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

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.

FOALS ARE GETTING HELP

PEDIATRICS ◽  
1989 ◽  
Vol 84 (4) ◽  
pp. A96-A96
Author(s):  
J. F. L.
Keyword(s):  
Intensive Care Unit ◽  
Veterinary Medicine ◽  
Intensive Care ◽  
Birth Defects ◽  
Human Medicine ◽  
University Of Pennsylvania ◽  
Twin Brother ◽  
Pennsylvania Hospital ◽  
The University

KENNETT SQUARE, Pa.—Nearly as rare as the colt that grows up to be a racing champion is the birth of twin foals. Yet a tiny and brave filly and her weaker twin brother grow stronger every day here in an intensive care unit for newborn horses. Established in 1983 and directed . . . by Dr. Wendy E. Vaala, a . . . veterinarian, the University of Pennsylvania's intensive care unit for foals was built. . . . It is one of only seven such units in the country, and they have led to the development of a new specialty in veterinary medicine—equine neonatology. Recipes for formula fed to foals were borrowed from those used at the University of Pennsylvania Hospital in Philadelphia. The intensive care unit uses ultrasound equipment, heart monitors and other devices commonly used in human neonatal medicine. Treatments for infections, poisoning, ulcers, birth defects, even difficult births were adopted from human medicine. . . . But there are no incubators. . . .The foals are too active.

scholarly journals Prognostic Factors for Acute Heart Failure (AHF) in the Cardiology Intensive Care Unit (ICU) of the University Hospital Point G (UH Pt G)

2019 ◽  
Vol 09 (01) ◽  
pp. 42-50
Author(s):  
Camara Youssouf ◽  
Ba Hamidou Oumar ◽  
Sangare Ibrahima ◽  
Toure Karamba ◽  
Coulibaly Souleymane ◽  
...  
Keyword(s):  
Heart Failure ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Prognostic Factors ◽  
Acute Heart Failure ◽  
University Hospital ◽  
Point G ◽  
The University

A “School Of Clinical Ethics”: Clinical Ethics Education for Clinicians and Philosophy Students

2021 ◽  
Vol 66 (Special Issue) ◽  
pp. 79-79
Author(s):  
Lucia Galvagni ◽  
◽  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Action Research ◽  
Clinical Ethics ◽  
Ethics Education ◽  
Ethical Analysis ◽  
Coordination Unit ◽  
Philosophy Department ◽  
The University ◽  
Previous Step

"The presentation intends to present and illustrate an experience of teaching clinical ethics realized with a group of clinicians and philosophy students and held at the Philosophy Department of the University of Trento, Italy (Spring 2013 and Spring 2015). The class was intended to train clinicians and students to the main concepts of clinical ethics and to a specific methodology to approach clinical matters with ethical and philosophical tools. The class offered a space and time of listening, confronting, debating and learning. The opportunity to dialogue and to reflect, starting form clinical cases presented by clinicians and to realize an ethical analysis of them, combining languages and competences, resulted extremely relevant for clinicians, for students involved and for the teachers themselves. It represented – as well – a first and previous step to start some action-research in specific clinical units, as the local Intensive Care Unit, the Transplantation Coordination Unit and the Mountain Medicine and Ethics Lab. "

PREVALENCE OF HIGH LEVEL AMINOGLYCOSIDE RESISTANCE AND VANCOMYCIN RESISTANT ENTEROCOCCI IN ENTEROCOCCAL ISOLATES IN A TERTIARY CARE HOSPITAL

2021 ◽  
pp. 3-5
Author(s):  
Sunita Agarwal ◽  
Nazneen Pathan ◽  
Shivra Batra ◽  
Rajni Sharma
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Tertiary Care ◽  
Automated System ◽  
Care Hospital ◽  
Enterococcus Species ◽  
Aminoglycoside Resistance ◽  
Vancomycin Resistant Enterococci ◽  
Vancomycin Resistant ◽  
High Level

Introduction: The emergence of High Level Aminoglycoside Resistance (Resistant to Gentamycin and Streptomycin) and Vancomycin Resistant Enterococci among Indoor and Intensive Care Unit admitted patient presents a serious challenge for clinicians. Objective: To determine Enterococcal burden in blood and urine specimens and to detect the prevalence of High Level Aminoglycoside Resistance and Vancomycin Resistant Enterococci. Material & Methods: One hundred ten Enterococci were isolated from blood and urine samples and processed according to standard laboratory protocol. Species identication and sensitivity was done using the VITEK 2 automated system (Biomerieux France) with the cards GPID and AST 67 respectively. Results: Out of 110 Enterococci isolates, 36 were from blood and 74 from urine were detected. Different Species isolated were Enterococcal faecium (59%), Enterococcal faecalis (34%), Enterococcal rafnosus (2.7%), Enterococcal gallinarum (1.8%), Enterococcal casseliavus (0.9%) and Enterococcal duran (0.9%).Out of 36 blood isolates, 14 (38%) were found to be both High Level Gentamycin Resistant (HLGR) & High Level Streptomycin Resistant (HLSR), 10 (27%) were only HLGR and 8 (22%) were only HLSR. 20 strain (55%) of Enterococcus species isolated in blood were VRE. All VRE strains were found to be resistant to both aminoglycosides ( HLAR).Among the 74 urinary isolates, 24 (34%) were found to be both HLGR & HLSR, only HLGR was observed in 20 (27%) and HLSR was observed in 11 (14%) isolates. 24 strains (34%) of Enterococcus species were found to be vancomycin resistant in urine. 23 strains out of 24 were resistant to high level of aminoglycosides. Conclusion: The prevalence of HLAR and VRE is very high among Enterococcus specimens from indoor/ intensive care unit patients. Early species identication and antibiotic sensitivity result can help in better clinical outcome.

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 Designing and evaluating an automated system for real-time medication administration error detection in a neonatal intensive care unit

2018 ◽  
Vol 25 (5) ◽  
pp. 555-563 ◽  
Author(s):  
Yizhao Ni ◽  
Todd Lingren ◽  
Eric S Hall ◽  
Matthew Leonard ◽  
Kristin Melton ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Real Time ◽  
Medication Errors ◽  
Neonatal Intensive Care ◽  
Current Practice ◽  
Medication Administration ◽  
Automated System ◽  
Patient Exposure ◽  
Potential Harm

Abstract Background Timely identification of medication administration errors (MAEs) promises great benefits for mitigating medication errors and associated harm. Despite previous efforts utilizing computerized methods to monitor medication errors, sustaining effective and accurate detection of MAEs remains challenging. In this study, we developed a real-time MAE detection system and evaluated its performance prior to system integration into institutional workflows. Methods Our prospective observational study included automated MAE detection of 10 high-risk medications and fluids for patients admitted to the neonatal intensive care unit at Cincinnati Children’s Hospital Medical Center during a 4-month period. The automated system extracted real-time medication use information from the institutional electronic health records and identified MAEs using logic-based rules and natural language processing techniques. The MAE summary was delivered via a real-time messaging platform to promote reduction of patient exposure to potential harm. System performance was validated using a physician-generated gold standard of MAE events, and results were compared with those of current practice (incident reporting and trigger tools). Results Physicians identified 116 MAEs from 10 104 medication administrations during the study period. Compared to current practice, the sensitivity with automated MAE detection was improved significantly from 4.3% to 85.3% (P = .009), with a positive predictive value of 78.0%. Furthermore, the system showed potential to reduce patient exposure to harm, from 256 min to 35 min (P < .001). Conclusions The automated system demonstrated improved capacity for identifying MAEs while guarding against alert fatigue. It also showed promise for reducing patient exposure to potential harm following MAE events.

Caring for “Socially Undesirable” Patients

1996 ◽  
Vol 5 (4) ◽  
pp. 500-510 ◽  
Author(s):  
Nancy S. Jecker
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Metabolic Acidosis ◽  
Renal Insufficiency ◽  
Suicide Attempts ◽  
University Hospital ◽  
Healthcare Team ◽  
Local Hospital ◽  
The University ◽  
Osmolar Gap

Mr. Bernard was a homeless man, aged 58. His medical history revealed alcohol abuse, seizure disorder, and two suicide attempts. Brought to the emergency room at a local hospital after being found “semi-comatose,” his respiratory distress led to his being intubated and placed on a ventilator. The healthcare team suspected the patient ingested antifreeze. Transferred from that hospital to the intensive care unit (ICU) of the university hospital, his diagnosis was “high osmolar gap with high-anion gap metabolic acidosis, most likely secondary to ethylene glycol ingestion and renal insufficiency.”

Sign in / Sign up

Export Citation Format

Share Document