Challenges for Predictive Modeling with Neural Network Techniques using Error-Prone Dietary Intake Data Article Swipe

MAKE IMPACT

Dylan Spicker , Amir Nazemi , Joy M. Hutchinson , Paul Fieguth , Sharon I. Kirkpatrick , Michael B. Wallace , Kevin W. Dodd · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2311.09338

Dietary intake data are routinely drawn upon to explore diet-health relationships. However, these data are often subject to measurement error, distorting the true relationships. Beyond measurement error, there are likely complex synergistic and sometimes antagonistic interactions between different dietary components, complicating the relationships between diet and health outcomes. Flexible models are required to capture the nuance that these complex interactions introduce. This complexity makes research on diet-health relationships an appealing candidate for the application of machine learning techniques, and in particular, neural networks. Neural networks are computational models that are able to capture highly complex, nonlinear relationships so long as sufficient data are available. While these models have been applied in many domains, the impacts of measurement error on the performance of predictive modeling has not been systematically investigated. However, dietary intake data are typically collected using self-report methods and are prone to large amounts of measurement error. In this work, we demonstrate the ways in which measurement error erodes the performance of neural networks, and illustrate the care that is required for leveraging these models in the presence of error. We demonstrate the role that sample size and replicate measurements play on model performance, indicate a motivation for the investigation of transformations to additivity, and illustrate the caution required to prevent model overfitting. While the past performance of neural networks across various domains make them an attractive candidate for examining diet-health relationships, our work demonstrates that substantial care and further methodological development are both required to observe increased predictive performance when applying these techniques, compared to more traditional statistical procedures.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2311.09338

PDF

https://arxiv.org/pdf/2311.09338

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4388787477

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4388787477

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2311.09338

Digital Object Identifier

Title

Challenges for Predictive Modeling with Neural Network Techniques using Error-Prone Dietary Intake Data

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-11-15

Full publication date if available

Authors

Dylan Spicker, Amir Nazemi, Joy M. Hutchinson, Paul Fieguth, Sharon I. Kirkpatrick, Michael B. Wallace, Kevin W. Dodd

List of authors in order

Landing page

https://arxiv.org/abs/2311.09338

Publisher landing page

PDF URL

https://arxiv.org/pdf/2311.09338

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2311.09338

Direct OA link when available

Concepts

Overfitting, Artificial neural network, Computer science, Machine learning, Artificial intelligence, Replicate, Sample (material), Predictive modelling, Data mining, Statistics, Mathematics, Chromatography, Chemistry

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload