Related Experiment Video
Updated: Jun 13, 2025
Author Spotlight: Exploring the Relationship Between Lipotoxicity and HFpEF
Published on: March 29, 2024
Development and validation of machine-learning models of diet management for hyperphenylalaninemia: a multicenter
Yajie Su1,2, Yaqiong Wang1, Jinfeng He3
1Centre for Molecular Medicine, Children's Hospital of Fudan University, and Institutes of Biomedical Sciences, Fudan University, Shanghai, China.
Insights
This study developed a machine learning model to predict phenylalanine (Phe) intake tolerance in children with hyperphenylalaninemia (HPA), improving dietary management. The model integrates genetic and metabolic data for personalized treatment strategies.
Area of Science:
- Biochemistry
- Genetics
- Computational Biology
Background:
- Managing hyperphenylalaninemia (HPA) requires careful assessment of dietary phenylalanine (Phe) tolerance.
- Current dietary management is time-intensive for clinicians and families.
Purpose of the Study:
- To develop a machine learning model for predicting dietary Phe intake tolerance in children with HPA.
- To enable precise, personalized dietary management over 10 years post-diagnosis.
Main Methods:
- Retrospective observational study of 204 children with HPA, collecting genotype, metabolic profiles, and Phe concentrations.
- Utilized a predicted allelic phenotype value (pAPV) model incorporating 2965 missense variants in the phenylalanine hydroxylase (PAH) gene.
- Trained a multiclass classification model on metabolic, genetic, and follow-up data, validated using tenfold cross-validation and independent datasets.
Main Results:
- The pAPV model demonstrated good predictive performance (RMSE 1.53 training, 2.38 test).
- The final model achieved high sensitivity (0.77-0.91) and specificity (0.8-1) across validation datasets.
- Robust performance indicated by positive predictive value (0.68-1), negative predictive value (0.8-0.98), F1 score (0.71-0.92), and balanced accuracy (0.8-0.92).
Conclusions:
- The developed model integrates metabolic and genetic data for accurate, age-specific Phe tolerance prediction in HPA patients.
- This approach facilitates precision management of HPA and offers a framework for other inborn errors of metabolism.
Background:
Assessing dietary phenylalanine (Phe) tolerance is crucial for managing hyperphenylalaninemia (HPA) in children. However, traditionally, adjusting the diet requires significant time from clinicians and parents. This study aims to investigate the development of a machine-learning model that predicts a range of dietary Phe intake tolerance for children with HPA over 10 years following diagnosis.
Methods:
In this multicenter retrospective observational study, we collected the genotypes of phenylalanine hydroxylase (PAH), metabolic profiles at screening and diagnosis, and blood Phe concentrations corresponding to dietary Phe intake from over 10 years of follow-up data for 204 children with HPA. To incorporate genetic information, allelic phenotype value (APV) was input for 2965 missense variants in the PAH gene using a predicted APV (pAPV) model. This model was trained on known pheno-genotype relationships from the BioPKU database, utilizing 31 features. Subsequently, a multiclass classification model was constructed and trained on a dataset featuring metabolic data, genetic data, and follow-up data from 3177 events. The final model was fine-tuned using tenfold validation and validated against three independent datasets.
Results:
The pAPV model achieved a good predictive performance with root mean squared error (RMSE) of 1.53 and 2.38 on the training and test datasets, respectively. The variants that cause amino acid changes in the region of 200-300 of PAH tend to exhibit lower pAPV. The final model achieved a sensitivity range of 0.77 to 0.91 and a specificity range of 0.8 to 1 across all validation datasets. Additional assessment metrics including positive predictive value (0.68-1), negative predictive values (0.8-0.98), F1 score (0.71-0.92), and balanced accuracy (0.8-0.92) demonstrated the robust performance of our model.
Conclusions:
Our model integrates metabolic and genetic information to accurately predict age-specific Phe tolerance, aiding in the precision management of patients with HPA. This study provides a potential framework that could be applied to other inborn errors of metabolism.
More Related Videos
10:31An Experimental Model of Diet-Induced Metabolic Syndrome in Rabbit: Methodological Considerations, Development, and Assessment
Published on: April 20, 2018
09:10Palatable Western-style Cafeteria Diet as a Reliable Method for Modeling Diet-induced Obesity in Rodents
Published on: November 1, 2019
