← All .science files
pmid:41358057
Explainable artificial intelligence and ensemble learning for hepatocellular carcinoma classification: State of the art, performance, and clinical implications.
World journal of hepatology · 2025 doi:10.4254/wjh.v17.i11.109494
Paper
partial
Experiment
partial
Data
partial
Analysis
absent
Execution
absent
Execution evidence has not yet been added to this .science file. Explore its methods, data and open questions to plan the next step.
Record details sci_version · id · kind · revision · content_hash · schema · created_at · updated_at · generator
generator object · 3 fields
paper object · 10 fields
claims array · 1 item
gaps array · 2 items
experiment object · 8 fields
steps array · 3 items
[0] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[1] object · 13 fields
parameters object · 0 fields
inputs array · 0 items
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
parameters object · 0 fields
inputs array · 0 items
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
materials array · 0 items
instruments array · 0 items
reagents array · 0 items
conditions object · 0 fields
gaps array · 3 items
data object · 3 fields
assets array · 2 items
[0] object · 15 fields
structure object · 1 field
[1] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 10 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[6] array · 6 items
[7] array · 6 items
[8] array · 6 items
[9] array · 6 items
gaps array · 1 item
capability object · 3 fields
readiness object · 8 fields
axes object · 0 fields
can_run object · 3 fields
dsl_operations array · 0 items
assets array · 2 items
steps array · 1 item
must_build object · 5 fields
dsl_operations array · 0 items
converters array · 0 items
readers array · 1 item
capabilities array · 0 items
data_gaps array · 1 item
gaps array · 1 item
review object · 5 fields
machine_critique object · 7 fields
providers array · 0 items
target_providers array · 0 items
disagreements array · 0 items
agreement_basis object · 2 fields
decisive_fields array · 4 items
human_critique object · 5 fields
stages array · 7 items
[0] object · 4 fields
[1] object · 4 fields
evidence object · 1 field
provider_errors array · 4 items
[0] object · 4 fields
[1] object · 4 fields
[2] object · 4 fields
[3] object · 4 fields
[2] object · 4 fields
[3] object · 4 fields
[4] object · 4 fields
[5] object · 4 fields
[6] object · 4 fields
gaps array · 3 items
provenance object · 7 fields
entities array · 1 item
activities array · 1 item
agents array · 1 item
lineage object · 4 fields
gaps array · 14 items
Complete file
{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41358057", "kind": "science-record", "revision": 2, "content_hash": "sha256:566c3c33774bb8774c4bf665bf1ed9cd1b0d08184d609a83e1e16855c940ea57", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Explainable artificial intelligence and ensemble learning for hepatocellular carcinoma classification: State of the art, performance, and clinical implications.", "doi": "10.4254/wjh.v17.i11.109494", "pmid": "41358057", "authors": null, "journal": "World journal of hepatology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41358057"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:41358057", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41358057' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41358057", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.4254/wjh.v17.i11.109494", "sha256": "sha256:fecc2cba01ed10f5cd8c3d8b49da02348ec565a2d254a89c3f7a11ed5fdbbab2", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.4254/wjh.v17.i11.109494", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41358057:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4a450cf4a1c25f6ee626bcabec17bac1adff2bccf9968c273a2c472b0b782f18", "bytes": 2797, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T1", "version": null, "note": "Explainable ensemble learning for hepatocellular carcinoma classification", "structure": {"pmcid": "PMC12679159", "section_index": 15, "section_title": "EXPLAINABLE ENSEMBLE LEARNING APPROACHES FOR HCC CLASSIFICATION", "row_count": 10, "column_count": 6}, "table": {"label": "Table 1", "caption": "Explainable ensemble learning for hepatocellular carcinoma classification", "rows": [["Ref.", "Ensemble learning method", "Explainability technique", "Dataset used (including size and type)", "Performance metrics", "Clinical relevance of top predictive features"], ["[119]", "Soft Voting Ensemble", "SHAP", "SEER program (n = 1897), External validation from two tertiary hospitals in China (n = 98)", "AUC: 0.779 (internal), 0.764 (external); Brier score: 0.191 (internal), 0.195 (external)", "Chemotherapy, radiation therapy, lung metastases (reflect metastatic burden and treatment history)"], ["[112]", "RF (best performing), NB, LR, KNN", "LIME", "NCBI GSE14520 microarray dataset (445 samples, 22268 genes)", "Accuracy: 96.53%; Precision: 97.30%; AUC: 0.95", "Gene expression profiles (e.g., TP53, CTNNB1 mutations linked to tumorigenesis)"], ["[118]", "Stacking Ensemble", "LIME", "Data from 1622 liver cancer patients (46 variables)", "AUC: 0.9826 (training), 0.9675 (testing)", "Tumor size, vascular invasion (key pathological determinants of staging)"], ["[127]", "AutoML (TPOT) leading to a Tree-based model (likely ensemble)", "TreeSHAP", "Publicly accessible metabolomics data of HCC patients and cirrhotic controls", "AUC: 0.81", "Metabolite ratios (e.g., glutamate/glutamine reflecting metabolic reprogramming in malignancy)"], ["[67]", "Stacking ensemble", "", "Dataset from 165 HCC patients at Coimbra's Hospital and University Centre (49 features)", "Accuracy: 0.9030; F1-score: 0.8857", "AFP, child score"], ["[126]", "RF, RR, AdaBoost, DT, LR", "", "Hospital Authority Data Collaboration Lab in Hong Kong (n = 124006 patients with chronic viral hepatitis)", "AUC: 0.842 (RR, training), 0.844 (RR, validation); 0.992 (RF, training), 0.837 (RF, validation)", "Viral load, platelet count (indicators of viral activity and portal hypertension)"], ["[70]", "GB (best performing), RT, RF, XGBoost", "SHAP", "Liver disease dataset", "Accuracy, precision, recall, specificity, AUC (high values reported)", "Bilirubin, albumin (liver function markers correlating with prognosis)"], ["[6]", "RF (best performing)", "SHAP", "Data from patients with HCC and HBV (training set: n = 361, Validation set: n = 155)", "AUC: 0.996 (training), 0.993 (validation)", "AFP, AST/ALT ratio, GGT (liver damage and tumor biomarkers validated against BCLC criteria)"], ["[125]", "XGBoost", "SHAP", "MRI data: 117 patients (training), 33 (external validation), 30 (prospective validation)", "AUC: 0.835 (training), 0.830 (internal), 0.816 (external), 0.776 (prospective)", "Arterial hyperenhancement, venous washout (LI-RADS imaging features for malignancy); Tumor margin irregularity (radiological indicator of invasiveness)"]], "row_count": 10, "column_count": 6, "numeric_cells": 25, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:41358057 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41358057", "asset:table:pmid:41358057:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41358057"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:c0aab2e0092decddea76e758216093183d5b3e61a2d9d07d2599318077cede6e", "type": "sep_package", "label": "SEP v1 package for pmid:41358057"}], "activities": [{"id": "activity:conversion:pmid:41358057", "type": "conversion", "used": ["package:c0aab2e0092decddea76e758216093183d5b3e61a2d9d07d2599318077cede6e"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41358057", "parent_hash": "sha256:167d549dd27f542bfbfa16b79ace51c39db7384334593628ff216bc029944036", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41358057 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41358057' does not resolve to a declared asset", "targets"]}