Comparative Analysis of Clustering Algorithms for Health Risk Profiling Based on Dietary and Physical Activity Patterns
Bibliographic record
Abstract
Non-Communicable Diseases (NCDs) continue to rise in line with changes in people's consumption patterns and lifestyles, so a data-driven approach is needed to understand health risk segmentation.This study aims to classify food consumption behaviors and healthy lifestyles among the productive age group.Data were collected from 321 respondents through a structured survey that included eating habits, physical activity, as well as demographic and health factors.Three clustering algorithms were tested, namely K-Means, Hierarchical Clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), with evaluation using Silhouette Score, Davies-Bouldin Index, and Dunn Index.The results showed that DBSCAN achieved the best performance (Silhouette Score = 0.416; Davies-Bouldin Index = 0.448; Dunn Index = 1.430), which indicates a separate cluster with a good degree of cohesiveness.In contrast, K-Means showed the lowest performance (Silhouette Score = 0.045; Davies-Bouldin Index = 2.936; Dunn Index = 0.251), while Hierarchical Clustering showed limited performance (Silhouette Score = 0.046; Davies-Bouldin Index = 2.956; Dunn Index = 0.239).For the K-Means analysis, the optimal number of clusters was determined to be k = 8 using the elbow method, which was subsequently consolidated.The cluster profiles identified three main groups: (1) individuals with healthy lifestyles, (2) moderate-risk individuals with high calorie consumption and low activity, and (3) high-risk individuals with poor diets and sedentary habits.These findings confirm that DBSCAN is effective in identifying patterns of health risks and can serve as the basis for designing more targeted promotive and preventive interventions to reduce the risk of NCDs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".