Abstract Acute kidney injury (AKI) is a syndrome that affects a large fraction of all critically ill patients, and early diagnosis to receive adequate treatment is as imperative as it is challenging to make early. Consequently, machine learning approaches have been developed to predict AKI ahead of time. However, the prevalence of AKI is often underestimated in state-of-the-art approaches, as they rely on an AKI event annotation solely based on creatinine, ignoring urine output. We construct and evaluate early warning systems for AKI in a multi-disciplinary ICU setting, using the complete KDIGO definition of AKI. We propose several variants of gradient-boosted decision tree (GBDT)-based models, including a novel time-stacking based approach. A state-of-the-art LSTM-based model previously proposed for AKI prediction is used as a comparison, which was not specifically evaluated in ICU settings yet. We find that optimal performance is achieved by using GBDT with the time-based stacking technique (AUPRC = 65.7%, compared with the LSTM-based model’s AUPRC = 62.6%), which is motivated by the high relevance of time since ICU admission for this task. Both models show mildly reduced performance in the limited training data setting, perform fairly across different subcohorts, and exhibit no issues in gender transfer. Following the official KDIGO definition substantially increases the number of annotated AKI events. In our study GBDTs outperform LSTM models for AKI prediction. Generally, we find that both model types are robust in a variety of challenging settings arising for ICU data.

Authors Xinrui Lyu, Bowen Fan, Matthias Hüser, Philip Hartout, Thomas Gumbsch, Martin Faltys, Tobias M. Merz, Gunnar Rätsch, and Karsten Borgwardt

Submitted Bioinformatics, ISMB 2024

Link DOI

Abstract The recent success of machine learning methods applied to time series collected from Intensive Care Units (ICU) exposes the lack of standardized machine learning benchmarks for developing and comparing such methods. While raw datasets, such as MIMIC-IV or eICU, can be freely accessed on Physionet, the choice of tasks and pre-processing is often chosen ad-hoc for each publication, limiting comparability across publications. In this work, we aim to improve this situation by providing a benchmark covering a large spectrum of ICU-related tasks. Using the HiRID dataset, we define multiple clinically relevant tasks in collaboration with clinicians. In addition, we provide a reproducible end-to-end pipeline to construct both data and labels. Finally, we provide an in-depth analysis of current state-of-the-art sequence modeling methods, highlighting some limitations of deep learning approaches for this type of data. With this benchmark, we hope to give the research community the possibility of a fair comparison of their work.

Authors Hugo Yèche, Rita Kuznetsova, Marc Zimmermann, Matthias Hüser, Xinrui Lyu, Martin Faltys, Gunnar Rätsch

Submitted NeurIPS 2021 (Datasets and Benchmarks)

Link

Abstract Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, contrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.

Authors Hugo Yèche, Gideon Dresdner, Francesco Locatello, Matthias Hüser, Gunnar Rätsch

Submitted ICML 2021

Link

Abstract The development of respiratory failure is common among patients in intensive care units (ICU). Large data quantities from ICU patient monitoring systems make timely and comprehensive analysis by clinicians difficult but are ideal for automatic processing by machine learning algorithms. Early prediction of respiratory system failure could alert clinicians to patients at risk of respiratory failure and allow for early patient reassessment and treatment adjustment. We propose an early warning system that predicts moderate/severe respiratory failure up to 8 hours in advance. Our system was trained on HiRID-II, a data-set containing more than 60,000 admissions to a tertiary care ICU. An alarm is typically triggered several hours before the beginning of respiratory failure. Our system outperforms a clinical baseline mimicking traditional clinical decision-making based on pulse-oximetric oxygen saturation and the fraction of inspired oxygen. To provide model introspection and diagnostics, we developed an easy-to-use web browser-based system to explore model input data and predictions visually.

Authors Matthias Hüser, Martin Faltys, Xinrui Lyu, Chris Barber, Stephanie L. Hyland, Thomas M. Merz, Gunnar Rätsch

Submitted arXiv Preprints

Link

Abstract Generating interpretable visualizations of multivariate time series in the intensive care unit is of great practical importance. Clinicians seek to condense complex clinical observations into intuitively understandable critical illness patterns, like failures of different organ systems. They would greatly benefit from a low-dimensional representation in which the trajectories of the patients' pathology become apparent and relevant health features are highlighted. To this end, we propose to use the latent topological structure of Self-Organizing Maps (SOMs) to achieve an interpretable latent representation of ICU time series and combine it with recent advances in deep clustering. Specifically, we (a) present a novel way to fit SOMs with probabilistic cluster assignments (PSOM), (b) propose a new deep architecture for probabilistic clustering (DPSOM) using a VAE, and (c) extend our architecture to cluster and forecast clinical states in time series (T-DPSOM). We show that our model achieves superior clustering performance compared to state-of-the-art SOM-based clustering methods while maintaining the favorable visualization properties of SOMs. On the eICU data-set, we demonstrate that T-DPSOM provides interpretable visualizations of patient state trajectories and uncertainty estimation. We show that our method rediscovers well-known clinical patient characteristics, such as a dynamic variant of the Acute Physiology And Chronic Health Evaluation (APACHE) score. Moreover, we illustrate how it can disentangle individual organ dysfunctions on disjoint regions of the two-dimensional SOM map.

Authors Laura Manduchi, Matthias Hüser, Martin Faltys, Julia Vogt, Gunnar Rätsch, Vincent Fortuin

Submitted ACM-CHIL 2021

Link

Abstract Dynamic assessment of mortality risk in the intensive care unit (ICU) can be used to stratify patients, inform about treatment effectiveness or serve as part of an early-warning system. Static risk scoring systems, such as APACHE or SAPS, have recently been supplemented with data-driven approaches that track the dynamic mortality risk over time. Recent works have focused on enhancing the information delivered to clinicians even further by producing full survival distributions instead of point predictions or fixed horizon risks. In this work, we propose a non-parametric ensemble model, Weighted Resolution Survival Ensemble (WRSE), tailored to estimate such dynamic individual survival distributions. Inspired by the simplicity and robustness of ensemble methods, the proposed approach combines a set of binary classifiers spaced according to a decay function reflecting the relevance of short-term mortality predictions. Models and baselines are evaluated under weighted calibration and discrimination metrics for individual survival distributions which closely reflect the utility of a model in ICU practice. We show competitive results with state-of-the-art probabilistic models, while greatly reducing training time by factors of 2-9x.

Authors Jonathan Heitz, Joanna Ficek-Pascual, Martin Faltys, Tobias M. Merz, Gunnar Rätsch, Matthias Hüser

Submitted Proceedings of the AAAI-2021 - Spring Symposium on Survival Prediction

Link

Abstract Intensive-care clinicians are presented with large quantities of measurements from multiple monitoring systems. The limited ability of humans to process complex information hinders early recognition of patient deterioration, and high numbers of monitoring alarms lead to alarm fatigue. We used machine learning to develop an early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data. It predicts 90% of circulatory-failure events in the test set, with 82% identified more than 2 h in advance, resulting in an area under the receiver operating characteristic curve of 0.94 and an area under the precision-recall curve of 0.63. On average, the system raises 0.05 alarms per patient and hour. The model was externally validated in an independent patient cohort. Our model provides early identification of patients at risk for circulatory failure with a much lower false-alarm rate than conventional threshold-based systems.

Authors Stephanie L. Hyland, Martin Faltys, Matthias Hüser, Xinrui Lyu, Thomas Gumbsch, Cristóbal Esteban, Christian Bock, Max Horn, Michael Moor, Bastian Rieck, Marc Zimmermann, Dean Bodenham, Karsten Borgwardt, Gunnar Rätsch & Tobias M. Merz

Submitted Nature Medicine

Link

Abstract Objective: Acute intracranial hypertension is an important risk factor of secondary brain damage after traumatic brain injury. Hypertensive episodes are often diagnosed reactively, leading to late detection and lost time for intervention planning. A pro-active approach that predicts critical events several hours ahead of time could assist in directing attention to patients at risk. Approach: We developed a prediction framework that forecasts onsets of acute intracranial hypertension in the next 8 hours. It jointly uses cerebral auto-regulation indices, spectral energies and morphological pulse metrics to describe the neurological state of the patient. One-minute base windows were compressed by computing signal metrics, and then stored in a multi-scale history, from which physiological features were derived. Main results: Our model predicted events up to 8 hours in advance with alarm recall rates of 90% at a precision of 30% in the MIMIC- III waveform database, improving upon two baselines from the literature. We found that features derived from high-frequency waveforms substantially improved the prediction performance over simple statistical summaries of low-frequency time series, and each of the three feature classes contributed to the performance gain. The inclusion of long-term history up to 8 hours was especially important. Significance: Our results highlight the importance of information contained in high-frequency waveforms in the neurological intensive care unit. They could motivate future studies on pre-hypertensive patterns and the design of new alarm algorithms for critical events in the injured brain.

Authors Matthias Hüser, Adrian Kündig, Walter Karlen, Valeria De Luca, Martin Jaggi

Submitted Physiological Measurement

Link DOI

Abstract High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose a new representation learning framework building on ideas from interpretable discrete dimensionality reduction and deep generative modeling. This framework allows us to learn discrete representations of time series, which give rise to smooth and interpretable embeddings with superior clustering performance. We introduce a new way to overcome the non-differentiability in discrete representation learning and present a gradient-based version of the traditional self-organizing map algorithm that is more performant than the original. Furthermore, to allow for a probabilistic interpretation of our method, we integrate a Markov model in the representation space. This model uncovers the temporal transition structure, improves clustering performance even further and provides additional explanatory insights as well as a natural representation of uncertainty. We evaluate our model in terms of clustering performance and interpretability on static (Fashion-)MNIST data, a time series of linearly interpolated (Fashion-)MNIST images, a chaotic Lorenz attractor system with two macro states, as well as on a challenging real world medical time series application on the eICU data set. Our learned representations compare favorably with competitor methods and facilitate downstream tasks on the real world data.

Authors Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch

Submitted ICLR 2019

Link

Abstract In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating on the prediction of clinically relevant outcomes, we show that in a practical setting, unsupervised representation learning can offer clear performance benefits over end-to-end supervised architectures. We experiment with using sequence-to-sequence (Seq2Seq) models in two different ways, as an autoencoder and as a forecaster, and show that the best performance is achieved by a forecasting Seq2Seq model with an integrated attention mechanism, proposed here for the first time in the setting of unsupervised learning for medical time series.

Authors Xinrui Lyu, Matthias Hüser, Stephanie L. Hyland, George Zerveas, Gunnar Rätsch

Submitted Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 - Spotlight

Link

Abstract Our comprehensive analysis of alternative splicing across 32 The Cancer Genome Atlas cancer types from 8,705 patients detects alternative splicing events and tumor variants by reanalyzing RNA and whole-exome sequencing data. Tumors have up to 30% more alternative splicing events than normal samples. Association analysis of somatic variants with alternative splicing events confirmed known trans associations with variants in SF3B1 and U2AF1 and identified additional trans-acting variants (e.g., TADA1, PPP2R1A). Many tumors have thousands of alternative splicing events not detectable in normal samples; on average, we identified ≈930 exon-exon junctions (“neojunctions”) in tumors not typically found in GTEx normals. From Clinical Proteomic Tumor Analysis Consortium data available for breast and ovarian tumor samples, we confirmed ≈1.7 neojunction- and ≈0.6 single nucleotide variant-derived peptides per tumor sample that are also predicted major histocompatibility complex-I binders (“putative neoantigens”).

Authors Andre Kahles, Kjong-Van Lehmann, Nora C. Toussaint, Matthias Hüser, Stefan Stark, Timo Sachsenberg, Oliver Stegle, Oliver Kohlbacher, Chris Sander, Gunnar Rätsch, The Cancer Genome Atlas Research Network

Submitted Cancer Cell

Link DOI

Abstract The deterioration of organ function in ICU patients requires swift response to prevent further damage to vital systems. Focusing on the circulatory system, we build a model to predict if a patient’s state will deteriorate in the near future. We identify circulatory system dys- function using the combination of excess lactic acid in the blood and low mean arterial blood pressure or the presence of vasoactive drugs. Using an observational cohort of 45,000 patients from a Swiss ICU, we extract and process patient time series and identify periods of circulatory system dysfunction to develop an early warning system. We train a gra- dient boosting model to perform binary classification every five minutes on whether the patient will deteriorate during an increasingly large win- dow into the future, up to the duration of a shift (8 hours). The model achieves an AUROC between 0.952 and 0.919 across the prediction win- dows, and an AUPRC between 0.223 and 0.384 for events with positive prevalence between 0.014 and 0.042. We also show preliminary results from a recurrent neural network. These results show that contemporary machine learning approaches combined with careful preprocessing of raw data collected during routine care yield clinically useful predictions in near real time [Workshop Abstract]

Authors Stephanie Hyland, Matthias Hüser, Xinrui Lyu, Martin Faltys, Tobias Merz, Gunnar Rätsch

Submitted Proceedings of the First Joint Workshop on AI in Health

Link

Authors Valeria De Luca, Matthias Hüser, Martin Jaggi, Walter Karlen, Emanuela Keller

Submitted 16th International Symposium on Intracranial Pressure and Neuromonitoring, Cambridge, MA, USA

Link

Authors Matthias Hüser, Valeria De Luca, Martin Jaggi, Walter Karlen, Emanuela Keller

Submitted Vasospasm - 13th International Conference on Neurovascular Events after Subarachnoid Hemorrhage

Link