Secondary relevance to vitamin D This paper mainly addresses another topic and also reports a vitamin D analysis, result or scientific synthesis.
This paper mainly addresses another topic and also reports a vitamin D analysis, result or scientific synthesis.
Why this paper is included
Supporting source evidence:
In contrast, HBV infection and anxiety were comparatively less prevalent in the LOLC group, suggesting a distinct risk profile for comorbidities between early: and late-onset liver cancer cases.Top Ten Comorbidities With Highest Prevalence Among Early: and Late-Onset Liver Cancer Cases by RaceRaceEarly-onset liver cancerLate-onset liver cancerComorbidityCases (n, %)Controls (n, %)OR (95% CI)ComorbidityCases (n, %)Controls (n, %)OR (95% CI)Asian and pacific islanderHBV165 (47.3%)24 (1.4%)64.3 (40.8-101.3)Hypertension2020 (64.1%)7379 (46.8%)2.0 (1.9-2.2)Hypertension95 (27.2%)306 (17.5%)1.8 (1.3-2.3)Diabetes1390 (44.1%)5490 (34.8%)1.5 (1.4-1.6)Cirrhosis77 (22.1%)8 (0.5%)61.5 (29.3-128.7)Hyperlipidemia1208 (38.3%)6937 (44.0%)0.8 (0.7-0.9)Hyperlipidemia72 (20.6%)415 (23.8%)0.8 (0.6-1.1)GERD/Peptic ulcer1069 (33.9%)3115 (19.8%)2.1 (1.9-2.3)GERD/Peptic ulcer71 (20.3%)176 (10.1%)2.3 (1.7-3.1)HBV901 (28.6%)319 (2.0%)19.4 (16.9-22.2)Diabetes69 (19.8%)314 (18.0%)1.1 (0.8-1.5)Cirrhosis877 (27.8%)116 (0.7%)52.0 (42.6-63.4)Steatosis of liver25 (7.2%)24 (1.4%)5.5 (3.1-9.8)HCV412 (13.1%)86 (0.6%)27.4 (21.6-34.7)Vitamin D Deficiency21 (6.0%)120 (6.9%)0.9 (0.5-1.4)Asthma269 (8.5%)1457 (9.2%)0.9 (0.8-1.0)HCV18 (5.2%)0 (0.0%)Undefined a Kidney Diseases235 (7.5%)1099 (7.0%)1.1 (0.9-1.2)Asthma17 (4.9%)132 (7.6%)0.6 (0.4-1.1)Hypothyroidism211 (6.7%)1042 (6.6%)1.0 (0.9-1.2)HispanicHypertension251 (56.3%)502 (22.5%)4.4 (3.6-5.5)Hypertension2951 (74.6%)9437 (47.7%)3.2 (3.0-3.5)Cirrhosis218 (48.9%)17 (0.8%)124.5 (74.6-207.7)Cirrhosis2284 (57.7%)428 (2.2%)61.7 (55.0-69.2)GERD/Peptic ulcer169 (37.9%)304 (13.6%)3.9 (3.1-4.8)Diabetes1966 (49.7%)7456 (37.7%)1.6 (1.5-1.7)Diabetes145 (32.5%)443 (19.9%)1.9 (1.6-2.4)GERD/Peptic ulcer1726 (43.6%)4625 (23.4%)2.5 (2.4-2.7)Hyperlipidemia85 (19.1%)429 (19.2%)1.0 (0.8-1.3)Hyperlipidemia1341 (33.9%)7918 (40.0%)0.8 (0.7-0.8)HCV82 (18.4%)19 (0.8%)26.2 (15.7-43.7)HCV1235 (31.2%)369 (1.9%)23.9 (21.1-27.0)Anemia54 (12.1%)159 (7.1%)1.8 (1.3-2.5)Alcohol Dependence1004 (25.4%)544 (2.8%)12.0 (10.8-13.4)Alcohol Dependence50 (11.2%)31 (1.4%)9.0 (5.7-14.2)Steatosis of liver550 (13.9%)349 (1.8%)9.0 (7.8-10.3)Anxiety49 (11.0%)146 (6.5%)1.8 (1.3-2.5)Hypothyroidism495 (12.5%)1582 (8.0%)1.6 (1.5-1.8)Steatosis of liver48 (10.8%)41 (1.8%)6.4 (4.2-9.9)Asthma411 (10.4%)1908 (9.6%)1.1 (1.0-1.2)WhiteHypertension202 (43.4%)358 (15.4%)4.2 (3.4-5.2)Hypertension3791 (66.8%)11,705 (41.3%)2.9 (2.7-3.0)GERD/Peptic ulcer161 (34.5%)240 (10.3%)4.6 (3.6-5.8)Cirrhosis2187 (38.6%)230 (0.8%)76.8 (66.7-88.3)Cirrhosis128 (27.5%)4 (0.2%)220.2 (80.9-599.6)GERD/Peptic ulcer1970 (34.7%)5750 (20.3%)2.1 (2.0-2.2)Hyperlipidemia89 (19.1%)325 (13.9%)1.5 (1.1-1.9)Hyperlipidemia1900 (33.5%)10,550 (37.2%)0.9 (0.8-0.9)Diabetes87 (18.7%)187 (8.0%)2.6 (2.0-3.5)Diabetes1870 (33.0%)5933 (20.9%)1.9 (1.7-2.0)Anxiety63 (13.5%)193 (8.3%)1.7 (1.3-2.3)HCV1780 (31.4%)351 (1.2%)36.5 (32.4-41.1)Asthma58 (12.4%)189 (8.1%)1.6 (1.2-2.2)Hypothyroidism837 (14.8%)2990 (10.5%)1.5 (1.4-1.6)Hypothyroidism43 (9.2%)138 (5.9%)1.6 (1.1-2.3)Alcohol Dependence829 (14.6%)603 (2.1%)7.9 (7.1-8.8)HCV41 (8.8%)14 (0.6%)16.0 (8.6-29.5)Asthma667 (11.8%)3114 (11.0%)1.1 (1.0-1.2)Cholangitis38 (8.2%)3 (0.1%)68.9 (21.2-224.1)Osteoarthritis427 (7.5%)3415 (12.0%)0.6 (0.5-0.7)Other/UnknownHypertension111 (35.5%)242 (15.5%)3.0 (2.3-3.9)Hypertension2392 (63.6%)7345 (39.0%)2.7 (2.5-2.9)GERD/Peptic ulcer91 (29.1%)120 (7.7%)4.9 (3.6-6.7)Cirrhosis1478 (39.3%)149 (0.8%)81.0 (68.1-96.4)Cirrhosis84 (26.8%)3 (0.2%)191.0 (59.9-609.2)Diabetes1334 (35.4%)4613 (24.5%)1.7 (1.6-1.8)Diabetes61 (19.5%)188 (12.0%)1.8 (1.3-2.4)GERD/Peptic ulcer1286 (34.2%)3301 (17.5%)2.4 (2.3-2.6)Hyperlipidemia54 (17.2%)229 (14.6%)1.2 (0.9-1.7)HCV1174 (31.2%)346 (1.8%)24.2 (21.3-27.5)HBV38 (12.1%)4 (0.3%)53.9 (19.1-152.3)Hyperlipidemia1170 (31.1%)6152 (32.7%)0.9 (0.9-1.0)HCV33 (10.5%)6 (0.4%)30.6 (12.7-73.8)Alcohol Dependence507 (13.5%)312 (1.7%)9.2 (8.0-10.7)Anxiety21 (6.7%)98 (6.3%)1.1 (0.7-1.8)Asthma378 (10.0%)1680 (8.9%)1.1 (1.0-1.3)Asthma21 (6.7%)107 (6.8%)1.0 (0.6-1.6)Hypothyroidism368 (9.8%)1356 (7.2%)1.4 (1.2-1.6)Vitamin D Deficiency21 (6.7%)55 (3.5%)2.0 (1.2-3.3)Steatosis of liver237 (6.3%)118 (0.6%)10.6 (8.5-13.3)Note: OR, odds ratio; HBV, Hepatitis B Virus; HCV, Hepatitis C Virus; GERD, Gastroesophageal Reflux Disease.aNo controls with HCV infection in the API group.
Source: Results. View original paper
Relevance classification does not establish study quality, causation or editorial approval.
Study design Study design awaiting verification.
Study design awaiting verification
The available source does not establish a sufficiently clear study design.
Meta-analysis unclear · Blinding unclear / not reported · Human research reported
How this paper was classified
Automatic source-based classification; awaiting editorial verification. This is not a quality score.
Patients were grouped based on self-reported race and ethnicity groups, identified using the following SNOMED codes: non-Hispanic Asian and Pacific Islanders (API) (race: 8515, 8557; ethnicity: 38003564), Hispanic (ethnicity: 38003563), non-Hispanic White (race: 8527; ethnicity: 38003564), and other or unknown races, the latter contained liver cancer cases in non-Hispanic Black, American Indian/Alaska Native, and other racial/ethnic groups and those with unknown races/ethnicities.
Source: Methods.
What the study types mean
- Systematic review
- Uses explicit methods to identify, assess and summarise research on a defined question.
- Scoping review
- Maps the extent and characteristics of research on a topic.
- Narrative review
- Discusses existing research; systematic-review methods have not been established by this classification.
- Review / evidence synthesis
- Reviews existing research; the exact review methods need further assessment.
- Randomised controlled trial
- Assigns participants or groups to comparison interventions by chance.
- Non-randomised intervention study
- Examines an intervention without random allocation.
- Cohort study
- Examines exposures and outcomes over time within a defined group.
- Case-control study
- Compares people with an outcome against people without it, examining exposures.
- Cross-sectional study
- Examines a population at a particular point in time.
- Observational study
- Observes exposures and outcomes without assigning the exposure; the subtype is not established here.
- Case report
- Describes an individual case.
- Case series
- Describes a group of individual cases.
- Secondary analysis
- Analyses existing study data; this paper is not automatically another independent trial.
- Laboratory study
- Investigates biological processes in a laboratory setting.
- Qualitative study
- Examines experiences or meanings using qualitative methods.
- Genetic instrumental-variable study
- Uses genetic variation as an instrument to investigate relationships; this is not a randomised treatment trial.
- Study protocol
- Describes planned methods and is not evidence that the planned study has reported results.
- Multiple reported designs
- More than one design is explicitly reported; examine the supporting methods.
- Study design awaiting verification
- The available source does not establish a sufficiently clear study design.
Meta-analysis combines numerical results from studies. Blinding describes who was unaware of treatment allocation. Neither is a separate quality grade. Study design, vitamin D relevance and document format are independent filters.
Abstracts
Racial Disparities in Comorbidity Patterns of Early-Onset Liver Cancer: A Machine Learning Analysis
Study design awaiting verification · Cancer Control : Journal of the Moffitt Cancer Center · 2025
Original publication title
Racial Disparities in Comorbidity Patterns of Early-Onset Liver Cancer: A Machine Learning Analysis
© The Author(s) 2025
Original publication · Publisher record · CC BY 4.0
Source wording retained. Formatting, section navigation and display-title punctuation adapted for this research record.
At a glance
Abstract: What background does the paper provide?
The incidence of early-onset liver cancer (EOLC) has been increasing in many countries, yet evidence on its etiology remains limited, particularly outside the Asian population. This case-control study explores the comorbidity patterns of EOLC and develops race/ethnicity-specific machine learning (ML) models to predict liver cancer risk.
Source: IntroductionAbstract: What methods does the paper describe?
We included patients diagnosed with primary liver cancer between ages 18 and 49 from the University of California Health Data Warehouse, matching each patient with five controls. ML classification methods, including decision trees, random forests, logistic regression, XGBoost, and LightGBM, were used to assess liver cancer risk based on demographics and comorbidities. Model performance was evaluated using F1 scores, and SHapley Additive exPlanations (SHAP) was applied to identify the most influential comorbidities within each racial group.
Source: MethodsAbstract: Results
A total of 1574 patients and 7870 controls were identified. Asian and Pacific Islanders (API) had significantly higher rates of Hepatitis B virus (HBV) infection, while Hispanics had higher prevalences of cirrhosis, hypertension, diabetes, and Hepatitis C virus (HCV) infection. Whites showed higher rates of anxiety, asthma, hypothyroidism, and cholangitis. Race/ethnicity-specific models for API (F1 score = 0.77, AUC = 0.90) and Hispanics (F1 score = 0.77, AUC = 0.92) outperformed the model for Whites (F1 score = 0.64, AUC = 0.87) in the validation dataset.
The SHAP results indicated that HBV infection was the dominant comorbidity for API, and HCV and metabolic disorders were notable among Hispanics. In contrast, the White population showed a broader and less concentrated comorbidity pattern.
Source: ResultsAbstract: Conclusions
Our study highlights significant racial disparities in comorbidity patterns for early-onset liver cancer, demonstrating the potential of ML models to identify high-risk populations and inform targeted prevention strategies.
Source: ConclusionsAuthors’ abstract
Introduction
The incidence of early-onset liver cancer (EOLC) has been increasing in many countries, yet evidence on its etiology remains limited, particularly outside the Asian population. This case-control study explores the comorbidity patterns of EOLC and develops race/ethnicity-specific machine learning (ML) models to predict liver cancer risk.
Methods
We included patients diagnosed with primary liver cancer between ages 18 and 49 from the University of California Health Data Warehouse, matching each patient with five controls. ML classification methods, including decision trees, random forests, logistic regression, XGBoost, and LightGBM, were used to assess liver cancer risk based on demographics and comorbidities. Model performance was evaluated using F1 scores, and SHapley Additive exPlanations (SHAP) was applied to identify the most influential comorbidities within each racial group.
Results
A total of 1574 patients and 7870 controls were identified. Asian and Pacific Islanders (API) had significantly higher rates of Hepatitis B virus (HBV) infection, while Hispanics had higher prevalences of cirrhosis, hypertension, diabetes, and Hepatitis C virus (HCV) infection. Whites showed higher rates of anxiety, asthma, hypothyroidism, and cholangitis. Race/ethnicity-specific models for API (F1 score = 0.77, AUC = 0.90) and Hispanics (F1 score = 0.77, AUC = 0.92) outperformed the model for Whites (F1 score = 0.64, AUC = 0.87) in the validation dataset.
The SHAP results indicated that HBV infection was the dominant comorbidity for API, and HCV and metabolic disorders were notable among Hispanics. In contrast, the White population showed a broader and less concentrated comorbidity pattern.
Conclusions
Our study highlights significant racial disparities in comorbidity patterns for early-onset liver cancer, demonstrating the potential of ML models to identify high-risk populations and inform targeted prevention strategies.
Publication and source details
Original title: Racial Disparities in Comorbidity Patterns of Early-Onset Liver Cancer: A Machine Learning Analysis
Bingya Ma; Kai Zheng; Fa-Chyi Lee; Yunxia Lu
Cancer Control : Journal of the Moffitt Cancer Center · 2025
Yunxia Lu, MD, PhD, Department of Population Health and Disease Prevention, Wen School of Population Health & Public Health University of California Irvine, 856 Health Sciences Quad, Irvine, CA 92697-3957, USA. Email: yunxia.lu@uci.edu© The Author(s) 20252025SAGE Publications Inc, unless otherwise noted. Manuscript content on this site is licensed under Creative Common Licenceshttps://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage). National Cancer Institutehttps://doi.org/10.13039/100000054 R25 CA112383 UCI Presidential Funding of Dr Oladele OgunseitanRepository JATS snapshot; version as supplied
Source retrieved: 2026-11-11T07:27:07.289983+00:00
DOI: 10.1177/10732748251363687 · PMC12317173