Filters








807 Hits in 23.9 sec

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

Ren-qi Yao, Xin Jin, Guo-wei Wang, Yue Yu, Guo-sheng Wu, Yi-bing Zhu, Lin Li, Yu-xuan Li, Peng-yue Zhao, Sheng-yu Zhu, Zhao-fan Xia, Chao Ren (+1 others)
2020 Frontiers in Medicine  
Machine learning-based algorithm might have significant application in the development of early warning system for septic patients following major operations.  ...  The incidence of postoperative sepsis is continually increased, while few studies have specifically focused on the risk factors and clinical outcomes associated with the development of sepsis after surgical  ...  YL, PZ, and SZ were consulted for clinical issues. All authors contributed to and revised the final manuscript.  ... 
doi:10.3389/fmed.2020.00445 pmid:32903618 pmcid:PMC7438711 fatcat:7akx4fgyfva7rgzffy6yavnkuu

Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection [article]

Tony Wang, Tom Velez, Emilia Apostolova, Tim Tschampel, Thuy L. Ngo, Joy Hardison
2018 arXiv   pre-print
Compared with conventional rule-based risk scoring tools, the sepsis knowledgebase-driven DBN algorithm offers improved performance for predicting mortality of infected patients in ICUs.  ...  The goal of this work is to identify patient at risk of life-threatening sepsis utilizing a data-centered and machine learning-driven approach.  ...  The endpoint of in-hospital mortality has become the standard metric for early warning systems assessing risk for yet-to-be identified sepsis patients in the ICU.  ... 
arXiv:1806.10174v1 fatcat:c3oftpy3q5hk5d6mqa2aowvz6i

Understanding the complexity of sepsis mortality prediction via rule discovery and analysis: a pilot study

Ying Wu, Shuai Huang, Xiangyu Chang
2021 BMC Medical Informatics and Decision Making  
Methods In this paper, a rule discovery and analysis (rule-based) method is used to predict the in-hospital death events of 2021 ICU patients diagnosed with sepsis using the MIMIC-III database.  ...  In addition, we discuss and explain in detail the rules with better risk prediction ability.  ...  For the purpose of better prediction, many machine learning models have been applied on a large number of potential risk factors of sepsis mortality in determining the outcomes, such as decision tree  ... 
doi:10.1186/s12911-021-01690-9 pmid:34839820 pmcid:PMC8628441 fatcat:x3ufiyapgbbdzoy4q7pd72hdfe

A Novel Composite Indicator of Predicting Mortality Risk for Heart Failure Patients With Diabetes Admitted to Intensive Care Unit Based on Machine Learning

Boshen Yang, Yuankang Zhu, Xia Lu, Chengxing Shen
2022 Frontiers in Endocrinology  
Nine machine learning models were compared, and the best one was selected to define indicators associated with hospital mortality for patients with HF with diabetes.  ...  Existing attributes most related to hospital mortality were identified using a visualization method developed for machine learning, namely, Shapley Additive Explanations (SHAP) method.  ...  Our study is the first to apply machine learning algorithms to patients with HF with diabetes in the environment of ICU.  ... 
doi:10.3389/fendo.2022.917838 pmid:35846312 pmcid:PMC9277005 fatcat:idszhwlylff7reroq5w7mfnksa

Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021

Laura Evans, Andrew Rhodes, Waleed Alhazzani, Massimo Antonelli, Craig M. Coopersmith, Craig French, Flávia R. Machado, Lauralyn Mcintyre, Marlies Ostermann, Hallie C. Prescott, Christa Schorr, Steven Simpson (+48 others)
2021 Intensive Care Medicine  
Sepsis survivors are at risk for hospital readmission, which has been associated with increased mortality or discharge to hospice [622, 623] .  ...  Meta-analysis of these studies suggests that critical care transition programmes reduce risk of in-hospital mortality and potentially reduce risk of ICU readmission.  ...  Specifically, we thank: Dana Mirman, sepsis survivor & member of the Board of Directors of Sepsis Alliance, Idelette Nutma and Marie Mach, and three additional public panel members. Dr.  ... 
doi:10.1007/s00134-021-06506-y pmid:34599691 pmcid:PMC8486643 fatcat:ykvcj5xza5aoxonrtf43osrmme

Outcome Prediction in Critically Ill Patients with Venous Thromboembolism and/or Cancer Using Machine Learning Algorithms: External Validation and Comparison with Scoring Systems

Vasiliki Danilatou, Stylianos Nikolakakis, Despoina Antonakaki, Christos Tzagkarakis, Dimitrios Mavroidis, Theodoros Kostoulas, Sotirios Ioannidis
2022 International Journal of Molecular Sciences  
Mortality prediction in the ICU has been a major medical challenge for which several scoring systems exist but lack in specificity.  ...  The main goal is to develop and validate interpretable machine learning (ML) models to predict early and late mortality, while exploiting all available data stored in the medical record.  ...  Automated Machine Learning Prediction of Early Mortality in ICU Patients with Thrombosis As early or in-hospital mortality define the outcomes of patients at discharge from the hospital, two different  ... 
doi:10.3390/ijms23137132 pmid:35806137 pmcid:PMC9266386 fatcat:6r2jrbyscfbjriwtxtghdhvi4m

Accurate detection of sepsis at ED triage using machine learning with clinical natural language processing [article]

Oleksandr Ivanov, Karin Molander, Robert Dunne, Stephen Liu, Kevin Masek, Erica Lewis, Lisa Wolf, Debbie Travers, Deena Brecher, Deb Delaney, Kyla Montgomery, Christian Reilly
2022 arXiv   pre-print
A machine learning model (KATE Sepsis) was developed using patient encounters with triage data from 16 participating hospitals.  ...  The purpose of this study was to determine whether EHR data can be extracted and synthesized with the latest machine learning algorithms (KATE Sepsis) and clinical natural language processing to produce  ...  Learning Algorithms We used XGBoost and logistic regression stack as an ML algorithm in this study.  ... 
arXiv:2204.07657v3 fatcat:mv5or2uumjhahjwgybkykaex5e

Immunological Endotyping of Chronic Critical Illness After Severe Sepsis

Brittany P. Fenner, D. B. Darden, Lauren S. Kelly, Jaimar Rincon, Scott C. Brakenridge, Shawn D. Larson, Frederick A. Moore, Philip A. Efron, Lyle L. Moldawer
2021 Frontiers in Medicine  
Due to enhanced recognition and improved management of severe sepsis, in-hospital mortality has been reduced by up to 40%.  ...  With that good news, a new syndrome has unfortunately replaced in-hospital multi-organ failure and death.  ...  This technique, using regression-based prediction models, may be further improved by the use of machine-learning algorithms and deep-learning technologies (167, 168) .  ... 
doi:10.3389/fmed.2020.616694 pmid:33659259 pmcid:PMC7917137 fatcat:sohksn3ptnaclh5suulftwtdzi

40th International Symposium on Intensive Care & Emergency Medicine 2020 – Part 2

2020 Critical Care  
Introduction: Intensive care unit (ICU) survivors are at risk of emergency hospital readmissions.  ...  Anemia resulted an independent risk factor for postoperative compli- cations and it increased the length of hospital stay and in-hospital mortality.  ...  ICU mortality was 29.5% and hospital mortality was 33.33%.  ... 
doi:10.1186/s13054-020-03187-9 pmid:32921314 fatcat:mu4ygabjwjhhbbojg5m7m2hd6y

ESICM LIVES 2021: Part 2

2021 Intensive Care Medicine Experimental  
A daily evaluation of delirium and SSD was done with Intensive Care Delirium Screening Checklist (ICDSC) and Confusion Assessment Method-ICU (CAM-ICU). Scales  ...  We aimed to investigate the prevalence of SSD, the association between SSD and clinical outcomes and understanding if SSD is an independent entity or precedes delirium. Methods.  ...  We used TMLE with an ensemble of machine learning algorithms as the primary model. The machine learning ensemble included Logistic Regression, a Neural Network, Naive Bayes, and XGboost.  ... 
doi:10.1186/s40635-021-00415-6 pmid:34633571 fatcat:ef5ksbl2gnf6nbh2b2hd4njr6q

40th International Symposium on Intensive Care & Emergency Medicine 2021

2021 Critical Care  
Obesity is a risk factor for severe coronavirus disease 2019 and might play a role in its pathophysiology.  ...  COVID-19 patients had longer ICU and hospital length of stay, and higher in-hospital mortality.  ...  Odenstedt-Hergés 1 a machine learning (ML) algorithm can detect events with cerebral hypoperfusion and ischemia in patients in the ICU or OR.  ... 
doi:10.1186/s13054-021-03769-1 pmid:34781995 pmcid:PMC8591444 fatcat:ornzgxr4lzhzxfoya72p6iq3pm

37th International Symposium on Intensive Care and Emergency Medicine (part 3 of 3)

M. Von Seth, L. Hillered, A. Otterbeck, K. Hanslin, A. Larsson, J. Sjölin, M. Lipcsey, ME Cove, N. S. Chew, L. H. Vu, R. Z. Lim, Z. Puthucheary (+1011 others)
2017 Critical Care  
Critical Care 2017, 21(Suppl 1):P349 P350 Pilot study showing reduced bone strength at 96 hours in rodent sepsis ME Cove 1 , NS Chew  ...  ARDS was an independent risk factor for ICU mortality (OR, 2.60; 95%CI, 1.04-6.53).  ...  For 90 day mortality, significant risk factors in the overall population were sepsis at Conclusions After multivariable Cox regression analysis, colloid use was not associated with an increased risk of  ... 
doi:10.1186/s13054-017-1629-x fatcat:sxmc4z5zdvhvnh5qdhhugi5h7y

41st International Symposium on Intensive Care and Emergency Medicine

2022 Critical Care  
We suggest that a gender-bias as well as social factors play a significant role in decision-making for the insertion of an EVD.  ...  In the multivariate analysis, EVD insertion was independently associated with male gender (OR 2.82, 95%-CI 1.61-4.95, p value < 0.001) irrespective of demographic or radiological features.  ...  Acute cor pulmonale is an independent risk factor for mortality in the ICU.  ... 
doi:10.1186/s13054-022-03927-z pmid:35337360 pmcid:PMC8948467 fatcat:7dsrwetbofc23itjl7ivvdq5bq

Using What You Get

Andre L. Holder, Gilles Clermont
2015 Critical care clinics  
It is possible to create physiologic signatures for each stage in the process of clinical decompensation and recovery to improve patient outcomes.  ...  The characterization of dynamic changes in hemodynamic and metabolic variables is implicit in the concept of physiologic signatures.  ...  Some clinicians and hospitals may be skeptical of using machine learning algorithms to drive identification and therapeutic management of critical illness.  ... 
doi:10.1016/j.ccc.2014.08.007 pmid:25435482 pmcid:PMC4476532 fatcat:qjpq6vfnwza2jj774r33nsvsxy

Typical patterns of expiratory flow and carbon dioxide in mechanically ventilated patients with spontaneous breathing

S. E. Rees, S. Larraza, N. Dey, S. Spadaro, J. B. Brohus, R. W. Winding, C. A. Volta, D. S. Karbing
2016 Journal of clinical monitoring and computing  
Typical patterns of expiratory flow and carbon dioxide in mechanically ventilated patients with spontaneous breathing Rees, Stephen Edward; Larraza Rico, Sebastián; Dey, N.; Spadaro, S.; Brohus, J.  ...  Conclusions: In inhalational opium addicted patients admitted to ICU enable of starting oral medications, pain is better controlled with Opium Tincture in comparison to Methadone.  ...  The combination of malnutrition and heavy caloric deficit were relevant nutritional QI associated with ICU mortality regardless of sex, age and Apache II.  ... 
doi:10.1007/s10877-016-9903-z pmid:27344663 fatcat:znxs3iq6vnawdn6se6h7fborja
« Previous Showing results 1 — 15 out of 807 results