Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index, and 1 are not checked yet.

Modeling health risks using neural network ensembles

Open access

Abstract

This study aims to demonstrate that demographics combined with biometrics can be used to predict obesity related chronic disease risk and produce a health risk score that outperforms body mass index (BMI)—the most commonly used biomarker for obesity. We propose training an ensemble of small neural networks to fuse demographics and biometrics inputs. The categorical outputs of the networks are then turned into a multi-dimensional risk map, which associates diverse inputs with stratified, output health risk. Our ensemble model is optimized and validated on disjoint subsets of nationally representative data (N~100,000) from the National Health and Nutrition Examination Survey (NHANES). To broaden applicability of the proposed method, we consider only non-invasive inputs that can be easily measured through modern devices. Our results show that: (a) neural networks can predict individual conditions (e.g., diabetes, hypertension) or the union of multiple (e.g., nine) health conditions; (b) Softmax model outputs can be used to stratify individual- or any-condition risk; (c) ensembles of neural networks improve generalizability; (d) multiple-input models outperform BMI (e.g., 75.1% area under the receiver operator curve for eight-input, any-condition models compared to 64.2% for BMI); (e) small neural networks are as effective as larger ones for the inference tasks considered; the proposed models are small enough that they can be expressed as human-readable equations, and they can be adapted to clinical settings to identify high-risk, undiagnosed populations.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0308922

Cites

50 of 51 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 An example of training a classification network. In the left panel, each dot corresponds to weight and waist circumference measurements for thousands of participants in NHANES. The dot colors (blue/orange) correspond to participants ground truth class (negative/positive to a given health condition, e.g., hypertension). In the right panel, a neural network classifies previously unseen data points as positive or negative according to a separating hypersurface in as many dimensions as the input biomarkers.
Fig 1 An example of training a classification network. In the left panel, each dot corresponds to weight and waist circumference measurements for thousands of participants in NHANES. The dot colors (blue/orange) correspond to participants ground truth class (negative/positive to a given health condition, e.g., hypertension). In the right panel, a neural network classifies previously unseen data points as positive or negative according to a separating hypersurface in as many dimensions as the input biomarkers.CC BY · PubMed Central
Fig 2 Visual overview of the proposed neural network ensemble.
Fig 2 Visual overview of the proposed neural network ensemble.CC BY · PubMed Central
Fig 3 A network’s categorical output can be converted into a risk map. The Softmax network output (A) can be interpreted as a surface defined over the multi-dimensional space of input biomarkers (C). We can then slice that surface into regions based on percentiles of Softmax network output. In each of these “risk regions” we calculate the condition prevalence by simply counting how many participants in that region are positive, versus the total number of people in the region (D). The multi-dimensional shape of the risk regions is defined by the network output, and the actual risk associated with each region is simply the condition prevalence in that region.
Fig 3 A network’s categorical output can be converted into a risk map. The Softmax network output (A) can be interpreted as a surface defined over the multi-dimensional space of input biomarkers (C). We can then slice that surface into regions based on percentiles of Softmax network output. In each of these “risk regions” we calculate the condition prevalence by simply counting how many participants in that region are positive, versus the total number of people in the region (D). The multi-dimensional shape of the risk regions is defined by the network output, and the actual risk associated with each region is simply the condition prevalence in that region.CC BY · PubMed Central
Fig 4 Visualization of 3D health risk maps via 2D slices for {percent body fat, waist circumference, thigh circumference} and {percent body fat, waist circumference, weight} input sets. The dark maroon regions correspond to the top 10% of Softmax model outputs; light maroon is the next 20%, white is the middle 40%, light green is the next 20%, and dark green is the lowest 10%.
Fig 4 Visualization of 3D health risk maps via 2D slices for {percent body fat, waist circumference, thigh circumference} and {percent body fat, waist circumference, weight} input sets. The dark maroon regions correspond to the top 10% of Softmax model outputs; light maroon is the next 20%, white is the middle 40%, light green is the next 20%, and dark green is the lowest 10%.CC BY · PubMed Central
Fig 5 BMI vs. the distribution of Softmax outputs conditioned on BMI for two different models: BMI-only input (A), and all 8 inputs (B). Both models predict the union (any) among nine common health conditions. (C) highlights the large stratification of Softmax outputs at 30 BMI for the 8-inputs model.
Fig 5 BMI vs. the distribution of Softmax outputs conditioned on BMI for two different models: BMI-only input (A), and all 8 inputs (B). Both models predict the union (any) among nine common health conditions. (C) highlights the large stratification of Softmax outputs at 30 BMI for the 8-inputs model.CC BY · PubMed Central
Fig 6 Any-condition prevalence is highly correlated with age.
Fig 6 Any-condition prevalence is highly correlated with age.CC BY · PubMed Central
Fig 7 Visualization of improved ensemble generalization compared to single models. The separating surface is similar between single networks and ensembles, but ensembles yield smoother, monotonic risk regions as we move immediately outside the region of high data density.
Fig 7 Visualization of improved ensemble generalization compared to single models. The separating surface is similar between single networks and ensembles, but ensembles yield smoother, monotonic risk regions as we move immediately outside the region of high data density.CC BY · PubMed Central
Fig 8 Average performance asymptotically increases (orange) and variability in performance asymptotically decreases (blue) as neural network models are added to the ensemble, as measured across 64 trials for each ensemble size.
Fig 8 Average performance asymptotically increases (orange) and variability in performance asymptotically decreases (blue) as neural network models are added to the ensemble, as measured across 64 trials for each ensemble size.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 49 references

Research works printed but not linked: 6

  1. World Health Organization Nutrition and Food Safety., 2008, Waist circumference and waist-hip ratio: report of a WHO expert consultation., 8
  2. National Institute of Diabetes and Digestive and Kidney Diseases, 2021, Overweight & obesity statistics.
  3. American Medical Association, 2023, AMA adopts new policy clarifying role of BMI as a measure in medicine.
  4. I Goodfellow, 2017, Deep learning.
  5. S Ioffe, 2015, Batch normalization: accelerating deep network training by reducing internal covariate shift. Proc. of the 32nd, International Conference on Machine Learning, 7
  6. I Goodfellow, 1916, Deep Learning., 180

Cited by

See all 7

Metadata

Authors
Smith, B. M., Criminisi, A., Sorek, N., Harari, Y., Sood, N., & Heymsfield, S. B.
Affiliations
  • Amazon (United States) (US)
  • Amazon (United Kingdom) (GB)
  • University of Southern California (US)
  • Pennington Biomedical Research Center (US)
Corresponding author
Smith, Brandon M.
Venue
PLOS ONE
Published
2024-10-09
Volume
19
Issue
10
Pages
e0308922
ISSN
1932-6203 (ISSN-L)
OpenAlex
W4403240915
Cited by
5
References
49
Citations by year
2026: 2 · 2025: 2 · 2024: 1
FWCI
1.53
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Funded by Amazon, Inc., Seattle, WA.
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Health Promotion and Cardiovascular Prevention
Keywords
health risk prediction, neural network ensembles, obesity, chronic disease risk, body mass index, biometrics, demographics, risk score, diabetes mellitus, hypertension, model generalization, NHANES
MeSH terms
Adult, Female, Humans, Male, Middle Aged, Nutrition Surveys, Obesity, Risk Factors, Body Mass Index, Neural Networks, Computer, Risk Assessment

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Modeling health risks using neural network ensembles. https://app.cochat.ai/papers/10.1371/journal.pone.0308922
The paper
Smith, B. M., Criminisi, A., Sorek, N., Harari, Y., Sood, N., & Heymsfield, S. B. (2024). Modeling health risks using neural network ensembles. PLOS ONE. https://doi.org/10.1371/journal.pone.0308922

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.