Wanten Joukje C, Bauer Noël J C, Chowdhury Mohita, Higham Aisling, de Pennington Nick, van den Biggelaar Frank J H M, Nuijts Rudy M M A
University Eye Clinic Maastricht, Maastricht University Medical Centre+, P Debyelaan 25, Maastricht, 6229HX, The Netherlands, 31 0433871594.
Ufonia Limited, Oxford, United Kingdom.
JMIR Form Res. 2025 Aug 18;9:e72574. doi: 10.2196/72574.
Given the increasing global demand for ophthalmologic care and the anticipated shortage of ophthalmology professionals, innovative solutions are essential for optimizing health care delivery. Digital health technologies offer promising opportunities to efficiently manage high patient volumes. Cataract surgery, with its established safety profile and routine postoperative care, provides an ideal setting for implementing such innovations. Structured clinical questions have proven effective in identifying patients requiring further assessment, supporting the feasibility of follow-up through telephone consultations. To further extend this approach, artificial intelligence-based follow-up systems may offer an opportunity to automate these interactions, reduce clinician workload, and streamline care pathways.
The aim of the study is to assess the clinical safety and effectiveness of an artificial intelligence-based follow-up call system (Dora-NL1) in identifying patients who require further assessment after cataract surgery in the Netherlands.
This prospective single-center study was conducted at the University Eye Clinic Maastricht, the Netherlands. Adult patients who underwent uncomplicated cataract surgery were eligible to participate. All patients received a Dora-NL1 follow-up telephone call at 1 and 4 weeks postoperatively in addition to standard care (a clinician-led telephone consultation at week 1 and an in-person hospital visit at week 4). The Dora-NL1 calls used a standard conversational flow to evaluate symptoms and recommend a clinical outcome. The recommended outcomes of Dora-NL1 were based on the symptoms reported by the patient. Clinical safety and accuracy were assessed by comparing Dora-NL1 outcomes to blinded clinician assessments of recorded calls and to standard postoperative care. Patient-reported usability was measured using the Telehealth Usability Questionnaire and Net Promoter Score.
A total of 105 patients with a mean age of 72 (SD 7) years were included in the analysis. Dora-NL1 demonstrated high agreement with clinician-supervised calls, with symptom evaluation accuracy ranging from 89% to 99% (κ=0.390-0.947) and care management decision accuracy between 83% and 88% (κ=0.640-0.753). At week 1, Dora-NL1 showed a sensitivity of 100% and a specificity of 42% compared to standard clinician-led telephone consultations with no missed clinical concerns. At week 4, compared to the in-person follow-up, Dora-NL1 failed to identify 4 (4.1%) patients who required unexpected management changes, including 3 with asymptomatic complications detected only via slit lamp examination and 1 with complaints in the nonoperated eye. Patients rated Dora-NL1 positively, with Net Promoter Scores of +13.5 and +12.6 at week 1 and 4, respectively. The Telehealth Usability Questionnaire was completed by 98 patients, yielding a mean score of 3.19 (SD 1.13) on a 5-point scale, highlighting its simplicity, ease of use, and audibility.
Dora-NL1 is a safe and effective tool for automated postoperative screening following cataract surgery. It offers a safe alternative to clinician-led telephone consultations in routine cases but cannot fully replace in-person examinations.
鉴于全球对眼科护理的需求不断增加，且预计眼科专业人员短缺，创新解决方案对于优化医疗服务至关重要。数字健康技术为高效管理大量患者提供了有前景的机会。白内障手术因其已确立的安全性和常规术后护理，为实施此类创新提供了理想环境。结构化临床问题已被证明在识别需要进一步评估的患者方面有效，支持通过电话咨询进行随访的可行性。为进一步扩展这种方法，基于人工智能的随访系统可能提供机会使这些互动自动化，减轻临床医生工作量，并简化护理路径。
本研究的目的是评估基于人工智能的随访呼叫系统（Dora-NL1）在识别荷兰白内障手术后需要进一步评估的患者方面的临床安全性和有效性。
这项前瞻性单中心研究在荷兰马斯特里赫特大学眼科诊所进行。接受无并发症白内障手术的成年患者有资格参与。除标准护理外（术后第1周由临床医生主导的电话咨询和术后第4周的门诊就诊），所有患者在术后1周和4周均接受Dora-NL1随访电话。Dora-NL1呼叫使用标准对话流程评估症状并推荐临床结果。Dora-NL1的推荐结果基于患者报告的症状。通过将Dora-NL1的结果与对录音电话的盲法临床医生评估以及标准术后护理进行比较，评估临床安全性和准确性。使用远程医疗可用性问卷和净推荐值来衡量患者报告的可用性。
共有105名平均年龄为72（标准差7）岁的患者纳入分析。Dora-NL1与临床医生监督的呼叫显示出高度一致性，但症状评估准确性在89%至99%之间（κ=0.390 - 0.947），护理管理决策准确性在83%至88%之间（κ=0.640 - 0.753）。在第1周，与标准临床医生主导的电话咨询相比，Dora-NL1的敏感性为100%，特异性为42%，未遗漏任何临床问题。在第4周，与门诊随访相比，Dora-NL1未能识别出4名（4.1%）需要意外管理变更的患者，其中3名仅通过裂隙灯检查发现无症状并发症，1名非手术眼有症状。患者对Dora-NL1评价积极，第1周和第4周的净推荐值分别为+13.5和+12.6。98名患者完成了远程医疗可用性问卷，在5分制上的平均得分为3.19（标准差1.13），突出了其简单性、易用性和可听性。
Dora-NL1是白内障手术后自动术后筛查的安全有效工具。在常规病例中，它为临床医生主导的电话咨询提供了一种安全替代方案，但不能完全取代门诊检查。
