Evaluation of post-hoc interpretability methods in time-series classification

Post-hoc interpretability methods are critical tools to explain neural-network results. Several post-hoc methods have emerged in recent years but they produce different results when applied to a given task, raising the question of which method is the most suitable to provide accurate post-hoc interpretability. To understand the performance of each method, quantitative evaluation of interpretability methods is essential; however, currently available frameworks have several drawbacks that hinder the adoption of post-hoc interpretability methods, especially in high-risk sectors. In this work we propose a framework with quantitative metrics to assess the performance of existing post-hoc interpretability methods, particularly in time-series classification. We show that several drawbacks identified in the literature are addressed, namely, the dependence on human judgement, retraining and the shift in the data distribution when occluding samples. We also design a synthetic dataset with known discriminative features and tunable complexity. The proposed methodology and quantitative metrics can be used to understand the reliability of interpretability methods results obtained in practical applications. In turn, they can be embedded within operational workflows in critical fields that require accurate interpretability results for, for example, regulatory policies.

Performance of Machine Learning Methods to Classify French Medical Publications

Many medical narratives are read by care professionals in their preferred language. These documents can be produced by organizations, authorities or national publishers. However, they are often hardly findable using the usual query engines based on English such as PubMed. This work explores the possibility to automatically categorize medical documents in French following an automatic Natural Language Processing pipeline. The pipeline is used to compare the performance of 6 different machine learning and deep neural network approaches on a large dataset of peer-reviewed weekly published Swiss medical journal in French covering major topics in medicine over the last 15 years. An accuracy of 96% was achieved for 5-topic classification and 81% for 20-topic classification.

Classification of Oncology Treatment Responses from French Radiology Reports with Supervised Machine Learning

The present study shows first attempts to automatically classify oncology treatment responses on the basis of the textual conclusion sections of radiology reports according to the RECIST classification. After a robust and extended manual annotation of 543 conclusion sections (5-to-50-word long), and after the training of several machine learning techniques (from traditional machine learning to deep learning), the best results show an accuracy score of 0.90 for a two-class classification (non-progressive vs. progressive disease) and of 0.82 for a four-class classification (complete response, partial response, stable disease, progressive disease) both with Logistic Regression approach. Some innovative solutions are further suggested to improve these scores in the future.

A Lightweight and Interpretable Model to Classify Bundle Branch Blocks from ECG Signals

Automatic classification of ECG signals has been a longtime research area with large progress having been made recently. However these advances have been achieved with increasingly complex models at the expense of model's interpretability. In this research, a new model based on multivariate autoregressive model (MAR) coefficients combined with a tree-based model to classify bundle branch blocks is proposed. The advantage of the presented approach is to build a lightweight model which combined with post-hoc interpretability can bring new insights into important cross-lead dependencies which are indicative of the diseases of interest.

Adaptive Time-Dependent Priors and Bayesian Inference to Evaluate SARS-CoV-2 Public Health Measures Validated on 31 Countries

With the rapid spread of the SARS-CoV-2 virus since the end of 2019, public health confinement measures to contain the propagation of the pandemic have been implemented. Our method to estimate the reproduction number using Bayesian inference with time-dependent priors enhances previous approaches by considering a dynamic prior continuously updated as restrictive measures and comportments within the society evolve. In addition, to allow direct comparison between reproduction number and introduction of public health measures in a specific country, the infection dates are inferred from daily confirmed cases and confirmed death. The evolution of this reproduction number in combination with the stringency index is analyzed on 31 European countries. We show that most countries required tough state interventions with a stringency index equal to 79.6 out of 100 to reduce their reproduction number below one and control the progression of the pandemic. In addition, we show a direct correlation between the time taken to introduce restrictive measures and the time required to contain the spread of the pandemic with a median time of 8 days. This analysis is validated by comparing the excess deaths and the time taken to implement restrictive measures. Our analysis reinforces the importance of having a fast response with a coherent and comprehensive set of confinement measures to control the pandemic. Only restrictions or combinations of those have shown to effectively control the pandemic.

Overview of prospects for inflammation pathways in autism spectrum disorders

Autism spectrum disorders (ASD) represent a heterogeneous group of neurodevelopmental disorders which are both severe and frequent. Understanding its pathophysiology could lead to identifying promising new markers and treatments. For years, a growing number of studies have pointed to an important involvement of the immuno-inflammatory system in ASD. Extensive reviews have already addressed this topic. Yet, this field of investigations is not well known to practitioners even those working with ASD patients. Our main objective is to provide an introduction to these new insights through a mini review of the literature. A first field of antenatal studies connects fetal features and maternal infections to ASD by means of the participation of maternal immune activation (MIA) associated with the production of a particular pro inflammatory cytokinic profile with IL-1, IL-6 and TNF and IL-17. Maternal autoantibodies and other immune-related disorders can also lead to impairment of fetal neurodevelopment. Other postnatal studies have shown the correlation between ASD and autoantibodies and between ASD and inflammatory environment through impaired interleukin levels (IL-6 being the most extensively investigated). Disruption of intestinal microbiota appears to be a possible pathogenic mechanism of ASD. The growing paths opened recently between immunology and psychiatry appear to be promising in the understanding of ASD. It could eventually participate in the development of diagnostic markers and help the emergence of new personalized therapeutics suitable for these patients.