Clinical validation of the Hilab lens for AI supported point of care CBC testing in pediatric oncology

Hilab镜头在儿科肿瘤学中用于人工智能辅助即时血细胞计数检测的临床验证

阅读:1

Abstract

BACKGROUND: Complete blood count (CBC) testing is critical for diagnosing and monitoring hematological conditions, including leukemia. However, conventional analyzers require specialized infrastructure and trained personnel, limiting access in resource-constrained settings. Point-of-care hematology devices provide a promising alternative by delivering rapid results with minimal complexity. This study aimed to evaluate the analytical performance of the Hilab Lens versus XE-2100. METHODS: Blood samples (n = 555) were analyzed using both devices at Erastinho Hospital, a pediatric oncology center. Device performance was assessed through precision testing, method comparison, sample type equivalence, evaluation of potential interferences, and caregiver satisfaction surveys. Agreement and correlation were evaluated using Bland-Altman plots and Passing-Bablok regression. RESULTS: Here we show that the Hilab Lens demonstrates high precision and consistency, meeting European Federation of Clinical Chemistry and Laboratory Medicine (EFLM). Method comparison revealed strong correlations (key analytes r ≥ 0.95), minimal bias, and robust agreement with the reference analyzer across all CBC parameters. The Hilab Lens achieved high accuracy in flagging studies (≥ 98.8%), particularly for band neutrophils and immature cells. No significant interferences were detected (p > 0.5). Caregivers reported high satisfaction with the test (mean score 4.65 on a 5-point scale). CONCLUSIONS: These results support the Hilab Lens as a reliable and accessible alternative to conventional hematology analyzers. Its ease of use and rapid turnaround make it suitable for environments where timely CBC testing is essential. The high acceptance observed in pediatric oncology suggests its potential for broader implementation in clinical practice.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。