scholarly journals Noninvasive Real-time Mortality Prediction in Intensive Care Units Based on Gradient Boosting Method (Preprint)

2020 ◽  
Author(s):  
Huizhen Jiang ◽  
Longxiang Su ◽  
Hao Wang ◽  
Dongkai Li ◽  
Congpu Zhao ◽  
...  
Keyword(s):  
Intensive Care ◽  
Real Time ◽  
Intensive Care Units ◽  
Prediction Models ◽  
Mortality Prediction ◽  
Gradient Boosting ◽  
Noninvasive Method ◽  
Icu Patients ◽  
The Real ◽  
Boosting Method

BACKGROUND It is especially necessary to pay attention to the critically ill patients in ICU(Intensive Care Units) real time. Scoring systems are mostly used in the risk prediction of mortality, while usually they are not so precise and real-time with the clinical data simply weighted, and it is also time-consuming for clinical staff. OBJECTIVE We would like to fuse all the medical data together and predict the real-time mortality of ICU patients by machine learning method, which would be valuable and significant. Besides, we want to explore predicting the mortality by noninvasive data to lessen the pain of patients. METHODS In this paper, we established 5 models to predict mortality real-time based on different features. Based on monitoring data, examination data and scoring data, we structured the feature engineering. 5 Real-time Mortality prediction models were RMM(Monitoring features), RMA(APACHE and monitoring features), RMS(SOFA and monitoring features), RMME(Monitoring and Examination features) and RM(all features from monitoring, examination data and scoring data). Then, we compared the performance of all models and put more focus on the noninvasive method RMM. RESULTS After extensive experiments, the performance of RMME was superior to that of other 4 models. With the scoring features included, the model showed worse performance. And, RMM only based on monitoring features performed better than that of RMA and RMS. Therefore, it is meaningful and practicable to predict mortality by the noninvasive way, which could reduce the extra physical damage to patients like drawing blood. Moreover, we explored the top 9 features relevant with the real-time mortality prediction. Top 9 features were "ABP (mmHg) invasive mean pressure", "Heart rate", "ABP (mmHg) invasive systolic pressure", "Oxygen concentration", "SPO2", "Balance of inflow and outflow", "Total input", "ABP (mmHg) invasive diastolic pressure" and "NBP-average pressure", which could be paid more focus on during the general clinical work. CONCLUSIONS This research could be helpful in real-time mortality prediction of ICU patients, especially by the noninvasive method. It is meaningful and friendly to patients, which is of strong practical significance.

Feature engineering combined with 1-D convolutional neural network for improved mortality prediction

2020 ◽  
Vol 16 (4) ◽  
Author(s):  
Rohit Verma ◽  
Saumil Maheshwari ◽  
Anupam Shukla
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Intensive Care ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Intensive Care Units ◽  
Mortality Prediction ◽  
Support Vector ◽  
Feature Engineering ◽  
Light Gradient

AbstractObjectivesThe appropriate care for patients admitted in Intensive care units (ICUs) is becoming increasingly prominent, thus recognizing the use of machine learning models. The real-time prediction of mortality of patients admitted in ICU has the potential for providing the physician with the interpretable results. With the growing crisis including soaring cost, unsafe care, misdirected care, fragmented care, chronic diseases and evolution of epidemic diseases in the domain of healthcare demands the application of automated and real-time data processing for assuring the improved quality of life. The intensive care units (ICUs) are responsible for generating a wealth of useful data in the form of Electronic Health Record (EHR). This data allows for the development of a prediction tool with perfect knowledge backing.MethodWe aimed to build the mortality prediction model on 2012 Physionet Challenge mortality prediction database of 4,000 patients admitted in ICU. The challenges in the dataset, such as high dimensionality, imbalanced distribution and missing values, were tackled with analytical methods and tools via feature engineering and new variable construction. The objective of the research is to utilize the relations among the clinical variables and construct new variables which would establish the effectiveness of 1-Dimensional Convolutional Neural Network (1-D CNN) with constructed features.ResultsIts performance with the traditional machine learning algorithms like XGBoost classifier, Light Gradient Boosting Machine (LGBM) classifier, Support Vector Machine (SVM), Decision Tree (DT), K-Neighbours Classifier (K-NN), and Random Forest Classifier (RF) and recurrent models like Long Short-Term Memory (LSTM) and LSTM-attention is compared for Area Under Curve (AUC). The investigation reveals the best AUC of 0.848 using 1-D CNN model.ConclusionThe relationship between the various features were recognized. Also, constructed new features using existing ones. Multiple models were tested and compared on different metrics.

scholarly journals Experiences of Patients With COVID-19 Admitted to the Intensive Care Units: A Qualitative Study

2021 ◽  
Vol 8 ◽  
pp. 237437352110073
Author(s):  
Reza Norouzadeh ◽  
Mohammad Abbasinia ◽  
Zahra Tayebi ◽  
Ehsan Sharifipour ◽  
Alireza Koohpaei ◽  
...  
Keyword(s):  
Intensive Care ◽  
Intensive Care Units ◽  
Health Care Providers ◽  
Spiritual Support ◽  
Care Providers ◽  
Structured Interviews ◽  
Icu Patients ◽  
Life Challenges ◽  
Care Models ◽  
The Face

This study aimed to describe the experiences of patients with COVID-19 admitted to the intensive care units (ICU). The data were analyzed by content analysis on 16 ICU patients with COVID-19. Data were collected by semi-structured interviews. Three categories were identified: (a) captured by a challenging incident with subcategories: perceived sudden and challenging death, fear of carelessness in overcrowding, worry about the family, and frustration with stigmatizing; (b) the flourishing of life with subcategories: spiritual-awakening, resilience in the face of life challenges, promoting health behaviors, and striving for recovery; and (c) honoring the blessings with subcategories: understanding the importance of nurses, realizing the value of family, and realizing the value of altruism. COVID-19 survivors experienced both positive and negative experiences. The results of this study could help health care providers identify the needs of ICU patients with COVID-19, including psychological, social, and spiritual support and design care models.

scholarly journals Estimating the Case Fatality Risk of COVID-19 using Cases from Outside China

2020 ◽  
Author(s):  
Nick Wilson ◽  
Amanda Kvalsvig ◽  
Lucy Telfar Barnard ◽  
Michael G Baker
Keyword(s):  
Intensive Care ◽  
Intensive Care Units ◽  
Meta Analysis ◽  
Case Fatality ◽  
Large Uncertainty ◽  
Icu Patients ◽  
Fatality Risk ◽  
Case Fatality Risk ◽  
Respiratory Conditions

AbstractThere is large uncertainty around the case fatality risk (CFR) for COVID-19 in China. Therefore, we considered symptomatic cases outside of China (countries/settings with 20+ cases) and the proportion who are in intensive care units (4.0%, 14/349 on 13 February 2020). Given what is known about CFRs for ICU patients with severe respiratory conditions from a meta-analysis, we estimated a CFR of 1.37% (95%CI: 0.57% to 3.22%) for COVID- 19 cases outside of China.

scholarly journals Colonization of central venous catheter in the intensive care units at the Institute of Cardiovascular Disease "Dedinje": One year study

2005 ◽  
Vol 52 (3) ◽  
pp. 33-37
Author(s):  
Ivana Cirkovic ◽  
Vera Mijac ◽  
Milena Svabic-Vlahovic ◽  
S. Dukic ◽  
I. Ilic ◽  
...  
Keyword(s):  
Intensive Care ◽  
Intensive Care Units ◽  
Antimicrobial Agents ◽  
Microbial Colonization ◽  
Central Venous ◽  
Candida Spp ◽  
Icu Patients ◽  
Gram Negative ◽  
Microbiological Methods ◽  
Increased Risk

Objectives: The application of Central Venous Catheters (CVC) is associated with increased risk of microbial colonization and infection. The aim of present study was to assess the frequency of pathogens colonizing CVC and to determine their susceptibility pattern to various antimicrobial agents. Materials and methods: A total of 253 samples of CVC from intensive care units (ICU) patients were received for culture during 2003. All microorganisms were identified by standard microbiological methods and the susceptibility to antimicrobial agents was determined according to NCCLS recommendations. Results: A total of 184 (72.7%) cultures were positive and 223 pathogens were isolated. Coagulase negative staphylococci (CNS) were the dominant isolates (24.7%), followed by Enterobacter spp. (12.1%), Pseudomonas spp. (11.7%), Enterococcus spp. (9.9%), Klebsiella spp. (8.6%), Candida spp. (7.6%), Acinetobacter spp. (7.6%), other Gram negative nonfermentative bacilli (5.8%), Serratia spp. (4.5%), Staphylococcus aureus (2.6%), Proteus mirabilis (2.2%), E. coli (1.8%) and Citrobacter spp. (0.9%). Meropenem (84.5%) and vancomycin (100%) remain the most effective antimicrobial agents against Gram negative and Gram positive bacteria, respectively. Conclusion: Gram negative bacilli and CNS are the commonest microorganisms colonizing CVC from ICU patients. The increasing resistance of the bacteria to antimicrobial agents is the major problem in spite of restricted policy of using antimicrobial agents in ICU.

scholarly journals Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Comparative Machine Learning Study (Preprint)

2020 ◽  
Author(s):  
Sujeong Hur ◽  
Ji Young Min ◽  
Junsang Yoo ◽  
Kyunga Kim ◽  
Chi Ryang Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Patient Safety ◽  
Intensive Care ◽  
Predictive Value ◽  
Prediction Models ◽  
Support Vector ◽  
Unplanned Extubation ◽  
Electronic Health Record Data ◽  
Icu Patients

BACKGROUND Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered as the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care. OBJECTIVE This study aimed to develop and validate prediction models for UE in ICU patients using machine learning. METHODS This study was conducted an academic tertiary hospital in Seoul. The hospital had approximately 2,000 inpatient beds and 120 intensive care unit (ICU) beds. The number of patients, on daily basis, was approximately 9,000 for the out-patient. The number of annual ICU admission was approximately 10,000. We conducted a retrospective study between January 1, 2010 and December 31, 2018. A total of 6,914 extubation cases were included. We developed an unplanned extubation prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model’s performance, we used area under the receiver operator characteristic curve (AUROC). Sensitivity, specificity, positive predictive value negative predictive value, and F1-score were also determined for each model. For performance evaluation, we also used calibration curve, the Brier score, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS Among the 6,914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was more likely to occur during the night shift compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality was higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.762, and for SVM was 0.740. CONCLUSIONS We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787, which was obtained using RF. CLINICALTRIAL N/A

Sign in / Sign up

Export Citation Format

Share Document