scholarly journals Letter to Editor: 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)

2021 ◽  
Author(s):  
Francisco Martos Pérez ◽  
Ricardo Gomez Huelgas ◽  
María Dolores Martín Escalante ◽  
José Manuel Casas Rojo
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Prognostic Factors ◽  
Retrospective Study ◽  
Intensive Care Unit Admission ◽  
Language Processing ◽  
Clinical Characteristics ◽  
Microbiological Diagnosis

UNSTRUCTURED Letter to Editor. Comment to “Clinical characteristics and prognostic factors for intensive care unit admission of patients with COVID-19: retrospective study using machine learning and natural language processing” publicado por Izquierdo et al en Journal of Medical Internet Research Dear Sir, The article by Izquierdo et al published in the recent issue of Journal of Medical Internet Research (1) employed a combination of conventional and machine-learning tools to describe the clinical characteristics of patients with COVID-19 and the factors that predict intensive care unit (ICU) admission. We would like to make some comments about its design. The authors should have provided the proportion of patients with positive microbiological diagnosis. If the artificial intelligence software’s capacity for retrieving this information is limited in some way, this should be explained. The classification bias introduced by the lack of microbiological confirmation may have been significant, since the study includes patients from 1 January 2020. Although some undiagnosed cases have likely been present prior to the first declared case (1st march 2020)(2) in Castilla-La Mancha, it is improbable that there were many of them. ICU admissions are related to many factors not addressed in the study. The decision not to admit a patient to the ICU because of short life expectancy, low quality of life, or high burden of comorbidities may have had a great impact during the first wave of the COVID-19 pandemic, when a scarcity of ICU beds was manifested in some regions of Spain. The 6,1% ICU admission rate reported by the authors was 36% lower than the 8,3% reported in a national survey of 15111 patients from 150 hospitals in Spain(3). We could hypothesize that the patients included in the study had a milder disease. However, given the absence of microbiological diagnosis in an unknown percentage of patients, inclusion of a significant proportion of patients without a real COVID-19 diagnosis cannot be ruled out. These doubts could have been resolved if a microbiological diagnosis had been a requisite for inclusion. The mortality rate, the most robust and relevant endpoint, should also been reported and the factors related to it analysed. Artificial intelligence is having an increasing impact on the rate of health care information processing. However, minimization of selection and classification biases should be guaranteed in the design of investigations. In this case, this could have been achieved by including only microbiologically confirmed cases and prolonging the period of inclusion, since most of the COVID-19 cases emerged after the end date of the study inclusion period. These changes in the design would have allowed for a better evaluation of the performance of artificial intelligence techniques, making the results obtained in the sample closer to those of real population.   Bibliography 1. Izquierdo JL, Ancochea J; Savana COVID-19 Research Group, Soriano JB. Clinical Characteristics and Prognostic Factors for Intensive Care Unit Admission of Patients With COVID-19: Retrospective Study Using Machine Learning and Natural Language Processing. J Med Internet Res. 2020;22(10):e21801. Published 2020 Oct 28. doi:10.2196/21801. PMID: 33090964 2. Europa Press (2020, march 1st). Un varón de 62 años ingresado en Guadalajara, primer caso positivo por coronavirus en C-LM. Retrieved 2020, January 8th. https://www.europapress.es/castilla-lamancha/noticia-varon-62-anos-ingresado-guadalajara-primer-caso-positivo-coronavirus-lm-20200301103741.html 3. Casas-Rojo JM, Antón-Santos JM, Millán-Núñez-Cortés J, et al. Clinical characteristics of patients hospitalized with COVID-19 in Spain: Results from the SEMI-COVID-19 Registry. Características clínicas de los pacientes hospitalizados con COVID-19 en España: resultados del Registro SEMI-COVID-19. Rev Clin Esp. 2020;220(8):480-494. doi:10.1016/j.rce.2020.07.003. PMID: 32762922

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 <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.

scholarly journals Predicting Intensive Care Unit admission among patients presenting to the emergency department using machine learning and natural language processing

PLoS ONE ◽  
2020 ◽  
Vol 15 (3) ◽  
pp. e0229331 ◽  
Author(s):  
Marta Fernandes ◽  
Rúben Mendes ◽  
Susana M. Vieira ◽  
Francisca Leite ◽  
Carlos Palos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Natural Language Processing ◽  
Intensive Care Unit Admission ◽  
Natural Language ◽  
Language Processing

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.

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.

scholarly journals Antimicrobial Stewardship Opportunities in Patients with Bacteremia Not Identified by BioFire FilmArray

2019 ◽  
Vol 57 (5) ◽  
Author(s):  
P. Ny ◽  
A. Ozaki ◽  
J. Pallares ◽  
P. Nieberg ◽  
A. Wong-Beringer
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Blood Culture ◽  
Intensive Care Unit Admission ◽  
Clinical Characteristics ◽  
Length Of Hospital Stay ◽  
Blood Cultures ◽  
Rapid Diagnostics ◽  
Admission Data ◽  
Culture Identification

ABSTRACTA subset of bacteremia cases are caused by organisms not detected by a rapid-diagnostics platform, BioFire blood culture identification (BCID), with unknown clinical characteristics and outcomes. Patients with ≥1 positive blood culture over a 15-month period were grouped by negative (NB-PC) versus positive (PB-PC) BioFire BCID results and compared with respect to demographics, infection characteristics, antibiotic therapy, and outcomes (length of hospital stay [LOS] and in-hospital mortality). Six percent of 1,044 positive blood cultures were NB-PC. The overall mean age was 65 ± 22 years, 54% of the patients were male, and most were admitted from home; fewer NB-PC had diabetes (19% versus 31%,P= 0.0469), although the intensive care unit admission data were similar. Anaerobes were identified in 57% of the bacteremia cases from the NB-PC group by conventional methods:Bacteroidesspp. (30%),Clostridium(11%), andFusobacteriumspp. (8%). Final identification of the NB-PC pathogen was delayed by 2 days (P< 0.01) versus the PB-PC group. The sources of bacteremia were more frequently unknown for the NB-PC group (32% versus 11%,P< 0.01) and of pelvic origin (5% versus 0.1%,P< 0.01) compared to urine (31% versus 9%,P< 0.01) for the PB-PC patients. Fewer NB-PC patients received effective treatment before (68% versus 84%,P= 0.017) and after BCID results (82% versus 96%,P= 0.0048). The median LOS was similar (7 days), but more NB-PC patients died from infection (26% versus 8%,P< 0.01). Our findings affirm the need for the inclusion of anaerobes in BioFire BCID or other rapid diagnostic platforms to facilitate the prompt initiation of effective therapy for bacteremia.

scholarly journals Artificial Intelligence in the Intensive Care Unit

2020 ◽  
Author(s):  
Massimiliano Greco ◽  
Pier F. Caruso ◽  
Maurizio Cecconi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Intensive Care ◽  
Language Processing ◽  
Laboratory Data ◽  
Kidney Injury ◽  
Support Vector ◽  
Learning Models ◽  
Electronic Health ◽  
Natural Terrain

AbstractThe diffusion of electronic health records collecting large amount of clinical, monitoring, and laboratory data produced by intensive care units (ICUs) is the natural terrain for the application of artificial intelligence (AI). AI has a broad definition, encompassing computer vision, natural language processing, and machine learning, with the latter being more commonly employed in the ICUs. Machine learning may be divided in supervised learning models (i.e., support vector machine [SVM] and random forest), unsupervised models (i.e., neural networks [NN]), and reinforcement learning. Supervised models require labeled data that is data mapped by human judgment against predefined categories. Unsupervised models, on the contrary, can be used to obtain reliable predictions even without labeled data. Machine learning models have been used in ICU to predict pathologies such as acute kidney injury, detect symptoms, including delirium, and propose therapeutic actions (vasopressors and fluids in sepsis). In the future, AI will be increasingly used in ICU, due to the increasing quality and quantity of available data. Accordingly, the ICU team will benefit from models with high accuracy that will be used for both research purposes and clinical practice. These models will be also the foundation of future decision support system (DSS), which will help the ICU team to visualize and analyze huge amounts of information. We plea for the creation of a standardization of a core group of data between different electronic health record systems, using a common dictionary for data labeling, which could greatly simplify sharing and merging of data from different centers.

Sign in / Sign up

Export Citation Format

Share Document