A quantitative approach for the comparison of additive local explanation methods

Doumard, Emmanuel; Aligon, Julien; Escriva, Elodie; Excoffier, Jean-Baptiste; Monsarrat, Paul; Soulé-Dupuy, Chantal

doi:10.1016/j.is.2022.102162

Cited by 12 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing R 2 and MAE on test dataset, XGBoost and MLP performed the best, with similar performances and the lowest standard deviations during cross‐validation for XGBoost (Figure 2a,b ; Figure S6 ). Given the high number of variables (high dimensionality) and number of subjects in the database, XGBoost was selected for its abilities to efficiently compute explanations (Doumard et al, 2023 ). The differential error of the model by age, predicting young individuals being older, or the opposite, was greatly minimized using the custom objective function during XGBoost training (Figure 2b ), with no significant impact on the global performance (0.72 and 8.1 on the test dataset for R 2 and MAE, respectively, Figure 2B ).…”

Section: Resultsmentioning

confidence: 99%

“…To define the contribution of each variable in individual PPA prediction, the Shapley Additive exPlanations (SHAP) Tree framework was applied on the XGBoost model with Custom Loss model (Doumard et al, 2023 ). The SHAP value integrates both the effect per se of a given biological variable and the effects of this variable in interaction with other biological parameters.…”

Section: Resultsmentioning

confidence: 99%

“…For PPA explainability, we used state‐of‐the‐art explainable techniques, such as the SHAP algorithm, to compute local explanations at the individual level. This integrates the effects of the biological variable per se, but also the effects of interactions between variables (Doumard et al, 2023 ). Compared to other indexes, PPA performs better to capture socio‐demographic disparities and medical conditions than KDM or homeostatic dysregulation (HD), and better capture mortality than KDM.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Explainable machine learning framework to predict personalized physiological aging

et al. 2023

Self Cite

View full text Add to dashboard Cite

Attaining personalized healthy aging requires accurate monitoring of physiological changes and identifying subclinical markers that predict accelerated or delayed aging. Classic biostatistical methods most rely on supervised variables to estimate physiological aging and do not capture the full complexity of inter‐parameter interactions. Machine learning (ML) is promising, but its black box nature eludes direct understanding, substantially limiting physician confidence and clinical usage. Using a broad population dataset from the National Health and Nutrition Examination Survey (NHANES) study including routine biological variables and after selection of XGBoost as the most appropriate algorithm, we created an innovative explainable ML framework to determine a Personalized physiological age (PPA). PPA predicted both chronic disease and mortality independently of chronological age. Twenty‐six variables were sufficient to predict PPA. Using SHapley Additive exPlanations (SHAP), we implemented a precise quantitative associated metric for each variable explaining physiological (i.e., accelerated or delayed) deviations from age‐specific normative data. Among the variables, glycated hemoglobin (HbA1c) displays a major relative weight in the estimation of PPA. Finally, clustering profiles of identical contextualized explanations reveal different aging trajectories opening opportunities to specific clinical follow‐up. These data show that PPA is a robust, quantitative and explainable ML‐based metric that monitors personalized health status. Our approach also provides a complete framework applicable to different datasets or variables, allowing precision physiological age estimation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable machine learning framework to predict personalized physiological aging

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each of them sheds light on a different aspect of the AI model’s computation and many times it has been shown that there is no mutual consent between them, leading to the so-called ‘disagreement’ problem ( Krishna et al., 2022 ). Currently, quality metrics for xAI methods ( Doumard et al., 2023 ; Schwalbe and Finzel, 2023 ) and benchmarks for its evaluation are being defined ( Agarwal et al., 2023 ) to motivate xAI research in directions that support trustworthy, reliable, actionable and causal explanations even if they don’t always align with human pre-conceived notions and expectations ( Holzinger et al., 2019 ; Magister et al., 2021 ; Finzel et al., 2022 ; Saranti et al., 2022 ; Cabitza et al., 2023 ; Holzinger et al., 2023c ).…”

Section: Accelerating Plant Breeding Processes With Explainable Aimentioning

confidence: 99%

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

Chang-Brahim,

Koppensteiner,

Beltrame

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Marker-assisted selection (MAS) plays a crucial role in crop breeding improving the speed and precision of conventional breeding programmes by quickly and reliably identifying and selecting plants with desired traits. However, the efficacy of MAS depends on several prerequisites, with precise phenotyping being a key aspect of any plant breeding programme. Recent advancements in high-throughput remote phenotyping, facilitated by unmanned aerial vehicles coupled to machine learning, offer a non-destructive and efficient alternative to traditional, time-consuming, and labour-intensive methods. Furthermore, MAS relies on knowledge of marker-trait associations, commonly obtained through genome-wide association studies (GWAS), to understand complex traits such as drought tolerance, including yield components and phenology. However, GWAS has limitations that artificial intelligence (AI) has been shown to partially overcome. Additionally, AI and its explainable variants, which ensure transparency and interpretability, are increasingly being used as recognised problem-solving tools throughout the breeding process. Given these rapid technological advancements, this review provides an overview of state-of-the-art methods and processes underlying each MAS, from phenotyping, genotyping and association analyses to the integration of explainable AI along the entire workflow. In this context, we specifically address the challenges and importance of breeding winter wheat for greater drought tolerance with stable yields, as regional droughts during critical developmental stages pose a threat to winter wheat production. Finally, we explore the transition from scientific progress to practical implementation and discuss ways to bridge the gap between cutting-edge developments and breeders, expediting MAS-based winter wheat breeding for drought tolerance.

show abstract

“…As an additive method, it assigns an influence value to each feature of each instance, which represents its contribution to the prediction. Moreover, an advantage of LIME over other additive methods such as KernelSHAP and coalitional-based methods is less computational complexity when the number of features increases [74], which is critical for the feasibility of this study.…”

Section: A Experimental Workflowmentioning

confidence: 99%

Explanations as a New Metric for Feature Selection: A Systematic Approach

Wang

Doumard

Soulé-Dupuy

et al. 2023

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

With the extensive use of Machine Learning (ML) in the biomedical field, there was an increasing need for Explainable Artificial Intelligence (XAI) to improve transparency and reveal complex hidden relationships between variables for medical practitioners, while meeting regulatory requirements. Feature Selection (FS) is widely used as a part of a biomedical ML pipeline to significantly reduce the number of variables while preserving as much information as possible. However, the choice of FS methods affects the entire pipeline including the final prediction explanations, whereas very few works investigate the relationship between FS and model explanations. Through a systematic workflow performed on 145 datasets and an illustration on medical data, the present work demonstrated the promising complementarity of two metrics based on explanations (using ranking and influence changes) in addition to accuracy and retention rate to select the most appropriate FS/ML models. Measuring how much explanations differ with/without FS are particularly promising for FS methods recommendation. While reliefF generally performs the best on average, the optimal choice may vary for each dataset. Positioning FS methods in a tridimensional space, integrating explanations-based metrics, accuracy and retention rate, would allow the user to choose the priorities to be given on each of the dimensions. In biomedical applica-

show abstract

A quantitative approach for the comparison of additive local explanation methods

Cited by 12 publications

References 29 publications

Explainable machine learning framework to predict personalized physiological aging

Explainable machine learning framework to predict personalized physiological aging

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

Explanations as a New Metric for Feature Selection: A Systematic Approach

Contact Info

Product

Resources

About