Acta Scientific Medical Sciences (ISSN: 2582-0931)

Research Article Volume 4 Issue 1

Study on the Performance of SigTuple AI100 in the Analysis of RBC, WBC, Platelet Morphology and WBC Differential Count in a Large Hospital Setup

Renu Ethirajan1* and Roja Ramani2

1Director Pathology - SigTuple Technologies Pvt Ltd., Bengaluru, Karnataka, India
2Manager Pathology - SigTuple Technologies Pvt Ltd., Bengaluru, Karnataka, India

*Corresponding Author: Renu Ethirajan, Director Pathology - SigTuple Technologies Pvt Ltd., Bengaluru, Karnataka, India.

Received: December 05, 2019; Published: December 12, 2019

×

Abstract

  In this study, we evaluate the performance of SigTuple AI100, powered by SHONITTM, a cloud based artificial intelligence (AI) system for the analysis of peripheral blood smears against the haematology automated analyser and results of manual microscopy in a large hospital setup. A blinded, randomized comparative study between results of AI100 and 7-part haematology analyser values for WBC differential counts, WBC morphological classification, RBC morphology and platelet morphology was conducted. The results of RBC and platelet morphology classification given by AI100 were compared with the results of the manual microscopy. The mean-absolute-difference between 5 Part differentials reported by AI100 and the Sysmex 7-Part haematology analyser for Neutrophil, Lymphocyte, Monocyte, Eosinophil and Basophil were 4.38%, 4.74%, 5.82%, 0.97%, and 0.53% respectively. The r2 coefficient mean of results of haematology analyser vs Shonit (AI100) for neutrophil, lymphocyte and eosinophil were 0.97, 0.97 and 0.92 respectively. AI100 can increase the throughput and decrease TAT; thereby increasing the productivity and efficiency of the pathologist.

Keywords: SigTuple AI100; RBC; WBC; Platelet

×

Citation

Citation: Renu Ethirajan and Roja Ramani. “Study on the Performance of SigTuple AI100 in the Analysis of RBC, WBC, Platelet Morphology and WBC Differential Count in a Large Hospital Setup". Acta Scientific Medical Sciences 4.1 (2020): 102-107.




Metrics

Acceptance rate30%
Acceptance to publication20-30 days
Impact Factor1.403

Indexed In





Contact US