Effectiveness of a Cloud-Based Telepathology System in China: Large-Sample Observational Study (Preprint)

Abstract

BACKGROUND Telepathology is a potent strategy to overcome the shortage of senior pathologists, whole slid imaging (WSI) is the most advanced means and has been widely used in telepathology owning to its complete scanning of glass slides, but WSI occupies large storage space and computing resource, and the WSI retrieval is time-consuming. To compensate for these shortcomings of WSI, we have established a cloud-based telepathology system and conducted detailed evaluation of its implementation effects. OBJECTIVE The cloud-based telepathology system in China has been running for more than four years, and a large number of cases were submitted. The main purpose of this study is to evaluate the operation effect of this system based on a large sample, including the overview of the submitted cases, timeliness of telepathology reports, diagnostic accuracy, and economic benefits. METHODS A total of 23,167 cases submitted to the cloud-based telepathology system of the National Telemedicine Center of China from January 2016 to December 2019 were collected as subjects. The variation tendency of the report-timeliness from the system were analyzed for years. 564 patients who also directly visited the First Affiliated Hospital of Zhengzhou University and obtained final diagnoses were followed up to analyze the diagnostic accuracy of the system. RESULTS The amounts of participated hospitals and submitted cases rose year by year. Most samples were captured from uterus, gastrointestinal tract, bone or soft tissue, breast, and esophagus. 17,495 cases were confirmed, including 12,088 benign lesions, 5217 malignant lesions, and 190 borderline lesions, the proportion of malignant lesions in esophagus, lung/mediastinum, urinary and thoracic cavity/pleura was higher than that in benign lesions, which was different from other 22 anatomic sites. The median turnaround time was 16.93 hours and shortened yearly (between 2018 and 2019 adjusted P= .012, other groups adjusted P＜ .001), 82.88% cases were diagnosed in 48 hours. The telepathological diagnosis of 11 cases were discrepant with the final diagnosis, and the diagnostic accuracy of the system was 98.05%, with no statistical difference from the final diagnosis in hospital(P= .549). 300,000 dollars were saved for patients every year with this system. CONCLUSIONS The novel cloud-based telepathology system has the potential to relieve the shortage of pathologists in primary hospitals and simultaneously reduced the high medical costs for patients in China. It should be therefore promoted further to enhance the efficiency, quantity and quality of telepathological diagnoses.