{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:54Z","timestamp":1788937614998,"version":"build-2803163510"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Liver cancer has high incidence and mortality worldwide, and timely identification is important for improving prognosis. However, prediction models based on routinely available clinical data remain insufficiently evaluated in hospitalized real-world populations. This study aimed to develop and interpret a machine-learning model for liver cancer prediction using multidimensional clinical and laboratory features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective real-world cohort included 9,284 hospitalized patients from Hainan General Hospital between January 2020 and December 2023. Patients were divided into a training set (n = 6,426) and an internal validation set (n = 2,858). Seventy-four demographic, clinical, and laboratory variables were collected. Feature selection was performed using least absolute shrinkage and selection operator regression in the training set. Six models were developed: logistic regression, random forest, support vector machine, k-nearest neighbors, extreme gradient boosting (XGBoost), and Elastic Net. Discrimination was assessed primarily using the area under the receiver operating characteristic curve (AUC). Decision curve analysis evaluated clinical net benefit, and SHapley Additive exPlanations (SHAP) were used for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Liver cancer accounted for 48.7% of the training cohort and 48.8% of the validation cohort. LASSO retained 57 nonzero model terms at the minimum-error penalty. XGBoost achieved the highest AUC among all models, with an AUC of 0.909 (95% CI, 0.903\u20130.915) in the training set and 0.802 (95% CI, 0.788\u20130.817) in the validation set. At a threshold of 0.5, validation accuracy, sensitivity, specificity, and F1 score were 0.730, 0.758, 0.698, and 0.753, respectively. Decision curve analysis showed that XGBoost provided the greatest net clinical benefit across a broad range of threshold probabilities. SHAP analysis identified serum sialic acid, the aspartate aminotransferase-to-alanine aminotransferase ratio, alkaline phosphatase, basophil percentage, and monocyte-to-lymphocyte ratio as the leading predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>XGBoost showed good discrimination and interpretability for liver cancer prediction in a hospitalized real-world cohort using routinely available clinical and laboratory data. The findings support the feasibility of leveraging large-scale inpatient laboratory data for risk-stratification model development. Serum sialic acid, the aspartate aminotransferase-to-alanine aminotransferase ratio, and alkaline phosphatase were important predictors. Prospective validation in outpatient, first-visit, high-risk, and external populations is required before broader clinical or screening application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1896989","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:30:16Z","timestamp":1788935416000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning models for predicting liver cancer: a real-world cohort study in China"],"prefix":"10.3389","volume":"14","author":[{"given":"Cexiong","family":"Fu","sequence":"first","affiliation":[{"name":"Department of Hepatobiliary Pancreatic Surgery, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Gastroenterology Endoscopy Center, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shibing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pediatric Surgery, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Traditional Chinese Internal Medicine, School of Traditional Chinese Medicine, Southern Medical University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Second Affiliated Hospital of Guilin Medical University","place":["Guilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1016\/j.cgh.2019.11.012","article-title":"GALAD score detects early hepatocellular carcinoma in an international cohort of patients with nonalcoholic steatohepatitis","volume":"18","author":"Best","year":"2020","journal-title":"Clin. Gastroenterol. Hepatol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"B3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3322\/caac.21338","article-title":"Cancer statistics in China, 2015","volume":"66","author":"Chen","year":"2016","journal-title":"CA Cancer J. Clin."},{"key":"B4","doi-asserted-by":"publisher","first-page":"103244","DOI":"10.1016\/j.artmed.2025.103244","article-title":"Applications of artificial intelligence in liver cancer: a scoping review","volume":"169","author":"Chierici","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.jhep.2018.03.019","article-title":"EASL clinical practice guidelines: management of hepatocellular carcinoma","volume":"69","year":"2018","journal-title":"J. Hepatol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"5653","DOI":"10.1038\/s41598-026-36261-3","article-title":"Machine learning integrating MRI and clinical features predicts early recurrence of hepatocellular carcinoma after resection","volume":"16","author":"Feng","year":"2026","journal-title":"Sci. Rep."},{"key":"B7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jncc.2024.01.006","article-title":"Cancer incidence and mortality in China, 2022","volume":"4","author":"Han","year":"2024","journal-title":"J. Natl. Cancer Cent."},{"key":"B8","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1002\/hep.29086","article-title":"AASLD guidelines for the treatment of hepatocellular carcinoma","volume":"67","author":"Heimbach","year":"2018","journal-title":"Hepatology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"112353","DOI":"10.1016\/j.ejrad.2025.112353","article-title":"Development and validation of interpretable machine learning model for pre-treatment predicting the response to targeted and immune therapy in hepatocellular carcinoma","volume":"191","author":"Huang","year":"2025","journal-title":"Eur. J. Radiol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1158\/1055-9965.EPI-13-0870","article-title":"The detection of hepatocellular carcinoma using a prospectively developed and validated model based on serological biomarkers","volume":"23","author":"Johnson","year":"2014","journal-title":"Cancer Epidemiol. Biomarkers Prev."},{"key":"B13","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1038\/bjc.2016.422","article-title":"Impact of disease stage and aetiology on survival in hepatocellular carcinoma: implications for surveillance","volume":"116","author":"Johnson","year":"2017","journal-title":"Br. J. Cancer"},{"key":"B16","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1186\/s12885-025-14147-3","article-title":"Gadoxetic acid-enhanced MRI for identifying cholangiocyte phenotype hepatocellular carcinoma by interpretable machine learning: individual application of SHAP","volume":"25","author":"Liu","year":"2025","journal-title":"BMC Cancer"},{"key":"B18","doi-asserted-by":"publisher","first-page":"6042","DOI":"10.1002\/sim.10277","article-title":"Bayesian decision curve analysis with BayesDCA","volume":"43","author":"Netto Flores Cruz","year":"2024","journal-title":"Stat. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1111\/hepr.13955","article-title":"Artificial intelligence\/neural network system that accurately diagnoses hepatocellular carcinoma in nonalcoholic steatohepatitis","volume":"53","author":"Okanoue","year":"2023","journal-title":"Hepatol. Res."},{"key":"B20","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.jhep.2022.08.036","article-title":"Blood-based biomarkers for hepatocellular carcinoma screening: approaching the end of the ultrasound era?","volume":"78","author":"Parikh","year":"2023","journal-title":"J. Hepatol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1713887","DOI":"10.3389\/fmed.2025.1713887","article-title":"Artificial intelligence in hepatocellular carcinoma screening: applications and challenges","volume":"12","author":"Rao","year":"2026","journal-title":"Front. Med. (Lausanne)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.1016\/j.jhep.2022.08.021","article-title":"Global burden of primary liver cancer in 2020 and predictions to 2040","volume":"77","author":"Rumgay","year":"","journal-title":"J. Hepatol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.ejca.2021.11.023","article-title":"Global, regional and national burden of primary liver cancer by subtype","volume":"161","author":"Rumgay","year":"","journal-title":"Eur. J. Cancer"},{"key":"B24","doi-asserted-by":"publisher","first-page":"101357","DOI":"10.1016\/j.jhepr.2025.101357","article-title":"Multicenter evaluation of abbreviated MRI and ultrasound for detecting early-stage hepatocellular carcinoma","volume":"7","author":"Seif El Dahan","year":"2025","journal-title":"JHEP Rep."},{"key":"B25","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1038\/s41571-023-00825-3","article-title":"Global trends in hepatocellular carcinoma epidemiology: implications for screening, prevention and therapy","volume":"20","author":"Singal","year":"2023","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"851","DOI":"10.3350\/cmh.2022.0037","article-title":"Impact of nationwide hepatocellular carcinoma surveillance on the prognosis in patients with chronic liver disease","volume":"28","author":"Sohn","year":"2022","journal-title":"Clin. Mol. Hepatol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1097\/cm9.0000000000002641","article-title":"Precision diagnosis of hepatocellular carcinoma","volume":"136","author":"Wang","year":"2023","journal-title":"Chin. Med. J. Engl."},{"key":"B28","doi-asserted-by":"publisher","first-page":"101364","DOI":"10.1016\/j.patter.2025.101364","article-title":"A multimodal LLM-agent framework for personalized clinical decision-making in hepatocellular carcinoma","volume":"6","author":"Wang","year":"2025","journal-title":"Patterns (N Y)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"109180","DOI":"10.1016\/j.cmpb.2025.109180","article-title":"Digital pathology-based prognostic model for hepatocellular carcinoma: integrating pathomics signatures with clinical parameters for recurrence prediction and biological interpretation","volume":"275","author":"Wang","year":"2026","journal-title":"Comput. Methods Programs Biomed."},{"key":"B30","doi-asserted-by":"publisher","first-page":"107","DOI":"10.3760\/cma.j.cn112150-20220117-00063","article-title":"Application of LASSO and its extended method in variable selection of regression analysis","volume":"57","author":"Xi","year":"2023","journal-title":"Zhonghua Yu Fang. Yi Xue Za Zhi"},{"key":"B32","doi-asserted-by":"publisher","first-page":"134","DOI":"10.3748\/wjg.v26.i2.134","article-title":"Construction of a risk score prognosis model based on hepatocellular carcinoma microenvironment","volume":"26","author":"Zhang","year":"2020","journal-title":"World J. Gastroenterol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1186\/s12885-024-13366-4","article-title":"Construction of a random survival forest model based on a machine learning algorithm to predict early recurrence after hepatectomy for adult hepatocellular carcinoma","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Cancer"},{"key":"B34","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1159\/000509424","article-title":"Guidelines for the diagnosis and treatment of hepatocellular carcinoma (2019 edition)","volume":"9","author":"Zhou","year":"2020","journal-title":"Liver Cancer"},{"key":"B35","doi-asserted-by":"publisher","first-page":"4148","DOI":"10.1002\/sim.10172","article-title":"Extending the DeLong algorithm for comparing areas under correlated receiver operating characteristic curves with missing data","volume":"43","author":"Zou","year":"2024","journal-title":"Stat. Med."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1896989\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:30:20Z","timestamp":1788935420000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1896989\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":29,"alternative-id":["10.3389\/fcell.2026.1896989"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1896989","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"1896989"}}