{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:12:25Z","timestamp":1784823145765,"version":"3.55.0"},"reference-count":50,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007446","name":"King Khalid University","doi-asserted-by":"publisher","award":["RGP1\/369\/45"],"award-info":[{"award-number":["RGP1\/369\/45"]}],"id":[{"id":"10.13039\/501100007446","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: Liver cancer ranks among the leading causes of cancer-related mortality, necessitating the development of novel diagnostic methods. Deregulated lipid metabolism, a hallmark of hepatocarcinogenesis, offers compelling prospects for biomarker identification. This study aims to employ explainable artificial intelligence (XAI) to identify lipidomic biomarkers for liver cancer and to develop a robust predictive model for early diagnosis. Materials and Methods: This study included 219 patients diagnosed with liver cancer and 219 healthy controls. Serum samples underwent untargeted lipidomic analysis with LC-QTOF-MS. Lipidomic data underwent univariate and multivariate analyses, including fold change (FC), t-tests, PLS-DA, and Elastic Network feature selection, to identify significant biomarker candidate lipids. Machine learning models (AdaBoost, Random Forest, Gradient Boosting) were developed and evaluated utilizing these biomarkers to differentiate liver cancer. The AUC metric was employed to identify the optimal predictive model, whereas SHAP was utilized to achieve interpretability of the model\u2019s predictive decisions. Results: Notable alterations in lipid profiles were observed: decreased sphingomyelins (SM d39:2, SM d41:2) and increased fatty acids (FA 14:1, FA 22:2) and phosphatidylcholines (PC 34:1, PC 32:1). AdaBoost exhibited a superior classification performance, achieving an AUC of 0.875. SHAP identified PC 40:4 as the most efficacious lipid for model predictions. The SM d41:2 and SM d36:3 lipids were specifically associated with an increased risk of low-onset cancer and elevated levels of the PC 40:4 lipid. Conclusions: This study demonstrates that untargeted lipidomics, in conjunction with explainable artificial intelligence (XAI) and machine learning, may effectively identify biomarkers for the early detection of liver cancer. The results suggest that alterations in lipid metabolism are crucial to the progression of liver cancer and provide valuable insights for incorporating lipidomics into precision oncology.<\/jats:p>","DOI":"10.3390\/medicina61030405","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T06:15:33Z","timestamp":1740550533000},"page":"405","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Untargeted Lipidomic Biomarkers for Liver Cancer Diagnosis: A Tree-Based Machine Learning Model Enhanced by Explainable Artificial Intelligence"],"prefix":"10.3390","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5406-098X","authenticated-orcid":false,"given":"Cemil","family":"Colak","sequence":"first","affiliation":[{"name":"Department of Biostatistics, and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-7958","authenticated-orcid":false,"given":"Fatma Hilal","family":"Yagin","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7556-958X","authenticated-orcid":false,"given":"Abdulmohsen","family":"Algarni","sequence":"additional","affiliation":[{"name":"Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6718-517X","authenticated-orcid":false,"given":"Ali","family":"Algarni","sequence":"additional","affiliation":[{"name":"Department of Informatics and Computer Systems, College of Computer Science, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5795-9966","authenticated-orcid":false,"given":"Fahaid","family":"Al-Hashem","sequence":"additional","affiliation":[{"name":"Department of Physiology, College of Medicine, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-5070","authenticated-orcid":false,"given":"Luca Paolo","family":"Ardig\u00f2","sequence":"additional","affiliation":[{"name":"Department of Teacher Education, NLA University College, Linstows Gate 3, 0166 Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA A Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2610","DOI":"10.1111\/j.1742-4658.2012.08644.x","article-title":"Lipid metabolism in cancer","volume":"279","author":"Santos","year":"2012","journal-title":"FEBS J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA A Cancer J. Clin."},{"key":"ref_4","first-page":"dyae053","article-title":"Factor modification in the association between high-density lipoprotein cholesterol and liver cancer risk in a nationwide cohort","volume":"53","author":"Nam","year":"2024","journal-title":"Leuk. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1038\/nrc.2017.96","article-title":"Sphingolipid metabolism in cancer signalling and therapy","volume":"18","author":"Ogretmen","year":"2018","journal-title":"Nat. Rev. Cancer"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.25163\/primeasia.519787","article-title":"Assessment of Lipid Profile in Hepatocellular Carcinoma Patients: A Prospective Study in Bangladesh","volume":"5","author":"Tahsin","year":"2024","journal-title":"J. Primeasia"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhu, H., Chen, H.-J., Wen, H.-Y., Wang, Z.-G., and Liu, S.-L. (2023). Engineered lipidic nanomaterials inspired by sphingomyelin metabolism for cancer therapy. Molecules, 28.","DOI":"10.3390\/molecules28145366"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Masnikosa, R., Cvetkovi\u0107, Z., and Piri\u0107, D. (2024). Tumor Biology Hides Novel Therapeutic Approaches to Diffuse Large B-Cell Lymphoma: A Narrative Review. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms252111384"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110273","DOI":"10.1016\/j.knosys.2023.110273","article-title":"Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities","volume":"263","author":"Saeed","year":"2023","journal-title":"Knowledge-Based Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Taha, A., Ochs, V., Kayhan, L.N., Enodien, B., Frey, D.M., Kr\u00e4henb\u00fchl, L., and Taha-Mehlitz, S. (2022). Advancements of Artificial Intelligence in Liver-Associated Diseases and Surgery. Medicina, 58.","DOI":"10.3390\/medicina58040459"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1002\/ijc.34726","article-title":"Identification of pre-diagnostic lipid sets associated with liver cancer risk using untargeted lipidomics and chemical set analysis: A nested case-control study within the ATBC cohort","volume":"154","author":"Barupal","year":"2024","journal-title":"Int. J. Cancer"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Alkhateeb, A., Colak, C., Azzeh, M., Yagin, B., and Rueda, L. (2023). A Fecal-Microbial-Extracellular-Vesicles-based Metabolomics Machine Learning Framework and biomarker discovery for predicting colorectal cancer patients. Metabolites, 13.","DOI":"10.3390\/metabo13050589"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Al-Hashem, F., Ahmad, I., Ahmad, F., and Alkhateeb, A. (2024). Pilot-Study to Explore Metabolic Signature of Type 2 Diabetes: A Pipeline of Tree-Based Machine Learning and Bioinformatics Techniques for Biomarkers Discovery. Nutrients, 16.","DOI":"10.3390\/nu16101537"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"122958","DOI":"10.1016\/j.eswa.2023.122958","article-title":"Elastic net-based high dimensional data selection for regression","volume":"244","author":"Chamlal","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s44196-023-00184-y","article-title":"An ensemble of Light Gradient Boosting Machine and adaptive boosting for prediction of type-2 diabetes","volume":"16","author":"Sai","year":"2023","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Colak, C., Algarni, A., Gormez, Y., Guldogan, E., and Ardig\u00f2, L.P. (2024). Hybrid Explainable Artificial Intelligence Models for Targeted Metabolomics Analysis of Diabetic Retinopathy. Diagnostics, 14.","DOI":"10.3390\/diagnostics14131364"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yagin, B., Yagin, F.H., Colak, C., Inceoglu, F., Kadry, S., and Kim, J. (2023). Cancer metastasis prediction and genomic biomarker identification through machine learning and eXplainable artificial intelligence in breast cancer research. Diagnostics, 13.","DOI":"10.3390\/diagnostics13213314"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ruiz-Perez, D., Guan, H., Madhivanan, P., Mathee, K., and Narasimhan, G. (2020). So you think you can PLS-DA?. BMC Bioinform., 21.","DOI":"10.1186\/s12859-019-3310-7"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1021\/acs.jproteome.5b01029","article-title":"Approaches to sample size determination for multivariate data: Applications to PCA and PLS-DA of omics data","volume":"15","author":"Saccenti","year":"2016","journal-title":"J. Proteome Res."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Musib, L., Coletti, R., Lopes, M.B., Mouri\u00f1o, H., and Carrasquinha, E. (2024). Priority-Elastic net for binary disease outcome prediction based on multi-omics data. BioData Min., 17.","DOI":"10.1186\/s13040-024-00401-0"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"210","DOI":"10.4274\/imj.galenos.2022.62443","article-title":"Prediction of breast cancer distant metastasis by artificial intelligence methods from an epidemiological perspective","volume":"23","author":"Akbulut","year":"2022","journal-title":"Istanb. Med. J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Carreira-Perpi\u00f1\u00e1n, M.\u00c1., and Zharmagambetov, A. (2020, January 19\u201320). Ensembles of bagged TAO trees consistently improve over random forests, AdaBoost and gradient boosting. Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference, Virtual.","DOI":"10.1145\/3412815.3416882"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1007\/s42452-020-3060-1","article-title":"Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest","volume":"2","author":"Sahin","year":"2020","journal-title":"SN Appl. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.1140\/epjs\/s11734-024-01308-x","article-title":"Searches for the BSM scenarios at the LHC using decision tree-based machine learning algorithms: A comparative study and review of random forest, AdaBoost, XGBoost and LightGBM frameworks","volume":"233","author":"Choudhury","year":"2024","journal-title":"Eur. Phys. J. Sp\u00e9c. Top."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2400304","DOI":"10.1002\/aisy.202400304","article-title":"A perspective on explainable artificial intelligence methods: SHAP and LIME","volume":"7","author":"Salih","year":"2024","journal-title":"Adv. Intell. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Weng, Y., and Lund, J. (2022). Applications of explainable artificial intelligence in diagnosis and surgery. Diagnostics, 12.","DOI":"10.3390\/diagnostics12020237"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"100078","DOI":"10.1016\/j.jfueco.2022.100078","article-title":"Modeling coking coal indexes by SHAP-XGBoost: Explainable artificial intelligence method","volume":"13","author":"Homafar","year":"2022","journal-title":"Fuel Commun."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"108591","DOI":"10.1109\/ACCESS.2023.3321509","article-title":"Assessment of hematological predictors via explainable artificial intelligence in the prediction of acute myocardial infarction","volume":"11","author":"Yilmaz","year":"2023","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Aygun, U., Algarni, A., Colak, C., Al-Hashem, F., and Ardig\u00f2, L.P. (2024). Platelet Metabolites as Candidate Biomarkers in Sepsis Diagnosis and Management Using the Proposed Explainable Artificial Intelligence Approach. J. Clin. Med., 13.","DOI":"10.3390\/jcm13175002"},{"key":"ref_30","first-page":"34","article-title":"Machine learning interpretability in diabetes risk assessment: A SHAP analysis","volume":"1","author":"Kutlu","year":"2024","journal-title":"Comput. Electron. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/s10555-024-10170-1","article-title":"Lipid metabolism and its implications in tumor cell plasticity and drug resistance: What we learned thus far?","volume":"43","author":"Vishwa","year":"2024","journal-title":"Cancer Metastasis Rev."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, T., Wusiman, M., Shuang, S., Chen, J.-D., Li, M.-C., Li, Z., Zou, J.-P., Wang, C., Liu, Z.-Y., and Fang, A.-P. (2024). Diagnostic and prognostic potential of tissue phospholipidomics in hepatocellular carcinoma: A prospective cohort study. Cancers, 5.","DOI":"10.21203\/rs.3.rs-4110772\/v1"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1002\/1878-0261.13520","article-title":"Comparative membrane lipidomics of hepatocellular carcinoma cells reveals diacylglycerol and ceramide as key regulators of Wnt\/\u03b2-catenin signaling and tumor growth","volume":"17","author":"Azbazdar","year":"2023","journal-title":"Mol. Oncol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"125371","DOI":"10.1016\/j.talanta.2023.125371","article-title":"Serum lipidomic profiling for liver cancer screening using surface-assisted laser desorption ionization MS and machine learning","volume":"268","author":"Wu","year":"2024","journal-title":"Talanta"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, Q., Zhang, X., Qi, J., Tian, X., Dovjak, E., Zhang, J., Du, H., Zhang, N., Zhao, J., and Zhang, Y. (2024). Comprehensive profiling of lipid metabolic reprogramming expands precision medicine for hepatocellular carcinoma. Hepatology.","DOI":"10.1097\/HEP.0000000000000962"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Kook, E., and Kim, D.-H. (2024). Elucidating the Role of Lipid-Metabolism-Related Signal Transduction and Inhibitors in Skin Cancer. Metabolites, 14.","DOI":"10.3390\/metabo14060309"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Singh, M.K., Han, S., Kim, S., and Kang, I. (2024). Targeting Lipid Metabolism in Cancer Stem Cells for Anticancer Treatment. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms252011185"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1038\/nrc2222","article-title":"Fatty acid synthase and the lipogenic phenotype in cancer pathogenesis","volume":"7","author":"Menendez","year":"2007","journal-title":"Nat. Rev. Cancer"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"49","DOI":"10.36253\/Substantia-1376","article-title":"History of Research on Phospholipid Metabolism and Applications to the Detection, Diagnosis, and Treatment of Cancer","volume":"6","author":"Cohen","year":"2022","journal-title":"Substantia"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.2174\/1568026623666230522103321","article-title":"Aberrant lipid metabolism in cancer: Current status and emerging therapeutic perspectives","volume":"23","author":"Irshad","year":"2023","journal-title":"Curr. Top. Med. Chem."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Nassar, A.F., Nie, X., Zhang, T., Yeung, J., Norris, P., He, J., Ogura, H., Babar, M.U., Muldoon, A., and Libreros, S. (2024). Is Lipid Metabolism of Value in Cancer Research and Treatment? Part I- Lipid Metabolism in Cancer. Metabolites, 14.","DOI":"10.3390\/metabo14060312"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"101936","DOI":"10.1016\/j.molmet.2024.101936","article-title":"Roles and therapeutic targeting of ceramide metabolism in cancer","volume":"83","author":"Wajapeyee","year":"2024","journal-title":"Mol. Metab."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/bs.acr.2018.04.007","article-title":"Mechanisms of ceramide-dependent cancer cell death","volume":"140","author":"Nganga","year":"2018","journal-title":"Adv. Cancer Res."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, L.P., G\u00f3mez de Cedr\u00f3n, M., and Ram\u00edrez de Molina, A. (2020). Alterations of Lipid Metabolism in Cancer: Implications in Prognosis and Treatment. Front. Oncol., 10.","DOI":"10.3389\/fonc.2020.577420"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1021\/jasms.3c00403","article-title":"Automated machine learning and explainable AI (AutoML-XAI) for metabolomics: Improving cancer diagnostics","volume":"35","author":"Bifarin","year":"2024","journal-title":"J. Am. Soc. Mass Spectrom."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1139\/gen-2020-0131","article-title":"Machine learning for precision medicine","volume":"64","author":"MacEachern","year":"2021","journal-title":"Genome"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"7053","DOI":"10.7150\/thno.41388","article-title":"Lipid metabolism alteration contributes to and maintains the properties of cancer stem cells","volume":"10","author":"Li","year":"2020","journal-title":"Theranostics"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"221","DOI":"10.5114\/pg.2024.143147","article-title":"The role of artificial intelligence and image processing in the diagnosis, treatment, and prognosis of liver cancer: A narrative-review","volume":"19","author":"Dimopoulos","year":"2024","journal-title":"Gastroenterol. Rev."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Verras, G.-I., and Mulita, F. (2024). Butyrylcholinesterase levels correlate with surgical site infection risk and severity after colorectal surgery: A prospective single-center study. Front. Surg., 11.","DOI":"10.3389\/fsurg.2024.1379410"},{"key":"ref_50","first-page":"e13","article-title":"Value of butyrylcholinesterase as a marker of surgical site infection following surgery for colorectal cancer","volume":"47","author":"Mulita","year":"2021","journal-title":"Eur. J. Surg. Oncol. (EJSO)"}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/61\/3\/405\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:42:46Z","timestamp":1760028166000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/61\/3\/405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":50,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["medicina61030405"],"URL":"https:\/\/doi.org\/10.3390\/medicina61030405","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,26]]}}}