Search

Background: The evident influence of GLP-1 agonists as semaglutide on gastric emptying even in adherence to recommended fasting protocols instigates debates., Objective: To investigate the effect of semaglutide on gastric content by gastric ultrasonography in volunteers., Setting: Private hospital., Methods: The present study is an observational, cross-sectional, and single-center study. We included 30 consecutive volunteers aged ≥18 years who had undergone a minimum fasting period of 8 hours for solid foods and 2 hours for clear, residue-free liquids. The intervention group consisted of 15 volunteers who had used semaglutide within the last 7 days, whereas the control group consisted of 15 volunteers who had never used semaglutide. The main objective was to determine whether the stomach was full or not., Results: Between June 2023 and August 2023, a total of 30 adult volunteers were included in the study, and no participant was excluded. The semaglutide group exhibited a higher prevalence of full stomach (11 of 15 [73%] versus 1 of 15 [7%], P < .001; adjusted to age P = .003). The semaglutide group also exhibited a higher prevalence of early satiety (10 of 15 [67%] versus 0 of 15 [0%], P < .001), loss of appetite (10 of 15 [67%] versus 0 of 15 [0%], P < .001), gastric fullness (8 of 15 [53%] versus 0 of 15 [0%], P = .002), and nausea (7 of 15 [47%] versus 1 of 15 [7%], P = .035). Additionally, there is no case in the semaglutide group with no gastric contents., Conclusions: The use of semaglutide is associated with full stomach even after appropriate overnight fasting. Semaglutide is also associated with increased gastrointestinal symptoms such as loss of appetite, early satiety, gastric fullness, and nausea., (Copyright © 2024 American Society for Metabolic and Bariatric Surgery. Published by Elsevier Inc. All rights reserved.)

Importance: Maneuvers assessing fluid responsiveness before an intravascular volume expansion may limit useless fluid administration, which in turn may improve outcomes., Objective: To describe maneuvers for assessing fluid responsiveness in mechanically ventilated patients., Registration: The protocol was registered at PROSPERO: CRD42019146781., Information Sources and Search: PubMed, EMBASE, CINAHL, SCOPUS, and Web of Science were search from inception to 08/08/2023., Study Selection and Data Collection: Prospective and intervention studies were selected., Statistical Analysis: Data for each maneuver were reported individually and data from the five most employed maneuvers were aggregated. A traditional and a Bayesian meta-analysis approach were performed., Results: A total of 69 studies, encompassing 3185 fluid challenges and 2711 patients were analyzed. The prevalence of fluid responsiveness was 49.9%. Pulse pressure variation (PPV) was studied in 40 studies, mean threshold with 95% confidence intervals (95% CI) = 11.5 (10.5-12.4)%, and area under the receiver operating characteristics curve (AUC) with 95% CI was 0.87 (0.84-0.90). Stroke volume variation (SVV) was studied in 24 studies, mean threshold with 95% CI = 12.1 (10.9-13.3)%, and AUC with 95% CI was 0.87 (0.84-0.91). The plethysmographic variability index (PVI) was studied in 17 studies, mean threshold = 13.8 (12.3-15.3)%, and AUC was 0.88 (0.82-0.94). Central venous pressure (CVP) was studied in 12 studies, mean threshold with 95% CI = 9.0 (7.7-10.1) mmHg, and AUC with 95% CI was 0.77 (0.69-0.87). Inferior vena cava variation (∆IVC) was studied in 8 studies, mean threshold = 15.4 (13.3-17.6)%, and AUC with 95% CI was 0.83 (0.78-0.89)., Conclusions: Fluid responsiveness can be reliably assessed in adult patients under mechanical ventilation. Among the five maneuvers compared in predicting fluid responsiveness, PPV, SVV, and PVI were superior to CVP and ∆IVC. However, there is no data supporting any of the above mentioned as being the best maneuver. Additionally, other well-established tests, such as the passive leg raising test, end-expiratory occlusion test, and tidal volume challenge, are also reliable., (© 2024. The Author(s).)

Background: Acute Gastrointestinal Injury (AGI) is associated with adverse clinical outcomes, including increased mortality. We aimed to investigate the potential of citrulline and intestinal fatty acid binding protein (I-FABP) as biomarkers for early AGI diagnosis and predicting outcomes in surgical patients., Methods: Prospective cohort study involving patients who underwent non-cardiac surgeries and were admitted to Intensive Care Units. AGI diagnosis was based on specific criteria, and severity was categorised following established guidelines. Statistical analyses were performed to assess the diagnostic accuracy of the biomarkers and their association with outcomes, P significant when <0.05., Results: AGI was identified in 40.3% of patients with varying severity. Mortality rates were significantly higher in the AGI group in the ICU (19.4% vs. 0%, p = 0.001) and hospital (22.6% vs. 2.17%, p = 0.003). Urinary I-FABP levels on days 3 and 7 showed reasonable and good accuracy for AGI diagnosis (AUC 0.732 and 0.813, respectively). Urinary I-FABP levels on days 2 and 3 accurately predict sepsis. Urinary citrulline levels on day one predicted mortality (AUC 0.87) furthermore urinary I-FABP levels on day 2 showed reasonable accuracy (sensitivity 83.3%, specificity 92.4%)., Conclusion: Urinary I-FABP and citrulline levels are promising diagnostic and prognostic markers in ICU patients following non-cardiac surgeries., Competing Interests: Declaration of competing interest There are no conflicts of interest by any of the authors. I remain at your disposal in case of any pending questions., (Copyright © 2024 Elsevier Inc. All rights reserved.)

Purpose: Limited evidence exists regarding outcomes associated with different correction rates of severe hyponatremia., Materials and Methods: This retrospective cohort analysis employed a multi-center ICU database to identify patients with sodium ≤120 mEq/L during ICU admission. We determined correction rates over the first 24 h and categorized them as rapid (> 8 mEq/L/day) or slow (≤ 8 mEq/L/day). The primary outcome was in-hospital mortality. Secondary outcomes included hospital-free days, ICU-free days, and neurological complications. We used inverse probability weighting for confounder adjustment., Results: Our cohort included 1024 patients; 451 rapid and 573 slow correctors. Rapid correction was associated with lower in-hospital mortality (absolute difference: -4.37%; 95% CI, -8.47 to -0.26%), longer hospital-free days (1.80 days; 95% CI, 0.82 to 2.79 days), and longer ICU-free days (1.16 days; 95% CI, 0.15 to 2.17 days). There was no significant difference in neurological complications (2.31%; 95% CI, -0.77 to 5.40%)., Conclusion: Rapid correction (>8 mEq/L/day) of severe hyponatremia within the first 24 h was associated with lower in-hospital mortality and longer ICU and hospital-free days without an increase in neurological complication. Despite major limitations, including the inability to identify the chronicity of hyponatremia, the results have important implications and warrant prospective studies., Competing Interests: Declaration of Competing Interest LAC is funded by the National Institute of Health through NIBIB R01 EB017205. The work of NHR is supported by T32-DK007199 and the Doris Duke Charitable Foundation Physician Scientist Fellowship Award Grant# 202182. The work of TK was supported by a Fulbright Japan Graduate Study Program. EM, QX, RS have no declarations of interest., (Copyright © 2023 Elsevier Inc. All rights reserved.)

The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care., (© 2022. The Author(s).)

In this study, we investigated the baseline characteristics and "trajectories" of clinical response in men and women after cardiac resynchronization therapy (CRT) implantation. Although women enjoy improved echocardiographic response after CRT compared with men, the kinetics of this response and its relation to functional performance and outcomes are less clear. We identified 592 patients who underwent CRT implantation at our center between 2004 and 2017 and were serially followed in a multidisciplinary clinic. Longitudinal linear mixed effects regression for cardiac response was specified, including interaction terms between time after CRT and sex , and Cox regression models were used to assess differences in all-cause mortality by gender after CRT. Women in our cohort were younger than men, had less frequent ischemic etiology of heart failure (24% vs 60% in men), a shorter QRS (151 vs 161 ms) and more frequent left bundle branch block (77% vs 52%) at baseline. Women had a greater improvement in left ventricular ejection fraction that was evident starting at approximately 1-month after CRT. We did not observe effect modification by gender in New York Heart Association class or 6-minute walk distance after CRT. Although women had improved mortality after CRT, after adjustment for potential confounders, gender was not associated with mortality after CRT. In conclusion, women were more likely to have CRT implantation for left bundle branch block and exhibited improved echocardiographic but not functional response within the first year after CRT. Clinical outcomes after CRT were not associated with gender in adjusted analysis., Competing Interests: Disclosures Dr. Das is a founding member and holds equity for LQT Therapeutics and Switch Therapeutics and receives research grant from Abbott. Dr. Singh has consulted for Abbott, Boston Scientific, Biotronik, CVRx, Cardiologs, Medtronic, Microport, EBR, Impulse Dynamics, Nopras Inc, National Century Health, Sanofi Inc., and Toray Inc. Dr. Heist has consulted for Boston Scientific, Pfizer, Medtronic, and Abbott; has equity in Oracle Health and receives research grant from Biotronik. The remaining authors have no conflicts of interest to declare., (Copyright © 2022 Elsevier Inc. All rights reserved.)

Objective: Our objective was to study the clinical monitoring capabilities of a low-cost fitness wristband while measuring patient satisfaction with a mobility permitting device in the emergency department., Methods: Patients enrolled were on continuous three-lead telemetry monitoring in a high acuity zone of the emergency department. Patients were given a fitness band to wear while simultaneously monitored with standard three-lead monitor. A brief survey was conducted upon study end, and data was compared between wristband and three-lead telemetry. Median heart rate (HR) values were calculated, a Bland-Altman plot was generated, and sensitivity and specificity were calculated for comparison of the formal telemetry and the inexpensive wristband., Results: Thirty-four patients with an average age of 61.5 years were enrolled. From June to October 2019, over 100 hours of data were collected. In comparison for comfort, participants scored 9.5 of 10, preferring wristband over telemetry. Using a correlation coefficient graph, we found a significant disparity of HR readings within a telemetry range of 40 to 140 beats/min. An R-value of 0.36 was detected. Using a Bland-Altman plot, we observed a significant difference in HR between the telemetry monitor and the wristband. The sensitivity and specificity of the wristband to detect bradycardia (HR <60 beats/min) were 76% and 86%, respectively, while the sensitivity and specificity of the wristband to detect tachycardia (HR >100 beats/min) were 92% and 51%, respectively., Conclusion: Inexpensive fitness bands cannot be a suitable tool for monitoring patient's HR because of inaccuracy in detecting bradycardia or tachycardia.

Importance: Heart failure with preserved ejection fraction (HFpEF) is a joint metabolic and cardiovascular disorder with significant noncardiac contributions., Objective: To define and quantify the metabolic cost of initiating exercise in individuals with and without HFpEF and its functional consequences., Design, Setting, and Participants: This prospective cohort study included individuals with hemodynamically confirmed HFpEF from the Massachusetts General Hospital Exercise Study (MGH-ExS) and community-dwelling participants from the Framingham Heart Study (FHS). Analysis began April 2016 and ended November 2020., Exposures: Internal work (IW), a measure of work equivalents required to initiate movement., Main Outcomes and Measures: Using breath-by-breath oxygen uptake (V̇o2) measurements and V̇o2-work rate associations, cost of initiating exercise (IW) in patients with HFpEF (MGH-ExS) and in community-dwelling individuals (FHS) was quantified. Linear regression was used to estimate associations between IW and clinical/hemodynamic measures., Results: Of 3231 patients, 184 (5.7%) had HFpEF and were from MGH-ExS, and 3047 (94.3%) were community-dwelling individuals from FHS. In the MGH-ExS cohort, 86 (47%) were women, the median (interquartile range) age was 63 (53-72) years, and the median (interquartile range) peak V̇o2 level was 13.33 (11.77-15.62) mL/kg/min. In the FHS cohort, 1620 (53%) were women, the median (interquartile range) age was 54 (48-60) years, and the median (interquartile range) peak V̇o2 level was 22.2 (17.85-27.35) mL/kg/min. IW was higher in patients with HFpEF and accounted for 27% (interquartile range, 21%-39%) of the total work (IW + measured external workload on the cycle), compared with 15% (interquartile range, 12%-20%) of that in FHS participants. Body mass index accounted for greatest explained variance in patients with HFpEF from MGH-ExS and FHS participants (22% and 18%, respectively), while resting cardiac output and biventricular filling pressures were not significantly associated with variance in IW in patients with HFpEF. A higher IW in patients with HFpEF was associated with a greater increase in left- and right-sided cardiac filing pressure during unloaded exercise, despite similar resting hemodynamic measures across IW., Conclusions and Relevance: This study found that internal work, a new body mass index-related measure reflecting the metabolic cost of initiating movement, is higher in individuals with HFpEF compared with middle-aged adults in the community and is associated with steep, early increases in cardiac filling pressures. These findings highlight the importance of quantifying heterogeneous responses to exercise initiation when evaluating functional intolerance in individuals at risk for or with HFpEF.

Coronavirus disease 2019 (COVID-19) is a respiratory disease with rapid human-to-human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to the exponential growth of infections, identifying patients with the highest mortality risk early is critical to enable effective intervention and prioritisation of care. Here, we present the COVID-19 early warning system (CovEWS), a risk scoring system for assessing COVID-19 related mortality risk that we developed using data amounting to a total of over 2863 years of observation time from a cohort of 66 430 patients seen at over 69 healthcare institutions. On an external cohort of 5005 patients, CovEWS predicts mortality from 78.8% (95% confidence interval [CI]: 76.0, 84.7%) to 69.4% (95% CI: 57.6, 75.2%) specificity at sensitivities greater than 95% between, respectively, 1 and 192 h prior to mortality events. CovEWS could enable earlier intervention, and may therefore help in preventing or mitigating COVID-19 related mortality.

Accurate outcome prediction in Intensive Care Units (ICUs) would allow for better treatment planning, risk adjustment of study populations, and overall improvements in patient care. In the past, prognostic models have focused on mortality using simple ordinal severity of illness scores which could be tabulated manually by a human. With the improvements in computing power and proliferation of electronic medical records, entirely new approaches have become possible. Here we review the latest advances in outcome prediction, paying close attention to methods which are widely applicable and provide a high-level overview of the challenges the field currently faces., Competing Interests: Declaration of Competing Interest ROD is an employee to Endpoint Health Inc. The other authors report no conflict of interest to declare., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Machine learning (ML) is a discipline of computer science in which statistical methods are applied to data in order to classify, predict, or optimize, based on previously observed data. Pulmonary and critical care medicine have seen a surge in the application of this methodology, potentially delivering improvements in our ability to diagnose, treat, and better understand a multitude of disease states. Here we review the literature and provide a detailed overview of the recent advances in ML as applied to these areas of medicine. In addition, we discuss both the significant benefits of this work as well as the challenges in the implementation and acceptance of this non-traditional methodology for clinical purposes.

Emergency department triage is the first point in time when a patient's acuity level is determined. The time to assign a priority at triage is short and it is vital to accurately stratify patients at this stage, since under-triage can lead to increased morbidity, mortality and costs. Our aim was to present a model that can assist healthcare professionals in triage decision making, namely in the stratification of patients through the risk prediction of a composite critical outcome-mortality and cardiopulmonary arrest. Our study cohort consisted of 235826 adult patients triaged at a Portuguese Emergency Department from 2012 to 2016. Patients were assigned to emergent, very urgent or urgent priorities of the Manchester Triage System (MTS). Demographics, clinical variables routinely collected at triage and the patients' chief complaint were used. Logistic regression, random forests and extreme gradient boosting were developed using all available variables. The term frequency-inverse document frequency (TF-IDF) natural language processing weighting factor was applied to vectorize the chief complaint. Stratified random sampling was used to split the data into train (70%) and test (30%) data sets. Ten-fold cross validation was performed in train to optimize model hyper-parameters. The performance obtained with the best model was compared against the reference model-a regularized logistic regression trained using only triage priorities. Extreme gradient boosting exhibited good calibration properties and yielded areas under the receiver operating characteristic and precision-recall curves of 0.96 (95% CI 0.95-0.97) and 0.31 (95% CI 0.26-0.36), respectively. The predictors ranked with higher importance by this model were the Glasgow coma score, the patients' age, pulse oximetry and arrival mode. Compared to the reference, the extreme gradient boosting model using clinical variables and the chief complaint presented higher recall for patients assigned MTS-3 and can identify those who are at risk of the composite outcome., Competing Interests: The authors have declared that no competing interests exist.

Rationale: Whether critical care improvements over the last 10 years extend to all hospitals has not been described. Objectives: To examine the temporal trends of critical care outcomes in minority and non-minority-serving hospitals using an inception cohort of critically ill patients. Measurements and Main Results: Using the Philips Health Care electronic ICU Research Institute Database, we identified minority-serving hospitals as those with an African American or Hispanic ICU census more than twice its regional mean. We examined almost 1.1 million critical illness admissions among 208 ICUs from across the United States admitted between 2006 and 2016. Adjusted hospital mortality (primary) and length of hospitalization (secondary) were the main outcomes. Large pluralities of African American (25%, n  = 27,242) and Hispanic individuals (48%, n  = 26,743) were cared for in minority-serving hospitals, compared with only 5.2% ( n  = 42,941) of white individuals. Over the last 10 years, although the risk of critical illness mortality steadily decreased by 2% per year (95% confidence interval [CI], 0.97-0.98) in non-minority-serving hospitals, outcomes within minority-serving hospitals did not improve comparably. This disparity in temporal trends was particularly noticeable among African American individuals, where each additional calendar year was associated with a 3% (95% CI, 0.96-0.97) lower adjusted critical illness mortality within a non-minority-serving hospital, but no change within minority-serving hospitals (hazard ratio, 0.99; 95% CI, 0.97-1.01). Similarly, although ICU and hospital lengths of stay decreased by 0.08 (95% CI, -0.08 to -0.07) and 0.16 (95% CI, -0.16 to -0.15) days per additional calendar year, respectively, in non-minority-serving hospitals, there was little temporal change for African American individuals in minority-serving hospitals. Conclusions: Critically ill African American individuals are disproportionately cared for in minority-serving hospitals, which have shown significantly less improvement than non-minority-serving hospitals over the last 10 years.

The risk stratification of patients in the emergency department begins at triage. It is vital to stratify patients early based on their severity, since undertriage can lead to increased morbidity, mortality and costs. Our aim was to present a new approach to assist healthcare professionals at triage in the stratification of patients and in identifying those with higher risk of ICU admission. Adult patients assigned Manchester Triage System (MTS) or Emergency Severity Index (ESI) 1 to 3 from a Portuguese and a United States Emergency Departments were analyzed. Variables routinely collected at triage were used and natural language processing was applied to the patient chief complaint. Stratified random sampling was applied to split the data in train (70%) and test (30%) sets and 10-fold cross validation was performed for model training. Logistic regression, random forests, and a random undersampling boosting algorithm were used. We compared the performance obtained with the reference model-using only triage priorities-with the models using additional variables. For both hospitals, a logistic regression model achieved higher overall performance, yielding areas under the receiver operating characteristic and precision-recall curves of 0.91 (95% CI 0.90-0.92) and 0.30 (95% CI 0.27-0.33) for the United States hospital and of 0.85 (95% CI 0.83-0.86) and 0.06 (95% CI 0.05-0.07) for the Portuguese hospital. Heart rate, pulse oximetry, respiratory rate and systolic blood pressure were the most important predictors of ICU admission. Compared to the reference models, the models using clinical variables and the chief complaint presented higher recall for patients assigned MTS/ESI 3 and can identify patients assigned MTS/ESI 3 who are at risk for ICU admission., Competing Interests: The authors have declared that no competing interests exist.

Objective: Severity of illness scores used in critical care for benchmarking, quality assurance and risk stratification have been mainly created in high-income countries. In low and middle-income countries (LMICs), they cannot be widely utilized due to the demand for large amounts of data that may not be available (e.g. laboratory results). We attempt to create a new severity prognostication model using fewer variables that are easier to collect in an LMIC., Setting: Two intensive care units, one private and one public, from São Paulo, Brazil PATIENTS: An ICU for the first time., Interventions: None., Measurements and Mains Results: The dataset from the private ICU was used as a training set for model development to predict in-hospital mortality. Three different machine learning models were applied to five different blocks of candidate variables. The resulting 15 models were then validated on a separate dataset from the public ICU, and discrimination and calibration compared to identify the best model. The best performing model used logistic regression on a small set of 10 variables: highest respiratory rate, lowest systolic blood pressure, highest body temperature and Glasgow Coma Scale during the first hour of ICU admission; age; prior functional capacity; type of ICU admission; source of ICU admission; and length of hospital stay prior to ICU admission. On the validation dataset, our new score, named SEVERITAS, had an area under the receiver operating curve of 0.84 (0.82 - 0.86) and standardized mortality ratio of 1.00 (0.91-1.08). Moreover, SEVERITAS had similar discrimination compared to SAPS-3 and better discrimination than the simplified TropICS and R-MPM., Conclusions: Our study proposes a new ICU mortality prediction model using simple logistic regression on a small set of easily collected variables may be better suited than currently available models for use in low and middle-income countries., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Objectives: Although one third or more of critically ill patients in the United States are obese, obesity is not incorporated as a contributing factor in any of the commonly used severity of illness scores. We hypothesize that selected severity of illness scores would perform differently if body mass index categorization was incorporated and that the performance of these score models would improve after consideration of body mass index as an additional model feature., Design: Retrospective cohort analysis from a multicenter ICU database which contains deidentified data for more than 200,000 ICU admissions from 208 distinct ICUs across the United States between 2014 and 2015., Setting: First ICU admission of patients with documented height and weight., Patients: One-hundred eight-thousand four-hundred two patients from 189 different ICUs across United States were included in the analyses, of whom 4,661 (4%) were classified as underweight, 32,134 (30%) as normal weight, 32,278 (30%) as overweight, 30,259 (28%) as obese, and 9,070 (8%) as morbidly obese., Interventions: None., Measurements and Main Results: To assess the effect of adding body mass index as a risk adjustment element to the Acute Physiology and Chronic Health Evaluation IV and Oxford Acute Severity of Illness scoring systems, we examined the impact of this addition on both discrimination and calibration. We performed three assessments based upon 1) the original scoring systems, 2) a recalibrated version of the systems, and 3) a recalibrated version incorporating body mass index as a covariate. We also performed a subgroup analysis in groups defined using World Health Organization guidelines for obesity. Incorporating body mass index into the models provided a minor improvement in both discrimination and calibration. In a subgroup analysis, model discrimination was higher in groups with higher body mass index, but calibration worsened., Conclusions: The performance of ICU prognostic models utilizing body mass index category as a scoring element was inconsistent across body mass index categories. Overall, adding body mass index as a risk adjustment variable led only to a minor improvement in scoring system performance.

In secondary analysis of electronic health records, a crucial task consists in correctly identifying the patient cohort under investigation. In many cases, the most valuable and relevant information for an accurate classification of medical conditions exist only in clinical narratives. Therefore, it is necessary to use natural language processing (NLP) techniques to extract and evaluate these narratives. The most commonly used approach to this problem relies on extracting a number of clinician-defined medical concepts from text and using machine learning techniques to identify whether a particular patient has a certain condition. However, recent advances in deep learning and NLP enable models to learn a rich representation of (medical) language. Convolutional neural networks (CNN) for text classification can augment the existing techniques by leveraging the representation of language to learn which phrases in a text are relevant for a given medical condition. In this work, we compare concept extraction based methods with CNNs and other commonly used models in NLP in ten phenotyping tasks using 1,610 discharge summaries from the MIMIC-III database. We show that CNNs outperform concept extraction based methods in almost all of the tasks, with an improvement in F1-score of up to 26 and up to 7 percentage points in area under the ROC curve (AUC). We additionally assess the interpretability of both approaches by presenting and evaluating methods that calculate and extract the most salient phrases for a prediction. The results indicate that CNNs are a valid alternative to existing approaches in patient phenotyping and cohort identification, and should be further investigated. Moreover, the deep learning approach presented in this paper can be used to assist clinicians during chart review or support the extraction of billing codes from text by identifying and highlighting relevant phrases for various medical conditions.