Clinician-artificial intelligence collaboration: A win-win solution for efficiency and reliability in atrial fibrillation diagnosis

Abstract

Given the biases and ethical concerns of AI models, the fully automatic diagnosis of diseases in clinical settings is challenging. In contrast, clinician-AI collaboration is considered essential to ensure the validity and reliability of utilizing AI models in clinical practice. However, effective strategies for clinician-AI collaboration remain largely unexplored. This study proposed a three-step general clinician-AI collaboration pipeline aimed at improving disease diagnosis efficiency: first, utilizing large real-world clinical datasets to evaluate and clarify clinicians’ diagnostic strengths/weaknesses; second, developing an AI model to complement clinicians’ weakness in disease diagnosis; and finally, proposing a clinician-AI collaboration strategy to leverage the strengths of both AI and clinicians. The effectiveness of this pipeline was validated through a study focusing on clinical paroxysmal atrial fibrillation (PAF) detection, utilizing 24-h Holter recordings from over 30,000 patients. In PAF detection, clinicians alone required a significant amount of time to identify the data and still overlooked 13.7% of PAF patients but successfully identified all non-atrial fibrillation (AF) patients. Conversely, AI alone rarely missed PAF patients but misidentified 23.3% of non-AF patients as having PAF. After implementing the proposed clinician-AI collaboration strategy, all patients were correctly identified, and clinicians’ workload was reduced by 76.7%. This study improves both the efficiency and reliability of PAF detection, bridging the gap between AI model development and its clinical application, thereby effectively promoting the application of AI models in clinical AF screening. This study was supported in part by the National Natural Science Foundation of China. • Clinicians often overlook patients with short atrial fibrillation episodes • Clinician-AI collaboration leveraged the strengths of both clinicians and AI • Clinician-AI collaboration overcame 13.7% human miss rate in atrial fibrillation • Clinician-AI collaboration reduced the clinicians’ workload by 76.7% While artificial intelligence (AI) has demonstrated promise in atrial fibrillation (AF) detection, translating these advancements into effective clinician-AI collaboration remains a critical barrier. Current approaches often fail to synergize human expertise with algorithmic precision. Here, researchers developed a novel clinician-AI collaborative framework that integrates AI’s pattern recognition capabilities with clinicians’ diagnostic acumen. In validation trials, clinician-only assessments missed 13.7% of paroxysmal AF cases, while AI-only assessments produced false positives in 23.3% of non-AF cases. Our collaborative paradigm achieved 100% diagnostic accuracy while reducing clinician workload by 76.7% through intelligent case prioritization. This operational paradigm bridges the implementation gap between AI development and clinical workflows, offering a validated blueprint for enhancing AF screening efficiency without compromising diagnostic rigor. Zhang et al. successfully developed a clinician-AI collaborative framework that synergized clinicians’ expertise with AI pattern recognition for AF detection based on 24-h Holter monitoring. Validation showed that the collaboration achieved perfect diagnostic accuracy while reducing clinician workload by 76.7%, overcoming the 13.7% paroxysmal AF miss rate of clinician-only assessments.

Ähnliche Arbeiten