Abstract Notable progress has been made in generalist medical large language models across various healthcare areas. However, large-scale modeling of in-hospital time series data - such as vital signs, lab results, and treatments in critical care - remains underexplored. Existing datasets are relatively small, but combining them can enhance patient diversity and improve model robustness. To effectively utilize these combined datasets for large-scale modeling, it is essential to address the distribution shifts caused by varying treatment policies, necessitating the harmonization of treatment variables across the different datasets. This work aims to establish a foundation for training large-scale multi-variate time series models on critical care data and to provide a benchmark for machine learning models in transfer learning across hospitals to study and address distribution shift challenges. We introduce a harmonized dataset for sequence modeling and transfer learning research, representing the first large-scale collection to include core treatment variables. Future plans involve expanding this dataset to support further advancements in transfer learning and the development of scalable, generalizable models for critical healthcare applications.

Authors Manuel Burger, Fedor Sergeev, Malte Londschien, Daphné Chopard, Hugo Yèche, Eike Gerdes, Polina Leshetkina, Alexander Morgenroth, Zeynep Babür, Jasmina Bogojeska, Martin Faltys, Rita Kuznetsova, Gunnar Rätsch

Submitted AIM-FM Workshop at NeurIPS 2024

Link DOI

Abstract Fatigue is one of the most prevalent symptoms of chronic diseases, such as Multiple Sclero- sis, Alzheimer’s, and Parkinson’s. Recently researchers have explored unobtrusive and continuous ways of fatigue monitoring using mobile and wearable devices. However, data quality and limited labeled data availability in the wearable health domain pose significant challenges to progress in the field. In this work, we perform a systematic evaluation of self-supervised learning (SSL) tasks for fatigue recognition using wearable sensor data. To establish our benchmark, we use Homekit2020, which is a large-scale dataset collected using Fitbit devices in everyday life settings. Our results show that the majority of the SSL tasks outperform fully supervised baselines for fatigue recognition, even in limited labeled data scenarios. In particular, the domain fea- tures and multi-task learning achieve 0.7371 and 0.7323 AUROC, which are higher than the other SSL tasks and supervised learning baselines. In most of the pre-training tasks, the performance is higher when using at least one data augmentation that reflects the potentially low quality of wearable data (e.g., missing data). Our findings open up promising opportunities for continuous assessment of fatigue in real settings and can be used to guide the design and development of health monitoring systems.

Authors Tamás Visy, Rita Kuznetsova, Christian Holz, Shkurta Gashi

Submitted CHIL 2024 (PMLR)

Link

Abstract Electronic Health Record (EHR) datasets from Intensive Care Units (ICU) contain a diverse set of data modalities. While prior works have successfully leveraged multiple modalities in supervised settings, we apply advanced self-supervised multi-modal contrastive learning techniques to ICU data, specifically focusing on clinical notes and time-series for clinically relevant online prediction tasks. We introduce a loss function Multi-Modal Neighborhood Contrastive Loss (MM-NCL), a soft neighborhood function, and showcase the excellent linear probe and zero-shot performance of our approach.

Authors Fabian Baldenweg, Manuel Burger, Gunnar Rätsch, Rita Kuznetsova

Submitted TS4H ICLR Workshop

Link DOI

Abstract Recent advances in deep learning architectures for sequence modeling have not fully transferred to tasks handling time-series from electronic health records. In particular, in problems related to the Intensive Care Unit (ICU), the state-of-the-art remains to tackle sequence classification in a tabular manner with tree-based methods. Recent findings in deep learning for tabular data are now surpassing these classical methods by better handling the severe heterogeneity of data input features. Given the similar level of feature heterogeneity exhibited by ICU time-series and motivated by these findings, we explore these novel methods' impact on clinical sequence modeling tasks. By jointly using such advances in deep learning for tabular data, our primary objective is to underscore the importance of step-wise embeddings in time-series modeling, which remain unexplored in machine learning methods for clinical data. On a variety of clinically relevant tasks from two large-scale ICU datasets, MIMIC-III and HiRID, our work provides an exhaustive analysis of state-of-the-art methods for tabular time-series as time-step embedding models, showing overall performance improvement. In particular, we evidence the importance of feature grouping in clinical time-series, with significant performance gains when considering features within predefined semantic groups in the step-wise embedding module.

Authors Rita Kuznetsova, Alizée Pace, Manuel Burger, Hugo Yèche, Gunnar Rätsch

Submitted ML4H 2023 (PMLR)

Link DOI

Abstract Clinicians are increasingly looking towards machine learning to gain insights about patient evolutions. We propose a novel approach named Multi-Modal UMLS Graph Learning (MMUGL) for learning meaningful representations of medical concepts using graph neural networks over knowledge graphs based on the unified medical language system. These representations are aggregated to represent entire patient visits and then fed into a sequence model to perform predictions at the granularity of multiple hospital visits of a patient. We improve performance by incorporating prior medical knowledge and considering multiple modalities. We compare our method to existing architectures proposed to learn representations at different granularities on the MIMIC-III dataset and show that our approach outperforms these methods. The results demonstrate the significance of multi-modal medical concept representations based on prior medical knowledge.

Authors Manuel Burger, Gunnar Rätsch, Rita Kuznetsova

Submitted ML4H 2023 (PMLR)

Link DOI

Abstract Intensive Care Units (ICU) require comprehensive patient data integration for enhanced clinical outcome predictions, crucial for assessing patient conditions. Recent deep learning advances have utilized patient time series data, and fusion models have incorporated unstructured clinical reports, improving predictive performance. However, integrating established medical knowledge into these models has not yet been explored. The medical domain's data, rich in structural relationships, can be harnessed through knowledge graphs derived from clinical ontologies like the Unified Medical Language System (UMLS) for better predictions. Our proposed methodology integrates this knowledge with ICU data, improving clinical decision modeling. It combines graph representations with vital signs and clinical reports, enhancing performance, especially when data is missing. Additionally, our model includes an interpretability component to understand how knowledge graph nodes affect predictions.

Authors Samyak Jain, Manuel Burger, Gunnar Rätsch, Rita Kuznetsova

Submitted ML4H 2023 (Findings Track)

Link DOI

Abstract In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and blood pressure. We use self-supervised training paradigms for language models to learn high-quality clinical feature embeddings, achieving a finer granularity than existing time-step and patient-level representation learning. We visualize the learnt embeddings via unsupervised dimension reduction techniques and observe a high degree of consistency with prior clinical knowledge. We also evaluate the model performance on the MIMIC-III benchmark and demonstrate the effectiveness of using clinical feature embeddings. We publish our code online for replication.

Authors Yurong Hu, Manuel Burger, Gunnar Rätsch, Rita Kuznetsova

Submitted NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice

Link DOI

Abstract Understanding deep learning model behavior is critical to accepting machine learning-based decision support systems in the medical community. Previous research has shown that jointly using clinical notes with electronic health record (EHR) data improved predictive performance for patient monitoring in the intensive care unit (ICU). In this work, we explore the underlying reasons for these improvements. While relying on a basic attention-based model to allow for interpretability, we first confirm that performance significantly improves over state-of-the-art EHR data models when combining EHR data and clinical notes. We then provide an analysis showing improvements arise almost exclusively from a subset of notes containing broader context on patient state rather than clinician notes. We believe such findings highlight deep learning models for EHR data to be more limited by partially-descriptive data than by modeling choice, motivating a more data-centric approach in the field.

Authors Severin Husmann, Hugo Yèche, Gunnar Rätsch, Rita Kuznetsova

Submitted Workshop on Learning from Time Series for Health, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Link

Abstract Models that can predict the occurrence of events ahead of time with low false-alarm rates are critical to the acceptance of decision support systems in the medical community. This challenging task is typically treated as a simple binary classification, ignoring temporal dependencies between samples, whereas we propose to exploit this structure. We first introduce a common theoretical framework unifying dynamic survival analysis and early event prediction. Following an analysis of objectives from both fields, we propose Temporal Label Smoothing (TLS), a simpler, yet best-performing method that preserves prediction monotonicity over time. By focusing the objective on areas with a stronger predictive signal, TLS improves performance over all baselines on two large-scale benchmark tasks. Gains are particularly notable along clinically relevant measures, such as event recall at low false-alarm rates. TLS reduces the number of missed events by up to a factor of two over previously used approaches in early event prediction.

Authors Hugo Yèche, Alizée Pace, Gunnar Rätsch, Rita Kuznetsova

Submitted ICML 2023

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