Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Liu, Xinyun; Jiang, Jian; Wei, Lili; Xing, Wen; Shang, Hailong; Liu, Guang-An; Liu, Feng

doi:10.1186/s12872-021-02314-w

Cited by 11 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that there are small differences between the regression models of the mlr3 implementation and the rest of the tested models. The reason the regression models perform better overall could be attributed to the fact that this model is better suited for this prediction problem (13). The Lasso Logistic Regression also performed better than Random Forest and Gradient Boosting Machines.…”

Section: Model Performancesmentioning

confidence: 97%

“…The choice of models in this study was dependent on the availability of the same models in mlr3 and PLP packages and utilized models similar to Liu et al (2021) (13) to enable utmost comparability. In particular, Liu et al utilize regularization logistic regression, random forest, and support vector machines to conduct their analyses.…”

Section: Model De Nitionmentioning

confidence: 99%

“…To benchmark the two approaches, a patient-level prediction task was needed to evaluate their performances in the entire process of creating prediction models for clinical problems. Therefore, we recreated a prediction study based on a peer-reviewed manuscript from Liu et al (2021), entitled "Prediction of all-cause mortality in coronary artery disease patients with atrial brillation based on machine learning models" (13). In brief, it investigates the relationship between patients with ischemic heart disease that suffer from atrial brillation and all-cause death.…”

Section: Cohort De Nitionmentioning

confidence: 99%

“…Similar to the manuscript from Liu et al (2021) (13), the entry event for the target cohort consists of the rst occurrence of atrial brillation for patients with ischemic heart disease. The patient records in Synpuf 5% are only available for the years 2008 to 2010 (9), thus, the time-at-risk was set to three years.…”

Section: Cohort De Nitionmentioning

confidence: 99%

“…DiscussionThe weaker performance of our models compared to the models used byLiu et al (2021) (13) can have multiple reasons. One of them could be the high dimensionality of the covariates, in other words, the large number of features used.…”

mentioning

confidence: 92%

See 4 more Smart Citations

A comparative patient-level prediction study in OMOP CDM demonstrates advantages for native and web-based implementations

Ahmadi

Nguyễn

Sedlmayr

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: The emergence of collaborations, which standardize and combine multiple clinical databases across different regions, provides a wealthy source of data, which is fundamental for clinical prediction models, such as patient-level predictions. With the aid of such large data pools, researchers are able to develop clinical prediction models for improved disease classification, risk assessment, and beyond. To fully utilize this potential, Machine Learning (ML) methods are commonly required to process these large amounts of data on disease-specific patient cohorts. As a consequence, the Observational Health Data Sciences and Informatics (OHDSI) collaborative develops a framework to facilitate the application of ML models for these standardized patient datasets by using the Observational Medical Outcomes Partnership (OMOP) common data model (CDM). Motivation: In this study, we compare the feasibility of current web-based OHDSI approaches, namely ATLAS and “Patient-level Prediction” (PLP), against a native solution (R based) to conduct such ML-based patient-level prediction analyses in OMOP. This will enable potential users to select the most suitable approach for their investigation. Methods: Each of the applied ML solutions was individually utilized to solve the same patient-level prediction task. Both approaches went through an exemplary benchmarking analysis to assess the weaknesses and strengths of the PLP R-Package. In this work, the performance of this package was subsequently compared versus the commonly used native R-package called Machine Learning in R 3 (mlr3), and its sub-packages. The approaches were evaluated on performance, execution time, availability of tools for handling imbalanced datasets, and ease of model implementation. Results: The results show that the PLP package has shorter execution times, which indicates great scalability, as well as intuitive code implementation, and numerous possibilities for visualization. However, limitations in comparison to native packages were depicted in the implementation of specific ML classifiers (e.g., Lasso), which may result in a decreased performance for real-world prediction problems. Conclusion: The ﬁndings here contribute to the overall effort of developing ML-based prediction models on a clinical scale and provide a snapshot for future studies that explicitly aim to develop patient-level prediction models in OMOP CDM.

show abstract

Section: Model Performancesmentioning

confidence: 97%

Section: Model De Nitionmentioning

confidence: 99%

Section: Cohort De Nitionmentioning

confidence: 99%

Section: Cohort De Nitionmentioning

confidence: 99%

mentioning

confidence: 92%

See 3 more Smart Citations

A comparative patient-level prediction study in OMOP CDM demonstrates advantages for native and web-based implementations

Ahmadi

Nguyễn

Sedlmayr

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

A machine learning-based predictive model for the in-hospital mortality of critically ill patients with atrial fibrillation

Luo,

Dong,

Liu

et al. 2024

International Journal of Medical Informatics

View full text Add to dashboard Cite

A comparative patient-level prediction study in OMOP CDM: applicative potential and insights from synthetic data

Ahmadi,

Nguyen,

Sedlmayr

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The emergence of collaborations, which standardize and combine multiple clinical databases across different regions, provide a wealthy source of data, which is fundamental for clinical prediction models, such as patient-level predictions. With the aid of such large data pools, researchers are able to develop clinical prediction models for improved disease classification, risk assessment, and beyond. To fully utilize this potential, Machine Learning (ML) methods are commonly required to process these large amounts of data on disease-specific patient cohorts. As a consequence, the Observational Health Data Sciences and Informatics (OHDSI) collaborative develops a framework to facilitate the application of ML models for these standardized patient datasets by using the Observational Medical Outcomes Partnership (OMOP) common data model (CDM). In this study, we compare the feasibility of current web-based OHDSI approaches, namely ATLAS and “Patient-level Prediction” (PLP), against a native solution (R based) to conduct such ML-based patient-level prediction analyses in OMOP. This will enable potential users to select the most suitable approach for their investigation. Each of the applied ML solutions was individually utilized to solve the same patient-level prediction task. Both approaches went through an exemplary benchmarking analysis to assess the weaknesses and strengths of the PLP R-Package. In this work, the performance of this package was subsequently compared versus the commonly used native R-package called Machine Learning in R 3 (mlr3), and its sub-packages. The approaches were evaluated on performance, execution time, and ease of model implementation. The results show that the PLP package has shorter execution times, which indicates great scalability, as well as intuitive code implementation, and numerous possibilities for visualization. However, limitations in comparison to native packages were depicted in the implementation of specific ML classifiers (e.g., Lasso), which may result in a decreased performance for real-world prediction problems. The findings here contribute to the overall effort of developing ML-based prediction models on a clinical scale and provide a snapshot for future studies that explicitly aim to develop patient-level prediction models in OMOP CDM.

show abstract

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Cited by 11 publications

References 22 publications

A comparative patient-level prediction study in OMOP CDM demonstrates advantages for native and web-based implementations

A comparative patient-level prediction study in OMOP CDM demonstrates advantages for native and web-based implementations

A machine learning-based predictive model for the in-hospital mortality of critically ill patients with atrial fibrillation

A comparative patient-level prediction study in OMOP CDM: applicative potential and insights from synthetic data

Contact Info

Product

Resources

About