Gilles Clermont

• MD, MS
• Professor (Full) at University of Pittsburgh

Intradialytic hypotension is associated with increased morbidity, and mortality. Several machine learning (ML) algorithms have been recently developed to predict intradialytic hypotension. We systematically reviewed ML models employed to predict intradialytic hypotension, their performance, methodological integrity, and clinical applicability. We c...

Objectives To examine the utility of day 3 sepsis phenotype classifications compared with day 1 and whether these could be reliably identified using routine clinical data on day 1. Design Retrospective cohort study of pediatric patients managed 2010–2014 and 2018–2020. Setting Academic children’s hospital. Patients One thousand eight hundred twe...

Most cases of acute kidney injury (AKI) resolve within 72 h. However, a small number of patients with persistent severe AKI have significantly worse outcomes. We sought to describe the occurrence, impact on outcome and risk factors associated with persistent severe AKI in critically ill patients using a standardized definition. Retrospective cohort...

Background and Aims The importance of risk stratification in patients with chest pain extends beyond diagnosis and immediate treatment. This study sought to evaluate the prognostic value of electrocardiogram feature-based machine learning models to risk-stratify all-cause mortality in those with chest pain. Methods This was a prospective observati...

Sepsis is a major public health emergency and one of the leading causes of morbidity and mortality in critically ill patients. For each hour treatment is delayed, shock-related mortality increases, so early diagnosis and intervention is of utmost importance. However, earlier recognition of shock requires active monitoring, which may be delayed due...

Background Perhaps nowhere else in the healthcare system than in the intensive care unit environment are the challenges to create useful models with direct time-critical clinical applications more relevant and the obstacles to achieving those goals more massive. Machine learning-based artificial intelligence (AI) techniques to define states and pre...

OBJECTIVES Early signs of bleeding are often masked by the physiologic compensatory responses delaying its identification. We sought to describe early physiologic signatures of bleeding during the blood donation process. SETTING Waveform-level vital sign data including electrocardiography, photoplethysmography (PPG), continuous noninvasive arteria...

Objective To investigate whether pediatric sepsis phenotypes are stable in time. Methods Retrospective cohort study examining children with suspected sepsis admitted to a PICU at a large free-standing children’s hospital during two distinct periods: 2010-2014 (Early Cohort) and 2018-2020 (Late Cohort). K-means consensus clustering was used to deri...

Background: Identification of bloodstream infection (BSI) in transplant recipients may be difficult due to immunosuppression. Accordingly, we aimed to compare responses to BSI in critically ill transplant and non-transplant recipients and to modify systemic inflammatory response syndrome (SIRS) criteria for transplant recipients. Methods: We ana...

Importance The efficacy of vitamin C for hospitalized patients with COVID-19 is uncertain. Objective To determine whether vitamin C improves outcomes for patients with COVID-19. Design, Setting, and Participants Two prospectively harmonized randomized clinical trials enrolled critically ill patients receiving organ support in intensive care units...

Background Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care. Objectives Our objective is to engage multidisciplinary users (p...

Objectives To automatically populate the case report forms (CRFs) for an international, pragmatic, multifactorial, response-adaptive, Bayesian COVID-19 platform trial. Methods The locations of focus included 27 hospitals and 2 large electronic health record (EHR) instances (1 Cerner Millennium and 1 Epic) that are part of the same health system in...

Background: Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care. Methods: We utilized the Physiobank Lon...

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the...

A significant proportion of clinical physiologic monitoring alarms are false. This often leads to alarm fatigue in clinical personnel, inevitably compromising patient safety. To combat this issue, researchers have attempted to build Machine Learning (ML) models capable of accurately adjudicating Vital Sign (VS) alerts raised at the bedside of hemod...

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report the first observational cohort study to deve...

Intensive care units (ICUs) are crucial resources within hospitals, caring for the most critically ill patients. We propose a novel modeling framework that improves the outflow of ICU patients by anticipating unit interactions and resource sharing within the system. Across an arbitrary bipartite network of units, we consider two types of downstream...

The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper Acuity-Based Allocation of ICU-Downstream Beds with Flexible Staffing by Valeva, S., Pang, G., Schaefer, A.J. and Clermont, G.

Introduction: Atrial fibrillation (AF) alerts from clinical monitoring systems are often inaccurate. Recently reported AF detectors utilize curated, publicly-available databases for model training. Real-world data rather than curated databases would be better suited to improve upon these inaccuracies, but labeling high-frequency waveform data over...

The idea that we can detect subacute potentially catastrophic illness earlier by using statistical models trained on clinical data is now well-established. We review evidence that supports the role of continuous cardiorespiratory monitoring in these predictive analytics monitoring tools. In particular, we review how continuous ECG monitoring reflec...

Background: General severity of illness scores are not well calibrated to predict mortality among patients receiving renal replacement therapy (RRT) for acute kidney injury (AKI). We developed machine learning models to make mortality prediction and compared their performance to that of the Sequential Organ Failure Assessment (SOFA) and HEpatic fa...

Objective: To examine the risk factors, resource utilization and 1-year mortality associated with vasopressor-resistant hypotension (VRH) compared with vasopressor-sensitive hypotension (VSH) among critically ill adults with vasodilatory shock. We also examined whether combination vasopressor therapy and patient phenotype were associated with mort...

A significant proportion of clinical physiologic monitoring alarms are false. This often leads to alarm fatigue in clinical personnel, inevitably compromising patient safety. To combat this issue, researchers have attempted to build Machine Learning (ML) models capable of accurately adjudicating Vital Sign (VS) alerts raised at the bedside of hemod...

Background: We evaluated the feasibility and discriminability of recently proposed Clinical Performance Measures for Neurocritical Care (Neurocritical Care Society) and Quality Indicators for Traumatic Brain Injury (Collaborative European NeuroTrauma Effectiveness Research in TBI; CENTER-TBI) extracted from electronic health record (EHR) flowsheet...

Introduction Targeted therapies for sepsis have failed to show benefit due to high variability among subjects. We sought to demonstrate different phenotypes of septic shock based solely on clinical features and show that these relate to outcome. Methods A retrospective analysis was performed of a 1,023-subject cohort with early septic shock from t...

Developing functional machine learning (ML)-based models to address unmet clinical needs requires unique considerations for optimal clinical utility. Recent debates about the rigours, transparency, explainability, and reproducibility of ML models, terms which are defined in this article, have raised concerns about their clinical utility and suitabi...

We introduce a novel contrastive representation learning objective and a training scheme for clinical time series. Specifically, we project high dimensional E.H.R. data to a closed unit ball of low dimension, encoding geometric priors so that the origin represents an idealized perfect health state and the euclidean norm is associated with the patie...

With recent advances in electronic data availability, algorithms and computing power, the potential of artificial intelligence (AI) in the care of the critically ill patients has increased. Current roles of AI models are broad, including developing diagnostic, prognostic, and management strategies. From a diagnostic standpoint, AI models are being...

Importance: The efficacy of antiplatelet therapy in critically ill patients with COVID-19 is uncertain. Objective: To determine whether antiplatelet therapy improves outcomes for critically ill adults with COVID-19. Design, setting, and participants: In an ongoing adaptive platform trial (REMAP-CAP) testing multiple interventions within multip...

Developing functional machine learning-based models to address unmet clinical needs requires unique considerations for optimal clinical utility. Recent debates about the rigors, transparency, explainability, and reproducibility of machine learning models, terms which are defined in this article, have raised concerns about their clinical utility and...

Supplementary Information in the form of Appendices

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2022. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2022. Further information about the Annual Update in Intensive Care and Emergency Medicine is available from https://link.springer.com/...

Sepsis is a potentially life-threatening inflammatory response to infection or severe tissue damage. It has a highly variable clinical course, requiring constant monitoring of the patient’s state to guide the management of intravenous fluids and vasopressors, among other interventions. Despite decades of research, there’s still debate among experts...

Early recognition of pathologic cardiorespiratory stress and forecasting cardiorespiratory decompensation in the critically ill is difficult even in highly monitored patients in the Intensive Care Unit (ICU). Instability can be intuitively defined as the overt manifestation of the failure of the host to adequately respond to cardiorespiratory stres...

Background: Characterization of coronavirus disease 2019 (COVID-19) endotypes may help explain variable clinical presentations and response to treatments. While risk factors for COVID-19 have been described, COVID-19 endotypes have not been elucidated. Objectives: We sought to identify and describe COVID-19 endotypes of hospitalized patients. Metho...

Background Artificial intelligence (AI) is increasingly used to support bedside clinical decisions, but information must be presented in usable ways within workflow. Graphical user interfaces (GUI) are front-facing presentations for communicating AI outputs, but clinicians are not routinely invited to participate in their design, hindering AI solut...

Background: Precision medicine focuses on the identification of therapeutic strategies that are effective for a group of patients based on similar unifying characteristics. The recent success of precision medicine in non–critical care settings has resulted from the confluence of large clinical and biospecimen repositories, innovative bioinformatics...

Importance: The evidence for benefit of convalescent plasma for critically ill patients with COVID-19 is inconclusive. Objective: To determine whether convalescent plasma would improve outcomes for critically ill adults with COVID-19. Design, setting, and participants: The ongoing Randomized, Embedded, Multifactorial, Adaptive Platform Trial f...

Exposure to pathogens elicits a complex immune response involving multiple interdependent pathways. This response may mitigate detrimental effects and restore health but, if imbalanced, can lead to negative outcomes including sepsis. This complexity and need for balance pose a challenge for clinicians and have attracted attention from modelers seek...

Deep Reinforcement Learning has achieved superhuman performance in various domains and has potential to provide new insights to open problems in critical care research. However there remain significant challenges which hinder its true potential. We investigate some of such challenges, and empirically show how results can depend on a number of desig...

We combine complementary strengths of Deep Representation Learning and first principle driven mechanistic models, to propose a novel architecture that produces recurrent, robust, patient specific, estimates of non-observable cardiovascular states. Our motivation stems from treating Sepsis at the ICU, where the systemic vascular resistance and cardi...

Eye tracking is used widely to investigate attention and cognitive processes while performing tasks in electronic medical record (EMR) systems. We explored a novel application of eye tracking to collect training data for a machine learning-based clinical decision support tool that predicts which patient data are likely to be relevant for a clinical...

With the extensive deployment of electronic medical record (EMR) systems, EMR usability remains a significant source of frustration to clinicians. There is a significant research need for software that emulates EMR systems and enables investigators to conduct laboratory-based human–computer interaction studies. We developed an open-source software...

Introduction: Higher net ultrafiltration (UFNET) rates are associated with mortality among critically ill patients with acute kidney injury (AKI) and treated with continuous renal replacement therapy (CRRT). Objective: The aim of the study was to discover whether UFNET rates are associated with renal recovery and independence from renal replacem...

PurposeTo study the efficacy of lopinavir-ritonavir and hydroxychloroquine in critically ill patients with coronavirus disease 2019 (COVID-19).Methods Critically ill adults with COVID-19 were randomized to receive lopinavir-ritonavir, hydroxychloroquine, combination therapy of lopinavir-ritonavir and hydroxychloroquine or no antiviral therapy (cont...

Objective: To develop a standardized format for exchanging clinical and physiologic data generated in the intensive care unit. Our goal was to develop a format that would accommodate the data collection pipelines of various sites but would not require dataset-specific schemas or ad-hoc tools for decoding and analysis. Approach: A number of cente...

Background The efficacy of interleukin-6 receptor antagonists in critically ill patients with coronavirus disease 2019 (Covid-19) is unclear. Methods We evaluated tocilizumab and sarilumab in an ongoing international, multifactorial, adaptive platform trial. Adult patients with Covid-19, within 24 hours after starting organ support in the intensiv...

Objectives: Critical care medicine is a natural environment for machine learning approaches to improve outcomes for critically ill patients as admissions to ICUs generate vast amounts of data. However, technical, legal, ethical, and privacy concerns have so far limited the critical care medicine community from making these data readily available....

Big data analytics research using heterogeneous electronic health record (EHR) data requires accurate identification of disease phenotype cases and controls. Overreliance on ground truth determination based on administrative data can lead to biased and inaccurate findings. Hospital-acquired venous thromboembolism (HA-VTE) is challenging to identify...

Biological systems are complex and evolving. Because of the intense network of interaction present, intuition often fails to predict the system-level impact of altering one of a few components of this system. At a preclinical level, gene knock-out mice often result in phenotypes that are more complex than a mouse with the inability to express a giv...

Objectives: To compare 5% albumin with 0.9% saline for large-volume resuscitation (> 60 mL/Kg within 24 hr), on mortality and development of acute kidney injury. Design: Retrospective cohort study. Setting: Patients admitted to ICUs in 13 hospitals across Western Pennsylvania. We analyzed two independent cohorts, the High-Density Intensive Car...

Objective Patient information can be retrieved more efficiently in electronic medical record (EMR) systems by using machine learning models that predict which information a physician will seek in a clinical context. However, information-seeking behavior varies across EMR users. To explicitly account for this variability, we derived hierarchical mod...

Background Maternal hemorrhage protocols involve risk screening. These protocols prepare clinicians for potential hemorrhage and transfusion in individual patients. Patient‐specific estimation and stratification of risk may improve maternal outcomes. Study Design and Methods Prediction models for hemorrhage and transfusion were trained and tested...

Background Even brief hypotension is associated with increased morbidity and mortality. We developed a machine learning model to predict the initial hypotension event among intensive care unit (ICU) patients and designed an alert system for bedside implementation. Materials and methods From the Medical Information Mart for Intensive Care III (MIMI...

Background: There are currently no effective and accurate blood loss volume (BLV) estimation methods that can be implemented in operating rooms. To improve the accuracy and reliability of BLV estimation and facilitate clinical implementation, we propose a novel estimation method using continuously monitored photoplethysmography (PPG) and invasive a...

With extensive deployment of electronic medical record (EMR) systems, EMR usability remains a major source of frustration to clinicians. There is a significant need for a simple EMR software package that will enable investigators to study design and usability in a laboratory setting. We developed an open-source software package that implements the...

Eye-tracking is used widely to investigate visual and cognitive processes in the context of electronic medical record systems. We investigated a novel application of eye tracking to collect training data for machine learning-based clinical decision support. Specifically, we recorded the information-seeking behavior of physicians while they used ele...

Objective Patient information can be retrieved more efficiently in electronic medical record (EMR) systems by using machine learning models that predict which information a physician will seek in a clinical context. However, information-seeking behavior varies across EMR users. To explicitly account for this variability, we derived hierarchical mod...

Background Complex electronic medical records (EMRs) presenting large amounts of data create risks of cognitive overload. We are designing a Learning EMR (LEMR) system that utilizes models of intensive care unit (ICU) physicians' data access patterns to identify and then highlight the most relevant data for each patient. Objectives We used insights...

Background. Even brief hypotension is associated with increased morbidity and mortality. We developed a machine learning model to predict the initial hypotension event among intensive care unit (ICU) patients, and designed an alert system for bedside implementation. Materials and Methods. From the Medical Information Mart for Intensive Care III (MI...

Background and AimsIntracranial compliance refers to the relationship between a change in intracranial volume and the resultant change in intracranial pressure (ICP). Measurement of compliance is useful in managing cardiovascular and respiratory failure; however, there are no contemporary means to assess intracranial compliance. Knowledge of intrac...

Background: Individualized hemodynamic monitoring approaches are not well validated. Thus, we evaluated the discriminative performance improvement that might occur when moving from noninvasive monitoring (NIM) to invasive monitoring and with increasing levels of featurization associated with increasing sampling frequency and referencing to a stabl...