Body Mass Index and Birth Weight Improve Polygenic Risk Score for Type 2 Diabetes

Moldovan, Avigail; Waldman, Yedael Y.; Brandes, Nadav; Linial, Michal

doi:10.3390/jpm11060582

Cited by 13 publications

(12 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our machine learning framework, the variants slightly contributed to the discriminatory value ( Figure 5 B). It emphasized the benefit of including not only genetic signals, but also orthogonal medical and environmental data into a single model, as exemplified for Type 2 diabetes (T2D) [ 59 ]).…”

Section: Discussionmentioning

confidence: 99%

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Blass

Sahar

Shraibman

et al. 2022

JPM

Self Cite

View full text Add to dashboard Cite

Endometriosis is a condition characterized by implants of endometrial tissues into extrauterine sites, mostly within the pelvic peritoneum. The prevalence of endometriosis is under-diagnosed and is estimated to account for 5–10% of all women of reproductive age. The goal of this study was to develop a model for endometriosis based on the UK-biobank (UKB) and re-assess the contribution of known risk factors to endometriosis. We partitioned the data into those diagnosed with endometriosis (5924; ICD-10: N80) and a control group (142,723). We included over 1000 variables from the UKB covering personal information about female health, lifestyle, self-reported data, genetic variants, and medical history prior to endometriosis diagnosis. We applied machine learning algorithms to train an endometriosis prediction model. The optimal prediction was achieved with the gradient boosting algorithms of CatBoost for the data-combined model with an area under the ROC curve (ROC-AUC) of 0.81. The same results were obtained for women from a mixed ethnicity population of the UKB (7112; ICD-10: N80). We discovered that, prior to being diagnosed with endometriosis, affected women had significantly more ICD-10 diagnoses than the average unaffected woman. We used SHAP, an explainable AI tool, to estimate the marginal impact of a feature, given all other features. The informative features ranked by SHAP values included irritable bowel syndrome (IBS) and the length of the menstrual cycle. We conclude that the rich population-based retrospective data from the UKB are valuable for developing unified machine learning endometriosis models despite the limitations of missing data, noisy medical input, and participant age. The informative features of the model may improve clinical utility for endometriosis diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Blass

Sahar

Shraibman

et al. 2022

JPM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other, non-genetic risk factors, such as age, sex, smoking status, parental disease status, physical activity and body mass index (BMI), which already form part of most clinical risk prediction models, have proven more effective at identifying individuals at high risk [19][20][21] . Therefore, combining both genetic and non-genetic factors should lead to improved risk prediction, as previously suggested in a study that showed a T2D prediction model including BMI and PGS outperforms models including only either one of these predictors 22 . Furthermore, additional inclusion of a number of biomarkers further increased its discriminative power 23,24 .…”

Section: Genetic Health Risk Limitationsmentioning

confidence: 85%

The necessity of incorporating non-genetic risk factors into polygenic risk score models

Dam

Folkertsma

Forte³

et al. 2022

Preprint

View full text Add to dashboard Cite

The growing public interest in genetic risk scores for various health conditions may inspire preventive health action. However, these risk scores can be deceiving as they do not consider other, easily attainable risk factors, such as sex, BMI, age, smoking habits, parental disease status and physical activity. We show improved performance in identifying the 10% most at-risk individuals for type 2 diabetes (T2D) and coronary artery disease (CAD) by including these common risk factors. Incidence in the highest risk group increases from 3.2- and 4.2-fold to 5.8 for T2D, when comparing the genetics-based model, common risk factor-based model and combined model, respectively. Similarly, we see an increase from 2.9- and 2.4-fold to 5.0-fold risk for CAD. Importantly, we show that genetic and common risk factors capture different risks. As such, it is paramount that all these variables are considered when reporting risk, unlike current practice with available genetic tests.

show abstract

“…In our machine learning framework, the variants slightly contributed to the discriminatory value (Figure 6B ). It emphasizes the benefit of including genetic variants with orthogonal medical and environmental data into a single model, as exemplified for Type 2 diabetes (T2D) [53]).…”

Section: Discussionmentioning

confidence: 99%

Unified Predictive Model for Endometriosis: Merging Clinical, Self-reporting and Genetic Information

Blass

Sahar

Shraibman

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Endometriosis is a condition characterized by implants of endometrial tissues into extrauterine sites, mostly within the pelvic peritoneum. The prevalence of endometriosis is under-diagnosed, and estimated to account for 5-10% of all women of reproductive age. The goal of this study is to develop a model for endometriosis based on the UK-biobank (UKBB). We partitioned the data into those diagnosed with endometriosis (5,924, ICD-10 N80) and a control group (142,576). We included over 1000 variables from UKBB covering personal information about female health, lifestyle, self-reported data, genetic variants, and medical history prior to endometriosis diagnosis. We applied machine learning algorithms to train an endometriosis prediction model. The optimal prediction was achieved with the gradient boosting algorithms of CatBoost for the data-combined model, with an area under the ROC curve (roc-AUC) of 0.78. We discovered that, prior to being diagnosed with endometriosis, women had significantly more ICD-10 diagnoses than the average unaffected woman. Informative features, ranked by SHAP values included irritable bowel syndrome (IBS) and the length of the menstrual cycle. We conclude that the rich population-based retrospective data from the UKBB is valuable for developing predictive models despite the limitations of missing data and noisy medical input. The informative features of the model may improve clinical utility for endometriosis diagnosis.

show abstract

Body Mass Index and Birth Weight Improve Polygenic Risk Score for Type 2 Diabetes

Cited by 13 publications

References 60 publications

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

The necessity of incorporating non-genetic risk factors into polygenic risk score models

Unified Predictive Model for Endometriosis: Merging Clinical, Self-reporting and Genetic Information

Contact Info

Product

Resources

About