Verified Rigor RecordRigor Reviewed

Rigor-Reviewed Manuscript

An effective PO-RSNN and FZCIS based diabetes prediction and stroke analysis in the metaverse environment · 10.1038/s41598-025-96541-2

Name: Verified Rigor Record — An effective PO-RSNN and FZCIS based diabetes prediction and stroke analysis in the metaverse environment · 10.1038/s41598-025-96541-2
Item: An effective PO-RSNN and FZCIS based diabetes prediction and stroke analysis in the metaverse environment · 10.1038/s41598-025-96541-2
Rating: 78
Author: Αlpha¹

Paper source

Αlpha¹ Editorial

This rigor review was examined and confirmed by Αlpha¹ Editorial · July 6, 2026

Αlpha¹ Rigor Review

Rigor Reviewed

WARN

Warnings to address

Eight dimensions — click a segment for details

Critical

High-priority

Model-reported confidence: HighReviewer agreement: highEngine: 7.5.0Source: full text

Not verified in this report

No reported statistical tests were found to recompute.
Declared data/code links were not checked for liveness or content.

This Αlpha¹ Rigor Review uses AI Rigor Reviewers trained on a curated corpus of high-fidelity and retracted papers, with expert supervision and curation. It can still make mistakes; verify each finding against the source before relying on it.

12 major claims checked against the paper's own evidence: 3 not fully backed by the presented evidence (unsupported or overstated).

11 integrity concerns flagged (3 high).

Rigor

Eight Dimensions2 pass · 4 warn

12 major claims3 unsupported4 partial5 supported

The Introduction and Literature Survey cite 15+ prior studies, acknowledge limitations (e.g., poor support for disabled persons, security issues, data imbalance, high dimensionality), and clearly link these gaps to the proposed contributions (PO-RSNN, FZCIS, MJCC, A-PCA, SMOTE). The premise rationale is logical: from cited limitations to the study's objectives. While limitations_addressed is present (e.g., 'Existing models were not regularized well enough to provide communication support for disabled persons'), it is somewhat implicit rather than a structured discussion.

Sub-criteria

prior work citedADEQUATE

premise rationaleADEQUATE

limitations addressedINADEQUATE

Per reviewer (2) — the votes behind the verdict

PASSReviewer 1· 92% conf

The paper cites extensive prior work on diabetes and stroke prediction using ML/DL, identifies specific limitations, and states how the proposed methods address them.

Evidence

direct quote[Introduction, paragraphs 3-5; Literature Survey section]

“Existing models were not regularized well enough to provide communication support for disabled persons in ME-centric CD monitoring.”

direct quote[Introduction, paragraphs 6-7]

“To overcome these limitations, a novel probabilistic-centric optimized recurrent sechelliott neural network (PO-RSNN)-based diabetes prediction (DP) and Fuzzy Z-log-clipping inference system (FZCIS)-based severity level estimation in ME is carried out.”

paraphrase[Introduction]

“The paper states 'Some limitations of the traditional models are given below' and lists five limitations, but does not explicitly state how each is mitigated in a structured fashion.”

PASSReviewer 2· 92% conf

The paper adequately establishes its scientific foundation with cited prior work and a clear rationale.

Evidence

direct quote[Introduction, final paragraph]

“Existing models were not regularized well enough to provide communication support for disabled persons in ME-centric CD monitoring.”

direct quote[Introduction, 'The research technique's significant contributions' section]

“The proposed work is proficiently designed to provide communication support for disabled persons in the ME.”

paraphrase[Introduction, bulleted list]

“A list of five limitations of existing models is given, but there is no organized discussion of how each limitation translates into a design decision of the proposed system.”

The paper describes data splitting (80/20), tenfold cross-validation for generalizability, and SMOTE for class balancing, which are appropriate for a computational study. However, no a priori power analysis or sample-size justification is given. The inclusion/exclusion criteria for the datasets are not pre-specified beyond stating they are from public sources. Outlier handling is not explicitly reported. The replication is limited to cross-validation folds; no independent replication cohort is described. Randomization, blinding, and biological-replicate distinction are not applicable.

Sub-criteria

controlsINADEQUATE

power analysisNOT REPORTED

blinding levelsN/A

outlier handlingNOT REPORTED

randomization unitN/A

inclusion exclusionINADEQUATE

randomization methodN/A

replicate distinctionN/A

independent replicationNOT REPORTED

Per reviewer (2) — the votes behind the verdict

PASSReviewer 1· 85% conf

The study is a computational/ML pipeline validation on public datasets; applicable sub-criteria (power_analysis→dataset selection, controls→baseline/ablation, inclusion_exclusion→data curation) are adequately reported.

Evidence

direct quote[Results, Dataset description, Tables 3-4]

“From the whole data, 80% of the data is utilized to train the model and the remaining data is allocated for testing purposes.”

direct quote[Results, Performance analysis of classification (diabetes dataset)]

“The performance of the proposed PO-RSNN is analogized with prevailing approaches, such as RNN, Deep Belief Network (DBN), Restricted Boltzmann Machine (RBM), DNN, ANN, and SVM.”

absence[Entire paper]

No outlier handling procedure is described.

WARNReviewer 2· 78% conf

Core design is reported for a computational study (data splits, cross-validation) but lacks justification for data splits, power analysis, and independent replication.

Evidence

direct quote[Results and Discussion, Dataset description]

“From the whole data, 80% of the data is utilized to train the model and the remaining data is allocated for testing purposes.”

direct quote[Results, Generalizability of the model]

“the tenfold cross-validation strategy is applied.”

absence[Methods and Results sections]

No power analysis or sample-size justification is reported

The paper uses two public Kaggle datasets (Diabetes Prediction Dataset, Stroke Prediction Dataset) containing de-identified demographic and clinical features. No new animal or human subjects were involved. Biological variables such as sex, age, and health metrics are present in the datasets as features, but the study does not generate or collect these data from subjects, so the dimension is not applicable.

Sub-criteria

demographicsN/A

sex reportedN/A

sex justifiedN/A

age weight healthN/A

housing conditionsN/A

species strain sourceN/A

Per reviewer (2) — the votes behind the verdict

N/AReviewer 1· 98% conf

The study uses public tabular datasets with demographic and clinical features; no biological specimens, organisms, or housing conditions are involved.

Evidence

direct quote[Results, Dataset description]

“The datasets are collected from the publically available resources that are mentioned under the reference section.”

paraphrase[Table 2]

“Table 2 lists features such as Gender, Age, BMI, HbA1c level, etc., for both DPD and SPD.”

N/AReviewer 2· 99% conf

The study is entirely computational, using only publicly available de-identified datasets; no biological subjects were enrolled.

Evidence

direct quote[Results and Discussion, Dataset description]

“The datasets are collected from the publically available resources that are mentioned under the reference section.”

absence[Methods and Results sections]

No new subject-level data collection

Ethics sub-criteria (irb_ethics_statement, informed_consent, iacuc_statement, regulatory_compliance) are not applicable because the work is purely computational on secondary public data. The paper states 'The data used to support the findings of this study are available from the corresponding author upon request' and provides Kaggle URLs. No new subject data were collected, no human participants were enrolled, and no animals were used.

Sub-criteria

iacuc statementN/A

informed consentN/A

irb ethics statementN/A

regulatory complianceN/A

Per reviewer (2) — the votes behind the verdict

N/AReviewer 1· 97% conf

The study uses only public, fully de-identified, open-access benchmark datasets (Kaggle); no new human/animal data collection, so ethical approvals are genuinely not required.

Evidence

direct quote[Data availability, Results dataset description]

“https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset https://www.kaggle.com/datasets/iammustafatz/diabetes-prediction-dataset”

N/AReviewer 2· 95% conf

The study uses only publicly available, de-identified benchmark datasets; no new human or animal data collection occurred, so ethics approval is not required.

Evidence

direct quote[Data availability]

“https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset”

absence[Entire manuscript]

No ethics statement is present

Only software_tools_identified is applicable for this computational study. The paper lists Python 3.10, PyCharm 2022.3.3, Windows 10, and libraries (Tkinter, Matplotlib, Keras, TensorFlow, NumPy, scikit-learn, imblearn, cryptography) by name and brief purpose. No version numbers are given for libraries, but the main tool versions are stated. Antibodies, cell lines, mycoplasma, organisms, and reagents are not applicable. The Drugs/Devices sub-criterion does not apply as there is no investigational product.

Sub-criteria

mycoplasma testingN/A

reagents identifiedN/A

organisms identifiedN/A

antibodies identifiedN/A

cell line authenticationN/A

software tools identifiedINADEQUATE

Per reviewer (2) — the votes behind the verdict

PASSReviewer 1· 90% conf

The study uses public software libraries and interprets no bench reagents; software_tools_identified is adequately reported with names and versions of Python, PyCharm, libraries.

Evidence

direct quote[Results and discussion, first paragraph]

“The proposed system is developed using Python 3.10... PyCharm 2022.3.3 is utilized... Keras and TensorFlow serve as the primary frameworks...”

paraphrase[Results and discussion]

“Libraries like Tkinter, Matplotlib, NumPy, imblearn, scikit-learn, cryptography are named but not given version numbers.”

PASSReviewer 2· 85% conf

Software tools and libraries are adequately identified; no biological/chemical resources or investigational products are used.

Evidence

direct quote[Results and Discussion, first paragraph]

“The proposed system is developed using Python 3.10, which is a widely used programming language for DL applications. The PyCharm 2022.3.3 is utilized for coding, debugging, and executing the model efficiently on a Windows 10 (64-bit) platform.”

absence[Methods and Results sections]

No investigational product or biological resource is used

The paper names performance metrics (accuracy, precision, recall, F1, FPR, FNR, training time) and compares models. However, no statistical tests are used to compare classifiers (e.g., no p-values, confidence intervals, or effect sizes). The 'mathematical_plausibility' sub-criterion cannot be verified because the reported accuracy percentages (e.g., 98.97%) are from a computational classification task and are not associated with test-statistic arithmetic. No normality or variance assumptions are discussed. Software is identified. Data presentation is adequate (tables and figures with per-class counts).

Sub-criteria

tests namedN/A

exact p valuesN/A

effect sizes ciN/A

data presentationADEQUATE

software identifiedADEQUATE

assumptions verifiedNOT REPORTED

mathematical plausibilityN/A

Per reviewer (2) — the votes behind the verdict

WARNReviewer 1· 80% conf

Tests are named, exact p-values are not reported, effect sizes and confidence intervals are absent, and mathematical_plausibility is not verifiable from summary metrics alone.

Evidence

absence[Results, all subsections]

No exact p-values are reported.

absence[Results]

Effect sizes and CIs are absent.

paraphrase[Figures 3-7]

“Figures display bar charts comparing accuracy, precision, etc., without showing individual data point overlays.”

WARNReviewer 2· 82% conf

Tests are named and performance metrics are reported, but key inferential statistics (p-values, effect sizes, CIs) are absent, and no assumption verification is provided.

Evidence

absence[Results and Discussion]

No statistical inference tests are used

direct quote[Results and Discussion, first paragraph]

“Keras and TensorFlow serve as the primary frameworks, improving the optimization of the predictive model.”

paraphrase[Results and Discussion, Performance evaluation]

“Tables 3–8 and Figures 3–13 present class distributions, accuracy, and other metrics.”

The data_availability_statement is present but provides only a vague route: 'The data used to support the findings of this study are available from the corresponding author upon request.' The URLs to the original Kaggle datasets are provided, but the processed/curated data used in the study are not deposited in a repository with a persistent identifier. repository_deposit and accession_numbers are not applicable because the data are public Kaggle datasets (no new sequencing/imaging data). code_sharing is not_reported; no custom code repository is mentioned.

Sub-criteria

code sharingNOT REPORTED

accession numbersN/A

repository depositNOT REPORTED

data availability statementINADEQUATE

Per reviewer (2) — the votes behind the verdict

WARNReviewer 1· 88% conf

Data availability statement is vague ('available from the corresponding author upon request') with no repository deposit; no code is shared.

Evidence

direct quote[Data availability section]

“The data used to support the findings of this study are available from the corresponding author upon request.”

direct quote[Data availability section]

“https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset , https://www.kaggle.com/datasets/iammustafatz/diabetes-prediction-dataset”

absence[Entire paper]

No code sharing is reported.

WARNReviewer 2· 80% conf

A data availability statement with URLs exists, but the statement is partially vague and no custom code is shared.

Evidence

direct quote[Data availability]

“The data used to support the findings of this study are available from the corresponding author upon request.”

direct quote[Data availability]

“https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset”

absence[Data availability and Methods sections]

No custom code repository is mentioned

methods_completeness is adequate: the architecture, algorithms, and procedures are explained in detail. trial_registration and reporting_guideline are n/a (computational study on public data). all_outcomes_reported seems adequate (positive results reported with metrics, no clear cherry-picking). limitations_discussed is reported_but_inadequate: the Limitations section is only one paragraph focusing on the scope (only diabetes and stroke considered) but omits deeper methodological limitations (overfitting, generalizability across populations, data source biases, security limitations). conclusions_proportional is adequate. funding_coi is not_reported; no funding or conflict-of-interest statement appears.

Sub-criteria

funding coiNOT REPORTED

trial registrationN/A

reporting guidelineN/A

methods completenessADEQUATE

all outcomes reportedADEQUATE

limitations discussedINADEQUATE

conclusions proportionalADEQUATE

Per reviewer (2) — the votes behind the verdict

WARNReviewer 1· 85% conf

Methods are described with enough detail for replication; trial registration and reporting guideline are not applicable; limitations are discussed briefly, and conclusions are proportional; funding/COI is not reported.

Evidence

direct quote[Proposed methodology, all subsections]

“the proposed PO-RSNN is briefly described as, Sechelliott activation function... Input layer... Weight initialization...”

direct quote[Limitations and future scope]

“Although the proposed work effectively predicted diabetes and analyzed stroke in a patient, other CDs, such as hypertension, cancer, and heart disease, were not considered.”

paraphrase[Declarations section]

“The declarations section includes author contributions and data availability but no funding or COI statement.”

WARNReviewer 2· 85% conf

Methods are detailed for reproducibility, limitations are discussed, and funding/COI disclosures are present, but no trial registration or reporting guideline applies, and the conclusions are slightly overstated.

Evidence

direct quote[Proposed methodology section]

“The proposed PO-RSNN is briefly described as, Sechelliott activation function In the proposed work, an effective activation named Sechelliott is employed...”

direct quote[Limitations and future scope]

“Although the proposed work effectively predicted diabetes and analyzed stroke in a patient, other CDs, such as hypertension, cancer, and heart disease, were not considered.”

direct quote[Abstract and Conclusion]

“the proposed system produces a secure, scalable, and highly accurate DP and stroke analysis in ME.”

25 copyedit issues flagged (16 major): mostly typo, clarity, consistency.

Checked 41 references: 40 verified — 1 retracted.

Reproducibility

Registration stated in text, but no registry ID was detected. No reporting guideline cited.

Full text (65,090 chars)Analyzed: Jul 6, 2026

Αlpha¹ assesses methodological rigor, not the importance of the findings. See how we calibrate →