Personalized VR experiences can be tailored based on BCI feedback, thereby enhancing the effectiveness of these interventions. The integration of this technology not only aids in understanding and leveraging neuroplasticity but also offers new perspectives for cognitive and therapeutic applications (Haftenberger & Dierks, 2023)
研究表明，VR 和 BCI 干预在康复、治疗恐惧症和焦虑症以及增强认知方面具有巨大潜力。可以根据 BCI 反馈定制个性化的 VR 体验，从而提高这些干预的有效性。这项技术的集成不仅有助于理解和利用神经可塑性，而且还为认知和治疗应用提供了新的视角（Haftenberger & Dierks，2023）.

In addition, the combination of AI VR and BCI technology can also provide a new perspective for the accurate diagnosis and personalized treatment of mild cognitive impairment. This integrated approach is expected to play an important role in the future mental health field, providing patients with more personalized and precise treatment plans (Yao et al., 2024)
此外，AI VR 和 BCI 技术的结合也可以为轻度认知障碍的准确诊断和个性化治疗提供新的视角。这种综合方法有望在未来的心理健康领域发挥重要作用，为患者提供更个性化和精确的治疗计划（Yao et al.， 2024）.

The prospects of interdisciplinary cooperation between psychiatry and artificial intelligence
精神病学与人工智能跨学科合作的前景

Interdisciplinary collaboration between medical professionals and engineers plays a vital role in the advancement of modern medical technology. This collaboration not only facilitates the development of precision medicine models but also enhances both clinical practice and the cultivation of interdisciplinary talent. Medical experts and engineers often encounter cognitive and epistemological barriers during their collaboration, which stem from the highly specialized knowledge and practical experience in their respective fields(van Baalen & Boon, 2024)
医疗专业人员和工程师之间的跨学科合作在现代医疗技术的进步中发挥着至关重要的作用。这种合作不仅促进了精准医学模式的发展，还促进了临床实践和跨学科人才的培养。医学专家和工程师在合作过程中经常会遇到认知和认识论障碍，这些障碍源于他们在各自领域的高度专业知识和实践经验（van Baalen & Boon， 2024）.

To overcome these challenges, researchers developed a framework to clarify the disciplinary perspectives of experts involved in interdisciplinary research collaborations. This framework enables experts to more clearly articulate their professional methods, thereby enhancing mutual understanding (van Baalen & Boon, 2024). For instance, in an interdisciplinary medical research project aimed at developing and implementing diffusion MRI technology for kidney cancer diagnosis, this framework was used to analyze and elucidate the disciplinary perspectives of participants, demonstrating its applicability in interdisciplinary research projects (van Baalen & Boon, 2024)
为了克服这些挑战，研究人员开发了一个框架来阐明参与跨学科研究合作的专家的学科观点。这个框架使专家能够更清晰地阐述他们的专业方法，从而增强相互理解（van Baalen & Boon，2024）。例如，在一个旨在开发和实施扩散 MRI 技术用于肾癌诊断的跨学科医学研究项目中，这个框架被用来分析和阐明参与者的学科观点，证明了它在跨学科研究项目中的适用性（van Baalen & Boon，2024 年）.

This framework not only facilitates the smooth progress of interdisciplinary research but also provides educators with a tool to support students in developing interdisciplinary professional skills. By integrating this framework and its philosophical foundation into health education, students can better understand and apply interdisciplinary knowledge and skills, thereby becoming versatile talents in their future careers(van Baalen & Boon, 2024)
该框架不仅促进了跨学科研究的顺利进行，还为教育工作者提供了一个工具，以支持学生发展跨学科专业技能。通过将这个框架及其哲学基础融入健康教育，学生可以更好地理解和应用跨学科知识和技能，从而成为他们未来职业生涯中的多才多艺的人才（van Baalen & Boon），2024 年）.

References
引用

AbuAlrob, M. A., Itbaisha, A., & Mesraoua, B. (2025). Unlocking new frontiers in epilepsy through AI: From seizure prediction to personalized medicine. Epilepsy Behav, 166, 110327. https://doi.org/10.1016/j.yebeh.2025.110327
AbuAlrob， M. A.， Itbaisha， A.， & Mesraoua， B. （2025 年）。通过 AI 解锁癫痫的新领域：从癫痫发作预测到个性化医疗。癫痫行为 166， 110327. https://doi.org/10.1016/j.yebeh.2025.110327

Achuthan, K., Ramanathan, S., Srinivas, S., & Raman, R. (2024). Advancing cybersecurity and privacy with artificial intelligence: current trends and future research directions. Front Big Data, 7, 1497535. https://doi.org/10.3389/fdata.2024.1497535
Achuthan， K.， Ramanathan， S.， Srinivas， S.， & Raman， R. （2024）。利用人工智能推进网络安全和隐私：当前趋势和未来研究方向。Front Big Data 7,1497535。 https://doi.org/10.3389/fdata.2024.1497535

Arriagada-Bruneau, G., López, C., & Davidoff, A. (2024). A Bias Network Approach (BNA) to Encourage Ethical Reflection Among AI Developers. Sci Eng Ethics, 31(1), 1. https://doi.org/10.1007/s11948-024-00526-9
Arriagada-Bruneau， G.， López， C.， & Davidoff， A. （2024）。一种偏见网络方法（BNA），以鼓励 AI 开发人员进行道德反思。科学工程伦理学 31（1），1。 https://doi.org/10.1007/s11948-024-00526-9

Auf, H., Svedberg, P., Nygren, J., Nair, M., & Lundgren, L. E. (2025). The Use of AI in Mental Health Services to Support Decision-Making: Scoping Review. J Med Internet Res, 27, e63548. https://doi.org/10.2196/63548
Auf， H.， Svedberg， P.， Nygren， J.， Nair， M.， & Lundgren， L. E. （2025）.在心理健康服务中使用人工智能来支持决策：范围审查。J Med 互联网研究 27，e63548。 https://doi.org/10.2196/63548

Bai, Y., Xia, X., Kang, J., Yang, Y., He, J., & Li, X. (2017). TDCS modulates cortical excitability in patients with disorders of consciousness. Neuroimage Clin, 15, 702-709. https://doi.org/10.1016/j.nicl.2017.01.025
Bai， Y.， Xia， X.， Kang， J.， Yang， Y.， He， J.， & Li， X. （2017）.TDCS 调节意识障碍患者的皮质兴奋性。神经影像临床 15， 702-709。 https://doi.org/10.1016/j.nicl.2017.01.025

Balli, M., Doğan, A. E., & Eser, H. Y. (2024). Improving Psychiatry Services with Artificial Intelligence: Opportunities and Challenges. Turk Psikiyatri Derg, 35(4), 317-328. https://doi.org/10.5080/u27604 (Psikiyatri Hizmetlerinin Yapay Zekâ ile Geliştirilmesi: Fırsatlar ve Zorluklar.)
Balli， M.， Dogan， A. E.， & Eser， H. Y. （2024 年）。利用人工智能改善精神病学服务：机遇与挑战。土耳其精神病学杂志 35（4），317-328。 https://doi.org/10.5080/u27604（利用人工智能改善精神病学服务：机遇与挑战。

Baran, F. D. E., & Cetin, M. (2025). AI-driven early diagnosis of specific mental disorders: a comprehensive study. Cogn Neurodyn, 19(1), 70. https://doi.org/10.1007/s11571-025-10253-x
Baran， F. D. E.， & Cetin， M. （2025）。人工智能驱动的特定精神障碍的早期诊断：一项综合研究。认知神经 dyn 19（1），70。 https://doi.org/10.1007/s11571-025-10253-x

Ben Berners-Lee, D. (2024). Training humans to supplement a machine learning system: The role of guides in a digital mental health intervention. Soc Sci Med, 365, 117586. https://doi.org/10.1016/j.socscimed.2024.117586
本·伯纳斯-李，D.（2024 年）。训练人类补充机器学习系统：指南在数字心理健康干预中的作用。Soc Sci Med 365， 117586. https://doi.org/10.1016/j.socscimed.2024.117586

Bottomley, D., & Thaldar, D. (2023). Liability for harm caused by AI in healthcare: an overview of the core legal concepts. Front Pharmacol, 14, 1297353. https://doi.org/10.3389/fphar.2023.1297353
Bottomley， D. 和 Thaldar， D. （2023）。医疗保健领域人工智能造成的伤害责任：核心法律概念概述。前药理学 14， 1297353。 https://doi.org/10.3389/fphar.2023.1297353

Cao, Y., Yin, H., Hua, X., Bi, S., & Zhou, D. (2025). Effects of artificial intelligence and virtual reality interventions in art therapy among older people with mild cognitive impairment. Australas J Ageing, 44(1), e70006. https://doi.org/10.1111/ajag.70006
曹， Y.，尹， H.，华， X.，毕， S.， & 周， D. （2025）.人工智能和虚拟现实干预对轻度认知障碍老年人艺术治疗的影响。Australas J Ageing 44（1）， e70006. https://doi.org/10.1111/ajag.70006

Chen, Y., Ou, Z., Zhou, D., & Wu, X. (2025). Advancements and Challenges of Artificial Intelligence-Assisted Electroencephalography in Epilepsy Management. J Clin Med, 14(12). https://doi.org/10.3390/jcm14124270
陈尹，欧， Z.，周， D.， & 吴， X. （2025）.人工智能辅助脑电图在癫痫管理中的进步和挑战。临床医学杂志 14（12）。 https://doi.org/10.3390/jcm14124270

Chen, Z., Liu, X., Yang, Q., Wang, Y. J., Miao, K., Gong, Z., Yu, Y., Leonov, A., Liu, C., Feng, Z., & Chuan-Peng, H. (2023). Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review. JAMA Netw Open, 6(3), e231671. https://doi.org/10.1001/jamanetworkopen.2023.1671
陈，Z.，刘晓波，杨奎，王耀杰，苗缪，龚，Z.，于 Y.，列昂诺夫，A.，刘 C.，冯，Z.和川鹏，H.（2023）。基于神经影像学的精神病学诊断人工智能模型中的偏倚风险评估：系统评价。JAMA Netw Open 6（3），e231671。 https://doi.org/10.1001/jamanetworkopen.2023.1671

Dalboni da Rocha, J. L., Lai, J., Pandey, P., Myat, P. S. M., Loschinskey, Z., Bag, A. K., & Sitaram, R. (2025). Artificial Intelligence for Neuroimaging in Pediatric Cancer. Cancers (Basel), 17(4). https://doi.org/10.3390/cancers17040622
Dalboni da Rocha， J. L.， Lai， J.， Pandey， P.， Myat， P. S. M.， Loschinskey， Z.， Bag， A. K.， & Sitaram， R. （2025）.用于小儿癌症神经影像学的人工智能。癌症（巴塞尔）17（4）。 https://doi.org/10.3390/cancers17040622

Feng, S., Feng, Z., Ling, C., Chang, C., & Feng, Z. (2021). Prediction of the COVID-19 epidemic trends based on SEIR and AI models. PLoS One, 16(1), e0245101. https://doi.org/10.1371/journal.pone.0245101
Feng， S.， Feng， Z.， Ling， C.， Chang， C.， & Feng， Z. （2021）.基于 SEIR 和 AI 模型预测 COVID-19 流行趋势。公共科学图书馆一号 16（1），e0245101。 https://doi.org/10.1371/journal.pone.0245101

Fisher, C. E. (2025). The real ethical issues with AI for clinical psychiatry. Int Rev Psychiatry, 37(1), 14-20. https://doi.org/10.1080/09540261.2024.2376575
费舍尔，CE （2025）。AI 在临床精神病学中的真正伦理问题。国际精神病学 37（1），14-20。 https://doi.org/10.1080/09540261.2024.2376575

Graham, S., Depp, C., Lee, E. E., Nebeker, C., Tu, X., Kim, H. C., & Jeste, D. V. (2019). Artificial Intelligence for Mental Health and Mental Illnesses: an Overview. Curr Psychiatry Rep, 21(11), 116. https://doi.org/10.1007/s11920-019-1094-0
Graham， S.， Depp， C.， Lee， E. E.， Nebeker， C.， Tu， X.， Kim， H. C.， & Jeste， D. V. （2019）.心理健康和精神疾病的人工智能：概述。Curr Psychiatry 代表 21（11），116。 https://doi.org/10.1007/s11920-019-1094-0

Haftenberger, A., & Dierks, C. (2023). [Legal integration of artificial intelligence into internal medicine : Data protection, regulatory, reimbursement and liability questions]. Inn Med (Heidelb), 64(11), 1044-1050. https://doi.org/10.1007/s00108-023-01598-8 (Rechtliche Einordnung von künstlicher Intelligenz in der Inneren Medizin : Von Datenschutz und Regulatorik, Erstattungs- und Haftungsfragen.)
哈夫滕伯格，A.和迪尔克斯，C.（2023）。[人工智能与内科的法律整合：数据保护、监管、报销和责任问题]。Inn Med （Heidelb） 64（11）， 1044-1050。 https://doi.org/10.1007/s00108-023-01598-8 （Rechtliche Einordnung von künstlicher Intelligenz in der Inneren Medizin ： Von Datenschutz und Regulatorik， Erstattungs- und Haftungsfragen.）

Hanna, M., Pantanowitz, L., Jackson, B., Palmer, O., Visweswaran, S., Pantanowitz, J., Deebajah, M., & Rashidi, H. (2024). Ethical and Bias Considerations in Artificial Intelligence (AI)/Machine Learning. Mod Pathol, 100686. https://doi.org/10.1016/j.modpat.2024.100686
Hanna， M.， Pantanowitz， L.， Jackson， B.， Palmer， O.， Visweswaran， S.， Pantanowitz， J.， Deebajah， M.， & Rashidi， H. （2024）.人工智能（AI）/机器学习中的道德和偏见考虑。Mod Pathol，100686。 https://doi.org/10.1016/j.modpat.2024.100686

Heuser, S., Steil, J., & Salloch, S. (2025). AI Ethics beyond Principles: Strengthening the Life-world Perspective. Sci Eng Ethics, 31(1), 7. https://doi.org/10.1007/s11948-025-00530-7
Heuser， S.， Steil， J.， & Salloch， S. （2025）.超越原则的 AI 伦理：加强生命世界视角。科学工程伦理学 31（1），7。 https://doi.org/10.1007/s11948-025-00530-7

Higgins, O., & Wilson, R. L. (2025). Integrating Artificial Intelligence (AI) With Workforce Solutions for Sustainable Care: A Follow Up to Artificial Intelligence and Machine Learning (ML) Based Decision Support Systems in Mental Health. Int J Ment Health Nurs, 34(2), e70019. https://doi.org/10.1111/inm.70019
Higgins， O.， & Wilson， R. L. （2025）.将人工智能（AI）与可持续护理的劳动力解决方案相结合：心理健康中基于人工智能和机器学习（ML）的决策支持系统的后续行动。国际保健护理杂志 34（2），e70019。 https://doi.org/10.1111/inm.70019

Kale, M., Wankhede, N., Pawar, R., Ballal, S., Kumawat, R., Goswami, M., Khalid, M., Taksande, B., Upaganlawar, A., Umekar, M., Kopalli, S. R., & Koppula, S. (2024). AI-driven innovations in Alzheimer's disease: Integrating early diagnosis, personalized treatment, and prognostic modelling. Ageing Res Rev, 101, 102497. https://doi.org/10.1016/j.arr.2024.102497
Kale， M.， Wankhede， N.， Pawar， R.， Ballal， S.， Kumawat， R.， Goswami， M.， Khalid， M.， Taksande， B.， Upaganlawar， A.， Umekar， M.， Kopalli， S. R.， & Koppula， S. （2024）.人工智能驱动的阿尔茨海默病创新：整合早期诊断、个性化治疗和预后建模。Ageing Res Rev 101， 102497. https://doi.org/10.1016/j.arr.2024.102497

Kim, M., Lee, S., Kim, S., Heo, J. I., Lee, S., Shin, Y. B., Cho, C. H., & Jung, D. (2025). Therapeutic Potential of Social Chatbots in Alleviating Loneliness and Social Anxiety: Quasi-Experimental Mixed Methods Study. J Med Internet Res, 27, e65589. https://doi.org/10.2196/65589
Kim， M.， Lee， S.， Kim， S.， Heo， J. I.， Lee， S.， Shin， Y. B.， Cho， C. H.， & Jung， D. （2025）.社交聊天机器人在缓解孤独和社交焦虑方面的治疗潜力：准实验混合方法研究。J Med 互联网研究 27，e65589。 https://doi.org/10.2196/65589

Kowald, D., Scher, S., Pammer-Schindler, V., Müllner, P., Waxnegger, K., Demelius, L., Fessl, A., Toller, M., Mendoza Estrada, I. G., Šimić, I., Sabol, V., Trügler, A., Veas, E., Kern, R., Nad, T., & Kopeinik, S. (2024). Establishing and evaluating trustworthy AI: overview and research challenges. Front Big Data, 7, 1467222. https://doi.org/10.3389/fdata.2024.1467222
Kowald， D.， Scher， S.， Pammer-Schindler， V.， Müllner， P.， Waxnegger， K.， Demelius， L.， Fessl， A.， Toller， M.， Mendoza Estrada， I. G.， Šimić， I.， Sabol， V.， Trügler， A.， Veas， E.， Kern， R.， Nad， T.， & Kopeinik， S. （2024）.建立和评估可信 AI：概述和研究挑战。Front Big Data 7,1467222。 https://doi.org/10.3389/fdata.2024.1467222

Li, Z., Kitajima, K., Hirata, K., Togo, R., Takenaka, J., Miyoshi, Y., Kudo, K., Ogawa, T., & Haseyama, M. (2021). Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer. EJNMMI Res, 11(1), 10. https://doi.org/10.1186/s13550-021-00751-4
李，Z.，北岛，K.，平田，K.，东乡，R.，竹中，J.，三好，Y.，工藤，K.，小川 T.和长谷山，M.（2021）。使用 FDG-PET/CT 人工智能辅助诊断乳腺癌患者腋窝淋巴结转移的初步研究。EJNMMI 研究 11（1），10。 https://doi.org/10.1186/s13550-021-00751-4

Luo, X., Zhang, A., Li, Y., Zhang, Z., Ying, F., Lin, R., Yang, Q., Wang, J., & Huang, G. (2024). Emergence of Artificial Intelligence Art Therapies (AIATs) in Mental Health Care: A Systematic Review. Int J Ment Health Nurs, 33(6), 1743-1760. https://doi.org/10.1111/inm.13384
罗晓东，张俊华，李俊英，张俊华，张俊华，林俊华，杨俊杰，王俊杰， & 黄俊杰（2024）.人工智能艺术疗法（AIAT）在心理健康护理中的出现：系统评价。国际保健杂志 33（6），1743-1760。 https://doi.org/10.1111/inm.13384

Machado, C., Estévez, M., & Rodriguez-Rojas, R. (2018). Zolpidem efficacy and safety in disorders of consciousness. Brain Inj, 32(4), 530-531. https://doi.org/10.1080/02699052.2018.1429664
Machado， C.， Estévez， M.， & Rodriguez-Rojas， R. （2018）。唑吡坦在意识障碍中的疗效和安全性。脑注射 32（4），530-531。 https://doi.org/10.1080/02699052.2018.1429664

Mohsin Khan, M., Shah, N., Shaikh, N., Thabet, A., Alrabayah, T., & Belkhair, S. (2024). Towards secure and trusted AI in healthcare: A systematic review of emerging innovations and ethical challenges. Int J Med Inform, 195, 105780. https://doi.org/10.1016/j.ijmedinf.2024.105780
Mohsin Khan， M.， Shah， N.， Shaikh， N.， Thabet， A.， Alrabayah， T.， & Belkhair， S. （2024）。迈向安全可信的医疗保健 AI：对新兴创新和道德挑战的系统评价。国际医学杂志 Inform 195， 105780. https://doi.org/10.1016/j.ijmedinf.2024.105780

Ng, J. Y., Maduranayagam, S. G., Suthakar, N., Li, A., Lokker, C., Iorio, A., Haynes, R. B., & Moher, D. (2025). Attitudes and perceptions of medical researchers towards the use of artificial intelligence chatbots in the scientific process: an international cross-sectional survey. Lancet Digit Health, 7(1), e94-e102. https://doi.org/10.1016/s2589-7500(24)00202-4
Ng， J. Y.， Maduranayagam， S. G.， Suthakar， N.， Li， A.， Lokker， C.， Iorio， A.， Haynes， R. B.， & Moher， D. （2025）.医学研究人员对在科学过程中使用人工智能聊天机器人的态度和看法：一项国际横断面调查。柳叶刀手指健康 7（1），e94-e102。 https://doi.org/10.1016/s2589-7500（24）00202-4

Nochaiwong, S., Ruengorn, C., Thavorn, K., Hutton, B., Awiphan, R., Phosuya, C., Ruanta, Y., Wongpakaran, N., & Wongpakaran, T. (2021). Global prevalence of mental health issues among the general population during the coronavirus disease-2019 pandemic: a systematic review and meta-analysis. Sci Rep, 11(1), 10173. https://doi.org/10.1038/s41598-021-89700-8
Nochaiwong， S.， Ruengorn， C.， Thavorn， K.， Hutton， B.， Awiphan， R.， Phosuya， C.， R.， R.， Wongpakaran， N.， & Wongpakaran， T. （2021）.2019 年冠状病毒病大流行期间全球普通人群心理健康问题的患病率：系统评价和荟萃分析。科学代表 11（1），10173。 https://doi.org/10.1038/s41598-021-89700-8

Ostojic, D., Lalousis, P. A., Donohoe, G., & Morris, D. W. (2024). The challenges of using machine learning models in psychiatric research and clinical practice. Eur Neuropsychopharmacol, 88, 53-65. https://doi.org/10.1016/j.euroneuro.2024.08.005
Ostojic， D.， Lalousis， P. A.， Donohoe， G.， & Morris， D. W. （2024）.在精神病学研究和临床实践中使用机器学习模型的挑战。欧洲神经精神药理学 88， 53-65。 https://doi.org/10.1016/j.euroneuro.2024.08.005

Othman, N. A., Panchapakesan, C., Loh, S. B., Zhang, M., Gupta, R. K., Martanto, W., Phang, Y. S., Morris, R. J. T., Loke, W. C., Tan, K. B., Subramaniam, M., & Yang, Y. (2024). Predicting public mental health needs in a crisis using social media indicators: a Singapore big data study. Sci Rep, 14(1), 23222. https://doi.org/10.1038/s41598-024-73978-5
奥斯曼，N. A.，潘查帕克桑，C.，Loh，S. B.，张，M.，古普塔，R. K.，马尔坦托，W.，Phang，Y. S.，莫里斯，R. J. T.，Loke，W. C.，Tan，K. B.，Subramaniam，M.和 Yang，Y.（2024）。使用社交媒体指标预测危机中的公众心理健康需求：新加坡大数据研究。科学代表 14（1），23222。 https://doi.org/10.1038/s41598-024-73978-5

Owen, D., Lynham, A. J., Smart, S. E., Pardiñas, A. F., & Camacho Collados, J. (2024). AI for Analyzing Mental Health Disorders Among Social Media Users: Quarter-Century Narrative Review of Progress and Challenges. J Med Internet Res, 26, e59225. https://doi.org/10.2196/59225
Owen， D.， Lynham， A. J.， Smart， S. E.， Pardiñas， A. F.， & Camacho Collados， J. （2024）.用于分析社交媒体用户心理健康障碍的 AI：进展和挑战的四分之一世纪叙述性回顾。J Med Internet Res 26，e59225。 https://doi.org/10.2196/59225

Qi, Z., Zeng, W., Zang, D., Wang, Z., Luo, L., Wu, X., Yu, J., & Mao, Y. (2024). Classifying disorders of consciousness using a novel dual-level and dual-modal graph learning model. J Transl Med, 22(1), 950. https://doi.org/10.1186/s12967-024-05729-z
齐，Z.，曾伟文，臧大渝，王志强，罗丽亮，吴晓明，于俊杰和毛 Y.（2024）。使用新颖的双级和双模态图学习模型对意识障碍进行分类。J Transl Med 22（1），950。 https://doi.org/10.1186/s12967-024-05729-z

Qu, S., Wu, X., Tang, Y., Zhang, Q., Huang, L., Cui, B., Jiao, S., Sun, Q., & Zeng, F. (2024). Analyzing brain-activation responses to auditory stimuli improves the diagnosis of a disorder of consciousness by non-linear dynamic analysis of the EEG. Sci Rep, 14(1), 17446. https://doi.org/10.1038/s41598-024-67825-w
曲淑娴、吴晓波、唐晖、张榕、黄淑娴、崔斌樟、焦淑娴、孙榆和曾芳（2024）。通过对 EEG 进行非线性动态分析，分析大脑激活对听觉刺激的反应可以改进意识障碍的诊断。科学代表 14（1），17446。 https://doi.org/10.1038/s41598-024-67825-w

Rony, M. K. K., Das, D. C., Khatun, M. T., Ferdousi, S., Akter, M. R., Khatun, M. A., Begum, M. H., Khalil, M. I., Parvin, M. R., Alrazeeni, D. M., & Akter, F. (2025). Artificial intelligence in psychiatry: A systematic review and meta-analysis of diagnostic and therapeutic efficacy. Digit Health, 11, 20552076251330528. https://doi.org/10.1177/20552076251330528
罗尼，M. K. K.，达斯，D. C.，哈顿，M. T.，费尔杜西，S.，阿克特，M. R.，哈顿，M. A.，贝古姆，M. H.，哈利勒，M. I.，帕尔文，M. R.，阿拉泽尼，DM，和阿克特，F.（2025）。精神病学中的人工智能：诊断和治疗效果的系统评价和荟萃分析。数字健康 11， 20552076251330528. https://doi.org/10.1177/20552076251330528

Rządeczka, M., Sterna, A., Stolińska, J., Kaczyńska, P., & Moskalewicz, M. (2025). The Efficacy of Conversational AI in Rectifying the Theory-of-Mind and Autonomy Biases: Comparative Analysis. JMIR Ment Health, 12, e64396. https://doi.org/10.2196/64396
Rządeczka， M.， Sterna， A.， Stolińska， J.， Kaczyńska， P.， & Moskalewicz， M. （2025）.对话式 AI 在纠正心智理论和自主偏见方面的功效：比较分析。JMIR 心理健康 12，e64396。 https://doi.org/10.2196/64396

Şahin, D., Kambeitz-Ilankovic, L., Wood, S., Dwyer, D., Upthegrove, R., Salokangas, R., Borgwardt, S., Brambilla, P., Meisenzahl, E., Ruhrmann, S., Schultze-Lutter, F., Lencer, R., Bertolino, A., Pantelis, C., Koutsouleris, N., & Kambeitz, J. (2024). Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis. Br J Psychiatry, 224(2), 55-65. https://doi.org/10.1192/bjp.2023.141
沙欣，D.，坎贝茨-伊兰科维奇，L.，伍德，S.，德怀尔，D.，厄普特格罗夫，R.，萨洛坎加斯，R.，博格沃特，S.，布兰比拉，P.，梅森扎尔，E.，鲁尔曼，S.，舒尔茨-卢特，F.，伦瑟，R.，贝托利诺，A.，潘特利斯，C.，库苏雷斯，N.，和坎贝茨，J.（2024）。精准精神病学中的算法公平性：临床精神病高危个体预测模型的分析。Br J 精神病学 224（2），55-65。 https://doi.org/10.1192/bjp.2023.141

Saito, T., Suzuki, H., & Kishi, A. (2022). Predictive Modeling of Mental Illness Onset Using Wearable Devices and Medical Examination Data: Machine Learning Approach. Front Digit Health, 4, 861808. https://doi.org/10.3389/fdgth.2022.861808
Saito， T.， Suzuki， H.， & Kishi， A. （2022 年）。使用可穿戴设备和体检数据对精神疾病发作进行预测建模：机器学习方法。Front Digit Health 4， 861808. https://doi.org/10.3389/fdgth.2022.861808

Sedlakova, J., & Trachsel, M. (2023). Conversational Artificial Intelligence in Psychotherapy: A New Therapeutic Tool or Agent? Am J Bioeth, 23(5), 4-13. https://doi.org/10.1080/15265161.2022.2048739
Sedlakova， J. 和 Trachsel， M. （2023）。心理治疗中的对话式人工智能：一种新的治疗工具还是代理？美国生物伦理杂志 23（5），4-13。 https://doi.org/10.1080/15265161.2022.2048739

Srivastav, A. K., Mishra, M. K., Lillard, J. W., Jr., & Singh, R. (2025). Transforming Pharmacogenomics and CRISPR Gene Editing with the Power of Artificial Intelligence for Precision Medicine. Pharmaceutics, 17(5). https://doi.org/10.3390/pharmaceutics17050555
斯里瓦斯塔夫，A. K.，米什拉，MK，利拉德，JW，Jr.和辛格，R.（2025）。利用人工智能的力量改变药物基因组学和 CRISPR 基因编辑，实现精准医疗。药剂学 17（5）。 https://doi.org/10.3390/pharmaceutics17050555

Taddese, A. A., Addis, A. C., & Tam, B. T. (2025). Data stewardship and curation practices in AI-based genomics and automated microscopy image analysis for high-throughput screening studies: promoting robust and ethical AI applications. Hum Genomics, 19(1), 16. https://doi.org/10.1186/s40246-025-00716-x
Taddese， A. A.， Addis， A. C.， & Tam， B. T. （2025）.用于高通量筛选研究的基于 AI 的基因组学和自动显微镜图像分析的数据管理和管理实践：促进稳健且合乎道德的 AI 应用程序。Hum 基因组学 19（1），16。 https://doi.org/10.1186/s40246-025-00716-x

Toppi, J., Quattrociocchi, I., Riccio, A., D'Ippolito, M., Aloisi, M., Colamarino, E., Pichiorri, F., Cincotti, F., Formisano, R., & Mattia, D. (2024). EEG-Derived Markers to Improve Prognostic Evaluation of Disorders of Consciousness. IEEE J Biomed Health Inform, 28(11), 6674-6684. https://doi.org/10.1109/jbhi.2024.3445118
Toppi， J.， Quattrociocchi， I.， Riccio， A.， D'Ippolito， M.， Aloisi， M.， Colamarino， E.， Pichiorri， F.， Cincotti， F.， Formisano， R.， & Mattia， D. （2024）.EEG 衍生的标志物改善意识障碍的预后评估。IEEE J 生物医学健康信息 28（11），6674-6684。 https://doi.org/10.1109/jbhi.2024.3445118

van Baalen, S., & Boon, M. (2024). Understanding disciplinary perspectives: a framework to develop skills for interdisciplinary research collaborations of medical experts and engineers. BMC Med Educ, 24(1), 1000. https://doi.org/10.1186/s12909-024-05913-1
van Baalen， S. 和 Boon， M. （2024）。了解学科观点：培养医学专家和工程师跨学科研究合作技能的框架。BMC 医学教育 24（1），1000。 https://doi.org/10.1186/s12909-024-05913-1

Washington, P., Park, N., Srivastava, P., Voss, C., Kline, A., Varma, M., Tariq, Q., Kalantarian, H., Schwartz, J., Patnaik, R., Chrisman, B., Stockham, N., Paskov, K., Haber, N., & Wall, D. P. (2020). Data-Driven Diagnostics and the Potential of Mobile Artificial Intelligence for Digital Therapeutic Phenotyping in Computational Psychiatry. Biol Psychiatry Cogn Neurosci Neuroimaging, 5(8), 759-769. https://doi.org/10.1016/j.bpsc.2019.11.015
华盛顿，P.，帕克，N.，斯里瓦斯塔瓦，P.，沃斯，C.，克莱恩，A.，瓦尔玛，M.，塔里克，Q.，卡兰塔里安，H.，施瓦茨，J.，帕特奈克，R.，克里斯曼，B.，斯托克姆，N.，帕斯科夫，K.，哈伯，N.和沃尔，DP（2020）。数据驱动的诊断和移动人工智能在计算精神病学中数字治疗表型的潜力。生物精神病学 Cogn Neurosci 神经影像学 5（8），759-769。 https://doi.org/10.1016/j.bpsc.2019.11.015

Willem, T., Fritzsche, M. C., Zimmermann, B. M., Sierawska, A., Breuer, S., Braun, M., Ruess, A. K., Bak, M., Schönweitz, F. B., Meier, L. J., Fiske, A., Tigard, D., Müller, R., McLennan, S., & Buyx, A. (2024). Embedded Ethics in Practice: A Toolbox for Integrating the Analysis of Ethical and Social Issues into Healthcare AI Research. Sci Eng Ethics, 31(1), 3. https://doi.org/10.1007/s11948-024-00523-y
Willem， T.， Fritzsche， M. C.， Zimmermann， B. M.， Sierawska， A.， Breuer， S.， Braun， M.， Ruess， A. K.， Bak， M.， Schönweitz， F. B.， Meier， L. J.， Fiske， A.， Tigard， D.， Müller， R.， McLennan， S.， & Buyx， A. （2024）.实践中的嵌入式伦理：将道德和社会问题分析整合到医疗保健 AI 研究中的工具箱。科学工程伦理学 31（1），3。 https://doi.org/10.1007/s11948-024-00523-y

Xu, H., Yang, X., Hu, Y., Wang, D., Liang, Z., Mu, H., Wang, Y., Shi, L., Gao, H., Song, D., Cheng, Z., Lu, Z., Zhao, X., Lu, J., Wang, B., & Hu, Z. (2024). Trusted artificial intelligence for environmental assessments: An explainable high-precision model with multi-source big data. Environ Sci Ecotechnol, 22, 100479. https://doi.org/10.1016/j.ese.2024.100479
徐， H.，杨， X.，胡， Y.，王 D.，梁， Z.，穆， H.，王 Y.，石， L.，高， H.，宋， D.，程， Z.，卢， Z.，赵， X.，卢， J.，王， B.， & 胡， Z. （2024）.用于环境评估的可信人工智能：具有多源大数据的可解释的高精度模型。环境科学 Ecotechnol 22， 100479. https://doi.org/10.1016/j.ese.2024.100479

Yao, Y., Hasan, W. Z. W., Jiao, W., Dong, X., Ramli, H. R., Norsahperi, N. M. H., & Wen, D. (2024). ChatGPT and BCI-VR: a new integrated diagnostic and therapeutic perspective for the accurate diagnosis and personalized treatment of mild cognitive impairment. Front Hum Neurosci, 18, 1426055. https://doi.org/10.3389/fnhum.2024.1426055
姚，Y.，哈桑，WZW，焦，W.，董，X.，拉姆利，HR，诺萨佩里，N.M.H.和温，D.（2024）。ChatGPT 和 BCI-VR：一种新的综合诊断和治疗视角，用于轻度认知障碍的准确诊断和个性化治疗。Front Hum Neurosci 18， 1426055. https://doi.org/10.3389/fnhum.2024.1426055

Yin, S. Q., & Li, Y. H. (2025). Advancing the diagnosis of major depressive disorder: Integrating neuroimaging and machine learning. World J Psychiatry, 15(3), 103321. https://doi.org/10.5498/wjp.v15.i3.103321
Yin， S. Q.， & Li， Y. H. （2025 年）。推进重度抑郁症的诊断：整合神经影像学和机器学习。世界精神病学杂志 15（3），103321。 https://doi.org/10.5498/wjp.v15.i3.103321

Zhang, Z., Jiao, Y., Zhang, M., Wei, B., Liu, X., Zhao, J., Tian, F., Hu, J., & Zhang, Q. (2022). AI-aided general clinical diagnoses verified by third-parties with dynamic uncertain causality graph extended to also include classification. Artif Intell Rev, 55(6), 4485-4521. https://doi.org/10.1007/s10462-021-10109-w
张 Z.，焦 Y.，张 M.，魏 B.，刘 X.，赵 J.，田 F.，胡 J. 和张 Q. （2022）。由第三方验证的 AI 辅助一般临床诊断，动态不确定因果关系图扩展为还包括分类。Artif Intell Rev 55（6），4485-4521。 https://doi.org/10.1007/s10462-021-10109-w

Zhao, S., Cao, Y., Yang, W., Yu, J., Xu, C., Dai, W., Li, S., Pan, G., & Luo, B. (2024). DOCTer: a novel EEG-based diagnosis framework for disorders of consciousness. J Neural Eng, 21(5). https://doi.org/10.1088/1741-2552/ad7904
赵淑娴，曹咏咪，杨淑娴，于濑吠，徐渝，戴淑娴，李淑娴，潘樟，罗樽極（2024）。DOCTer：一种基于脑电图的新型意识障碍诊断框架。神经工程杂志 21（5）。 https://doi.org/10.1088/1741-2552/ad7904