Explainable machine learning framework to predict personalized physiological aging.

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.

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

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 applications, where each medical condition may have its own preferences, this framework will make it possible to offer the healthcare professional the appropriate FS technique, to select the variables that have an important explainable impact, even if this comes at the expense of a limited drop of accuracy.

Local Explanation-Based Method for Healthcare Risk Stratification.

Decision support tools in healthcare require a strong confidence in the developed Machine Learning (ML) models both in terms of performances and in their ability to provide users a deeper understanding of the underlying situation. This study presents a novel method to construct a risk stratification based on ML and local explanations. An open-source dataset was used to demonstrate the efficiency of this method that well identified the main subgroups of patients. Therefore, this method could help practitioners adjust and build protocols to improve care deliveries that would better reflect patient's risk level and profile.

Systemic Periodontal Risk Score Using an Innovative Machine Learning Strategy: An Observational Study.

Early diagnosis is crucial for individuals who are susceptible to tooth-supporting tissue diseases (e.g., periodontitis) that may lead to tooth loss, so as to prevent systemic implications and maintain quality of life. The aim of this study was to propose a personalized explainable machine learning algorithm, solely based on non-invasive predictors that can easily be collected in a clinic, to identify subjects at risk of developing periodontal diseases. To this end, the individual data and periodontal health of 532 subjects was assessed. A machine learning pipeline combining a feature selection step, multilayer perceptron, and SHapley Additive exPlanations (SHAP) explainability, was used to build the algorithm. The prediction scores for healthy periodontium and periodontitis gave final F1-scores of 0.74 and 0.68, respectively, while gingival inflammation was harder to predict (F1-score of 0.32). Age, body mass index, smoking habits, systemic pathologies, diet, alcohol, educational level, and hormonal status were found to be the most contributive variables for periodontal health prediction. The algorithm clearly shows different risk profiles before and after 35 years of age and suggests transition ages in the predisposition to developing gingival inflammation or periodontitis. This innovative approach to systemic periodontal disease risk profiles, combining both ML and up-to-date explainability algorithms, paves the way for new periodontal health prediction strategies.

Coalitional Strategies for Efficient Individual Prediction Explanation.

As Machine Learning (ML) is now widely applied in many domains, in both research and industry, an understanding of what is happening inside the black box is becoming a growing demand, especially by non-experts of these models. Several approaches had thus been developed to provide clear insights of a model prediction for a particular observation but at the cost of long computation time or restrictive hypothesis that does not fully take into account interaction between attributes. This paper provides methods based on the detection of relevant groups of attributes -named coalitions- influencing a prediction and compares them with the literature. Our results show that these coalitional methods are more efficient than existing ones such as SHapley Additive exPlanation (SHAP). Computation time is shortened while preserving an acceptable accuracy of individual prediction explanations. Therefore, this enables wider practical use of explanation methods to increase trust between developed ML models, end-users, and whoever impacted by any decision where these models played a role.

PRYNT: a tool for prioritization of disease candidates from proteomics data using a combination of shortest-path and random walk algorithms.

The urinary proteome is a promising pool of biomarkers of kidney disease. However, the protein changes observed in urine only partially reflect the deregulated mechanisms within kidney tissue. In order to improve on the mechanistic insight based on the urinary protein changes, we developed a new prioritization strategy called PRYNT (PRioritization bY protein NeTwork) that employs a combination of two closeness-based algorithms, shortest-path and random walk, and a contextualized protein-protein interaction (PPI) network, mainly based on clique consolidation of STRING network. To assess the performance of our approach, we evaluated both precision and specificity of PRYNT in prioritizing kidney disease candidates. Using four urinary proteome datasets, PRYNT prioritization performed better than other prioritization methods and tools available in the literature. Moreover, PRYNT performed to a similar, but complementary, extent compared to the upstream regulator analysis from the commercial Ingenuity Pathway Analysis software. In conclusion, PRYNT appears to be a valuable freely accessible tool to predict key proteins indirectly from urinary proteome data. In the future, PRYNT approach could be applied to other biofluids, molecular traits and diseases. The source code is freely available on GitHub at: https://github.com/Boizard/PRYNT and has been integrated as an interactive web apps to improved accessibility ( https://github.com/Boizard/PRYNT/tree/master/AppPRYNT ).