Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 17, 2025PLoS ONEOpen Access

Classifying complex multimorbidity using latent class analysis and machine learning to generate insights into clustering of mental and cardiometabolic conditions

View Full Paper
Ask AI
Bookmark
Share

Key result

The Random Forest model outperformed other machine learning algorithms in classifying complex multimorbidity clusters, achieving an AUROC of 0.805.

Why the study?

Complex multimorbidity, particularly the intersection of cardiometabolic disorders and mental health conditions, poses a serious threat to public health systems and requires priority interventions.

Population

46,736 responses from the CDC BRFSS 2015 dataset

Comparison

Six machine learning algorithms (MLR, MNB, DT, RF, XGB, and ANN)

Design

Latent class analysis and machine learning classification study

Authors

MMM. MukherjeeHTHruthik Reddy ThokalaRARaja Hashim Ali

Discussion

Loading...

Member takes

Overview

May inform targeted multimorbidity interventions; hypothesis-generating from cross-sectional data and requires prospective validation.

Study Design

Type

Cross-Sectional (n=46,736)

Structured PICO

P
Population
46,736 US adults with prediabetes, diabetes, or a history of stroke from the 2015 BRFSS dataset, analyzed to classify complex multimorbidity clusters.
E
Exposure
Latent class analysis (LCA) to identify complex multimorbidity clusters, followed by training six machine learning algorithms (MLR, MNB, DT, RF, XGB, and ANN) to classify individuals into clusters.
O
Outcome
Performance of machine learning models evaluated through AUROC, accuracy, precision, recall, and F1 score.

Main Result

Effect estimate: AUROC 0.805 (95% CI 0.800-0.809)

p-value: p=0.0000

Machine learning models, particularly Random Forest, can accurately classify complex cardiometabolic and mental health multimorbidity clusters, providing a decision support tool for targeted public health interventions.

Limitations

  • Lack of detailed categories of mental health problems

Cite This Study

Mukherjee et al. (2025) conducted a cross-sectional in Complex multimorbidity (cardiometabolic and mental health conditions) (n=46,736). Random Forest machine learning model vs. Other machine learning models (MLR, MNB, DT, XGB, ANN) was evaluated on Classification of complex multimorbidity clusters (AUROC) (AUROC 0.805, 95% CI 0.800-0.809, p=0.0000). The Random Forest model outperformed other machine learning algorithms in classifying complex multimorbidity clusters, achieving an AUROC of 0.805.

synapsesocial.com/papers/6a9c7228e4895faeb35d2b6bhttps://doi.org/10.1371/journal.pone.0335676
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine learning classification of prevalent chronic disease using multidimensional social, behavioral, and psychological determinants: A cross-sectional analysis of the 2024 national health interview survey2026
  2. 2Characterizing the role of early life factors in machine learning-based multimorbidity risk prediction2025
  3. 3A Machine Learning Approach to Prediction and Multimorbidity Risk Factor Identification in a low- and middle-income country2025
  4. 4Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey2025 · 4 citations
  5. 5Revisiting the dynamic risk profile of cardiovascular/non‐cardiovascular multimorbidity in incident atrial fibrillation patients and five cardiovascular/non‐cardiovascular outcomes: A machine‐learning approach2021 · 27 citations