False arrhythmia alarms in intensive care units (ICUs) are a continuing problem despite considerable effort from industrial and academic algorithm developers. Of all life-threatening arrhythmias, ventricular tachycardia (VT) stands out as the most challenging arrhythmia to detect reliably. We introduce a new annotated VT alarm database, VTaC (Ventricular Tachycardia annotated alarms from ICUs) consisting of over 5,000 waveform recordings with VT alarms triggered by bedside monitors in the ICU. Each VT alarm waveform in the dataset has been labeled by at least two independent human expert annotators. The dataset encompasses data collected from ICUs in two major US hospitals and includes data from three leading bedside monitor manufacturers, providing a diverse and representative collection of alarm waveform data. Each waveform recording comprises at least two electrocardiogram (ECG) leads and one or more pulsatile waveforms, such as photoplethysmogram (PPG or PLETH) and arterial blood pressure (ABP) waveforms. We demonstrate the utility of this new benchmark dataset for the task of false arrhythmia alarm reduction, and present performance of multiple machine learning approaches, including conventional supervised machine learning, deep learning, semi-supervised learning, and generative approaches for the task of VT false alarm reduction.

Early and accurate prediction of sepsis onset remains a major challenge in intensive care, where timely detection and subsequent intervention can significantly improve patient outcomes. While machine learning models have shown promise in this domain, their success is often limited by the amount and diversity of training data available to individual hospitals and Intensive Care Units (ICUs). Federated Learning (FL) addresses this issue by enabling collaborative model training across institutions without requiring data sharing, thus preserving patient privacy. In this work, we propose a federated, attention-enhanced Long Short-Term Memory model for sepsis onset prediction, trained on multi-centric ICU data. Unlike existing approaches that rely on fixed prediction windows, our model supports variable prediction horizons, enabling both short- and long-term forecasting in a single unified model. During analysis, we put particular emphasis on the improvements through our approach in terms of early sepsis detection, i.e., predictions with large prediction windows by conducting an in-depth temporal analysis. Our results prove that using FL does not merely improve overall prediction performance (with performance approaching that of a centralized model), but is particularly beneficial for early sepsis onset prediction. Finally, we show that our choice of employing a variable prediction window rather than a fixed window does not hurt performance significantly but reduces computational, communicational, and organizational overhead.

Missing data is a persistent challenge in federated learning on electronic health records, particularly when institutions collect time-series data at varying temporal granularities. To address this, we propose Federated Markov Imputation (FMI), a privacy-preserving method that enables Intensive Care Units (ICUs) to collaboratively build global transition models for temporal imputation. We evaluate FMI on a real-world sepsis onset prediction task using the MIMIC-IV dataset and show that it outperforms local imputation baselines, especially in scenarios with irregular sampling intervals across ICUs.

Intensive care unit (ICU) is a crucial hospital department that handles life-threatening cases. Nowadays machine learning (ML) is being leveraged in healthcare ubiquitously. In recent years, management of ICU became one of the most significant parts of the hospital functionality (largely but not only due to the worldwide COVID-19 pandemic). This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset. The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer). Given that LOS prediction is often framed as a classification task, this study categorizes LOS into three groups: less than two days, less than a week, and a week or more. As the first ML-based approach targeting LOS prediction for neurological disorder patients, this study does not aim to outperform existing methods but rather to assess their effectiveness in this specific context. The findings provide insights into the applicability of ML techniques for improving ICU resource management and patient care. According to the results, Random Forest model proved to outperform others on static, achieving an accuracy of 0.68, a precision of 0.68, a recall of 0.68, and F1-score of 0.67. While BERT model outperformed LSTM model on time-series data with an accuracy of 0.80, a precision of 0.80, a recall of 0.80 and F1-score 0.80.

False arrhythmia alarms in intensive care units (ICUs) are a continuing problem despite considerable effort from industrial and academic algorithm developers. Of all life-threatening arrhythmias, ventricular tachycardia (VT) stands out as the most challenging arrhythmia to detect reliably. We introduce a new annotated VT alarm database, VTaC (Ventricular Tachycardia annotated alarms from ICUs) consisting of over 5,000 waveform recordings with VT alarms triggered by bedside monitors in the ICU. Each VT alarm waveform in the dataset has been labeled by at least two independent human expert annotators. The dataset encompasses data collected from ICUs in two major US hospitals and includes data from three leading bedside monitor manufacturers, providing a diverse and representative collection of alarm waveform data.

Sepsis and septic shock are a critical medical condition affecting millions globally, with a substantial mortality rate. This paper uses state-of-the-art deep learning (DL) architectures to introduce a multi-step forecasting system to predict vital signs indicative of septic shock progression in Intensive Care Units (ICUs). Our approach utilizes a short window of historical vital sign data to forecast future physiological conditions. We introduce a DL-based vital sign forecasting system that predicts up to 3 hours of future vital signs from 6 hours of past data. We further adopt the DILATE loss function to capture better the shape and temporal dynamics of vital signs, which are critical for clinical decision-making. We compare three DL models, N-BEATS, N-HiTS, and Temporal Fusion Transformer (TFT), using the publicly available eICU Collaborative Research Database (eICU-CRD), highlighting their forecasting capabilities in a critical care setting. We evaluate the performance of our models using mean squared error (MSE) and dynamic time warping (DTW) metrics. Our findings show that while TFT excels in capturing overall trends, N-HiTS is superior in retaining short-term fluctuations within a predefined range. This paper demonstrates the potential of deep learning in transforming the monitoring systems in ICUs, potentially leading to significant improvements in patient care and outcomes by accurately forecasting vital signs to assist healthcare providers in detecting early signs of physiological instability and anticipating septic shock.

Senior author and data science lead Professor Aldo Faisal, Director of Imperial's Centre in AI for Healthcare at the Departments of Computing and Bioengineering, said: "In the ever-changing landscape of the pandemic, clinicians are constantly learning and adapting to patient needs, which themselves change every day. Critically, we have set up a standing digital service evaluation of UK ICUs, getting day-by-day treatment data from ICUs across the nations. Our machine learning tool could help track patient progress in real time and help inform ICU guidelines by filling the gaps of patient care – reflecting back to clinicians to identify best practice quickly and benefit from sharing.

This technique, known as proning, is commonly used in this setting to improve oxygenation of the lungs, but is not suitable for all patients. Researchers from Imperial College London gave the algorithm each patient's data on a daily basis instead of only on admission so that it could more accurately track their condition. They believe the system could be used to improve guidelines in clinical practice going forward and could be applied to potential future waves of the pandemic and other diseases treated in similar clinical settings. First author of the study Dr Brijesh Patel said: "Most studies look at the health of a patient on admission to ICU and whether they were discharged or sadly died. In ICU there is a huge amount of information which we use at the bedside to manage patients on a day-by-day basis and our study focuses on how the patients' state changed daily. "This helped focus our attention on which specific parameters matter the most and how the importance of each parameter changes over time.

Researchers used AI to identify which daily changing clinical parameters best predict intervention responses in critically ill COVID-19 patients. The investigators used machine learning to predict which patients might get worse and not respond positively to being turned onto their front in intensive care units (ICUs) – a technique known as proning that is commonly used in this setting to improve oxygenation of the lungs. While the AI model was used on a retrospective cohort of patient data collected during the pandemic's first wave, the study demonstrates the ability of AI methods to predict patient outcomes using routine clinical information used by ICU medics. The researchers say the approach, where each patient's data were analysed day-by-day instead of only on admission, could be used to improve guidelines in clinical practice going forward. It could be applied to potential future waves of the pandemic and other diseases treated in similar clinical settings. This is the first study that examines daily COVID-19 patient data, using AI to understand the clinical response to the rapidly changing needs of patients in ICUs.

Death rate among COVID-19 patients admitted to intensive care units (ICU) across the world has reduced compared to the toll at the beginning of the pandemic, according to a new study. The result of the study offered a beacon of hope to the coronavirus patients in the ICUs by finding the fatality rate among those in intensive care has fallen by almost a third in Europe, America and Asia. While new cases continued to surge in some parts of the world, coronavirus-related fatalities were also showing signs of waning, according to a research team headed by Tim Cook, a consultant in anesthesia and intensive care medicine of England's Royal United Hospitals Bath NHS Foundation Trust. Researchers said, overall, ICU deaths dropped from almost 60% in March to around 42% at the end of May. The difference in ratio meant thousands of lives were saved and reflected the rapid learning process that took place on a global scale as to what types of drugs work against the deadly virus, an article published on WebMD, stated.