Review History


All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.

Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.

View examples of open peer review.

Summary

  • The initial submission of this article was received on January 22nd, 2025 and was peer-reviewed by 2 reviewers and the Academic Editor.
  • The Academic Editor made their initial decision on April 8th, 2025.
  • The first revision was submitted on May 8th, 2025 and was reviewed by 1 reviewer and the Academic Editor.
  • The article was Accepted by the Academic Editor on June 24th, 2025.

Version 0.2 (accepted)

· Jun 24, 2025 · Academic Editor

Accept

Thanks for undertaking a thorough revision of the paper.

[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]

Reviewer 1 ·

Basic reporting

the paper has been greatly improved

Experimental design

the paper has been greatly improved

Validity of the findings

the paper has been greatly improved

Additional comments

the paper has been greatly improved

Version 0.1 (original submission)

· Apr 8, 2025 · Academic Editor

Major Revisions

After going through your paper and reviewing the comments made by the reviewers on your paper, i agree with the comments made by the reviewers, that the paper need a lot of improvement. In particular you need to pay attention to the language related changes. Please have somebody read and edit the language for you. The reviewers also provide you a detailed suggestion on how to improve the paper. The paper needs more work, but it doable. Based on the reviewers' comments, if you choose to modify, please undertake the revision and submit it as a revised paper.

**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.

**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff

Reviewer 1 ·

Basic reporting

This paper proposes a novel prediction model that enhances the reliability and lifetime testing processes of digital microfluidic systems. Traditional methods have shortcomings due to their heavy reliance on real-time monitoring data, resulting in delays and inefficiencies in evaluating complex droplet behaviors. To address these issues, the authors introduce an integrated model that combines Attention-based Bidirectional Long Short-Term Memory (BiLSTM) with eXtreme Gradient Boosting (XGBoost) in a Stacking approach. This model aims to provide an efficient identification of health states and accurate predictions of failure times for digital microfluidic devices. I would suggest revisions as below:
1. How does the performance of the proposed BiLSTM-XGBoost model quantitatively compare to other advanced machine learning models beyond those mentioned (like BiGRU), particularly in diverse operational conditions of digital microfluidic systems? Are there scenarios where it may underperform?
2. some references about xgboost and explainable AI to enhance the litterature review: Explainable AI models for predicting drop coalescence in microfluidics device; Explainable AI model for predicting equivalent viscous damping in dual frame-wall resilient system
3. Is the BiLSTM-XGBoost model adaptable to other types of microfluidic systems or different domains altogether? How might the model's structure change if applied to other fields, and what limitations might arise?
4. Can the authors provide more detail on how the attention mechanism impacts the model's performance? Specifically, what features or aspects of the data does the model prioritize, and how was this selectivity validated?

Experimental design

see above

Validity of the findings

see above

Additional comments

n/a

Reviewer 3 ·

Basic reporting

detailed report is attached.

Experimental design

detailed report is attached.

Validity of the findings

detailed report is attached.

Additional comments

detailed report is attached.

Annotated reviews are not available for download in order to protect the identity of reviewers who chose to remain anonymous.

All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.