Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong

Abstract BackgroundPatients with cancer and cancer survivors often experience multiple chronic health conditions, which can impact symptom burden and treatment outcomes. Despite the high prevalence of multimorbidity, research on cancer prognosis has predominantly focused on ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun Sing Lam, Rong Hua, Herbert Ho-Fung Loong, Chun-Kit Ngan, Yin Ting Cheung
Format: Article
Language:English
Published: JMIR Publications 2025-07-01
Series:JMIR Cancer
Online Access:https://cancer.jmir.org/2025/1/e71937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850073457994235904
author Chun Sing Lam
Rong Hua
Herbert Ho-Fung Loong
Chun-Kit Ngan
Yin Ting Cheung
author_facet Chun Sing Lam
Rong Hua
Herbert Ho-Fung Loong
Chun-Kit Ngan
Yin Ting Cheung
author_sort Chun Sing Lam
collection DOAJ
description Abstract BackgroundPatients with cancer and cancer survivors often experience multiple chronic health conditions, which can impact symptom burden and treatment outcomes. Despite the high prevalence of multimorbidity, research on cancer prognosis has predominantly focused on cancers in isolation. There is growing interest in machine learning techniques for cancer studies. However, these methods have not been applied in the context of supportive care for patients with cancer who have multimorbidity. Furthermore, few studies have investigated the associations between comorbidity clusters and mortality outcomes. ObjectiveThis study investigated comorbidity clusters among patients with cancer using machine learning and examined their associations with mortality outcomes in two large representative samples from the United States and Hong Kong. MethodsThis study used data from the National Health and Nutrition Examination Survey (NHANES) and the Hospital Authority Data Collaboration Laboratory (HADCL). Participants aged ≥20 years with a history of cancer were included. The study used a two-step framework to identify clusters of comorbidities in NHANES. In the first step, we used four machine learning techniques, including the Bernoulli mixture model and partition-based methods, to cluster the comorbidities. In the second step, domain experts reviewed and ranked the identified clusters to ensure clinical relevance. The clusters that had the highest average rank were selected for further analysis. The associations between comorbidity clusters and mortality outcomes were analyzed using Cox proportional hazards models. We conducted an external validation to evaluate the generalizability of the clusters identified in the NHANES cohort and their associations with mortality using HADCL. The same number of clusters was replicated based on the distinctive patterns and distribution of comorbidities observed within each cluster. ResultsThe study included 4390 participants in NHANES and 12,484 participants in HADCL. Four comorbidity clusters were identified: low comorbidity, metabolic, cardiovascular disease (CVD), and respiratory. In NHANES, participants in the respiratory cluster had the highest risk of all-cause mortality (adjusted hazard ratio [aHR] 1.62, 95% CI 1.26‐2.08; P<P<PPPP ConclusionsHigh comorbidity burden clusters showed increased all-cause and CVD-related mortality in patients with cancer. These findings highlight the significance of considering comorbidity burden in cancer care. Machine learning approaches can provide valuable insights into complex multimorbidity profiles. Further research is needed to deepen understanding of the relationships between multimorbidity and cancer-specific outcomes.
format Article
id doaj-art-0f025e123f4042b9820f6a160da52ba9
institution DOAJ
issn 2369-1999
language English
publishDate 2025-07-01
publisher JMIR Publications
record_format Article
series JMIR Cancer
spelling doaj-art-0f025e123f4042b9820f6a160da52ba92025-08-20T02:46:49ZengJMIR PublicationsJMIR Cancer2369-19992025-07-0111e71937e7193710.2196/71937Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong KongChun Sing Lamhttp://orcid.org/0000-0002-6478-6706Rong Huahttp://orcid.org/0009-0009-2473-9487Herbert Ho-Fung Loonghttp://orcid.org/0000-0002-6607-1106Chun-Kit Nganhttp://orcid.org/0000-0003-2151-0459Yin Ting Cheunghttp://orcid.org/0000-0001-9874-8938 Abstract BackgroundPatients with cancer and cancer survivors often experience multiple chronic health conditions, which can impact symptom burden and treatment outcomes. Despite the high prevalence of multimorbidity, research on cancer prognosis has predominantly focused on cancers in isolation. There is growing interest in machine learning techniques for cancer studies. However, these methods have not been applied in the context of supportive care for patients with cancer who have multimorbidity. Furthermore, few studies have investigated the associations between comorbidity clusters and mortality outcomes. ObjectiveThis study investigated comorbidity clusters among patients with cancer using machine learning and examined their associations with mortality outcomes in two large representative samples from the United States and Hong Kong. MethodsThis study used data from the National Health and Nutrition Examination Survey (NHANES) and the Hospital Authority Data Collaboration Laboratory (HADCL). Participants aged ≥20 years with a history of cancer were included. The study used a two-step framework to identify clusters of comorbidities in NHANES. In the first step, we used four machine learning techniques, including the Bernoulli mixture model and partition-based methods, to cluster the comorbidities. In the second step, domain experts reviewed and ranked the identified clusters to ensure clinical relevance. The clusters that had the highest average rank were selected for further analysis. The associations between comorbidity clusters and mortality outcomes were analyzed using Cox proportional hazards models. We conducted an external validation to evaluate the generalizability of the clusters identified in the NHANES cohort and their associations with mortality using HADCL. The same number of clusters was replicated based on the distinctive patterns and distribution of comorbidities observed within each cluster. ResultsThe study included 4390 participants in NHANES and 12,484 participants in HADCL. Four comorbidity clusters were identified: low comorbidity, metabolic, cardiovascular disease (CVD), and respiratory. In NHANES, participants in the respiratory cluster had the highest risk of all-cause mortality (adjusted hazard ratio [aHR] 1.62, 95% CI 1.26‐2.08; P<P<PPPP ConclusionsHigh comorbidity burden clusters showed increased all-cause and CVD-related mortality in patients with cancer. These findings highlight the significance of considering comorbidity burden in cancer care. Machine learning approaches can provide valuable insights into complex multimorbidity profiles. Further research is needed to deepen understanding of the relationships between multimorbidity and cancer-specific outcomes.https://cancer.jmir.org/2025/1/e71937
spellingShingle Chun Sing Lam
Rong Hua
Herbert Ho-Fung Loong
Chun-Kit Ngan
Yin Ting Cheung
Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
JMIR Cancer
title Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
title_full Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
title_fullStr Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
title_full_unstemmed Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
title_short Association Between Comorbidity Clusters and Mortality in Patients With Cancer: Predictive Modeling Using Machine Learning Approaches of Data From the United States and Hong Kong
title_sort association between comorbidity clusters and mortality in patients with cancer predictive modeling using machine learning approaches of data from the united states and hong kong
url https://cancer.jmir.org/2025/1/e71937
work_keys_str_mv AT chunsinglam associationbetweencomorbidityclustersandmortalityinpatientswithcancerpredictivemodelingusingmachinelearningapproachesofdatafromtheunitedstatesandhongkong
AT ronghua associationbetweencomorbidityclustersandmortalityinpatientswithcancerpredictivemodelingusingmachinelearningapproachesofdatafromtheunitedstatesandhongkong
AT herberthofungloong associationbetweencomorbidityclustersandmortalityinpatientswithcancerpredictivemodelingusingmachinelearningapproachesofdatafromtheunitedstatesandhongkong
AT chunkitngan associationbetweencomorbidityclustersandmortalityinpatientswithcancerpredictivemodelingusingmachinelearningapproachesofdatafromtheunitedstatesandhongkong
AT yintingcheung associationbetweencomorbidityclustersandmortalityinpatientswithcancerpredictivemodelingusingmachinelearningapproachesofdatafromtheunitedstatesandhongkong