Pooled Population Pharmacokinetic Analysis and Dose Recommendations for Ciprofloxacin in Intensive Care Unit Patients with Obesity.

Recent studies have explored the influence of obesity and critical illness on ciprofloxacin pharmacokinetics. However, variation across the subpopulation of individuals with obesity admitted to the intensive care unit (ICU) with varying renal function remains unexamined. This study aims to characterize ciprofloxacin pharmacokinetics in ICU patients with obesity and provide dose recommendations for this special population. Individual patient data of 34 ICU patients with obesity (BMI >30 kg/m2) from four studies evaluating ciprofloxacin pharmacokinetics in ICU patients were pooled and combined with data from a study involving 10 individuals with obesity undergoing bariatric surgery. All samples were collected after intravenous administration. Non-linear mixed effects modeling and simulation were used to develop a population pharmacokinetic model and describe ciprofloxacin exposure in plasma. Model-based dose evaluations were performed using a pharmacokinetic/pharmacodynamic target of AUC/MIC >125. The data from patients with BMI ranging from 30.2 to 58.1 were best described by a two-compartment model with first-order elimination and a proportional error model. The inclusion of Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) as a covariate on clearance reduced inter-individual variability from 57.3% to 38.5% (P < .001). Neither body weight nor ICU admission significantly influenced clearance or volume of distribution. Renal function is a viable predictor for ciprofloxacin clearance in ICU patients with obesity, while critical illness and body weight do not significantly alter clearance. As such, body weight and critical illness do not need to be accounted for when dosing ciprofloxacin in ICU patients with obesity. Individuals with CKD-EPI >60 mL/min/1.73 m2 may require higher dosages for the treatment of pathogens with minimal inhibitory concentration ≥0.25 mg/L.

The Incidence of Pulmonary Embolism in Hospitalized Non-ICU Patients with COVID-19 during the First Wave: A Multicenter Retrospective Cohort Study in the Netherlands.

INTRODUCTION: During the first COVID-19 outbreak in 2020 in the Netherlands, the incidence of pulmonary embolism (PE) appeared to be high in COVID-19 patients admitted to the intensive care unit (ICU). This study was performed to evaluate the incidence of PE during hospital stay in COVID-19 patients not admitted to the ICU. METHODS: Data were retrospectively collected from 8 hospitals in the Netherlands. Patients admitted between February 27, 2020, and July 31, 2020, were included. Data extracted comprised clinical characteristics, medication use, first onset of COVID-19-related symptoms, admission date due to COVID-19, and date of PE diagnosis. Only polymerase chain reaction (PCR)-positive patients were included. All PEs were diagnosed with computed tomography pulmonary angiography (CTPA). RESULTS: Data from 1,852 patients who were admitted to the hospital ward were collected. Forty patients (2.2%) were diagnosed with PE within 28 days following hospital admission. The median time to PE since admission was 4.5 days (IQR 0.0-9.0). In all 40 patients, PE was diagnosed within the first 2 weeks after hospital admission and for 22 (55%) patients within 2 weeks after onset of symptoms. Patient characteristics, pre-existing comorbidities, anticoagulant use, and laboratory parameters at admission were not related to the development of PE. CONCLUSION: In this retrospective multicenter cohort study of 1,852 COVID-19 patients only admitted to the non-ICU wards, the incidence of CTPA-confirmed PE was 2.2% during the first 4 weeks after onset of symptoms and occurred exclusively within 2 weeks after hospital admission.

Use of artificial intelligence in critical care: opportunities and obstacles.

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 predict future events are commonplace activities of modern life. However, their penetration into acute care medicine has been slow, stuttering and uneven. Major obstacles to widespread effective application of AI approaches to the real-time care of the critically ill patient exist and need to be addressed. MAIN BODY: Clinical decision support systems (CDSSs) in acute and critical care environments support clinicians, not replace them at the bedside. As will be discussed in this review, the reasons are many and include the immaturity of AI-based systems to have situational awareness, the fundamental bias in many large databases that do not reflect the target population of patient being treated making fairness an important issue to address and technical barriers to the timely access to valid data and its display in a fashion useful for clinical workflow. The inherent "black-box" nature of many predictive algorithms and CDSS makes trustworthiness and acceptance by the medical community difficult. Logistically, collating and curating in real-time multidimensional data streams of various sources needed to inform the algorithms and ultimately display relevant clinical decisions support format that adapt to individual patient responses and signatures represent the efferent limb of these systems and is often ignored during initial validation efforts. Similarly, legal and commercial barriers to the access to many existing clinical databases limit studies to address fairness and generalizability of predictive models and management tools. CONCLUSIONS: AI-based CDSS are evolving and are here to stay. It is our obligation to be good shepherds of their use and further development.

Reinforcement learning for intensive care medicine: actionable clinical insights from novel approaches to reward shaping and off-policy model evaluation.

BACKGROUND: Reinforcement learning (RL) holds great promise for intensive care medicine given the abundant availability of data and frequent sequential decision-making. But despite the emergence of promising algorithms, RL driven bedside clinical decision support is still far from reality. Major challenges include trust and safety. To help address these issues, we introduce cross off-policy evaluation and policy restriction and show how detailed policy analysis may increase clinical interpretability. As an example, we apply these in the setting of RL to optimise ventilator settings in intubated covid-19 patients. METHODS: With data from the Dutch ICU Data Warehouse and using an exhaustive hyperparameter grid search, we identified an optimal set of Dueling Double-Deep Q Network RL models. The state space comprised ventilator, medication, and clinical data. The action space focused on positive end-expiratory pressure (peep) and fraction of inspired oxygen (FiO2) concentration. We used gas exchange indices as interim rewards, and mortality and state duration as final rewards. We designed a novel evaluation method called cross off-policy evaluation (OPE) to assess the efficacy of models under varying weightings between the interim and terminal reward components. In addition, we implemented policy restriction to prevent potentially hazardous model actions. We introduce delta-Q to compare physician versus policy action quality and in-depth policy inspection using visualisations. RESULTS: We created trajectories for 1118 intensive care unit (ICU) admissions and trained 69,120 models using 8 model architectures with 128 hyperparameter combinations. For each model, policy restrictions were applied. In the first evaluation step, 17,182/138,240 policies had good performance, but cross-OPE revealed suboptimal performance for 44% of those by varying the reward function used for evaluation. Clinical policy inspection facilitated assessment of action decisions for individual patients, including identification of action space regions that may benefit most from optimisation. CONCLUSION: Cross-OPE can serve as a robust evaluation framework for safe RL model implementation by identifying policies with good generalisability. Policy restriction helps prevent potentially unsafe model recommendations. Finally, the novel delta-Q metric can be used to operationalise RL models in clinical practice. Our findings offer a promising pathway towards application of RL in intensive care medicine and beyond.

Artificial intelligence to advance acute and intensive care medicine.

PURPOSE OF REVIEW: This review explores recent key advancements in artificial intelligence for acute and intensive care medicine. As artificial intelligence rapidly evolves, this review aims to elucidate its current applications, future possibilities, and the vital challenges that are associated with its integration into emergency medical dispatch, triage, medical consultation and ICUs. RECENT FINDINGS: The integration of artificial intelligence in emergency medical dispatch (EMD) facilitates swift and accurate assessment. In the emergency department (ED), artificial intelligence driven triage models leverage diverse patient data for improved outcome predictions, surpassing human performance in retrospective studies. Artificial intelligence can streamline medical documentation in the ED and enhances medical imaging interpretation. The introduction of large multimodal generative models showcases the future potential to process varied biomedical data for comprehensive decision support. In the ICU, artificial intelligence applications range from early warning systems to treatment suggestions. SUMMARY: Despite promising academic strides, widespread artificial intelligence adoption in acute and critical care is hindered by ethical, legal, technical, organizational, and validation challenges. Despite these obstacles, artificial intelligence's potential to streamline clinical workflows is evident. When these barriers are overcome, future advancements in artificial intelligence have the potential to transform the landscape of patient care for acute and intensive care medicine.

Guideline-informed reinforcement learning for mechanical ventilation in critical care.

Reinforcement Learning (RL) has recently found many applications in the healthcare domain thanks to its natural fit to clinical decision-making and ability to learn optimal decisions from observational data. A key challenge in adopting RL-based solution in clinical practice, however, is the inclusion of existing knowledge in learning a suitable solution. Existing knowledge from e.g. medical guidelines may improve the safety of solutions, produce a better balance between short- and long-term outcomes for patients and increase trust and adoption by clinicians. We present a framework for including knowledge available from medical guidelines in RL. The framework includes components for enforcing safety constraints and an approach that alters the learning signal to better balance short- and long-term outcomes based on these guidelines. We evaluate the framework by extending an existing RL-based mechanical ventilation (MV) approach with clinically established ventilation guidelines. Results from off-policy policy evaluation indicate that our approach has the potential to decrease 90-day mortality while ensuring lung protective ventilation. This framework provides an important stepping stone towards implementations of RL in clinical practice and opens up several avenues for further research.

Does Reinforcement Learning Improve Outcomes for Critically Ill Patients? A Systematic Review and Level-of-Readiness Assessment.

OBJECTIVE: Reinforcement learning (RL) is a machine learning technique uniquely effective at sequential decision-making, which makes it potentially relevant to ICU treatment challenges. We set out to systematically review, assess level-of-readiness and meta-analyze the effect of RL on outcomes for critically ill patients. DATA SOURCES: A systematic search was performed in PubMed, Embase.com, Clarivate Analytics/Web of Science Core Collection, Elsevier/SCOPUS and the Institute of Electrical and Electronics Engineers Xplore Digital Library from inception to March 25, 2022, with subsequent citation tracking. DATA EXTRACTION: Journal articles that used an RL technique in an ICU population and reported on patient health-related outcomes were included for full analysis. Conference papers were included for level-of-readiness assessment only. Descriptive statistics, characteristics of the models, outcome compared with clinician's policy and level-of-readiness were collected. RL-health risk of bias and applicability assessment was performed. DATA SYNTHESIS: A total of 1,033 articles were screened, of which 18 journal articles and 18 conference papers, were included. Thirty of those were prototyping or modeling articles and six were validation articles. All articles reported RL algorithms to outperform clinical decision-making by ICU professionals, but only in retrospective data. The modeling techniques for the state-space, action-space, reward function, RL model training, and evaluation varied widely. The risk of bias was high in all articles, mainly due to the evaluation procedure. CONCLUSION: In this first systematic review on the application of RL in intensive care medicine we found no studies that demonstrated improved patient outcomes from RL-based technologies. All studies reported that RL-agent policies outperformed clinician policies, but such assessments were all based on retrospective off-policy evaluation.

Augmented intelligence facilitates concept mapping across different electronic health records.

INTRODUCTION: With the advent of artificial intelligence, the secondary use of routinely collected medical data from electronic healthcare records (EHR) has become increasingly popular. However, different EHR systems typically use different names for the same medical concepts. This obviously hampers scalable model development and subsequent clinical implementation for decision support. Therefore, converting original parameter names to a so-called ontology, a standardized set of predefined concepts, is necessary but time-consuming and labor-intensive. We therefore propose an augmented intelligence approach to facilitate ontology alignment by predicting correct concepts based on parameter names from raw electronic health record data exports. METHODS: We used the manually mapped parameter names from the multicenter "Dutch ICU data warehouse against COVID-19" sourced from three types of EHR systems to train machine learning models for concept mapping. Data from 29 intensive care units on 38,824 parameters mapped to 1,679 relevant and unique concepts and 38,069 parameters labeled as irrelevant were used for model development and validation. We used the Natural Language Toolkit (NLTK) to preprocess the parameter names based on WordNet cognitive synonyms transformed by term-frequency inverse document frequency (TF-IDF), yielding numeric features. We then trained linear classifiers using stochastic gradient descent for multi-class prediction. Finally, we fine-tuned these predictions using information on distributions of the data associated with each parameter name through similarity score and skewness comparisons. RESULTS: The initial model, trained using data from one hospital organization for each of three EHR systems, scored an overall top 1 precision of 0.744, recall of 0.771, and F1-score of 0.737 on a total of 58,804 parameters. Leave-one-hospital-out analysis returned an average top 1 recall of 0.680 for relevant parameters, which increased to 0.905 for the top 5 predictions. When reducing the training dataset to only include relevant parameters, top 1 recall was 0.811 and top 5 recall was 0.914 for relevant parameters. Performance improvement based on similarity score or skewness comparisons affected at most 5.23% of numeric parameters. CONCLUSION: Augmented intelligence is a promising method to improve concept mapping of parameter names from raw electronic health record data exports. We propose a robust method for mapping data across various domains, facilitating the integration of diverse data sources. However, recall is not perfect, and therefore manual validation of mapping remains essential.

Determining and assessing characteristics of data element names impacting the performance of annotation using Usagi.

INTRODUCTION: Hospitals generate large amounts of data and this data is generally modeled and labeled in a proprietary way, hampering its exchange and integration. Manually annotating data element names to internationally standardized data element identifiers is a time-consuming effort. Tools can support performing this task automatically. This study aimed to determine what factors influence the quality of automatic annotations. METHODS: Data element names were used from the Dutch COVID-19 ICU Data Warehouse containing data on intensive care patients with COVID-19 from 25 hospitals in the Netherlands. In this data warehouse, the data had been merged using a proprietary terminology system while also storing the original hospital labels (synonymous names). Usagi, an OHDSI annotation tool, was used to perform the annotation for the data. A gold standard was used to determine if Usagi made correct annotations. Logistic regression was used to determine if the number of characters, number of words, match score (Usagi's certainty) and hospital label origin influenced Usagi's performance to annotate correctly. RESULTS: Usagi automatically annotated 30.5% of the data element names correctly and 5.5% of the synonymous names. The match score is the best predictor for Usagi finding the correct annotation. It was determined that the AUC of data element names was 0.651 and 0.752 for the synonymous names respectively. The AUC for the individual hospital label origins varied between 0.460 to 0.905. DISCUSSION: The results show that Usagi performed better to annotate the data element names than the synonymous names. The hospital origin in the synonymous names dataset was associated with the amount of correctly annotated concepts. Hospitals that performed better had shorter synonymous names and fewer words. Using shorter data element names or synonymous names should be considered to optimize the automatic annotating process. Overall, the performance of Usagi is too poor to completely rely on for automatic annotation.

Assessing the FAIRness of databases on the EHDEN portal: A case study on two Dutch ICU databases.

OBJECTIVE: To address the growing need for effective data reuse in health research, healthcare institutions need to make their data Findable, Accessible, Interoperable, and Reusable (FAIR). A prevailing method to model databases for interoperability is the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), developed by the Observational Health Data Sciences and Informatics (OHDSI) initiative. A European repository for OMOP CDM-converted databases called the "European Health Data & Evidence Network (EHDEN) portal" was developed, aiming to make these databases Findable and Accessible. This paper aims to assess the FAIRness of databases on the EHDEN portal. MATERIALS AND METHODS: Two researchers involved in the OMOP CDM conversion of separate Dutch Intensive Care Unit (ICU) research databases each manually assessed their own database using seventeen metrics. These were defined by the FAIRsFAIR project as a list of minimum requirements for a database to be FAIR. Each metric is given a score from zero to four based on how well the database adheres to the metric. The maximum score for each metric varies from one to four based on the importance of the metric. RESULTS: Fourteen out of the seventeen metrics were unanimously rated: seven were rated the highest score, one was rated half of the highest score, and five were rated the lowest score. The remaining three metrics were assessed differently for the two use cases. The total scores achieved were 15.5 and 12 out of a maximum of 25. CONCLUSION: The main omissions in supporting FAIRness were the lack of globally unique identifiers such as Uniform Resource Identifiers (URIs) in the OMOP CDM and the lack of metadata standardization and linkage in the EHDEN portal. By implementing these in future updates, the EHDEN portal can be more FAIR.

A guide to sharing open healthcare data under the General Data Protection Regulation.

Sharing healthcare data is increasingly essential for developing data-driven improvements in patient care at the Intensive Care Unit (ICU). However, it is also very challenging under the strict privacy legislation of the European Union (EU). Therefore, we explored four successful open ICU healthcare databases to determine how open healthcare data can be shared appropriately in the EU. A questionnaire was constructed based on the Delphi method. Then, follow-up questions were discussed with experts from the four databases. These experts encountered similar challenges and regarded ethical and legal aspects to be the most challenging. Based on the approaches of the databases, expert opinion, and literature research, we outline four distinct approaches to openly sharing healthcare data, each with varying implications regarding data security, ease of use, sustainability, and implementability. Ultimately, we formulate seven recommendations for sharing open healthcare data to guide future initiatives in sharing open healthcare data to improve patient care and advance healthcare.

Generalizable calibrated machine learning models for real-time atrial fibrillation risk prediction in ICU patients.

BACKGROUND: Atrial Fibrillation (AF) is the most common arrhythmia in the intensive care unit (ICU) and is associated with increased morbidity and mortality. Identification of patients at risk for AF is not routinely performed as AF prediction models are almost solely developed for the general population or for particular ICU populations. However, early AF risk identification could help to take targeted preemptive actions and possibly reduce morbidity and mortality. Predictive models need to be validated across hospitals with different standards of care and convey their predictions in a clinically useful manner. Therefore, we designed AF risk models for ICU patients using uncertainty quantification to provide a risk score and evaluated them on multiple ICU datasets. METHODS: Three CatBoost models, utilizing feature windows comprising data 1.5-13.5, 6-18, or 12-24 hours before AF occurrence, were built using 2-repeat-10-fold cross-validation on AmsterdamUMCdb, the first freely available European ICU database. Furthermore, AF Patients were matched with no-AF patients for training. Transferability was validated using a direct and a recalibration evaluation on two independent external datasets, MIMIC-IV and GUH. The calibration of the predicted probability, used as an AF risk score, was measured using the Expected Calibration Error (ECE) and the presented Expected Signed Calibration Error (ESCE). Additionally, all models were evaluated across time during the ICU stay. RESULTS: The model performance reached Areas Under the Curve (AUCs) of 0.81 at internal validation. Direct external validation showed partial generalizability with AUCs reaching 0.77. However, recalibration resulted in performances matching or exceeding that of the internal validation. All models furthermore showed calibration capabilities demonstrating adequate risk prediction competence. CONCLUSION: Ultimately, recalibrating models reduces the challenge of generalization to unseen datasets. Moreover, utilizing the patient-matching methodology together with the assessment of uncertainty calibration can serve as a step toward the development of clinical AF prediction models.

Age-related changes in plasma biomarkers and their association with mortality in COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19)-induced mortality occurs predominantly in older patients. Several immunomodulating therapies seem less beneficial in these patients. The biological substrate behind these observations is unknown. The aim of this study was to obtain insight into the association between ageing, the host response and mortality in patients with COVID-19. METHODS: We determined 43 biomarkers reflective of alterations in four pathophysiological domains: endothelial cell and coagulation activation, inflammation and organ damage, and cytokine and chemokine release. We used mediation analysis to associate ageing-driven alterations in the host response with 30-day mortality. Biomarkers associated with both ageing and mortality were validated in an intensive care unit and external cohort. RESULTS: 464 general ward patients with COVID-19 were stratified according to age decades. Increasing age was an independent risk factor for 30-day mortality. Ageing was associated with alterations in each of the host response domains, characterised by greater activation of the endothelium and coagulation system and stronger elevation of inflammation and organ damage markers, which was independent of an increase in age-related comorbidities. Soluble tumour necrosis factor receptor 1, soluble triggering receptor expressed on myeloid cells 1 and soluble thrombomodulin showed the strongest correlation with ageing and explained part of the ageing-driven increase in 30-day mortality (proportion mediated: 13.0%, 12.9% and 12.6%, respectively). CONCLUSIONS: Ageing is associated with a strong and broad modification of the host response to COVID-19, and specific immune changes likely contribute to increased mortality in older patients. These results may provide insight into potential age-specific immunomodulatory targets in COVID-19.

Evolution of Clinical Phenotypes of COVID-19 Patients During Intensive Care Treatment: An Unsupervised Machine Learning Analysis.

BACKGROUND: Identification of clinical phenotypes in critically ill COVID-19 patients could improve understanding of the disease heterogeneity and enable prognostic and predictive enrichment. However, previous attempts did not take into account temporal dynamics with high granularity. By including the dimension of time, we aim to gain further insights into the heterogeneity of COVID-19. METHODS: We used granular data from 3202 adult COVID patients in the Dutch Data Warehouse that were admitted to one of 25 Dutch ICUs between February 2020 and March 2021. Parameters including demographics, clinical observations, medications, laboratory values, vital signs, and data from life support devices were selected. Twenty-one datasets were created that each covered 24 h of ICU data for each day of ICU treatment. Clinical phenotypes in each dataset were identified by performing cluster analyses. Both evolution of the clinical phenotypes over time and patient allocation to these clusters over time were tracked. RESULTS: The final patient cohort consisted of 2438 COVID-19 patients with a ICU mortality outcome. Forty-one parameters were chosen for cluster analysis. On admission, both a mild and a severe clinical phenotype were found. After day 4, the severe phenotype split into an intermediate and a severe phenotype for 11 consecutive days. Heterogeneity between phenotypes appears to be driven by inflammation and dead space ventilation. During the 21-day period, only 8.2% and 4.6% of patients in the initial mild and severe clusters remained assigned to the same phenotype respectively. The clinical phenotype half-life was between 5 and 6 days for the mild and severe phenotypes, and about 3 days for the medium severe phenotype. CONCLUSIONS: Patients typically do not remain in the same cluster throughout intensive care treatment. This may have important implications for prognostic or predictive enrichment. Prominent dissimilarities between clinical phenotypes are predominantly driven by inflammation and dead space ventilation.

Diagnosing acute kidney injury ahead of time in critically ill septic patients using kinetic estimated glomerular filtration rate.

INTRODUCTION: Accurate and actionable diagnosis of Acute Kidney Injury (AKI) ahead of time is important to prevent or mitigate renal insufficiency. The purpose of this study was to evaluate the performance of Kinetic estimated Glomerular Filtration Rate (KeGFR) in timely predicting AKI in critically ill septic patients. METHODS: We conducted a retrospective analysis on septic ICU patients who developed AKI in AmsterdamUMCdb, the first freely available European ICU database. The reference standard for AKI was the Kidney Disease: Improving Global Outcomes (KDIGO) classification based on serum creatinine and urine output (UO). Prediction of AKI was based on stages defined by KeGFR and UO. Classifications were compared by length of ICU stay (LOS), need for renal replacement therapy and 28-day mortality. Predictive performance and time between prediction and diagnosis were calculated. RESULTS: Of 2492 patients in the cohort, 1560 (62.0%) were diagnosed with AKI by KDIGO and 1706 (68.5%) by KeGFR criteria. Disease stages had agreement of kappa = 0.77, with KeGFR sensitivity 93.2%, specificity 73.0% and accuracy 85.7%. Median time to recognition of AKI Stage 1 was 13.2 h faster for KeGFR, and 7.5 h and 5.0 h for Stages 2 and 3. Outcomes revealed a slight difference in LOS and 28-day mortality for Stage 1. CONCLUSIONS: Predictive performance of KeGFR combined with UO criteria for diagnosing AKI is excellent. Compared to KDIGO, deterioration of renal function was identified earlier, most prominently for lower stages of AKI. This may shift the actionable window for preventing and mitigating renal insufficiency.

Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis.

BACKGROUND: The optimal indication, dose, and timing of corticosteroids in sepsis is controversial. Here, we used reinforcement learning to derive the optimal steroid policy in septic patients based on data on 3051 ICU admissions from the AmsterdamUMCdb intensive care database. METHODS: We identified septic patients according to the 2016 consensus definition. An actor-critic RL algorithm using ICU mortality as a reward signal was developed to determine the optimal treatment policy from time-series data on 277 clinical parameters. We performed off-policy evaluation and testing in independent subsets to assess the algorithm's performance. RESULTS: Agreement between the RL agent's policy and the actual documented treatment reached 59%. Our RL agent's treatment policy was more restrictive compared to the actual clinician behavior: our algorithm suggested withholding corticosteroids in 62% of the patient states, versus 52% according to the physicians' policy. The 95% lower bound of the expected reward was higher for the RL agent than clinicians' historical decisions. ICU mortality after concordant action in the testing dataset was lower both when corticosteroids had been withheld and when corticosteroids had been prescribed by the virtual agent. The most relevant variables were vital parameters and laboratory values, such as blood pressure, heart rate, leucocyte count, and glycemia. CONCLUSIONS: Individualized use of corticosteroids in sepsis may result in a mortality benefit, but optimal treatment policy may be more restrictive than the routine clinical practice. Whilst external validation is needed, our study motivates a 'precision-medicine' approach to future prospective controlled trials and practice.