SupplementsExercise

Lifestyle habits including age, BMI, smoking status, and treatment pill intake predict breast cancer survival in female patients

This study analyzed 21,219 female breast cancer patients from the UK Biobank and found that age, BMI, smoking status, and treatment pill intake are key lifestyle-related factors influencing survival. The XGBoost model achieved AUCs of 0.748, 0.749, and 0.765 at 3, 6, and 9 years, respectively, and high-risk patients had significantly worse survival (P < 0.0001).

Last updated: Jul 23, 2026•0 RCTs•📖 Read as article →

Evidence Score

Evidence Score32/100
Human RCT☆☆☆☆☆
Meta-analysis☆☆☆☆☆
Mechanism★★★★★
Safety★★★★☆
Confidencelow

Study Evidence

Study 1. Interpretable machine-learning survival prediction of breast cancer prognosis from lifestyle factors: evidence from UK biobank.

observational

Yao Y, Zhai X, Liang Z, Lam CK, Xie H, Tong HHY, Tong T, Chen Y, Mann RM, He M, Li K, Tan T · Breast cancer (Tokyo, Japan) (2026)

Participants: N/A
Duration: 9 years (follow-up for survival prediction)
Intervention: Analysis of lifestyle habits including dietary habits, exercise frequency, sleep quality, tobacco and alcohol use
Outcome: Breast cancer survival (3-year, 6-year, 9-year AUC; Kaplan-Meier survival curves; SHAP feature importance)
Effect Size: N/A
Population: 21,219 female breast cancer patients from the UK Biobank

Result:

PubMed: 42467394DOI: 10.1007/s12282-026-01893-w

Mechanism Graph

Lifestyle factors (age, BMI, smoking, treatment pill intake) are identified as key prognostic variables
↓
Machine learning model (XGBoost) integrates these factors to calculate risk scores
↓
High-risk patients based on median risk score show significantly worse survival outcomes
↓
SHAP analysis confirms dominant influence of these characteristics on mortality risk

Limitations

  • ⚠Observational study design cannot establish causality between lifestyle habits and survival
  • ⚠Sleep quality was mentioned but not identified as a key feature in the final model, limiting specific sleep-related conclusions

Frequently Asked Questions

What lifestyle factors were most important for predicting breast cancer survival?▼

Age, BMI, smoking status, and treatment pill intake were identified as critical characteristics influencing survival.

How well did the machine learning model predict survival?▼

The XGBoost model achieved AUCs of 0.748 at 3 years, 0.749 at 6 years, and 0.765 at 9 years, indicating moderate predictive performance.

Was sleep quality a significant predictor in this study?▼

Sleep quality was included in the analysis but was not among the top features selected; age, BMI, smoking, and treatment pill intake were the key predictors.

What population was studied?▼

The study analyzed 21,219 female breast cancer patients from the UK Biobank, a large-scale population-based cohort.

Products

Affiliate links coming soon. We only recommend products that match the doses and forms used in the cited research.

References

  1. 1.Yao Y, Zhai X, Liang Z, Lam CK, Xie H, Tong HHY, Tong T, Chen Y, Mann RM, He M, Li K, Tan T. "Interpretable machine-learning survival prediction of breast cancer prognosis from lifestyle factors: evidence from UK biobank.." Breast cancer (Tokyo, Japan), 2026. PMID: 42467394 DOI: 10.1007/s12282-026-01893-w
Disclaimer: This content is for educational purposes only and is not medical advice. Evidence scores reflect the quality and quantity of available research, not clinical recommendations. Always consult a healthcare professional before starting any supplement or intervention.