arXiv subjects

Avelino Javer

Publications and source records attributed to Avelino Javer.

5 recordsLinked to original sources

arXiv2021

Compensating trajectory bias for unsupervised patient stratification using adversarial recurrent neural networks

Electronic healthcare records are an important source of information which can be used in patient stratification to discover novel disease phenotypes. However, they can be challenging to work with as data is often sparse and irregularly sampled. One approach to solve these limitations is learning dense embeddings that represent individual patient trajectories using a recurrent neural network autoencoder (RNN-AE). This process can be susceptible to unwanted data biases. We show that patient embeddings and clusters using previously proposed RNN-AE models might be impacted by a trajectory bias, meaning that results are dominated by the amount of data contained in each patients trajectory, instead of clinically relevant details. We investigate this bias on 2 datasets (from different hospitals) and 2 disease areas as well as using different parts of the patient trajectory. Our results using 2 previously published baseline methods indicate a particularly strong bias in case of an event-to-end trajectory. We present a method that can overcome this issue using an adversarial training scheme on top of a RNN-AE. Our results show that our approach can reduce the trajectory bias in all cases.

cs.LG↗

arXiv2021

Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes

The increase in availability of longitudinal electronic health record (EHR) data is leading to improved understanding of diseases and discovery of novel phenotypes. The majority of clustering algorithms focus only on patient trajectories, yet patients with similar trajectories may have different outcomes. Finding subgroups of patients with different trajectories and outcomes can guide future drug development and improve recruitment to clinical trials. We develop a recurrent neural network autoencoder to cluster EHR data using reconstruction, outcome, and clustering losses which can be weighted to find different types of patient clusters. We show our model is able to discover known clusters from both data biases and outcome differences, outperforming baseline models. We demonstrate the model performance on $29,229$ diabetes patients, showing it finds clusters of patients with both different trajectories and different outcomes which can be utilized to aid clinical decision making.

cs.LG↗

arXiv2020

Prediction of the onset of cardiovascular diseases from electronic health records using multi-task gated recurrent units

In this work, we propose a multi-task recurrent neural network with attention mechanism for predicting cardiovascular events from electronic health records (EHRs) at different time horizons. The proposed approach is compared to a standard clinical risk predictor (QRISK) and machine learning alternatives using 5-year data from a NHS Foundation Trust. The proposed model outperforms standard clinical risk scores in predicting stroke (AUC=0.85) and myocardial infarction (AUC=0.89), considering the largest time horizon. Benefit of using an \gls{mt} setting becomes visible for very short time horizons, which results in an AUC increase between 2-6%. Further, we explored the importance of individual features and attention weights in predicting cardiovascular events. Our results indicate that the recurrent neural network approach benefits from the hospital longitudinal information and demonstrates how machine learning techniques can be applied to secondary care.

cs.LG↗

arXiv2019

Semantic filtering through deep source separation on microscopy images

By their very nature microscopy images of cells and tissues consist of a limited number of object types or components. In contrast to most natural scenes, the composition is known a priori. Decomposing biological images into semantically meaningful objects and layers is the aim of this paper. Building on recent approaches to image de-noising we present a framework that achieves state-of-the-art segmentation results requiring little or no manual annotations. Here, synthetic images generated by adding cell crops are sufficient to train the model. Extensive experiments on cellular images, a histology data set, and small animal videos demonstrate that our approach generalizes to a broad range of experimental settings. As the proposed methodology does not require densely labelled training images and is capable of resolving the partially overlapping objects it holds the promise of being of use in a number of different applications.

cs.CV↗

arXiv2015

Individuality and universality in the growth-division laws of single E. coli cells

The mean size of exponentially dividing E. coli cells cultured in different nutrient conditions is known to depend on the mean growth rate only. However, the joint fluctuations relating cell size, doubling time and individual growth rate are only starting to be characterized. Recent studies in bacteria (i) revealed the near constancy of the size extension in a single cell cycle (adder mechanism), and (ii) reported a universal trend where the spread in both size and doubling times is a linear function of the population means of these variables. Here, we combine experiments and theory and use scaling concepts to elucidate the constraints posed by the second observation on the division control mechanism and on the joint fluctuations of sizes and doubling times. We found that scaling relations based on the means both collapse size and doubling-time distributions across different conditions, and explain how the shape of their joint fluctuations deviates from the means. Our data on these joint fluctuations highlight the importance of cell individuality: single cells do not follow the dependence observed for the means between size and either growth rate or inverse doubling time. Our calculations show that these results emerge from a broad class of division control mechanisms (including the adder mechanism as a particular case) requiring a certain scaling form of the so-called "division hazard rate function", which defines the probability rate of dividing as a function of measurable parameters. This gives a rationale for the universal body-size distributions observed in microbial ecosystems across many microbial species, presumably dividing with multiple mechanisms. Additionally, our experiments show a crossover between fast and slow growth in the relation between individual-cell growth rate and division time, which can be understood in terms of different regimes of genome replication control.

q-bio.CB↗