In Journal of medical Internet research ; h5-index 88.0
BACKGROUND : Misdiagnosis, arbitrary charges and annoying queues, and clinic waiting times among others are long-standing phenomena in the medical industry across the world, These factors can con-tribute to patient anxiety about misdiagnosis by clinicians. However, with the increasing use of big data growth in biomedical and healthcare communities, the performance of artificial intelligence (Al) techniques of diagnosis is improving, and can help avoid medical practice errors, including under the current circumstance of the COVID-19.
OBJECTIVE : This study aims to visualize and measure patients' heterogeneous preferences from various angles of Artificial intelligence (AI) diagnosis versus clinicians in the context of the COVID-19 epidemic in china. We also aim to to illustrate the different decision-making factors of the latent class of discrete choice experiment (DCE) and prospects for the application of AI techniques in judgment and management during the pandemic of SARS-CoV-2 and future.
METHODS : A DCE approach was the main analysis method applied in this paper. Attributes from different dimensions that have been hypothesized: diagnostic method; outpatient waiting time, diagnosis time, accuracy, follow-up after diagnosis and diagnostic expense. After that, a questionnaire is to be formed. With collected data from the DCE questionnaire, we apply Sawtooth software to construct a generalized logit (GMNL) and mixed logit (MXL) models and Latent class (LC) model with the datasets. Moreover, we calculate the variables' coefficients, Standard Error (SE), p-value and odds ratio (OR), and form a utility report to present the importance and weighted percentage of attributes.
RESULTS : A total of 55.74% of the respondents (428 out of 767) opted for AI diagnosis regardless of the description of the clinicians. In the GMNL model, we found that people most prefer the 100% accuracy the most (OR 4.548, 95% CI 4.048, 5.110, p < 0.001). For the latent class model, the most acceptable model consists of three latent classes of respondents. The attributes with the most substantial effect and highest percentage weights are the accuracy (39.29% in general) and expense of diagnosis (21.69% in general), especially the preferences for diagnosis 'accuracy' attribute, which is constant across classes. For Class 1 and Class 3, people prefer the AI + clinicians method (class 1: OR 1.247 95% CI 1.036, 1.463, p < 0.001; class 2: OR 1.958 95% CI 1.769, 2.167, p < 0.001). For Class 2, people prefer the AI method (OR 1.546 95% CI 0.883, 2.707, p =0.370). and the odds ratio of levels of attributes increases with the increase of accuracy across all classes.
CONCLUSIONS : Latent class analysis was prominent and useful in quantifying preferences for attributes of diagnosis choice. People's preference for the 'accuracy' and 'diagnosis expense' are palpable. Artificial Intelligence (AI) will have a potential market. However, accuracy and diagnosis expenses need to be taken into consideration.
Liu Taoran, Tsang Winghei, Huang Fengqiu, Lau Oiying, Chen Yanhui, Sheng Jie, Guo Yiwei, Akinwunmi Babatunde, Zhang Casper Jp, Ming Wai-Kit