scholarly journals In This Issue

2021 ◽  
Vol 23 (2) ◽  
pp. 123-123
Author(s):  
Rinaldo Bellomo ◽  
Keyword(s):  
Intensive Care Unit ◽  
Critical Care ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Language Processing ◽  
Large Scale ◽  
Health Staff ◽  
Behavioural Disturbance ◽  
Binary State ◽  
The Difference

What is delirium? How do we diagnose it? What is the difference between delirium and behavioural disturbance? Is delirium a useful clinical construct? Is behavioural disturbance a more useful clinical construct for intensivists? Can we do large-scale epidemiological assessment of behavioural disturbance given that it is not a binary state and that it cannot be diagnosed by numbers? These are fundamental questions in the practice of modern intensive care medicine given that such “states” appear to affect one-third or more of patients admitted to the intensive care unit (ICU). In this issue of Critical Care and Resuscitation, we present the first attempt to address this concept using the technique of natural language processing and applying it to electronic ICU notes by nurses, doctors and allied health staff. The findings may surprise you, fascinate you, and make you think about these concepts from a different perspective, as summarised in a thoughtful editorial by Professor Reade.

Predicting Mortality in the Surgical Intensive Care Unit Using Artificial Intelligence and Natural Language Processing of Physician Documentation

2018 ◽  
Vol 84 (7) ◽  
pp. 1190-1194 ◽  
Author(s):  
Joshua Parreco ◽  
Antonio Hidalgo ◽  
Robert Kozol ◽  
Nicholas Namias ◽  
Rishi Rattan
Keyword(s):  
Artificial Intelligence ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Severity Of Illness ◽  
Surgical Intensive Care Unit ◽  
Surgical Intensive Care ◽  
Severity Of Injury

The purpose of this study was to use natural language processing of physician documentation to predict mortality in patients admitted to the surgical intensive care unit (SICU). The Multiparameter Intelligent Monitoring in Intensive Care III database was used to obtain SICU stays with six different severity of illness scores. Natural language processing was performed on the physician notes. Classifiers for predicting mortality were created. One classifier used only the physician notes, one used only the severity of illness scores, and one used the physician notes with severity of injury scores. There were 3838 SICU stays identified during the study period and 5.4 per cent ended with mortality. The classifier trained with physician notes with severity of injury scores performed with the highest area under the curve (0.88 ± 0.05) and accuracy (94.6 ± 1.1%). The most important variable was the Oxford Acute Severity of Illness Score (16.0%). The most important terms were “dilated” (4.3%) and “hemorrhage” (3.7%). This study demonstrates the novel use of artificial intelligence to process physician documentation to predict mortality in the SICU. The classifiers were able to detect the subtle nuances in physician vernacular that predict mortality. These nuances provided improved performance in predicting mortality over physiologic parameters alone.

Practice Patterns and Opinions on Current Clinical Practice Guidelines Regarding the Management of Delirium in the Intensive Care Unit

2016 ◽  
Vol 30 (2) ◽  
pp. 162-171 ◽  
Author(s):  
Yoonsun Mo ◽  
Anthony E. Zimmermann ◽  
Michael C. Thomas
Keyword(s):  
Intensive Care Unit ◽  
Critical Care ◽  
Intensive Care ◽  
Large Scale ◽  
Online Survey ◽  
Early Mobilization ◽  
Screening Tools ◽  
Delirium Management ◽  
New Guidelines ◽  
Pharmacologic Agents

Objective: The aim of this study was to determine current delirium practices in the intensive care unit (ICU) setting and evaluate awareness and adoption of the 2013 Pain, Agitation, and Delirium (PAD) guidelines with emphasis on delirium management. Design, Setting, and Participants: A large-scale, multidisciplinary, online survey was administered to physician, pharmacist, nurse, and mid-level practitioner members of the Society of Critical Care Medicine (SCCM) between September 2014 and October 2014. A total of 635 respondents completed the survey. Measurements and Main Results: Nonpharmacologic interventions such as early mobilization were used in most ICUs (83%) for prevention of delirium. A majority of respondents (97%) reported using pharmacologic agents to treat hyperactive delirium. Ninety percent of the respondents answered that they were aware of the 2013 PAD guidelines, and 75% of respondents felt that their delirium practices have been changed as a result of the new guidelines. In addition, logistic regression analysis of this study showed that respondents who use delirium screening tools were twice more likely to be fully aware of key components of the updated guidelines (odds ratio [OR] = 2.07, 95% confidence interval [CI] = 1.20-3.60). Conclusions: Most critical care practitioners are fully aware and knowledgeable of key recommendations in the new guidelines and have changed their delirium practices accordingly.

scholarly journals Intensive Care Unit Services Preparedness for the Pandemic: An Efficiency Analysis

2021 ◽  
Vol 14 ◽  
pp. 117863292110375
Author(s):  
Songul Cinaroglu
Keyword(s):  
Intensive Care Unit ◽  
Critical Care ◽  
Intensive Care ◽  
Health Resources ◽  
Public Hospitals ◽  
Teaching Hospitals ◽  
Efficient Management ◽  
Study Results ◽  
Before And After ◽  
The Difference

Intensive care unit (ICU) services efficiency and the shortage of critical care professionals has been a challenge during pandemic. Thus, preparing ICUs is a prominent part of any pandemic response. The objective of this study is to examine the efficiencies of ICU services in Turkey right before the pandemic. Data were gathered from the Public Hospital Statistical Year Book for the year 2017. Analysis are presented at hospital level by comparing teaching and non-teaching hospitals. Bootstrapped data envelopment analysis procedure was used to gather more precise efficiency scores. Three analysis levels are incorporated into the study such as, all public hospitals (N = 100), teaching (N = 53), non-teaching hospitals (N = 47), and provinces that are providing high density of ICU services through the country (N = 54). Study results reveal that average efficiency scores of ICU services obtained from teaching hospitals (eff = 0.65) is higher than non-teaching (eff = 0.54) hospitals. After applying the bootstrapping techniques, efficiency scores are significantly improved and the difference between before and after bootstrapping results are statistically significant ( P < .05). Province based analysis indicates that, ICU services efficiencies are high for provinces located in southeast part of the country and highly populated places, such as İstanbul. Evidence-based operational design that considers the spatial distribution of health resources and effective planning of critical care professionals are critical for efficient management of intensive care. Study results will be helpful for health policy makers to deeply understand dynamics of critical care.

scholarly journals Clinical Characteristics and Prognostic Factors for Intensive Care Unit Admission of Patients With COVID-19: Retrospective Study Using Machine Learning and Natural Language Processing (Preprint)

2020 ◽  
Author(s):  
Jose Luis Izquierdo ◽  
Julio Ancochea ◽  
Joan B Soriano ◽  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Clinical Characteristics ◽  
Epidemiological Methods ◽  
Icu Admission ◽  
La Mancha

BACKGROUND Many factors involved in the onset and clinical course of the ongoing COVID-19 pandemic are still unknown. Although big data analytics and artificial intelligence are widely used in the realms of health and medicine, researchers are only beginning to use these tools to explore the clinical characteristics and predictive factors of patients with COVID-19. OBJECTIVE Our primary objectives are to describe the clinical characteristics and determine the factors that predict intensive care unit (ICU) admission of patients with COVID-19. Determining these factors using a well-defined population can increase our understanding of the real-world epidemiology of the disease. METHODS We used a combination of classic epidemiological methods, natural language processing (NLP), and machine learning (for predictive modeling) to analyze the electronic health records (EHRs) of patients with COVID-19. We explored the unstructured free text in the EHRs within the Servicio de Salud de Castilla-La Mancha (SESCAM) Health Care Network (Castilla-La Mancha, Spain) from the entire population with available EHRs (1,364,924 patients) from January 1 to March 29, 2020. We extracted related clinical information regarding diagnosis, progression, and outcome for all COVID-19 cases. RESULTS A total of 10,504 patients with a clinical or polymerase chain reaction–confirmed diagnosis of COVID-19 were identified; 5519 (52.5%) were male, with a mean age of 58.2 years (SD 19.7). Upon admission, the most common symptoms were cough, fever, and dyspnea; however, all three symptoms occurred in fewer than half of the cases. Overall, 6.1% (83/1353) of hospitalized patients required ICU admission. Using a machine-learning, data-driven algorithm, we identified that a combination of age, fever, and tachypnea was the most parsimonious predictor of ICU admission; patients younger than 56 years, without tachypnea, and temperature &lt;39 degrees Celsius (or &gt;39 ºC without respiratory crackles) were not admitted to the ICU. In contrast, patients with COVID-19 aged 40 to 79 years were likely to be admitted to the ICU if they had tachypnea and delayed their visit to the emergency department after being seen in primary care. CONCLUSIONS Our results show that a combination of easily obtainable clinical variables (age, fever, and tachypnea with or without respiratory crackles) predicts whether patients with COVID-19 will require ICU admission.

scholarly journals Natural Language Processing for Cohort Discovery in a Discharge Prediction Model for the Neonatal ICU

2016 ◽  
Vol 07 (01) ◽  
pp. 101-115 ◽  
Author(s):  
Christoph Lehmann ◽  
Daniel Fabbri ◽  
Michael Temple
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Neonatal Intensive Care Unit ◽  
Prediction Model ◽  
Language Processing ◽  
Neonatal Intensive Care ◽  
Social Issues ◽  
Original Model

SummaryDischarging patients from the Neonatal Intensive Care Unit (NICU) can be delayed for non-medical reasons including the procurement of home medical equipment, parental education, and the need for children’s services. We previously created a model to identify patients that will be medically ready for discharge in the subsequent 2–10 days. In this study we use Natural Language Processing to improve upon that model and discern why the model performed poorly on certain patients.We retrospectively examined the text of the Assessment and Plan section from daily progress notes of 4,693 patients (103,206 patient-days) from the NICU of a large, academic children’s hospital. A matrix was constructed using words from NICU notes (single words and bigrams) to train a supervised machine learning algorithm to determine the most important words differentiating poorly performing patients compared to well performing patients in our original discharge prediction model.NLP using a bag of words (BOW) analysis revealed several cohorts that performed poorly in our original model. These included patients with surgical diagnoses, pulmonary hypertension, retinopathy of prematurity, and psychosocial issues.The BOW approach aided in cohort discovery and will allow further refinement of our original discharge model prediction. Adequately identifying patients discharged home on g-tube feeds alone could improve the AUC of our original model by 0.02. Additionally, this approach identified social issues as a major cause for delayed discharge.A BOW analysis provides a method to improve and refine our NICU discharge prediction model and could potentially avoid over 900 (0.9%) hospital days.AUC – Area under the Curve, CART -- Classification And Regression Trees, DTD – Days to Dis- charge, GI – Gastrointestinal, LOS – Length of Stay, NICU – Neonatal Intensive Care Unit, NS – Neurosurgery, RF – Random Forest.

scholarly journals Adding the Capacity for an Intensive Care Unit Dedicated to COVID 19, Preserving the Operational Capability of a French Golden Hour Offset Surgical Team in Sahel

2020 ◽  
Author(s):  
Henri de Lesquen ◽  
Marie Bergez ◽  
Antoine Vuong ◽  
Alexandre Boufime-Jonqheere ◽  
Nicolas de l’Escalopier
Keyword(s):  
Intensive Care Unit ◽  
Critical Care ◽  
Intensive Care ◽  
Large Scale ◽  
Damage Control ◽  
Surgical Care ◽  
Damage Control Surgery ◽  
Surgical Team ◽  
Golden Hour ◽  
Surgical Teams

Abstract Introduction In April 2020, the military medical planning needs to be recalibrated to support the COVID-19 crisis during a large-scale combat operation carried out by the French army in Sahel. Material and Methods Since 2019, proper positioning of Forward Surgical Teams (FSTs) has been imperative in peer-to-near-peer conflict and led to the development of a far-forward surgical asset: The Golden Hour Offset Surgical Team (GHOST). Dedicated to damage control surgery close to combat, GHOST made the FST aero-mobile again, with a light logistical footprint and a fast setting. On 19 and 25 March 2020, Niger and Mali confirmed their first COVID-19 cases, respectively. The pandemic was ongoing in Sahel, where 5,100 French soldiers were deployed in the Barkhane Operation. Results For the first time, the FST had to provide, continuously, both COVID critical care and surgical support to the ongoing operation in Liptako. Its deployment on a Main Operating Base had to be rethought on Niamey, to face the COVID crisis and support ongoing operations. This far-forward surgical asset, embedded with a doctrinal Role-1, sat up a 4-bed COVID intensive care unit while maintaining a casualty surgical care capacity. A COVID training package has been developed to prepare the FST for this innovative employment. This far-forward surgical asset was designed to support a COVID-19 intensive care unit before evacuation, preserving forward surgical capability for battalion combat teams. Conclusion Far-forward surgical assets like GHOST have demonstrated their mobility and effectiveness in a casualty care system and could be adapted as critical care facilities to respond to the COVID crisis in wartime.

scholarly journals Clinical Characteristics and Prognostic Factors for Intensive Care Unit Admission of Patients With COVID-19: Retrospective Study Using Machine Learning and Natural Language Processing

10.2196/21801 ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. e21801 ◽  
Author(s):  
Jose Luis Izquierdo ◽  
Julio Ancochea ◽  
Joan B Soriano ◽  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Clinical Characteristics ◽  
Epidemiological Methods ◽  
Icu Admission ◽  
La Mancha

Background Many factors involved in the onset and clinical course of the ongoing COVID-19 pandemic are still unknown. Although big data analytics and artificial intelligence are widely used in the realms of health and medicine, researchers are only beginning to use these tools to explore the clinical characteristics and predictive factors of patients with COVID-19. Objective Our primary objectives are to describe the clinical characteristics and determine the factors that predict intensive care unit (ICU) admission of patients with COVID-19. Determining these factors using a well-defined population can increase our understanding of the real-world epidemiology of the disease. Methods We used a combination of classic epidemiological methods, natural language processing (NLP), and machine learning (for predictive modeling) to analyze the electronic health records (EHRs) of patients with COVID-19. We explored the unstructured free text in the EHRs within the Servicio de Salud de Castilla-La Mancha (SESCAM) Health Care Network (Castilla-La Mancha, Spain) from the entire population with available EHRs (1,364,924 patients) from January 1 to March 29, 2020. We extracted related clinical information regarding diagnosis, progression, and outcome for all COVID-19 cases. Results A total of 10,504 patients with a clinical or polymerase chain reaction–confirmed diagnosis of COVID-19 were identified; 5519 (52.5%) were male, with a mean age of 58.2 years (SD 19.7). Upon admission, the most common symptoms were cough, fever, and dyspnea; however, all three symptoms occurred in fewer than half of the cases. Overall, 6.1% (83/1353) of hospitalized patients required ICU admission. Using a machine-learning, data-driven algorithm, we identified that a combination of age, fever, and tachypnea was the most parsimonious predictor of ICU admission; patients younger than 56 years, without tachypnea, and temperature <39 degrees Celsius (or >39 ºC without respiratory crackles) were not admitted to the ICU. In contrast, patients with COVID-19 aged 40 to 79 years were likely to be admitted to the ICU if they had tachypnea and delayed their visit to the emergency department after being seen in primary care. Conclusions Our results show that a combination of easily obtainable clinical variables (age, fever, and tachypnea with or without respiratory crackles) predicts whether patients with COVID-19 will require ICU admission.

Sign in / Sign up

Export Citation Format

Share Document