Artificial Intelligence in the Intensive Care Unit

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.

Download Full-text

Adopting a smart toothbrush with artificial intelligence may improve oral care in patients admitted to the intensive care unit

Critical Care ◽

10.1186/s13054-019-2512-8 ◽

2019 ◽

Vol 23 (1) ◽

Author(s):

Tommaso Scquizzato ◽

Arianna Gazzato

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Intensive Care ◽

Oral Care

Download Full-text

Artificial Intelligence Algorithm for Predicting Cardiac Arrest Using Electrocardiography

10.21203/rs.3.rs-68766/v1 ◽

2020 ◽

Author(s):

Joon-myoung Kwon ◽

Kyung-Hee Kim ◽

Ki-Hyun Jeon ◽

Soo Youn Lee ◽

Jinsik Park ◽

...

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Cardiac Arrest ◽

Intensive Care ◽

External Validation ◽

High Risk Group ◽

Validation Data ◽

Intelligence Algorithm ◽

Artificial Intelligence Algorithm ◽

Intensive Care Unit Transfer

Abstract Background: In-hospital cardiac arrest is a major burden in health care. Although several track-and-trigger systems are used to predict cardiac arrest, they often have unsatisfactory performances. We hypothesized that a deep-learning-based artificial intelligence algorithm (DLA) could effectively predict cardiac arrest using electrocardiography (ECG). We developed and validated a DLA for predicting cardiac arrest using ECG. Methods: We conducted a retrospective study that included 47,505 ECGs of 25,672 adult patients admitted to two hospitals, who underwent at least one ECG from October 2016 to September 2019. The endpoint was occurrence of cardiac arrest within 24 hours from ECG. Using subgroup analyses in patients who were initially classified as non-event, we confirmed the delayed occurrence of cardiac arrest and unexpected intensive care unit transfer over 14 days.Results: We used 32,294 ECGs of 10,461 patients and 4,483 ECGs of 4,483 patients from a hospital were used as development and internal validation data, respectively. Additionally, 10,728 ECGs of 10,728 patients from another hospital were used as external validation data, which confirmed the robustness of the developed DLA. During internal and external validation, the areas under the receiver operating characteristic curves of the DLA in predicting cardiac arrest within 24 hours were 0.913 and 0.948, respectively. The high risk group of the DLA showed a significantly higher hazard for delayed cardiac arrest (5.74% vs. 0.33%, P < 0.001) and unexpected intensive care unit transfer (4.23% vs. 0.82%, P < 0.001). A sensitivity map of the DLA displayed the ECG regions used to predict cardiac arrest, with the DLA focused most on the QRS complex. Conclusions: Our DLA successfully predicted cardiac arrest using diverse formats of ECG. The results indicate that cardiac arrest could be screened and predicted not only with a conventional 12-lead ECG, but also with a single-lead ECG using a wearable device that employs our DLA.

Download Full-text

A novel artificial intelligence based intensive care unit monitoring system: using physiological waveforms to identify sepsis

Philosophical Transactions of The Royal Society A Mathematical Physical and Engineering Sciences ◽

10.1098/rsta.2020.0252 ◽

2021 ◽

Vol 379 (2212) ◽

Cited By ~ 1

Author(s):

Maximiliano Mollura ◽

Li-Wei H. Lehman ◽

Roger G. Mark ◽

Riccardo Barbieri

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Intensive Care ◽

Vital Sign ◽

Relevant Information ◽

Great Opportunity ◽

Diagnosis And Prognosis ◽

Challenges And Opportunities ◽

Multivariate Modelling ◽

Decision Making Processes

A massive amount of multimodal data are continuously collected in the intensive care unit (ICU) along each patient stay, offering a great opportunity for the development of smart monitoring devices based on artificial intelligence (AI). The two main sources of relevant information collected in the ICU are the electronic health records (EHRs) and vital sign waveforms continuously recorded at the bedside. While EHRs are already widely processed by AI algorithms for prompt diagnosis and prognosis, AI-based assessments of the patients’ pathophysiological state using waveforms are less developed, and their use is still limited to real-time monitoring for basic visual vital sign feedback at the bedside. This study uses data from the MIMIC-III database (PhysioNet) to propose a novel AI approach in ICU patient monitoring that incorporates features estimated by a closed-loop cardiovascular model, with the specific goal of identifying sepsis within the first hour of admission. Our top benchmark results (AUROC = 0.92, AUPRC = 0.90) suggest that features derived by cardiovascular control models may play a key role in identifying sepsis, by continuous monitoring performed through advanced multivariate modelling of vital sign waveforms. This work lays foundations for a deeper data integration paradigm which will help clinicians in their decision-making processes. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Download Full-text

Artificial intelligence in the intensive care unit

Critical Care ◽

10.1186/s13054-018-2301-9 ◽

2019 ◽

Vol 23 (1) ◽

Cited By ~ 14

Author(s):

Christopher A. Lovejoy ◽

Varun Buch ◽

Mahiben Maruthappu

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Intensive Care

Download Full-text

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)

10.2196/preprints.27142 ◽

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

Download Full-text

Validation of an Automatic Tagging System for Identifying Respiratory and Hemodynamic Deterioration Events in the Intensive Care Unit

Healthcare Informatics Research ◽

10.4258/hir.2021.27.3.241 ◽

2021 ◽

Vol 27 (3) ◽

pp. 241-248

Author(s):

Danielle Jeddah ◽

Ofer Chen ◽

Ari M. Lipsky ◽

Andrea Forgacs ◽

Gershon Celniker ◽

...

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Intensive Care ◽

Model Development ◽

Automated System ◽

Automatic Tagging ◽

Hemodynamic Deterioration ◽

University Of Massachusetts ◽

The University ◽

Tagging System

Objectives: Predictive models for critical events in the intensive care unit (ICU) might help providers anticipate patient deterioration. At the heart of predictive model development lies the ability to accurately label significant events, thereby facilitating the use of machine learning and similar strategies. We conducted this study to establish the validity of an automated system for tagging respiratory and hemodynamic deterioration by comparing automatic tags to tagging by expert reviewers.Methods: This retrospective cohort study included 72,650 unique patient stays collected from Electronic Medical Records of the University of Massachusetts’ eICU. An enriched subgroup of stays was manually tagged by expert reviewers. The tags generated by the reviewers were compared to those generated by an automated system.Results: The automated system was able to rapidly and efficiently tag the complete database utilizing available clinical data. The overall agreement rate between the automated system and the clinicians for respiratory and hemodynamic deterioration tags was 89.4% and 87.1%, respectively. The automatic system did not add substantial variability beyond that seen among the reviewers.Conclusions: We demonstrated that a simple rule-based tagging system could provide a rapid and accurate tool for mass tagging of a compound database. These types of tagging systems may replace human reviewers and save considerable resources when trying to create a validated, labeled database used to train artificial intelligence algorithms. The ability to harness the power of artificial intelligence depends on efficient clinical validation of targeted conditions; hence, these systems and the methodology used to validate them are crucial.

Download Full-text