Establishment of a nomogram model based on immune-related genes using machine learning for aortic dissection diagnosis and immunomodulation assessment.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39991758", "kind": "science-record", "revision": 4, "content_hash": "sha256:422699bb19935df0ffc71189386b4a8adbcdb7a67d2d3065df4be80e2621d72b", "created_at": "2026-11-01T20:30:14Z", "updated_at": "2026-11-01T22:56:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Establishment of a nomogram model based on immune-related genes using machine learning for aortic dissection diagnosis and immunomodulation assessment.", "doi": "10.7150/ijms.100572", "pmid": "39991758", "authors": ["Yanjun Hou", "Yangyang Zhao", "Zhensu Shi", "Yipeng Pan", "Kaijia Shi", "Chaoyang Zhao", "Shengnan Liu", "Yongkun Chen", "Lini Zhao", "Jizhen Wu", "Guangquan Ge", "Wei Jie"], "journal": "International journal of medical sciences", "year": 2025, "abstract": "The clinical manifestation of aortic dissection (AD) is complex and varied, making early diagnosis crucial for patient survival. This study aimed to identify immune-related markers to establish a nomogram model for AD diagnosis. Three datasets from GEO-GSE52093, GSE147026 and GSE153434-were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained. Then, 15 pivotal genes were screened by the protein-protein interaction network. Through machine learning including the Least Absolute Shrinkage and Selection Operator algorithm, random forest algorithm, and multivariate logistic regression, four key feature genes were obtained-CXCL1, ITGA5, PTX3, and TIMP1-and the diagnostic scores based on these four genes were proved to be effective in distinguishing between AD patients and healthy donors. External dataset (GSE98770 and GSE190635) validation revealed this nomogram displayed strong predictive significance. Further analysis revealed that these genes are related with neutrophils, resting NK cells, resting mast cells, activated mast cells, activated dendritic cells, central memory CD4 T cells, γδ T cells, natural killer T cells, and myeloid-derived suppressor cells in AD. Finally, these four genes were validated to be upregulated in AD patients' tissue and serum samples compared with controls. These results suggest that this nomogram model, using machine learning identified four immune-related genes CXCL1, ITGA5, PTX3, and TIMP1, displays superior diagnostic ability in distinguishing AD and healthy individuals, and immune cells commonly associated with these hub genes may be therapeutic targets for AD.", "claims": [{"id": "claim-method", "statement": "Three datasets from GEO—GSE52093, GSE147026 and GSE153434—were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39991758", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Three datasets from GEO—GSE52093, GSE147026 and GSE153434—were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39991758", "locator": "sections[29] \"Data availability\" paragraph 2", "quote": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A four-gene diagnostic nomogram based on CXCL1, ITGA5, PTX3, and TIMP1 showed strong diagnostic performance for aortic dissection, with ROC AUC values of 0.972 in the training set and 0.933 in the GSE98770 external validation set.", "kind": "quantitative", "target": {"value": 0.05, "unit": "p-value", "tolerance": null, "source": "First, in terms of the training set, the scores for AD patients were significantly higher than those of the unaffected population (P < 0.05) (Figure 4A), and the AUC value of the ROC curve was higher, at 0.972 (Figure 4B)."}, "evidence": [{"asset": "source:pmid:39991758", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Three datasets from GEO—GSE52093, GSE147026 and GSE153434—were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained."}, {"asset": "source:pmid:39991758", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Through machine learning including the Least Absolute Shrinkage and Selection Operator algorithm, random forest algorithm, and multivariate logistic regression, four key feature genes were obtained—CXCL1, ITGA5, PTX3, and TIMP1—and the diagnostic scores based on these four genes were proved to be effective in distinguishing between AD patients and healthy donors."}, {"asset": "source:pmid:39991758", "locator": "sections[20] \"Validation and performance evaluation of the predictive models\" paragraph 2", "quote": "First, in terms of the training set, the scores for AD patients were significantly higher than those of the unaffected population (P < 0.05) (Figure 4A), and the AUC value of the ROC curve was higher, at 0.972 (Figure 4B)."}, {"asset": "source:pmid:39991758", "locator": "sections[20] \"Validation and performance evaluation of the predictive models\" paragraph 2", "quote": "Second, the diagnostic scores in the AD group were significantly higher than those in the unaffected population in the external validation set (GSE98770) (P < 0.05) (Figure 4D), and the ROC curve showed an AUC value of 0.933 for the model (Figure 4E)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A four-gene diagnostic nomogram based on CXCL1, ITGA5, PTX3, and TIMP1 showed strong diagnostic performance for aortic dissection, with ROC AUC values of 0.972 in the training set and 0.933 in the GSE98770 external validation set.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39991758"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE147026"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE147026"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39991758", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijms.100572", "sha256": "sha256:4a2a2c1f4ea6156b1d30bfc1b43420f3e159cf513b339f324f31d022264a00e6", "bytes": 56606, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijms.100572", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11843136", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE147026", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE147026", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147026", "version": null, "note": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4412476", "GSM4412477", "GSM4412478", "GSM4412479", "GSM4412480", "GSM4412481", "GSM4412482", "GSM4412483"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Transcriptome analyses in aortic dissection and normal human aorta", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE153434", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE153434", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE153434", "version": null, "note": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4644214", "GSM4644215", "GSM4644216", "GSM4644217", "GSM4644218", "GSM4644219", "GSM4644220", "GSM4644221", "GSM4644222", "GSM4644223", "GSM4644224", "GSM4644225", "GSM4644226", "GSM4644227", "GSM4644228", "GSM4644229", "GSM4644230", "GSM4644231", "GSM4644232", "GSM4644233"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "Exaggerated autophagy as molecular characterization of Stanford type A aortic dissection: A transcriptome analysis of human ascending aortic tissues", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE190635", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE190635", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE190635", "version": null, "note": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5726864", "GSM5726865", "GSM5726866", "GSM5726867", "GSM5726868", "GSM5726869", "GSM5726870", "GSM5726871"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from aortic dissection patients and the healthy controls", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE52093", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE52093", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52093", "version": null, "note": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1259275", "GSM1259276", "GSM1259277", "GSM1259278", "GSM1259279", "GSM1259280", "GSM1259281", "GSM1259282", "GSM1259283", "GSM1259284", "GSM1259285", "GSM1259286"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression of ascending aorta from patients with acute Stanford type A aortic dissection", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE98770", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE98770", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE98770", "version": null, "note": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2611536", "GSM2611537", "GSM2611538", "GSM2611539", "GSM2611540", "GSM2611541", "GSM2611542", "GSM2611543", "GSM2611544", "GSM2611545", "GSM2611546", "GSM2628221", "GSM2628222", "GSM2628223", "GSM2628224", "GSM2628225", "GSM2628226", "GSM2628227", "GSM2628228", "GSM2628229", "GSM2628230", "GSM2628231"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "14550;17660", "taxon": "Homo sapiens", "title": "Gene expression profiling of acute type A aortic dissection combined with in vitro assessment", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE147026 not downloaded", "asset:data:geo:GSE147026 licence not read", "asset:data:geo:GSE153434 not downloaded", "asset:data:geo:GSE153434 licence not read", "asset:data:geo:GSE190635 not downloaded", "asset:data:geo:GSE190635 licence not read", "asset:data:geo:GSE52093 not downloaded", "asset:data:geo:GSE52093 licence not read", "asset:data:geo:GSE98770 not downloaded", "asset:data:geo:GSE98770 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Three datasets from GEO—GSE52093, GSE147026 and GSE153434—were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "student's t-test"}}, {"id": "method-3", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 0.05, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.reader_differs_from_extractor", "method.machine_learning_random_forest"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE52093", "GSE147026", "GSE153434", "GSE98770", "GSE190635"], "resolved_accessions": ["GSE52093", "GSE147026", "GSE153434", "GSE98770", "GSE190635"], "statements": ["Data is provided within the manuscript or supplementary information files. R code used in this study has been uploaded to github. The link for download is: http://github.com/Houyanjun1/code."], "basis": "The paper names GSE52093, GSE147026, GSE153434, GSE98770, GSE190635 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39991758", "data:geo:GSE147026"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE147026"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:46:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15870, "completion_tokens": 2134, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:39991758", "type": "paper", "label": "pmid:39991758"}, {"id": "source:pmid:39991758", "type": "manuscript", "label": "PMID 39991758 full text"}, {"id": "data:geo:GSE147026", "type": "dataset", "label": "GEO GSE147026"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39991758", "type": "paper", "label": "pmid:39991758"}, {"id": "source:pmid:39991758", "type": "manuscript", "label": "PMID 39991758 full text"}, {"id": "data:geo:GSE147026", "type": "dataset", "label": "GEO GSE147026"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39991758", "type": "extraction", "used": ["source:pmid:39991758"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE147026", "type": "accession_resolution", "used": ["data:geo:GSE147026"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39991758", "parent_hash": "sha256:ec1c80882a246064f5684f2275896e3033589fa3520a34398b37129379df4d4d", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE147026 licence not read", "asset:data:geo:GSE147026 not downloaded", "asset:data:geo:GSE153434 licence not read", "asset:data:geo:GSE153434 not downloaded", "asset:data:geo:GSE190635 licence not read", "asset:data:geo:GSE190635 not downloaded", "asset:data:geo:GSE52093 licence not read", "asset:data:geo:GSE52093 not downloaded", "asset:data:geo:GSE98770 licence not read", "asset:data:geo:GSE98770 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["pattern in patient samples were examined by ELISA. Results showed that the four hub genes were"], "order_basis": "paper_text_order:5846", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Three datasets from GEO—GSE52093, GSE147026 and GSE153434—were combined and used for identification of immune-related causative genes using weighted gene co-expression network analysis, and 136 immune-related genes were obtained."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}