A novel miRNA-based model for predicting the 3-year recurrence risk of hepatocellular carcinoma following liver transplantation.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40672061", "kind": "science-record", "revision": 2, "content_hash": "sha256:19a82fb07aaa89f9d459cb95a110bec45fdfebd0fb1bbeffc40da7414980e0aa", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "A novel miRNA-based model for predicting the 3-year recurrence risk of hepatocellular carcinoma following liver transplantation.", "doi": "10.21037/jgo-2025-9", "pmid": "40672061", "authors": null, "journal": "Journal of gastrointestinal oncology", "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:40672061"], "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:40672061", "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:40672061' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40672061", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/jgo-2025-9", "sha256": "sha256:2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/jgo-2025-9", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40672061:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0aa2b68028b5da6bebec976bec79c7efb0a44138618700c12e6c647b8013cb3", "bytes": 724, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t1", "version": null, "note": "Logistic regression model analyses of the correlations between the five miRNAs expression in HCC tissues and the 3-year recurrence of HCC following liver transplantation", "structure": {"pmcid": "PMC12261023", "section_index": 11, "section_title": "Construction and validation of a miRNA-based risk score", "row_count": 7, "column_count": 5}, "table": {"label": "Table 1", "caption": "Logistic regression model analyses of the correlations between the five miRNAs expression in HCC tissues and the 3-year recurrence of HCC following liver transplantation", "rows": [["Variables", "Univariate analysis", "", "Multivariate analysis"], ["OR (95% CI)", "P value", "Coefficient (β)"], ["hsa-miR-454", "2.877 (1.398, 5.922)", "0.004", "", "1.232"], ["hsa-miR-1293", "2.207 (1.211, 4.021)", "0.01", "", "1.259"], ["hsa-miR-139", "0.434 (0.239, 0.787)", "0.006", "", "−1.004"], ["hsa-miR-99a", "0.466 (0.252, 0.862)", "0.02", "", "−0.493"], ["hsa-miR-130a", "0.428 (0.234, 0.783)", "0.006", "", "−0.449"]], "row_count": 7, "column_count": 5, "numeric_cells": 21, "header_rows": 2, "locator": "section[11]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:40672061:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0c7c0468c4a4e2b72eb1da7f0452f7d7438047e4cfb151d8e7b8d44450f93213", "bytes": 558, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t2", "version": null, "note": "Logistic regression model analyses of risk factors of hepatocellular carcinoma recurrence within 3 years after liver transplantation", "structure": {"pmcid": "PMC12261023", "section_index": 12, "section_title": "Establishment and validation of a combined model", "row_count": 4, "column_count": 6}, "table": {"label": "Table 2", "caption": "Logistic regression model analyses of risk factors of hepatocellular carcinoma recurrence within 3 years after liver transplantation", "rows": [["Variables", "Univariate analysis", "", "Multivariate analysis"], ["OR (95% CI)", "P value", "OR (95% CI)", "P value"], ["Milan criteria", "2.955 (1.049, 8.325)", "0.04", "", "7.494 (1.444, 38.908)", "0.02"], ["Risk score", "2.718 (1.683, 4.390)", "<0.001", "", "3.074 (1.760, 5.372)", "<0.001"]], "row_count": 4, "column_count": 6, "numeric_cells": 10, "header_rows": 2, "locator": "section[12]/table-wrap[1]#t2"}}], "gaps": ["asset:source:pmid:40672061 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:40672061", "asset:table:pmid:40672061:1", "asset:table:pmid:40672061:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40672061"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "5a17f1b4010e8b53774efe188d78493cf4ec17ab4aa844ef889e7f4de3ac6d1f", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response_sha256": "sha256:63e32721c8fa3afe54a6559e3f60fea63d039d32292019adf35b1f834dc39c94", "raw_response_chars": 4908}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "2bf20f01b60a880d58c2f1a6bad4bce9b1d10a0765d81cc44f2a3a7b4dbc0f8f", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response_sha256": "sha256:3187882ab9e7b4029ead2b94f52f54d569fa33e26883c9e434a0dac32a3e77fd", "raw_response_chars": 60262}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "19ac11d2620bfbc676ec6d75454e8a0484c7d278b3e7281fd87bb338e51fdf9e", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response": "{\"parent_value\":0.901,\"unit\":\"AUC\",\"evidence\":\"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].\",\"target_result\":\"AUC = 0.901\",\"number_stated\":true}", "reading": {"parent_value": 0.901, "unit": "AUC", "evidence": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "target_result": "AUC = 0.901", "number_stated": true, "source_locator": "chars 1203-1363 of source sha256 2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b"}, "recorded_at": "2026-10-31T15:21:18.735523+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "af0ce5158e01bde795837fb8d19da34f995600c53861de3c1ecb0d9d02227044", "source_hash": "2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b", "raw_response": "<think>We need answer JSON only. Need identify headline numerical result paper states for main finding. Registered target vague \"headline numerical result ... main finding\". Likely AUC=0.901 for five miRNA-based risk score. Or combined nomogram AUC=0.926? Need parse wording. Abstract: \"The five miRNA-based risk score displayed a good predictive efficacy ... [area under curve (AUC)=0.901...]. Furthermore, a nomogram integrating... high predictive accuracy (AUC=0.926)... remarkably better than MC...\" Main model headline result perhaps AUC 0.901; ultimate combined model perhaps 0.926. User asks \"single numerical result that a replication of the registered target has to reproduce\" and target registered \"headline numerical result the paper itself states for its main finding\". Need infer which number is headline. Likely 0.901 AUC because \"five miRNA-based risk score\" is main finding; combined nomogram also major. Title novel miRNA-based model. Headline numerical result likely AUC=0.901. Need unit exactly paper prints. Unit could \"area under the curve (AUC)\" or \"AUC\". Schema parent_value number, unit string. They request unit paper prints, evidence exact contiguous quotation containing number, don't shorten quote. Quote whole clause as needed. We can quote: \"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P&lt;0.001].\" This exact contiguous. Unit likely \"AUC\" (dimensionless). Target result sentence perhaps same. Need JSON valid escaping. number_stated true. parent_value 0.901, unit \"AUC\". Could unit be \"area under the curve (AUC)\"? \"The unit must be the unit the paper prints.\" For AUC, dimensionless but paper prints \"area under the curve (AUC)\". Usually these extraction tasks expect unit perhaps \"AUC\". Need be precise. Maybe parent value 0.901 and unit \"area under the curve (AUC)\". Evidence exact quote.\n\nBut determine headline number perhaps 0.926. Let's deeply assess likely source/task conventions. The prompt generated to extract claims only, registered target is semantic. \"headline numerical result the paper itself states for its main finding.\" Main finding described perhaps five miRNA risk score, AUC 0.901. Combined nomogram is further development. \"a replication of registered target has to reproduce.\" Likely expected metric from abstract. Could target_result say \"AUC = 0.901 for five miRNA-based risk score predicting 3-year recurrence risk after LT.\" Evidence full sentence. Good.\n\nNeed \"headline number only\" means only numeric result, but JSON includes evidence etc. We comply.\n\nExact quote punctuation? Source has \"[area under the curve (AUC) =0.901, P&lt;0.001].\" Need exact spacing. Quote whole clause/sentence. Evidence exact contiguous. Unit must be paper prints. Could set \"area under the curve (AUC)\" precisely. Parent_value 0.901. target_result maybe \"The five miRNA-based risk score had an area under the curve (AUC) =0.901 for predicting the 3-year recurrence risk of HCC post-LT.\" Though says only headline number, perhaps target_result should mention target, no extraneous numbers? They ask \"Report headline number only: value ...\". But schema includes target_result. Likely concise. We need not include P. Evidence necessarily includes P because exact sentence and cannot shorten? Could perhaps quote exact contiguous subclause \"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901\" but that ends awkwardly and is exact contiguous, yet \"do not shorten it\" means perhaps quote full clause including P. They explicitly say exact contiguous quotation contains number, do not shorten it, no ellipsis. \"When that is how text links them, quote the whole clause.\" So full sentence including P best.\n\nCould evidence instead be exactly \"[area under the curve (AUC) =0.901, P&lt;0.001]\" but target attribution is previous sentence context, likely whole sentence. Yes.\n\nDoes \"unit\" need no unit, because AUC is unitless? They say unit must be unit paper prints. In paper the metric label \"area under the curve (AUC)\" not a physical unit. Many schemas use unit string perhaps \"AUC\". Use \"AUC\". Yet \"The unit must be the unit the paper prints.\" Paper prints AUC, so fine.\n\nJSON only. Ensure no markdown.</think>\n\n{\"parent_value\":0.901,\"unit\":\"area under the curve (AUC)\",\"evidence\":\"The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].\",\"target_result\":\"The five miRNA-based risk score achieved an AUC of 0.901 for predicting 3-year HCC recurrence risk after liver transplantation.\",\"number_stated\":true}", "reading": {"parent_value": 0.901, "unit": "area under the curve (AUC)", "evidence": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "target_result": "The five miRNA-based risk score achieved an AUC of 0.901 for predicting 3-year HCC recurrence risk after liver transplantation.", "number_stated": true, "source_locator": "chars 1203-1363 of source sha256 2c47cb6f2515f267edf1153515fb495f310b57cecf1bc7f7ef96c3a955f2237b"}, "recorded_at": "2026-10-31T15:21:22.610368+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The nomogram integrating the miRNA-based model with Milan criteria achieved an area under the curve (AUC) of 0.926 (P<0.001) for predicting 3-year HCC recurrence after liver transplantation.", "minimax_alt": "The five miRNA-based risk score displayed a good predictive efficacy for the 3-year recurrence risk of HCC post-LT [area under the curve (AUC) =0.901, P<0.001].", "decisive": false}, "analysis_methods": {"minimax": ["differential expression analysis", "Kaplan-Meier method", "least absolute shrinkage and selection operator (LASSO)-logistic regression", "multivariate logistic regression", "receiver operating characteristic curve analysis", "area under the curve (AUC)", "concordance index", "calibration plots", "decision curve analysis"], "minimax_alt": ["Differential expression analysis", "Kaplan-Meier method", "Least absolute shrinkage and selection operator (LASSO)-logistic regression", "Multivariate logistic regression", "Concordance index", "Calibration plots", "Decision curve analysis", "Receiver operating characteristic curves and area under the curve (AUC)", "Student’s t-test", "Mann-Whitney test", "DIANA-microT-CDS miRNA target prediction with Targetscan validation", "Overlapping analysis of miRNA-mRNA negative regulatory relationships", "Gene Ontology and KEGG pathway enrichment analysis with DAVID 6.7"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic curve analysis evaluated using the area under the curve (AUC)", "minimax_alt": "Area under the curve (AUC) analysis", "decisive": true}, "unit": {"minimax": "AUC", "minimax_alt": "area under the curve (AUC)", "decisive": true}}, "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": []}}, {"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"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:3342053886f181f92f8af3bf09000d5b38ead8a0593ea1f14ac24c9ed84772b5", "type": "sep_package", "label": "SEP v1 package for pmid:40672061"}], "activities": [{"id": "activity:conversion:pmid:40672061", "type": "conversion", "used": ["package:3342053886f181f92f8af3bf09000d5b38ead8a0593ea1f14ac24c9ed84772b5"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"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:40672061", "parent_hash": "sha256:5b4561e45e0dc008e93815f6faa92c4abb194289e2db489aa363b9f1e3888ec1", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40672061 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "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:40672061' does not resolve to a declared asset", "targets"]}