Microbiome disease-state classification evaluates independent disease/control cohorts through leave-one-out prediction.
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Splits | Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Metrics | Accuracy, precision and recall.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Baselines | Random forest, XGBoost, principal-component regression, lasso and SVM.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Leakage controls | The source explicitly removes the held-out sample from both learning stages.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Entity type | Paper-specific computational evaluation protocol.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Organisms | Human gut microbial communities.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Assays | Microbiome profiles with disease/control labels.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Allowed inputs | Microbiome composition/features.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Adaptation | Embedding and classifier training are repeated inside leave-one-out folds, excluding the held-out subject sample.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls. Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training. Accuracy, precision and recall. Random forest, XGBoost, principal-component regression, lasso and SVM. The source explicitly removes the held-out sample from both learning stages. The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Each evaluation records what was tested and under which conditions.
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| MDL4Microbiome: microbiome disease-state classification Configuration: MDL4MicrobiomeTask: microbiome disease-state classificationDataset: CRC microbiome cohort Multimodal deep learning model on colorectal-cancer versus healthy microbiome samples Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.97 accuracy Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedMultimodal deep learning applied to classify healthy and disease states of human microbiome · Table 3, CRC row, MDL4Microbiome column Source checking is not independent reproduction. |
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Multimodal deep learning applied to classify healthy and disease states of human microbiome | PMC archival version PMC8763943.1 | Read source DOI: 10.1038/s41598-022-04773-3 |
primary comparison table screened
Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.
Stable record: reported-task-e2009c35eabd69Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
18 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Input: Microbiome composition/features.","Evaluation: Embedding and classifier training are repeated inside leave-one-out folds, excluding the held-out subject sample.","Readout: Accuracy, precision and recall."] Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Embedding and classifier training are repeated inside leave-one-out folds, excluding the held-out subject sample. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Accuracy, precision and recall. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Random forest, XGBoost, principal-component regression, lasso and SVM. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The source explicitly removes the held-out sample from both learning stages. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | unreported automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-09-17-d277315f7d76 · Record review: needs review
Stable ID: reported-task-e2009c35eabd69