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.

Comparison of predictive models for cumulative live birth rate after treatment with ART.

RESEARCH QUESTION: Can a machine learning model better predict the cumulative live birth rate for a couple after intrauterine insemination or embryo transfer than Cox regression based on their personal characteristics? STUDY DESIGN: Retrospective cohort study conducted in two French infertility centres (Créteil and Tenon Hospitals) between 2012 and 2019, including 1819 and 1226 couples at Créteil and Tenon, respectively. Two models were applied: a Cox regression, which is almost exclusively used in assisted reproductive technology (ART) predictive modelling, and a tree ensemble-based model using XGBoost implementation. Internal validations were performed on each hospital dataset separately; an external validation was then carried out on the Tenon Hospital's population. RESULTS: The two populations were significantly different, with Tenon having more severe cases than Créteil, although internal validations show comparable results (C-index of 60% for both populations). As for the external validation, the XGBoost model stands out as being more stable than Cox regression, with the latter having a higher performance loss (C-index of 60% and 58%, respectively). The explicability method indicates that the XGBoost model relies strongly on features such as the ages of a couple, causes of infertility, and the woman's body mass index or infertility duration, which is consistent with the ART literature about risk factors. CONCLUSIONS: Overall performances are still relatively modest, which is coherent with all reported ART predictive models. Explicability-based methods would allow access to new knowledge, to gain a greater comprehension of which characteristics and interactions really influence a couple's journey. These models can be used by practitioners and patients to make better informed decisions about performing ART.

Analysis of COVID-19 inpatients in France during first lockdown of 2020 using explainability methods.

The COVID-19 pandemic rapidly puts a heavy pressure on hospital centers, especially on intensive care units. There was an urgent need for tools to understand typology of COVID-19 patients and identify those most at risk of aggravation during their hospital stay. Data included more than 400 patients hospitalized due to COVID-19 during the first wave in France (spring of 2020) with clinical and biological features. Machine learning and explainability methods were used to construct an aggravation risk score and analyzed feature effects. The model had a robust AUC ROC Score of 81%. Most important features were age, chest CT Severity and biological variables such as CRP, O2 Saturation and Eosinophils. Several features showed strong non-linear effects, especially for CT Severity. Interaction effects were also detected between age and gender as well as age and Eosinophils. Clustering techniques stratified inpatients in three main subgroups (low aggravation risk with no risk factor, medium risk due to their high age, and high risk mainly due to high CT Severity and abnormal biological values). This in-depth analysis determined significantly distinct typologies of inpatients, which facilitated definition of medical protocols to deliver the most appropriate cares for each profile. Graphical Abstract Graphical abstract represents main methods used and results found with a focus on feature impact on aggravation risk and identified groups of patients.

Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs.

OBJECTIVE: To assess the ability of a deep learning model to distinguish between diabetic retinopathy (DR), sickle cell retinopathy (SCR), retinal vein occlusions (RVOs) and healthy eyes using ultra-widefield colour fundus photography (UWF-CFP). METHODS AND ANALYSIS: In this retrospective study, UWF-CFP images of patients with retinal vascular disease (DR, RVO, and SCR) and healthy controls were included. The images were used to train a multilayer deep convolutional neural network to differentiate on UWF-CFP between different vascular diseases and healthy controls. A total of 224 UWF-CFP images were included, of which 169 images were of retinal vascular diseases and 55 were healthy controls. A cross-validation technique was used to ensure that every image from the dataset was tested once. Established augmentation techniques were applied to enhance performances, along with an Adam optimiser for training. The visualisation method was integrated gradient visualisation. RESULTS: The best performance of the model was obtained using 10 epochs, with an overall accuracy of 88.4%. For DR, the area under the receiver operating characteristics (ROC) curve (AUC) was 90.5% and the accuracy was 85.2%. For RVO, the AUC was 91.2% and the accuracy 88.4%. For SCR, the AUC was 96.7% and the accuracy 93.8%. For healthy controls, the ROC was 88.5% with an accuracy that reached 86.2%. CONCLUSION: Deep learning algorithms can classify several retinal vascular diseases on UWF-CPF with good accuracy. This technology may be a useful tool for telemedicine and areas with a shortage of ophthalmic care.

Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysis.

Characteristics of patients at risk of developing severe forms of COVID-19 disease have been widely described, but very few studies describe their evolution through the following waves. Data was collected retrospectively from a prospectively maintained database from a University Hospital in Paris area, over a year corresponding to the first three waves of COVID-19 in France. Evolution of patient characteristics between non-severe and severe cases through the waves was analyzed with a classical multivariate logistic regression along with a complementary Machine-Learning-based analysis using explainability methods. On 1076 hospitalized patients, severe forms concerned 29% (123/429), 31% (66/214) and 18% (79/433) of each wave. Risk factors of the first wave included old age (≥ 70 years), male gender, diabetes and obesity while cardiovascular issues appeared to be a protective factor. Influence of age, gender and comorbidities on the occurrence of severe COVID-19 was less marked in the 3rd wave compared to the first 2, and the interactions between age and comorbidities less important. Typology of hospitalized patients with severe forms evolved rapidly through the waves. This evolution may be due to the changes of hospital practices and the early vaccination campaign targeting the people at high risk such as elderly and patients with comorbidities.

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.