scholarly journals Prediction of Unplanned 30- day Readmission for ICU Patients with Heart Failure

2021 ◽  
Author(s):  
Maryam Pishgar ◽  
Houshang Darabi ◽  
Julian Theis ◽  
Hadis Anahideh ◽  
Amer Ardati ◽  
...  
Keyword(s):  
Heart Failure ◽  
Intensive Care ◽  
Financial Burden ◽  
Operating Characteristics ◽  
Icu Patients ◽  
Targeted Interventions ◽  
Risk Of Death ◽  
Severity Scores ◽  
Patients With Heart Failure ◽  
Time Information

ABSTRACT Background Intensive Care Unit (ICU) readmissions in patients with Heart Failure (HF) result in a significant risk of death and financial burden for patients and healthcare systems. Prediction of at-risk patients for readmission allows for targeted interventions that reduce morbidity and mortality. Methods and Results We presented a process mining approach for the prediction of unplanned 30-day readmission of ICU patients with HF. A patients health record can be understood as a sequence of observations called event logs; used to discover a process model. Time information was extracted using the DREAM (Decay Replay Mining) algorithm. Demographic information and severity scores upon admission were then combined with the time information and fed to a Neural Network (NN) model to further enhance the prediction efficiency. Results By using the Medical Information Mart for Intensive Care III (MIMIC-III) dataset of 3411 ICU patients with HF, our proposed model yielded an Area Under the Receiver Operating Characteristics (AUROC) of 0.920. Conclusions The proposed approach was capable of modeling the time-related variables and incorporating the medical history of patients from prior hospital visits for prediction. Thus, our approach significantly improved the outcome prediction compared to that of other ML-based models and health calculators.

scholarly journals Deep Learning Model for Mortality Prediction of ICU Patients with Paralytic Ileus

2021 ◽  
Author(s):  
Martha Razo ◽  
Maryam Pishgar ◽  
Houshang Darabi
Keyword(s):  
Intensive Care ◽  
Deep Learning ◽  
Paralytic Ileus ◽  
Significant Risk ◽  
Learning Model ◽  
Mortality Prediction ◽  
Icu Patients ◽  
Targeted Interventions ◽  
Risk Of Death ◽  
Deep Learning Model

AbstractBackgroundParalytic Ileus (PI) patients in the Intensive Care Unit (ICU) are at a significant risk of death. Prediction of at-risk patients for mortality after 24 hours of admission of ICU PI patients is important to increase the life expectancy of PI patients.Methods and ResultsThe proposed framework, DLMP (Deep Learning Model for Mortality Prediction of ICU Patients with PI) is a powerful deep learning model consisting of six total unique clinical lab items and two demographics as inputs to a Neural Network(NN) of only two neuron layers. Using the Medical Information Mart for Intensive Care III (MIMIC-III) dataset of 1,017 ICU PI patients, the DLMP resulted in the best prediction performance with an AUC score of 0.866.ConclusionThe proposed approach is capable of modeling the mortality of ICU patients after 24 hours admission using only six unique total clinical data and two demographics with a simple NN architecture. DLMP framework significantly improves the outcome prediction compared to the process mining and machine learning models. The proposed DLMP has the potential of allowing clinicians to create targeted interventions that reduce mortality for PI patients in an ICU setting.

scholarly journals COVID-19 in patients with heart failure: the new and the old epidemic

2020 ◽  
Vol 97 (1145) ◽  
pp. 175-179
Author(s):  
Nicolò Sisti ◽  
Serafina Valente ◽  
Giulia Elena Mandoli ◽  
Ciro Santoro ◽  
Carlotta Sciaccaluga ◽  
...  
Keyword(s):  
Heart Failure ◽  
Intensive Care ◽  
Cardiovascular Diseases ◽  
Chronic Heart Failure ◽  
Poor Prognosis ◽  
Myocardial Injury ◽  
Careful Monitoring ◽  
Clinical Challenge ◽  
Patients With Heart Failure ◽  
Acute Decompensation

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has spread in nearly 200 countries in less than 4 months since its first identification; accordingly, the coronavirus disease 2019 (COVID 2019) has affirmed itself as a clinical challenge. The prevalence of pre-existing cardiovascular diseases in patients with COVID19 is high and this dreadful combination dictates poor prognosis along with the higher risk of intensive care mortality. In the setting of chronic heart failure, SARS-CoV-2 can be responsible for myocardial injury and acute decompensation through various mechanisms. Given the clinical and epidemiological complexity of COVID-19, patiens with heart failure may require particular care since the viral infection has been identified, considering an adequate re-evaluation of medical therapy and a careful monitoring during ventilation.

scholarly journals Effect of Empagliflozin on the Clinical Stability of Patients with Heart Failure and a Reduced Ejection Fraction: The EMPEROR-Reduced Trial

Circulation ◽  
2020 ◽  
Author(s):  
Milton Packer ◽  
Stefan D. Anker ◽  
Javed Butler ◽  
Gerasimos S. Filippatos ◽  
João Pedro Ferreira ◽  
...  
Keyword(s):  
Heart Failure ◽  
Ejection Fraction ◽  
Functional Class ◽  
Hazard Ratio ◽  
Double Blind ◽  
Reduced Ejection Fraction ◽  
Risk Of Death ◽  
Nyha Functional Class ◽  
Patients With Heart Failure

Background: Empagliflozin reduces the risk of cardiovascular death or hospitalization for heart failure in patients with heart failure and a reduced ejection fraction, with or without diabetes, but additional data are needed about the effect of the drug on inpatient and outpatient events that reflect worsening heart failure. Methods: We randomly assigned 3730 patients with class II-IV heart failure with an ejection fraction of ≤40% to double-blind treatment with placebo or empagliflozin (10 mg once daily), in addition to recommended treatments for heart failure, for a median of 16 months. We prospectively collected information on inpatient and outpatient events reflecting worsening heart failure and prespecified their analysis in individual and composite endpoints. Results: Empagliflozin reduced the combined risk of death, hospitalization for heart failure or an emergent/urgent heart failure visit requiring intravenous treatment (415 vs 519 patients; empagliflozin vs placebo, respectively; hazard ratio 0.76, 95% CI: 0.67-0.87), P <0.0001. This benefit reached statistical significance at 12 days after randomization. Empagliflozin reduced the total number of heart failure hospitalizations that required intensive care (hazard ratio 0.67, 95% CI 0.50-0.90, P=0.008) and that required a vasopressor or positive inotropic drug or mechanical or surgical intervention (hazard ratio 0.64, 95% CI: 0.47-0.87, P=0.005). As compared with placebo, fewer patients in the empagliflozin group reported intensification of diuretics (297 vs 414), hazard ratio 0.67, 95% CI: 0.56-0.78, P<0.0001. Additionally, patients assigned to empagliflozin were 20-40% more likely to experience an improvement in NYHA functional class and were 20-40% less likely to experience worsening of NYHA functional class, with statistically significant effects that were apparent 28 days after randomization and maintained during long-term follow-up. The risk of any inpatient or outpatient worsening heart failure event in the placebo group was high (48.1 per 100 patient-years of follow-up), and it was reduced by empagliflozin (hazard ratio 0.70, 95% CI: 0.63-0.78), P<0.0001. Conclusions: In patients with heart failure and a reduced ejection fraction, empagliflozin reduced the risk and total number of inpatient and outpatient worsening heart failure events, with benefits seen early after initiation of treatment and sustained for the duration of double-blind therapy. Clinical Trial Registration: URL: https://clinicaltrials.gov Unique Identifier: NCT03057977

Atrial fibrillation and the risk of death in patients with heart failure: a literature-based meta-analysis

2009 ◽  
Vol 40 (5) ◽  
pp. 347-356 ◽  
Author(s):  
C. A. Wasywich ◽  
A. J. Pope ◽  
J. Somaratne ◽  
K. K. Poppe ◽  
G. A. Whalley ◽  
...  
Keyword(s):  
Heart Failure ◽  
Atrial Fibrillation ◽  
Meta Analysis ◽  
Risk Of Death ◽  
Patients With Heart Failure

scholarly journals The Utility of Predicting Hospitalizations Among Patients With Heart Failure Using mHealth: Observational Study (Preprint)

2020 ◽  
Author(s):  
Susie Cartledge ◽  
Ralph Maddison ◽  
Sara Vogrin ◽  
Roman Falls ◽  
Odgerel Tumur ◽  
...  
Keyword(s):  
Heart Failure ◽  
Heart Rate ◽  
Respiratory Symptoms ◽  
Low Cost ◽  
Area Under The Curve ◽  
Likert Scale ◽  
Subjective Symptom ◽  
Targeted Interventions ◽  
Patients With Heart Failure ◽  
Heart Failure Decompensation

BACKGROUND Heart failure decompensation is a major driver of hospitalizations and represents a significant burden to the health care system. Identifying those at greatest risk of admission can allow for targeted interventions to reduce this risk. OBJECTIVE This paper aims to compare the predictive value of objective and subjective heart failure respiratory symptoms on imminent heart failure decompensation and subsequent hospitalization within a 30-day period. METHODS A prospective observational pilot study was conducted. People living at home with heart failure were recruited from a single-center heart failure outpatient clinic. Objective (blood pressure, heart rate, weight, B-type natriuretic peptide) and subjective (4 heart failure respiratory symptoms scored for severity on a 5-point Likert scale) data were collected twice weekly for a 30-day period. RESULTS A total of 29 participants (median age 79 years; 18/29, 62% men) completed the study. During the study period, 10 of the 29 participants (34%) were hospitalized as a result of heart failure. For objective data, only heart rate exhibited a between-group difference. However, it was nonsignificant for variability (<i>P</i>=.71). Subjective symptom scores provided better prediction. Specifically, the highest precision of heart failure hospitalization was observed when patients with heart failure experienced severe dyspnea, orthopnea, and bendopnea on any given day (area under the curve of 0.77; sensitivity of 83%; specificity of 73%). CONCLUSIONS The use of subjective respiratory symptom reporting on a 5-point Likert scale may facilitate a simple and low-cost method of predicting heart failure decompensation and imminent hospitalization. Serial collection of symptom data could be augmented using ecological momentary assessment of self-reported symptoms within a mobile health monitoring strategy for patients at high risk for heart failure decompensation.

scholarly journals Prediction of in-hospital mortality of Clostriodiodes difficile infection using critical care database: a big data-driven, machine learning approach

2021 ◽  
Vol 8 (1) ◽  
pp. e000761
Author(s):  
Hao Du ◽  
Kewin Tien Ho Siah ◽  
Valencia Zhang Ru-Yan ◽  
Readon Teh ◽  
Christopher Yu En Tan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Critical Care ◽  
Intensive Care ◽  
Hospital Mortality ◽  
Receiver Operating Curve ◽  
Study Cohort ◽  
Risk Of Death ◽  
Severity Scores ◽  
Mimic Iii ◽  
Care Database

Research objectivesClostriodiodes difficile infection (CDI) is a major cause of healthcare-associated diarrhoea with high mortality. There is a lack of validated predictors for severe outcomes in CDI. The aim of this study is to derive and validate a clinical prediction tool for CDI in-hospital mortality using a large critical care database.MethodologyThe demographics, clinical parameters, laboratory results and mortality of CDI were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. We subsequently trained three machine learning models: logistic regression (LR), random forest (RF) and gradient boosting machine (GBM) to predict in-hospital mortality. The individual performances of the models were compared against current severity scores (Clostridiodes difficile Associated Risk of Death Score (CARDS) and ATLAS (Age, Treatment with systemic antibiotics, leukocyte count, Albumin and Serum creatinine as a measure of renal function) by calculating area under receiver operating curve (AUROC). We identified factors associated with higher mortality risk in each model.Summary of resultsFrom 61 532 intensive care unit stays in the MIMIC-III database, there were 1315 CDI cases. The mortality rate for CDI in the study cohort was 18.33%. AUROC was 0.69 (95% CI, 0.60 to 0.76) for LR, 0.71 (95% CI, 0.62 to 0.77) for RF and 0.72 (95% CI, 0.64 to 0.78) for GBM, while previously AUROC was 0.57 (95% CI, 0.51 to 0.65) for CARDS and 0.63 (95% CI, 0.54 to 0.70) for ATLAS. Albumin, lactate and bicarbonate were significant mortality factors for all the models. Free calcium, potassium, white blood cell, urea, platelet and mean blood pressure were present in at least two of the three models.ConclusionOur machine learning derived CDI in-hospital mortality prediction model identified pertinent factors that can assist critical care clinicians in identifying patients at high risk of dying from CDI.

scholarly journals Clinical characteristics and outcomes of patients with heart failure admitted to the intensive care unit with coronavirus disease 2019 (COVID19): a multicenter cohort study

2021 ◽  
Vol 20 (Supplement_1) ◽  
Author(s):  
H Badreldin ◽  
DR Hafidh ◽  
DR Bin Saleh ◽  
DR Al Sulaiman ◽  
DR Al Juhani ◽  
...  
Keyword(s):  
Heart Failure ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Clinical Characteristics ◽  
P Value ◽  
Heart Failure Patients ◽  
Icu Admission ◽  
Patients With Heart Failure

Abstract Funding Acknowledgements Type of funding sources: None. Background Patients with heart failure in the setting of COVID-19 requiring admission to the intensive care unit may present a set of unique challenges. There is limited data to describe the clinical characteristics and outcomes in this subset of the patient population. Purpose The study"s purpose was to extensively describe the characteristics and outcomes of heart failure patients admitted to the intensive care unit with COVID-19 compared to non-heart failure patients . Methods We conducted a multicenter, prospective analysis for all adult critically ill patients with heart failure admitted to intensive care units (ICUs) between March 1 to August 31, 2020, with an objectively confirmed diagnosis of COVID-19. Results A total of 723 critically ill patients with COVID-19 had been admitted in ICUs, 59 patients with heart failure, and 664 patients with no heart failure before ICU admission. Heart failure patients had significantly more comorbid conditions such as diabetes mellitus, hypertension, dyslipidemia, atrial fibrillation, and acute coronary syndrome. Higher baseline severity scores (APACHE II & SOFA score) and nutritional risk (NUTRIC Score) were observed in heart failure patients. Also, heart failure patients had more acute kidney injury during ICU admission and required more mechanical ventilation within 24 hours of ICU admission. Patients with heart failure had a similar incidence of thrombosis compared to patients with no heart failure. Critically ill patients with COVID-19 and heart failure had similar ICU length of stay (LOS), mechanical ventilation duration, and hospital LOS compared to patients with no heart failure. During ICU stay, patients with heart failure had more in-hospital and ICU deaths in comparison to the non-heart failure group (64.3% vs. 44.6%, P-value &lt;0.01) and (54.5% vs. 39%, P-value = 0.02) respectively. Conclusion In this observational study evaluating the clinical characteristics and outcomes of critically ill COVID-19 patients with heart failure, patients with COVID-19 and heart failure had similar ICU LOS, duration of MV and hospital LOS, thrombosis rate compared to patients with no heart failure. However, during ICU stay, patients with heart failure had more in-hospital and ICU deaths than the non-heart failure group.

scholarly journals Clostridioides difficile infections in the intensive care unit: a monocentric cohort study

Infection ◽  
2020 ◽  
Vol 48 (3) ◽  
pp. 421-427
Author(s):  
Rebeca Cruz Aguilar ◽  
Jon Salmanton-García ◽  
Jonathan Carney ◽  
Boris Böll ◽  
Matthias Kochanek ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Financial Burden ◽  
Apache Ii ◽  
University Hospital ◽  
Apache Ii Score ◽  
High Risk Population ◽  
Cure Rate ◽  
Clostridioides Difficile ◽  
Severity Scores

Abstract Introduction Patient-level data from Clostridioides difficile infections (CDI) treated in an intensive care setting is limited, despite the growing medical and financial burden of CDI. Methods We retrospectively analyzed data from 100 medical intensive care unit patients at the University Hospital Cologne with respect to demography, diagnostics, severity scores, treatment, and outcome. To analyze factors influencing response to treatment and death, a backward-stepwise multiple logistic regression model was applied. Results Patients had significant comorbidities including 26% being immunocompromised. The mean Charlson Comorbidity Index was 6.3 (10-year survival rate of 2.25%). At the time of diagnosis, the APACHE II was 17.4±6.3 (predicted mortality rate of 25%), and the ATLAS score was 5.2±1.9 (predicted cure rate of 75%). Overall, 47% of CDI cases were severe, 35% were complicated, and 23% were both. At least one concomitant antibiotic was given to 74% of patients. The cure rate after 10 and 90 days was 56% and 51%, respectively. Each unit increment in APACHE II score was associated with poorer treatment response (OR 0.931; 95% CI 0.872–0.995; p = 0.034). Age above 65 years was associated with death (OR 2.533; 95% CI 1.031–6.221; p = 0.043), and overall mortality at 90 days was 56%. Conclusions CDI affects a high-risk population, in whom predictive scoring tools are not accurate, and outcomes are poor despite intensive treatment. Further research in this field is warranted to improve prediction scoring and patient outcomes.

Landiolol vs Esmolol on hemodynamic response during weaning of post-operative ICU patients with heart failure

2021 ◽  
Author(s):  
Maria Anifanti ◽  
Ioanna Iona ◽  
Kyriaki Tsikritsaki ◽  
Serafeim Chrysikos ◽  
Alexandros Kalogeromitros ◽  
...  
Keyword(s):  
Heart Failure ◽  
Hemodynamic Response ◽  
Icu Patients ◽  
Patients With Heart Failure
Sign in / Sign up

Export Citation Format

Share Document