The recent article by represents a commendable step toward realizing AI-integrated microscopy as a scalable diagnostic solution for schistosomiasis. The validation of AiDx Assist in a dual-endemic setting for S. haematobium and S. mansoni reflects a well-designed response to the WHO’s call for point-of-care tools meeting target product profiles (). Particularly notable is the strong sensitivity and specificity (>90%) achieved in detecting S. haematobium in urine, both in semi-automated and fully automated modes. These results suggest readiness for deployment in urogenital schistosomiasis control programs.
However, the relatively lower sensitivity of the fully automated detection for S. mansoni in stool (56.9%) warrants further algorithm refinement. The discrepancy between semi- and fully automated performance suggests that AI misclassification or under-detection remains a technical bottleneck—likely influenced by the morphological variability and background complexity of stool slides (; ). One avenue to improve performance could be the integration of convolutional neural networks trained on a broader dataset including diverse egg presentations and artifacts ().
A notable strength of the study is its dual-sample analysis (stool and urine) in a field setting—a rare approach that mimics real-world application. Moreover, the incidental visualization of Ascaris lumbricoides and Trichuris trichiura eggs in retrospect highlights the potential of AiDx Assist as a multi-parasite detection platform. We propose formalizing this potential through a prospective multi-pathogen training dataset and validation study, as demonstrated by other AI-parasitology platforms (; ).
To further bolster the impact and utility of AiDx Assist, we suggest three enhancements:
Expand stool slide training sets to include polyparasitism and low-intensity infections, thus aligning performance with the WHO-recommended Kato–Katz sensitivity thresholds.
Develop modular AI plug-ins for soil-transmitted helminths, aligning with WHO’s integrated helminth control strategies dating back to early guidance () and reaffirmed in the 2030 NTD roadmap ().
Pilot longitudinal field evaluations to assess device durability, technician learning curves, and integration into MDA programs.
If these are pursued, AiDx Assist could evolve into a truly transformative tool—not only for schistosomiasis control but for broader parasitic diagnostics in LMICs.
Statements
Author contributions
NR: Validation, Conceptualization, Writing – review & editing, Writing – original draft. SR: Writing – review & editing, Validation.
Funding
The author(s) declare that no financial support was received for the research and/or publication of this article.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Generative AI statement
The author(s) declare that Generative AI was used in the creation of this manuscript. The authors verify and take full responsibility for the use of Generative AI in the preparation of this manuscript. Generative AI (ChatGPT, OpenAI) was used to assist in language refinement, formatting references in journal style, and improving clarity in scientific writing. All content generated by AI has been carefully reviewed, edited, and validated by the author(s) to ensure accuracy, originality, and adherence to ethical standards.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1
BogochI. I.MarksM.WardB. J.MacleanJ. D.UtzingerJ. (2013). Evaluation of an automated microscopy system for detection of helminth eggs in stool. Am. J. Trop. Med. Hyg.89, 133–137. doi: 10.4269/ajtmh.12-0457
2
CoulibalyJ. T.KnoppS.N’GuessanN. A.SiluéK. D.FürstT.LohourignonL. K.et al. (2016). Accuracy of Kato–Katz and FLOTAC for diagnosing helminths in school-aged children. PloS Negl. Trop. Dis.10, e0004568. doi: 10.1371/journal.pntd.0004568
3
HemachandranK.AlasiryA.MarzouguiM.GanieS. M.PiseA. A.AlouaneM. T.-H.et al. (2023). Performance analysis of deep learning algorithms in diagnosis of malaria disease. Diagn. 13, 534. doi: 10.3390/diagnostics13030534
4
KitturN.BinderS.CampbellC. H. (2022). Machine learning applications for neglected tropical disease diagnostics. PloS Negl. Trop. Dis.16, e0010692. doi: 10.1371/journal.pntd.0010692
5
McManusD. P.DunneD. W.SackoM.UtzingerJ.VennervaldB. J.ZhouX. N. (2018). Schistosomiasis. Nat. Rev. Dis. Primers. 4, 13. doi: 10.1038/s41572-018-0013-8
6
MeulahB.HoekstraP. T.PopoolaS.JujjavarapuS.AderogbaM.FadareJ. O.et al. (2025). Evaluation of the AiDx Assist device for automated detection of Schistosoma eggs in stool and urine samples in Nigeria. Front. Parasitol.4. doi: 10.3389/fpara.2025.1440299
7
World Health Organization (2002). Prevention and control of schistosomiasis and soil-transmitted helminthiasis: report of a WHO expert committee. Available online at: https://apps.who.int/iris/handle/10665/42588 (Accessed May 10, 2025).
8
World Health Organization (2021). Ending the neglect to attain the Sustainable Development Goals: a roadmap for neglected tropical diseases 2021–2030. Available online at: https://www.who.int/publications/i/item/9789240010352 (Accessed May 10, 2025).
Summary
Keywords
AI-powered diagnostics, schistosomiasis, AiDx Assist evaluation, stool samples, urine samples
Citation
Rattanapitoon NK and Rattanapitoon SK (2025) Commentary: Evaluation of the AiDx Assist device for automated detection of Schistosoma eggs in stool and urine samples in Nigeria. Front. Parasitol. 4:1633767. doi: 10.3389/fpara.2025.1633767
Received
23 May 2025
Accepted
07 July 2025
Published
22 July 2025
Volume
4 - 2025
Edited by
Maria Isabel Jercic, Public Health Institute of Chile, Chile
Reviewed by
Pengfei Cai, QIMR Berghofer Medical Research Institute, Australia
Updates
Copyright
© 2025 Rattanapitoon and Rattanapitoon.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Nathkapach Kaewpitoon Rattanapitoon, nathkapach.ratt@sut.ac.th
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.