Search

We address the tasks of Bayesian state estimation and forecasting for a model-free process in an unsupervised learning setup. For a model-free process, we do not have any a-priori knowledge of the process dynamics. In the article, we propose DANSE - a Data-driven Nonlinear State Estimation method. DANSE provides a closed-form posterior of the state of the model-free process, given linear measurements of the state. In addition, it provides a closed-form posterior for forecasting. A data-driven recurrent neural network (RNN) is used in DANSE to provide the parameters of a prior of the state. The prior depends on the past measurements as input, and then we find the closed-form posterior of the state using the current measurement as input. The data-driven RNN captures the underlying non-linear dynamics of the model-free process. The training of DANSE, mainly learning the parameters of the RNN, is executed using an unsupervised learning approach. In unsupervised learning, we have access to a training dataset comprising only a set of (noisy) measurement data trajectories, but we do not have any access to the state trajectories. Therefore, DANSE does not have access to state information in the training data and can not use supervised learning. Using simulated linear and non-linear process models (Lorenz attractor and Chen attractor), we evaluate the unsupervised learning-based DANSE. We show that the proposed DANSE, without knowledge of the process model and without supervised learning, provides a competitive performance against model-driven methods, such as the Kalman filter (KF), extended KF (EKF), unscented KF (UKF), a data-driven deep Markov model (DMM) and a recently proposed hybrid method called KalmanNet. In addition, we show that DANSE works for high-dimensional state estimation., QC 20240503

We propose DANSE - a data-driven non-linear state estimation method. DANSE provides a closed-form posterior of the state of a model-free process, given linear measurements of the state in a Bayesian setup, like the celebrated Kalman filter (KF). Non-linear dynamics of the state are captured by data-driven recurrent neural networks (RNNs). The training of DANSE combines maximum-likelihood and gradient-descent in an unsupervised framework, i.e. only measurement data and no process data are required. Using simulated linear and non-linear process models, we demonstrate that DANSE - without knowledge of the process model - provides competitive performance against model-based approaches such as KF, unscented KF (UKF), extended KF (EKF), and a hybrid approach such as KalmanNet., Part of ISBN 9789464593600QC 20240502

Aim: To investigate the relation between autonomic regulation, measured using heart rate variability (HRV), body weight and degree of prematurity in infants. Further to assess utility to include body weight in a machine learning-based sepsis prediction algorithm. Methods: Longitudinal cohort study including 378 infants hospitalised in two neonatal intensive care units. Continuous vital sign data collection was performed prospectively from the time of NICU admission to discharge. Clinically relevant events were annotated retrospectively. HRV described using sample entropy of inter-beat intervals and assessed for its correlation with body weight measurements and age. Weight values were then added to a machine learning-based algorithm for neonatal sepsis detection. Results: Sample entropy showed a positive correlation with increasing body weight and postconceptual age. Very low birth weight infants exhibited significantly lower HRV compared to infants with a birth weight >1500 g. This persisted when reaching similar weight and at the same postconceptual age. Adding body weight measures improved the algorithm's ability to predict sepsis in the overall population. Conclusion: We revealed a positive correlation of HRV with increasing body weight and maturation in infants. Restricted HRV, proven helpful in detecting acute events such as neonatal sepsis, might reflect prolonged impaired development of autonomic control., QC 20230626

Early and accurate neonatal sepsis detection (NSD) can help reduce mortality, morbidity and antibiotic consumption in premature infants. NSD models are often designed and evaluated in case control setups and using data derived from patient electrocardiogram (ECG) only. In this article, we evaluate our models in a more realistic retrospective cohort study setup. We use data from different modalities, including ECG, chest impedance, pulse oximetry, demographics factors and repetitive measurements of body weights. We study both the vanilla and long-short-term-memory (LSTM) Recurrent Neural Networks (RNN) architectures in a sequence to sequence mapping framework for NSD. We compare the performances of the models with logistic regression (LR) on a variety of classification metrics in a leave-one-out cross validation framework. The population we used contains 118 very low birth weight infants, among which 10 experienced sepsis. We showed that LSTM-based RNNs are both (1) more conservative and (2) more precise than LR or vanilla RNN, with a true negative rate at least +26% higher and a precision score of 0.16 compared to 0.06 for LR. This indicates that LSTM-based RNNs have the potential to reduce the false alarm rate of existing linear models, while providing a reliable diagnostic aid for neonatal sepsis., Part of ISBN 9781665470292QC 20230801

QC 20211201

QC 20211201

Aim: To systematically summarise the current evidence of employing clinical decision support algorithms (CDSAs) using non-invasive parameters for sepsis prediction in neonates. Methods: A comprehensive search in PubMed, CENTRAL and EMBASE was conducted. Screening, data extraction and risk of bias were performed by two authors. The certainty of the evidence was assessed using GRADE. PROSPERO ID: CRD42020205143. Results: After abstract and full-text screening, 36 studies comprising 18,096 infants were included. Most CDSAs evaluated heart rate (HR)-based parameters. Two publications derived from one randomised-controlled trial assessing HR characteristics reported significant reduction in 30-day septicaemia-related mortality. Thirty-four non-randomised studies found promising yet inconclusive results. Conclusion: Heart rate-based parameters are reliable components of CDSAs for sepsis prediction, particularly in combination with additional vital signs and demographics. However, inconclusive evidence and limited standardisation restricts clinical implementation of CDSAs outside of a controlled research environment. Further experimentation and comparison of parameter combinations and testing of new CDSAs are warranted., QC 20220502

Hidden Markov model (HMM) has been successfully used for sequential data modeling problems. In this work, we propose to power the modeling capacity of HMM by bringing in neural network based generative models. The proposed model is termed as GenHMM. In the proposed GenHMM, each HMM hidden state is associated with a neural network based generative model that has tractability of exact likelihood and provides efficient likelihood computation. A generative model in GenHMM consists of a mixture of generators that are realized by flow models. A learning algorithm for GenHMM is proposed in expectation-maximization framework. The convergence of the learning GenHMM is analyzed. We demonstrate the efficiency of GenHMM by classification tasks on practical sequential data., QC 20210621

We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that combines the state transitions of a hidden Markov model (HMM) and the neural network based probability distributions for the hidden states of the HMM, can provide a robust classification performance. The combined model is called normalizing-flow mixture model based HMM (NMM-HMM). It can be trained using a combination of expectation-maximization (EM) and backpropagation. We verify the improved robustness of NMM-HMM classifiers in an application to speech recognition., QC 20210503

We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants. We investigate the use of classical Gaussian mixture model basedHMM, and a recently proposed neural network based HMM. To improve the neural network based HMM, we propose a discriminative training approach. Experimental results show the potential of HMMs over logistic regression, support vector machine and extreme learning machine., QC 20210324