Healthcare Expenditure Prediction with Neighbourhood Variables – A Random Forest Model

Mohnen, Sigrid M.; Rotteveel, Adriënne H.; Doornbos, Gerda; Polder, J.J.

doi:10.1515/spp-2019-0010

Cited by 12 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the chief advantages of using ML models is their learning capacities, enabling them to capture much more complex patterns, sometimes even ascending into semantic and abstract levels, albeit requiring substantially more data points in exchange. In the particular case of decision trees, random forests and gradient boosting machines, collinearity is not a problem, which means no potentially predictive information has to be discarded, and missing values do not require any form of filling [ 58 , 59 ]. However, there is also an increased risk of identifying spurious (non-significant) associations, mainly due to issues of overfitting [ 60 ].…”

Section: Discussionmentioning

confidence: 99%

Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry

et al. 2022

View full text Add to dashboard Cite

Previous studies that assessed risk factors for venous thromboembolism (VTE) in COVID-19 patients have shown inconsistent results. Our aim was to investigate VTE predictors by both logistic regression (LR) and machine learning (ML) approaches, due to their potential complementarity. This cohort study of a large Brazilian COVID-19 Registry included 4120 COVID-19 adult patients from 16 hospitals. Symptomatic VTE was confirmed by objective imaging. LR analysis, tree-based boosting, and bagging were used to investigate the association of variables upon hospital presentation with VTE. Among 4,120 patients (55.5% men, 39.3% critical patients), VTE was confirmed in 6.7%. In multivariate LR analysis, obesity (OR 1.50, 95% CI 1.11–2.02); being an ex-smoker (OR 1.44, 95% CI 1.03–2.01); surgery ≤ 90 days (OR 2.20, 95% CI 1.14–4.23); axillary temperature (OR 1.41, 95% CI 1.22–1.63); D-dimer ≥ 4 times above the upper limit of reference value (OR 2.16, 95% CI 1.26–3.67), lactate (OR 1.10, 95% CI 1.02–1.19), C-reactive protein levels (CRP, OR 1.09, 95% CI 1.01–1.18); and neutrophil count (OR 1.04, 95% CI 1.005–1.075) were independent predictors of VTE. Atrial fibrillation, peripheral oxygen saturation/inspired oxygen fraction (SF) ratio and prophylactic use of anticoagulants were protective. Temperature at admission, SF ratio, neutrophil count, D-dimer, CRP and lactate levels were also identified as predictors by ML methods. By using ML and LR analyses, we showed that D-dimer, axillary temperature, neutrophil count, CRP and lactate levels are risk factors for VTE in COVID-19 patients. Supplementary Information The online version contains supplementary material available at 10.1007/s11739-022-03002-z.

show abstract

Section: Discussionmentioning

confidence: 99%

Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In recent work, Iwendi et al [93] used an RF model with the AdaBoost algorithm to the severity of Covid-19, death, or recovery rate for a patient. Due to their simple and self-explanatory structure, these models are also implemented for predicting the depression of Alzheimer's patients [91], healthcare monitoring systems [47], prediction of medical expenditures [98].…”

Section: Machine Learningmentioning

confidence: 99%

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

Rasheed¹,

Qayyum²,

Ghaly³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

show abstract

“…This approach has been used extensively to construct social exclusion measures within the literature, where for example Dell'Anno and Amendola (2015) used PCA to determine the weights and component loadings in an exclusion index for 28 European countries. However, the derivation of weights through PCA is considered to lack transparency (Decancq and Lugo 2013) as it may assign lower weights to a crucial indicator simply because it is weakly correlated with other indicators (Best et al 2020;Mohnen et al 2020). The process is also considered arbitrary as the decision to retain components is largely discretionary (OECD 2008).…”

Section: Social Exclusion Measures and Weighting And Aggregationmentioning

confidence: 99%

Composite Measures for Assessing Multidimensional Social Exclusion in Later Life: Conceptual and Methodological Challenges

2021

View full text Add to dashboard Cite

Although there are a number of approaches to constructing a measure of multidimensional social exclusion in later life, theoretical and methodological challenges exist around the aggregation and weighting of constituent indicators. This is in addition to a reliance on secondary data sources that were not designed to collect information on social exclusion. In this paper, we address these challenges by comparing a range of existing and novel approaches to constructing a composite measure and assess their performance in explaining social exclusion in later life. We focus on three widely used approaches (sum-of-scores with an applied threshold; principal component analysis; normalisation with linear aggregation), and three novel supervised machine-learning based approaches (least absolute shrinkage and selection operator; classification and regression tree; random forest). Using an older age social exclusion conceptual framework, these approaches are applied empirically with data from Wave 1 of The Irish Longitudinal Study on Ageing (TILDA). The performances of the approaches are assessed using variables that are causally related to social exclusion.

show abstract

Healthcare Expenditure Prediction with Neighbourhood Variables – A Random Forest Model

Cited by 12 publications

References 60 publications

Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry

Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

Composite Measures for Assessing Multidimensional Social Exclusion in Later Life: Conceptual and Methodological Challenges

Contact Info

Product

Resources

About