JMIRx Medxmed34JMIRx MedJMIRx Med2563-6316JMIR PublicationsToronto, Canadav5i1e6038910.2196/60389Peer-Review ReportPeer Review of “Machine Learning–Based Hyperglycemia Prediction: Enhancing Risk Assessment in a Cohort of Undiagnosed Individuals”AlamFakhareOakland University, RochesterMI, United StatesMeinertEdward202411920245e603890905202409052024© Fakhare Alam. Originally published in JMIRx Med (https://med.jmirx.org), 11.9.2024. 2024

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIRx Med, is properly cited. The complete bibliographic information, a link to the original publication on https://med.jmirx.org/, as well as this copyright and license information must be included.

https://www.medrxiv.org/content/10.1101/2023.11.22.23298939v1http://preprints.jmir.org/preprint/56993https://med.jmirx.org/2024/1/e60174https://med.jmirx.org/2024/1/e56993hyperglycemiadiabetesmachine learninghypertensionrandom forest

This is the peer-review report for “Machine Learning–Based Hyperglycemia Prediction: Enhancing Risk Assessment in a Cohort of Undiagnosed Individuals.”

Round 1 ReviewGeneral Comments

This paper [1] introduces a machine learning (ML) methodology for predicting hyperglycemia in one of the cohorts taken from a suburban Nigerian region. The authors present the details of the methodology for participant recruitment and screening, data analysis, and selection of ML models.

Specific CommentsMajor Comments

The introduction and motivation behind the work are well written. However, there is not enough literature done on the ML aspect of noncommunicable disease prediction; please also cite some of the recent work where ML-based methods are used for noncommunicable disease prediction.

Before selecting the features, was there any domain expert consulted? If yes, please provide reasoning on some aspect of feature selection.

How were the different ML models selected for the experiment? Please elaborate on some selection criteria such as the combination of tree-based models with other ensemble approaches such as random forest.

Minor Comments

In Table 2, please reduce the decimal precision up to 2 digits.

Figure 1 could be improved with a flow diagram to provide better readability and details of each step.

None declared.

AbbreviationsML

machine learning

ReferencesOyebolaK LigaliF OwoloyeA Machine learning–based hyperglycemia prediction: enhancing risk assessment in a cohort of undiagnosed individualsJMIRx Med20245e5699310.2196/56993