A Post-Hoc Interpretable Ensemble Model to Feature Effect Analysis in Warfarin Dose Prediction for Chinese Patients

Zhang, Yuzhen; Xie, Cheng; Xue, Liang; Tao, Yanyun; Yue, Guoqi; Bin, Jiang

doi:10.1109/jbhi.2021.3092170

Cited by 3 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In brief, the Shapley theory originating from the coalitional game assumes that each variable plays a role in one game and the influence of variable on final outcome is measured. ,, In this study, the SHAP theory was used with variables serving as molecular descriptors and final outcome serving as environmental impacts, respectively. Shapley values not only indicate the importance of features and identify the features that exert greater influence on the models but also demonstrate the correlation between molecular descriptors and predicted results. ,, The more positive or negative the Shapley values are, the larger positive or negative influence of the descriptor to environmental impacts, and vice versa.…”

Section: Resultsmentioning

confidence: 98%

“…Such an issue is expected to be addressed by an increase in the size of the commercial database as the models continue to be updated and improved in the future as more data become available. Third, the models are interpreted by posthoc analysis where different feature combinations are employed to validate performances of models. , A challenge remains with respect to interpretation of the way the molecular descriptors affect the output values, since their physicochemical meanings are unlikely to be readily interpretable. Future effort is motivated by the needed to search for descriptors that are better understood and interpreted.…”

Section: Resultsmentioning

confidence: 99%

“…Machine learning models should seek for both predicting accuracy and mechanistic interpretation. , Therefore, it is also crucial to highlight the importance of molecular descriptors and their comprehension. The state-of-the-art SHAP method for interpretation was introduced by calculating Shapley values to quantify the contributions of input features.…”

Section: Resultsmentioning

confidence: 99%

“…Shapley values not only indicate the importance of features and identify the features that exert greater influence on the models but also demonstrate the correlation between molecular descriptors and predicted results. 59,61,62 The more positive or negative the Shapley values are, the larger positive or negative influence of the descriptor to environmental impacts, and vice versa.…”

Section: Model Interpretationmentioning

confidence: 99%

See 3 more Smart Citations

Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals

Sun

Wang

Ren

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

Machine learning (ML) provides an efficient manner for rapid prediction of the life-cycle environmental impacts of chemicals, but challenges remain due to low prediction accuracy and poor interpretability of the models. To address these issues, we focused on data processing by using a mutual information-permutation importance (MI-PI) feature selection method to filter out irrelevant molecular descriptors from the input data, which improved the model interpretability by preserving the physicochemical meanings of original molecular descriptors without generation of new variables. We also applied a weighted Euclidean distance method to mine the data most relevant to the predicted targets by quantifying the contribution of each feature, thereby the prediction accuracy was improved. On the basis of above data processing, we developed artificial neural network (ANN) models for predicting the life-cycle environmental impacts of chemicals with R 2 values of 0.81, 0.81, 0.84, 0.75, 0.73, and 0.86 for global warming, human health, metal depletion, freshwater ecotoxicity, particulate matter formation, and terrestrial acidification, respectively. The ML models were interpreted using the Shapley additive explanation method by quantifying the contribution of each input molecular descriptor to environmental impact categories. This work suggests that the combination of feature selection by MI-PI and source data selection based on weighted Euclidean distance has a promising potential to improve the accuracy and interpretability of the models for predicting the life-cycle environmental impacts of chemicals.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Model Interpretationmentioning

confidence: 99%

See 2 more Smart Citations

Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals

Sun

Wang

Ren

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…It was found that recent papers can be classified into three types of databases, namely clinical [13], [18], [27], [33], registry [10], [12], [20], [24], [25], [29], [34], and knowledge [14], [15], [16], [17], [19], [21], [22], [23], [26], [28], [30], [31], [32], [35]. Additionally, based on review papers of existing XAI models [48], [49], the XAI algorithms used were divided into the following four categories: surrogate The main advantage of an explanatory technique such as SHAP is that it has solid roots in game theory, which ensures that the explanation of a prediction instance is fairly distributed across the features.…”

Section: ) Xai Methodsmentioning

confidence: 99%

Explainable Artificial Intelligence for Patient Safety: A Review of Application in Pharmacovigilance

et al. 2023

View full text Add to dashboard Cite

Explainable AI (XAI) is a methodology that complements the black box of artificial intelligence, and its necessity has recently been highlighted in various fields. The purpose of this research is to identify studies in the field of pharmacovigilance using XAI. Though there have been many previous attempts to select papers, with a total of 781 papers being confirmed, only 25 of them manually met the selection criteria. This study presents an intuitive review of the potential of XAI technologies in the field of pharmacovigilance. In the included studies, clinical data, registry data, and knowledge data were used to investigate drug treatment, side effects, and interaction studies based on tree models, neural network models, and graph models. Finally, key challenges for several research issues for the use of XAI in pharmacovigilance were identified. Although artificial intelligence (AI) is actively used in drug surveillance and patient safety, gathering adverse drug reaction information, extracting drug-drug interactions, and predicting effects, XAI is not normally utilized. Therefore, the potential challenges involved in its use alongside future prospects should be continuously discussed.

show abstract

Optimal 18F-FDG PET/CT radiomics model development for predicting EGFR mutation status and prognosis in lung adenocarcinoma: a multicentric study

Zuo

Liu

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

PurposeTo develop and interpret optimal predictive models to identify epidermal growth factor receptor (EGFR) mutation status and subtypes in patients with lung adenocarcinoma based on multicentric 18F-FDG PET/CT data, and further construct a prognostic model to predict their clinical outcome.MethodsThe 18F-FDG PET/CT imaging and clinical characters of 767 patients with lung adenocarcinoma from 4 cohorts were collected. Seventy-six radiomics candidates using cross-combination method to identity EGFR mutation status and subtypes were built. Further, Shapley additive explanations and local interpretable model-agnostic explanations were used for optimal models’ interpretation. Moreover, in order to predict the overall survival, a multivariate Cox proportional hazard model based on handcrafted radiomics features and clinical characteristics was constructed. The predictive performance and clinical net benefit of the models were evaluated via area under receiver operating characteristic (AUC), C-index and decision curve analysis. ResultsAmong the 76 radiomics candidates, light gradient boosting machine classifier (LGBM) combined with recursive feature elimination wrapped LGBM feature selection method achieved best performance in predicting EGFR mutation status (AUC reached 0.80, 0.61, 0.71 in the internal test cohort and two external test cohorts, respectively). And extreme gradient boosting classifier combined with support vector machine feature selection method achieved best performance in predicting EGFR subtypes (AUC reached 0.76, 0.63, 0.61 in the internal test cohort and two external test cohorts, respectively). The C-index of the Cox proportional hazard model achieved 0.863.ConclusionsThe integration of cross-combination method and the external validation from multi-center data achieved a good prediction and generalization performance in predicting EGFR mutation status and its subtypes. The combination of handcrafted radiomics features and clinical factors achieved good performance in predicting prognosis. With the urgent needs of multicentric 18F-FDG PET/CT trails, robust and explainable radiomics models have great potential in decision making and prognosis prediction of lung adenocarcinoma.

show abstract

A Post-Hoc Interpretable Ensemble Model to Feature Effect Analysis in Warfarin Dose Prediction for Chinese Patients

Cited by 3 publications

References 37 publications

Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals

Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals

Explainable Artificial Intelligence for Patient Safety: A Review of Application in Pharmacovigilance

Optimal 18F-FDG PET/CT radiomics model development for predicting EGFR mutation status and prognosis in lung adenocarcinoma: a multicentric study

Contact Info

Product

Resources

About