An artificial intelligence tool to predict fluid requirement in the intensive care unit: a proof-of-concept study

Purpose The DRG-ÖRG IRP (Deutsche Röntgengesellschaft-Österreichische Röntgengesellschaft international radiomics platform) represents a web-/cloud-based radiomics platform based on a public-private partnership. It offers the possibility of data sharing, annotation, validation and certification in the field of artificial intelligence, radiomics analysis, and integrated diagnostics. In a first proof-of-concept study, automated myocardial segmentation and automated myocardial late gadolinum enhancement (LGE) detection using radiomic image features will be evaluated for myocarditis data sets. Materials and Methods The DRG-ÖRP IRP can be used to create quality-assured, structured image data in combination with clinical data and subsequent integrated data analysis and is characterized by the following performance criteria: Possibility of using multicentric networked data, automatically calculated quality parameters, processing of annotation tasks, contour recognition using conventional and artificial intelligence methods and the possibility of targeted integration of algorithms. In a first study, a neural network pre-trained using cardiac CINE data sets was evaluated for segmentation of PSIR data sets. In a second step, radiomic features were applied for segmental detection of LGE of the same data sets, which were provided multicenter via the IRP. Results First results show the advantages (data transparency, reliability, broad involvement of all members, continuous evolution as well as validation and certification) of this platform-based approach. In the proof-of-concept study, the neural network demonstrated a Dice coefficient of 0.813 compared to the expert's segmentation of the myocardium. In the segment-based myocardial LGE detection, the AUC was 0.73 and 0.79 after exclusion of segments with uncertain annotation.The evaluation and provision of the data takes place at the IRP, taking into account the FAT (fairness, accountability, transparency) and FAIR (findable, accessible, interoperable, reusable) criteria. Conclusion It could be shown that the DRG-ÖRP IRP can be used as a crystallization point for the generation of further individual and joint projects. The execution of quantitative analyses with artificial intelligence methods is greatly facilitated by the platform approach of the DRG-ÖRP IRP, since pre-trained neural networks can be integrated and scientific groups can be networked.In a first proof-of-concept study on automated segmentation of the myocardium and automated myocardial LGE detection, these advantages were successfully applied.Our study shows that with the DRG-ÖRP IRP, strategic goals can be implemented in an interdisciplinary way, that concrete proof-of-concept examples can be demonstrated, and that a large number of individual and joint projects can be realized in a participatory way involving all groups. Key Points: Citation Format

Download Full-text

Characterisation of Textile Embedded Electrodes for Use in a Neonatal Smart Mattress Electrocardiography System

Sensors ◽

10.3390/s21030999 ◽

2021 ◽

Vol 21 (3) ◽

pp. 999

Author(s):

Henry Dore ◽

Rodrigo Aviles-Espinosa ◽

Zhenhua Luo ◽

Oana Anton ◽

Heike Rabe ◽

...

Keyword(s):

Intensive Care Unit ◽

Heart Rate ◽

Intensive Care ◽

High Resolution ◽

Neonatal Intensive Care Unit ◽

Real Time ◽

Neonatal Intensive Care ◽

Delivery Room ◽

Proof Of Concept ◽

Heart Rate Monitoring

Heart rate monitoring is the predominant quantitative health indicator of a newborn in the delivery room. A rapid and accurate heart rate measurement is vital during the first minutes after birth. Clinical recommendations suggest that electrocardiogram (ECG) monitoring should be widely adopted in the neonatal intensive care unit to reduce infant mortality and improve long term health outcomes in births that require intervention. Novel non-contact electrocardiogram sensors can reduce the time from birth to heart rate reading as well as providing unobtrusive and continuous monitoring during intervention. In this work we report the design and development of a solution to provide high resolution, real time electrocardiogram data to the clinicians within the delivery room using non-contact electric potential sensors embedded in a neonatal intensive care unit mattress. A real-time high-resolution electrocardiogram acquisition solution based on a low power embedded system was developed and textile embedded electrodes were fabricated and characterised. Proof of concept tests were carried out on simulated and human cardiac signals, producing electrocardiograms suitable for the calculation of heart rate having an accuracy within ±1 beat per minute using a test ECG signal, ECG recordings from a human volunteer with a correlation coefficient of ~ 87% proved accurate beat to beat morphology reproduction of the waveform without morphological alterations and a time from application to heart rate display below 6 s. This provides evidence that flexible non-contact textile-based electrodes can be embedded in wearable devices for assisting births through heart rate monitoring and serves as a proof of concept for a complete neonate electrocardiogram monitoring system.

Download Full-text

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

The American Surgeon ◽

10.1177/000313481808400736 ◽

2018 ◽

Vol 84 (7) ◽

pp. 1190-1194 ◽

Cited By ~ 3

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.

Download Full-text

Artificial Intelligence in the Intensive Care Unit

Critical Care ◽

10.1186/s13054-020-2785-y ◽

2020 ◽

Vol 24 (1) ◽

Cited By ~ 5

Author(s):

Guillermo Gutierrez

Keyword(s):

Artificial Intelligence ◽

Intensive Care Unit ◽

Intensive Care

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

Sa2023 USE OF ARTIFICIAL INTELLIGENCE TO PREVENT SEVERE PERFORATION DURING ENDOSCOPIC SUBMUCOSAL DISSECTION FOR COLORECTAL NEOPLASM: A PROOF-OF-CONCEPT STUDY

Gastrointestinal Endoscopy ◽

10.1016/j.gie.2020.03.1819 ◽

2020 ◽

Vol 91 (6) ◽

pp. AB247-AB248

Author(s):

Taishi Okumura ◽

Shinei Kudo ◽

Takemasa Hayashi ◽

Yuichi Mori ◽

Masashi Misawa ◽

...

Keyword(s):

Artificial Intelligence ◽

Endoscopic Submucosal Dissection ◽

Colorectal Neoplasm ◽

Proof Of Concept ◽

Concept Study ◽

Submucosal Dissection

Download Full-text

Is the COVID-19 Pandemic a Good Time to Include Aspergillus Molecular Detection to Categorize Aspergillosis in ICU Patients? A Monocentric Experience

Journal of Fungi ◽

10.3390/jof6030105 ◽

2020 ◽

Vol 6 (3) ◽

pp. 105 ◽

Cited By ~ 6

Author(s):

Jean-Pierre Gangneux ◽

Florian Reizine ◽

Hélène Guegan ◽

Kieran Pinceaux ◽

Pierre Le Balch ◽

...

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Invasive Aspergillosis ◽

Molecular Detection ◽

Good Time ◽

Proof Of Concept ◽

Icu Patients ◽

Blood Samples ◽

Fungal Burden ◽

Higher Sensitivity

(1) Background: The diagnosis of invasive aspergillosis (IA) in an intensive care unit (ICU) remains a challenge and the COVID-19 epidemic makes it even harder. Here, we evaluated Aspergillus PCR input to help classifying IA in SARS-CoV-2-infected patients. (2) Methods: 45 COVID-19 patients were prospectively monitored twice weekly for Aspergillus markers and anti-Aspergillus serology. We evaluated the concordance between (I) Aspergillus PCR and culture in respiratory samples, and (II) blood PCR and serum galactomannan. Patients were classified as putative/proven/colonized using AspICU algorithm and two other methods. (3) Results: The concordance of techniques applied on respiratory and blood samples was moderate (kappa = 0.58 and kappa = 0.63, respectively), with a higher sensitivity of PCR. According to AspICU, 9/45 patients were classified as putative IA. When incorporating PCR results, 15 were putative IA because they met all criteria, probably with a lack of specificity in the context of COVID-19. Using a modified AspICU algorithm, eight patients were classified as colonized and seven as putative IA. (4) Conclusion: An appreciation of the fungal burden using PCR and Aspergillus serology was added to propose a modified AspICU algorithm. This proof of concept seemed relevant, as it was in agreement with the outcome of patients, but will need validation in larger cohorts.

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