A locally optimised machine learning approach to early prognostication of long-term neurological outcomes after out-of-hospital cardiac arrest.

Background: Out-of-hospital cardiac arrest (OHCA) represents a major burden for society and health care, with an average incidence in adults of 67 to 170 cases per 100,000 person-years in Europe and in-hospital survival rates of less than 10%. Patients and practitioners would benefit from a prognostication tool for long-term good neurological outcomes. Objective: We aim to develop a machine learning (ML) pipeline on a local database to classify patients according to their neurological outcomes and identify prognostic features. Methods: We collected clinical and biological data consecutively from 595 patients who presented OHCA and were routed to a single regional cardiac arrest centre in the south of France. We applied recursive feature elimination and ML analyses to identify the main features associated with a good neurological outcome, defined as a Cerebral Performance Category score less than or equal to 2 at six months post-OHCA. Results: We identified 12 variables 24 h after admission, capable of predicting a six-month good neurological outcome. The best model (extreme gradient boosting) achieved an AUC of 0.96 and an accuracy of 0.92 in the test cohort. Conclusion: We demonstrated that it is possible to build accurate, locally optimised prediction and prognostication scores using datasets of limited size and breadth. We proposed and shared a generic machine-learning pipeline which allows external teams to replicate the approach locally.

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.

Perioperative Risk Assessment of Patients Using the MyRISK Digital Score Completed Before the Preanesthetic Consultation: Prospective Observational Study.

BACKGROUND: The ongoing COVID-19 pandemic has highlighted the potential of digital health solutions to adapt the organization of care in a crisis context. OBJECTIVE: Our aim was to describe the relationship between the MyRISK score, derived from self-reported data collected by a chatbot before the preanesthetic consultation, and the occurrence of postoperative complications. METHODS: This was a single-center prospective observational study that included 401 patients. The 16 items composing the MyRISK score were selected using the Delphi method. An algorithm was used to stratify patients with low (green), intermediate (orange), and high (red) risk. The primary end point concerned postoperative complications occurring in the first 6 months after surgery (composite criterion), collected by telephone and by consulting the electronic medical database. A logistic regression analysis was carried out to identify the explanatory variables associated with the complications. A machine learning model was trained to predict the MyRISK score using a larger data set of 1823 patients classified as green or red to reclassify individuals classified as orange as either modified green or modified red. User satisfaction and usability were assessed. RESULTS: Of the 389 patients analyzed for the primary end point, 16 (4.1%) experienced a postoperative complication. A red score was independently associated with postoperative complications (odds ratio 5.9, 95% CI 1.5-22.3; P=.009). A modified red score was strongly correlated with postoperative complications (odds ratio 21.8, 95% CI 2.8-171.5; P=.003) and predicted postoperative complications with high sensitivity (94%) and high negative predictive value (99%) but with low specificity (49%) and very low positive predictive value (7%; area under the receiver operating characteristic curve=0.71). Patient satisfaction numeric rating scale and system usability scale median scores were 8.0 (IQR 7.0-9.0) out of 10 and 90.0 (IQR 82.5-95.0) out of 100, respectively. CONCLUSIONS: The MyRISK digital perioperative risk score established before the preanesthetic consultation was independently associated with the occurrence of postoperative complications. Its negative predictive strength was increased using a machine learning model to reclassify patients identified as being at intermediate risk. This reliable numerical categorization could be used to objectively refer patients with low risk to teleconsultation.

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.