Dataset Information

Performance of a fully-automated system on a WHO malaria microscopy evaluation slide set.

ABSTRACT:

Background

Manual microscopy remains a widely-used tool for malaria diagnosis and clinical studies, but it has inconsistent quality in the field due to variability in training and field practices. Automated diagnostic systems based on machine learning hold promise to improve quality and reproducibility of field microscopy. The World Health Organization (WHO) has designed a 55-slide set (WHO 55) for their External Competence Assessment of Malaria Microscopists (ECAMM) programme, which can also serve as a valuable benchmark for automated systems. The performance of a fully-automated malaria diagnostic system, EasyScan GO, on a WHO 55 slide set was evaluated.

Methods

The WHO 55 slide set is designed to evaluate microscopist competence in three areas of malaria diagnosis using Giemsa-stained blood films, focused on crucial field needs: malaria parasite detection, malaria parasite species identification (ID), and malaria parasite quantitation. The EasyScan GO is a fully-automated system that combines scanning of Giemsa-stained blood films with assessment algorithms to deliver malaria diagnoses. This system was tested on a WHO 55 slide set.

Results

The EasyScan GO achieved 94.3?% detection accuracy, 82.9?% species ID accuracy, and 50?% quantitation accuracy, corresponding to WHO microscopy competence Levels 1, 2, and 1, respectively. This is, to our knowledge, the best performance of a fully-automated system on a WHO 55 set.

Conclusions

EasyScan GO's expert ratings in detection and quantitation on the WHO 55 slide set point towards its potential value in drug efficacy use-cases, as well as in some case management situations with less stringent species ID needs. Improved runtime may enable use in general case management settings.

SUBMITTER: Horning MP

PROVIDER: S-EPMC7905596 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Performance of a fully-automated system on a WHO malaria microscopy evaluation slide set.

Horning Matthew P MP Delahunt Charles B CB Bachman Christine M CM Luchavez Jennifer J Luna Christian C Hu Liming L Jaiswal Mayoore S MS Thompson Clay M CM Kulhare Sourabh S Janko Samantha S Wilson Benjamin K BK Ostbye Travis T Mehanian Martha M Gebrehiwot Roman R Yun Grace G Bell David D Proux Stephane S Carter Jane Y JY Oyibo Wellington W Gamboa Dionicia D Dhorda Mehul M Vongpromek Ranitha R Chiodini Peter L PL Ogutu Bernhards B Long Earl G EG Tun Kyaw K Burkot Thomas R TR Lilley Ken K Mehanian Courosh C

Malaria journal 20210225 1

<h4>Background</h4>Manual microscopy remains a widely-used tool for malaria diagnosis and clinical studies, but it has inconsistent quality in the field due to variability in training and field practices. Automated diagnostic systems based on machine learning hold promise to improve quality and reproducibility of field microscopy. The World Health Organization (WHO) has designed a 55-slide set (WHO 55) for their External Competence Assessment of Malaria Microscopists (ECAMM) programme, which can ...[more]

PMID: 33632222

Similar Datasets

Project description:Streptococcus agalactiae [group B Streptococcus (GBS)] poses a major threat as the primary cause of early-onset neonatal invasive disease, particularly when mothers are colonized rectovaginally. Although culture remains the gold standard for antepartum GBS screening, quantitative polymerase chain reaction (qPCR) offers advantages in terms of sensitivity and turnaround time. The aim of this study was to validate the clinical utility of an automated qPCR laboratory-developed test (LDT) for antepartum GBS screening using the Panther Fusion Open Access system (Hologic, California, USA). The LDT targeted a conserved region of the GBS surface immunogenic protein gene, demonstrating no cross-reactivity and high coverage (99.82%-99.99%). The limit of detection (LoD) was 118 CFU/mL. Comparison with commercial qPCR assays (Panther Fusion GBS and VIASURE Streptococcus B Real-Time) revealed an overall agreement of 99.7%, with a robust Cohen's kappa coefficient of 0.992. Testing of 285 rectovaginal swabs from pregnant women and 15 external quality assessment samples demonstrated exceptional diagnostic performance of the LDT, achieving a diagnostic sensitivity and specificity of 100%, underscoring its accuracy. Prevalence and predictive values were also determined to reinforce test reliability. Our research highlights the limitations of culture-based screening and supports the suitability of our qPCR-based LDT for GBS detection in a clinical setting.IMPORTANCERectovaginal colonization by GBS is a major risk factor for early-onset invasive neonatal disease. The most effective approach to reducing the incidence of early-onset disease (EOD) has been described as universal screening, involving assessment of GBS colonization status in late pregnancy and intrapartum antibiotic prophylaxis. Despite its turnaround time and sensitivity limitations, culture remains the gold standard method for GBS screening. However, nucleic acid amplification-based tests, such as qPCR, have been utilized due to their speed and high sensitivity and specificity. This study validated the clinical usefulness of an automated qPCR-LDT for antepartum GBS screening through the Panther Fusion Open Access system (Hologic). Our study addresses the critical need for more robust, sensitive, and rapid strategies for GBS screening in pregnant women that could favorably impact the incidence of EOD.

Dataset Information

Performance of a fully-automated system on a WHO malaria microscopy evaluation slide set.

Background

Methods

Results

Conclusions

Publications

Performance of a fully-automated system on a WHO malaria microscopy evaluation slide set.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets