Machine learning approaches and genetic determinants that influence the development of type 2 diabetes mellitus: a genetic association study in Brazilian patients
2024

Machine Learning and Genetic Factors in Type 2 Diabetes

Sample size: 286 publication 10 minutes Evidence: moderate

Author Information

Author(s): K.F. Santos, L.P. Assunção, R.S. Santos, A.A.S. Reis

Primary Institution: Universidade Federal de Goiás

Hypothesis

This study investigates the association of specific genetic polymorphisms with the development of type 2 diabetes mellitus (T2DM) in Brazilian patients.

Conclusion

The study found that certain genetic polymorphisms, particularly GSTT1 and GSTP1, may contribute to the susceptibility to T2DM in the Brazilian population.

Supporting Evidence

  • The GSTT1-null genotype was associated with a 3.16-fold increased risk of T2DM.
  • Women with the GSTT1-null genotype showed a 3.66-fold increased risk of developing T2DM.
  • The AG genotype of the GSTP1 rs1695 polymorphism was associated with a reduced risk of T2DM.

Takeaway

Researchers looked at how certain genes might make people more likely to get type 2 diabetes, and they found some important links.

Methodology

The study included 120 T2DM patients and 166 non-diabetic controls, analyzing genetic polymorphisms and using machine learning models for risk assessment.

Potential Biases

Potential biases may arise from the selection of participants and the reliance on self-reported data for lifestyle factors.

Limitations

The study's sample size may limit the generalizability of the findings, and the predominance of female participants could influence the results.

Participant Demographics

The mean age of participants was around 60 years, with a higher proportion of women in both the case and control groups.

Statistical Information

P-Value

0.000267

Confidence Interval

1.721–5.972

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1590/1414-431X2024e13957

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication