Ministry of Health Sri Lanka, Colombo, Sri Lanka.
Institute of Applied Health Research, University of Birmingham, Birmingham, West Midlands, UK.
BMJ Open. 2024 Feb 1;14(2):e077156. doi: 10.1136/bmjopen-2023-077156.
Coexisting multiple health conditions is common among older people, a population that is increasing globally. The potential for polypharmacy, adverse events, drug interactions and development of additional health conditions complicates prescribing decisions for these patients. Artificial intelligence (AI)-generated decision-making tools may help guide clinical decisions in the context of multiple health conditions, by determining which of the multiple medication options is best. This study aims to explore the perceptions of healthcare professionals (HCPs) and patients on the use of AI in the management of multiple health conditions.
A qualitative study will be conducted using semistructured interviews. Adults (≥18 years) with multiple health conditions living in the West Midlands of England and HCPs with experience in caring for patients with multiple health conditions will be eligible and purposively sampled. Patients will be identified from Clinical Practice Research Datalink (CPRD) Aurum; CPRD will contact general practitioners who will in turn, send a letter to patients inviting them to take part. Eligible HCPs will be recruited through British HCP bodies and known contacts. Up to 30 patients and 30 HCPs will be recruited, until data saturation is achieved. Interviews will be in-person or virtual, audio recorded and transcribed verbatim. The topic guide is designed to explore participants' attitudes towards AI-informed clinical decision-making to augment clinician-directed decision-making, the perceived advantages and disadvantages of both methods and attitudes towards risk management. Case vignettes comprising a common decision pathway for patients with multiple health conditions will be presented during each interview to invite participants' opinions on how their experiences compare. Data will be analysed thematically using the Framework Method.
This study has been approved by the National Health Service Research Ethics Committee (Reference: 22/SC/0210). Written informed consent or verbal consent will be obtained prior to each interview. The findings from this study will be disseminated through peer-reviewed publications, conferences and lay summaries.
共存多种健康状况在老年人中很常见，而老年人的数量在全球范围内正在增加。这些患者的药物治疗方案变得复杂，因为存在潜在的多种药物治疗、不良事件、药物相互作用和新的健康状况的发展。人工智能（AI）生成的决策工具可以通过确定多种药物选择中哪一种最好，帮助指导多种健康状况下的临床决策。本研究旨在探讨医疗保健专业人员（HCP）和患者对 AI 在管理多种健康状况中的应用的看法。
本研究将采用半结构式访谈进行定性研究。符合条件的参与者为居住在英格兰西米德兰兹的患有多种健康状况的成年人（≥18 岁）和有多种健康状况患者护理经验的 HCP。将从临床实践研究数据链接（CPRD）Aurum 中识别患者；CPRD 将联系全科医生，全科医生将向患者发送一封信，邀请他们参加。通过英国 HCP 机构和已知联系人招募合格的 HCP。将招募多达 30 名患者和 30 名 HCP，直到达到数据饱和。访谈将以面对面或虚拟的方式进行，录音并逐字转录。该主题指南旨在探讨参与者对 AI 支持的临床决策的态度，以补充临床医生指导的决策，以及对这两种方法的优势和劣势的看法，以及对风险管理的态度。在每次访谈中，将呈现一个包含多种健康状况患者常见决策途径的案例情景，以邀请参与者就他们的经验如何与这些情景进行比较发表意见。将使用框架方法对数据进行主题分析。
本研究已获得国民保健服务研究伦理委员会的批准（参考号：22/SC/0210）。在每次访谈之前，将获得书面知情同意或口头同意。本研究的结果将通过同行评议的出版物、会议和通俗易懂的摘要进行传播。
