Giansanti Daniele, Carico Elisabetta, Lastrucci Andrea, Giarnieri Enrico
Centre TISP, Istituto Superiore di Sanità, 00161 Roma, Italy.
Department of Clinical and Molecular Medicine, Cytopathology unit Sapienza University, Sant'Andrea Hospital, 00189 Roma, Italy.
Healthcare (Basel). 2025 Apr 14;13(8):903. doi: 10.3390/healthcare13080903.
The integration of artificial intelligence (AI) in healthcare, particularly in digital cytology, has the potential to enhance diagnostic accuracy and workflow efficiency. However, AI adoption remains limited due to technological and human-related barriers. Understanding the perceptions and experiences of healthcare professionals is essential for overcoming these challenges and facilitating effective AI implementation.
This study aimed to assess AI integration in digital cytology workflows by evaluating professionals' perspectives on its benefits, challenges, and requirements for successful adoption.
A survey was conducted among 150 professionals working in public and private healthcare settings in Italy, including laboratory technicians (35%), medical doctors (25%), biologists (20%), and specialists in diagnostic technical sciences (20%). Data were collected through a structured Computer-Assisted Web Interview (CAWI) and a Virtual Focus Group (VFG) to capture quantitative and qualitative insights on AI familiarity, perceived advantages, and barriers to adoption.
The findings indicated varying levels of AI familiarity among professionals. While many recognized AI's potential to improve diagnostic accuracy and streamline workflows, concerns were raised regarding resistance to change, implementation costs, and doubts about AI reliability. Participants emphasized the need for structured training and continuous support to facilitate AI adoption in digital cytology.
Addressing barriers such as resistance, cost, and trust is essential for the successful integration of AI in digital cytology workflows. Tailored training programs and ongoing professional support can enhance AI adoption, ultimately optimizing diagnostic processes and improving clinical outcomes.
人工智能（AI）在医疗保健领域的整合，尤其是在数字细胞学中，有可能提高诊断准确性和工作流程效率。然而，由于技术和人为相关的障碍，人工智能的采用仍然有限。了解医疗保健专业人员的看法和经验对于克服这些挑战和促进人工智能的有效实施至关重要。
本研究旨在通过评估专业人员对人工智能在数字细胞学工作流程中的益处、挑战和成功采用的要求的看法，来评估人工智能的整合情况。
对意大利公共和私立医疗保健机构的150名专业人员进行了一项调查，其中包括实验室技术人员（35%）、医生（25%）、生物学家（20%）和诊断技术科学专家（20%）。通过结构化的计算机辅助网络访谈（CAWI）和虚拟焦点小组（VFG）收集数据，以获取关于人工智能熟悉程度、感知优势和采用障碍的定量和定性见解。
研究结果表明，专业人员对人工智能的熟悉程度各不相同。虽然许多人认识到人工智能有提高诊断准确性和简化工作流程的潜力，但也有人对变革阻力、实施成本以及对人工智能可靠性的怀疑表示担忧。参与者强调需要结构化培训和持续支持，以促进人工智能在数字细胞学中的采用。
解决诸如阻力、成本和信任等障碍对于人工智能在数字细胞学工作流程中的成功整合至关重要。量身定制的培训计划和持续的专业支持可以提高人工智能的采用率，最终优化诊断流程并改善临床结果。
