Predictive and interpretable models via the stacked elastic net

Rauschenberger, Armin; Glaab, Enrico; Wiel, Mark A. van de

doi:10.1093/bioinformatics/btaa535

Cited by 14 publications

(9 citation statements)

References 14 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Elastic net was used for classification task, which was preferred due to its ability to address collinearity and to work successfully with high-dimensional but small datasets (Zou and Hastie, 2005; Rauschenberger et al , 2021). Furthermore, it performs feature selection and deals with grouping effects, thereby rendering classifiers more easily interpretable (Liu et al , 2016).…”

Section: Experiments and Resultsmentioning

confidence: 99%

Quality assessment of web-based information on type 2 diabetes

Ölçer

Temizel

2021

OIR

View full text Add to dashboard Cite

PurposeThis paper proposes a framework that automatically assesses content coverage and information quality of health websites for end-users.Design/methodology/approachThe study investigates the impact of textual and content-based features in predicting the quality of health-related texts. Content-based features were acquired using an evidence-based practice guideline in diabetes. A set of textual features inspired by professional health literacy guidelines and the features commonly used for assessing information quality in other domains were also used. In this study, 60 websites about type 2 diabetes were methodically selected for inclusion. Two general practitioners used DISCERN to assess each website in terms of its content coverage and quality.FindingsThe proposed framework outputs were compared with the experts' evaluation scores. The best accuracy was obtained as 88 and 92% with textual features and content-based features for coverage assessment respectively. When both types of features were used, the proposed framework achieved 90% accuracy. For information quality assessment, the content-based features resulted in a higher accuracy of 92% against 88% obtained using the textual features.Research limitations/implicationsThe experiments were conducted for websites about type 2 diabetes. As the whole process is costly and requires extensive expert human labelling, the study was carried out in a single domain. However, the methodology is generalizable to other health domains for which evidence-based practice guidelines are available.Practical implicationsFinding high-quality online health information is becoming increasingly difficult due to the high volume of information generated by non-experts in the area. The search engines fail to rank objective health websites higher within the search results. The proposed framework can aid search engine and information platform developers to implement better retrieval techniques, in turn, facilitating end-users' access to high-quality health information.Social implicationsErroneous, biased or partial health information is a serious problem for end-users who need access to objective information on their health problems. Such information may cause patients to stop their treatments provided by professionals. It might also have adverse financial implications by causing unnecessary expenditures on ineffective treatments. The ability to access high-quality health information has a positive effect on the health of both individuals and the whole society.Originality/valueThe paper demonstrates that automatic assessment of health websites is a domain-specific problem, which cannot be addressed with the general information quality assessment methodologies in the literature. Content coverage of health websites has also been studied in the health domain for the first time in the literature.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Quality assessment of web-based information on type 2 diabetes

Ölçer

Temizel

2021

OIR

View full text Add to dashboard Cite

show abstract

“…In high-dimensional problems such as PRS which involve a large number of SNPs, the best tuning parameters may be in the gaps or outside the bounds of the fixed grid being considered 23 . Recent works, in both theory and PRS applications, have demonstrated that ensembling multiple predictors can yield better prediction accuracy than choosing a single best predictor from grid search [24][25][26][27][28][29][30] .…”

Section: Mainmentioning

confidence: 99%

“…26, 2023, and have missing baseline measurements for age, sex, and the first ten PCs, and further restricting to unrelated samples so that no pair has relationship closer than fourth degree93 , we have a total of 318,052 samples for analysis. 40,000 samples were randomly chosen for tuning and validation -with 20,000 samples in each split.…”

mentioning

confidence: 99%

Ensembled best subset selection using summary statistics for polygenic risk prediction

Chen,

Zhang,

Mazumder

et al. 2023

Preprint

View full text Add to dashboard Cite

Polygenic risk scores (PRS) enhance population risk stratification and advance personalized medicine, yet existing methods face a tradeoff between predictive power and computational efficiency. We introduce ALL-Sum, a fast and scalable PRS method that combines an efficient summary statistic-based L0L2penalized regression algorithm with an ensembling step that aggregates estimates from different tuning parameters for improved prediction performance. In extensive large-scale simulations across a wide range of polygenicity and genome-wide association studies (GWAS) sample sizes, ALL-Sum consistently outperforms popular alternative methods in terms of prediction accuracy, runtime, and memory usage. We analyze 27 published GWAS summary statistics for 11 complex traits from 9 reputable data sources, including the Global Lipids Genetics Consortium, Breast Cancer Association Consortium, and FinnGen, evaluated using individual-level UKBB data. ALL-Sum achieves the highest accuracy for most traits, particularly for GWAS with large sample sizes. We provide ALL-Sum as a user-friendly command-line software with pre-computed reference data for streamlined user-end analysis.

show abstract

“…Moreover, if cross-validation is applied for both hyperparameter optimization and performance estimation (see Tip 7 ), a nested cross-validation scheme is required, i.e., while an outer cross-validation loop is used for performance estimation, an inner cross-validation loop is used for hyperparameter optimization. An alternative to selecting single hyperparameters by cross-validation is to combine multiple hyperparameters by stacked generalization [ 37 , 95 , 96 ]. Furthermore, predictive models avoiding explicit hyperparameter optimization may be chosen, e.g., random forests [ 97 – 99 ].…”

Section: Tip 6: Optimize Model Parameters and Feature Selection Witho...mentioning

confidence: 99%