Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

  • Loading metrics

Open Access

Expression of Concern

Expression of Concern: Hybrid feature selection and classification technique for early prediction and severity of diabetes type 2

  • The PLOS One Editors

After this article [1] was published, the following concerns were noted:

  • The Editors have concerns about the article’s peer review.
  • The article uses terminology that differs from standards in the field, e.g., “Engineered Minority Oversampling Procedure (Destroyed)” instead of “synthetic minority oversampling technique (SMOTE)” and others. The corresponding author acknowledged that they used software for English language improvement during the revision process which may have introduced these phrases.
  • The article cited in [1] as Reference 22 [2,3] was retracted after [1] was published. The corresponding author provides [4] as a replacement reference.
  • The dataset used in this article [1] is not available on the UC Irvine Machine Learning Repository as stated in the article. The corresponding author stated that at the time of the study, the data was available at this source and they provided an alternative source [5].

In light of the cumulative issues, the PLOS One Editors issue this Expression of Concern.

References

  1. 1. Talari P, Bharathiraja N, Kaur G, Alshahrani H, Al Reshan MS, Sulaiman A, et al. Hybrid feature selection and classification technique for early prediction and severity of diabetes type 2. PLoS ONE. 2024;19(1):e0292100. pmid:38236900
  2. 2. Marappan R, Vardhini PAH, Kaur G, Murugesan S, Kathiravan M, Bharathiraja N, et al. Retracted article: Efficient evolutionary modeling in solving maximization of lifetime of wireless sensor healthcare networks. Soft Comput. 2023;27(16):11853–67.
  3. 3. Marappan R, Vardhini PAH, Kaur G, Murugesan S, Kathiravan M, Bharathiraja N, et al. Retraction Note: Efficient evolutionary modeling in solving maximization of lifetime of wireless sensor healthcare networks. Soft Comput. 2024;28(S1):371–371.
  4. 4. Kamel Rahimi A, Canfell OJ, Chan W, Sly B, Pole JD, Sullivan C, et al. Machine learning models for diabetes management in acute care using electronic medical records: A systematic review. Int J Med Inform. 2022;162:104758. pmid:35398812
  5. 5. UCI Machine Learning, Kaggle Team. Pima Indians Diabetes Database. Kaggle. Available from: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database

    Citation: The PLOS One Editors (2025) Expression of Concern: Hybrid feature selection and classification technique for early prediction and severity of diabetes type 2. PLoS One 20(5): e0324149. https://doi.org/10.1371/journal.pone.0324149

    Published: May 8, 2025

    Copyright: © 2025 The PLOS One Editors. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.