scholarly journals Evaluating a sepsis prediction machine learning algorithm in the emergency department and intensive care unit: a before and after comparative study

2017 ◽  
Author(s):  
Hoyt Burdick ◽  
Eduardo Pino ◽  
Denise Gabel-Comeau ◽  
Carol Gu ◽  
Heidi Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Intensive Care ◽  
Length Of Stay ◽  
Learning Algorithm ◽  
Detection System ◽  
Machine Learning Algorithm ◽  
Implementation Phase ◽  
Before And After ◽  
Sepsis Detection

AbstractIntroductionSepsis is a major health crisis in US hospitals, and several clinical identification systems have been designed to help care providers with early diagnosis of sepsis. However, many of these systems demonstrate low specificity or sensitivity, which limits their clinical utility. We evaluate the effects of a machine learning algodiagnostic (MLA) sepsis prediction and detection system using a before-and-after clinical study performed at Cabell Huntington Hospital (CHH) in Huntington, West Virginia. Prior to this study, CHH utilized the St. John’s Sepsis Agent (SJSA) as a rules-based sepsis detection system.MethodsThe Predictive algoRithm for EValuation and Intervention in SEpsis (PREVISE) study was carried out between July 1, 2017 and August 30, 2017. All patients over the age of 18 who were admitted to the emergency department or intensive care units at CHH were monitored during the study. We assessed pre-implementation baseline metrics during the month of July, 2017, when the SJSA was active. During implementation in the month of August, 2017, SJSA and the MLA concurrently monitored patients for sepsis risk. At the conclusion of the study period, the primary outcome of sepsis-related in-hospital mortality and secondary outcome of sepsis-related hospital length of stay were compared between the two groups.ResultsSepsis-related in-hospital mortality decreased from 3.97% to 2.64%, a 33.5% relative decrease (P = 0.038), and sepsis-related length of stay decreased from 2.99 days in the pre-implementation phase to 2.48 days in the post-implementation phase, a 17.1% relative reduction (P < 0.001).ConclusionReductions in patient mortality and length-of-stay were observed with use of a machine learning algorithm for early sepsis detection in the emergency department and intensive care units at Cabell Huntington Hospital, and may present a method for improving patient outcomes.Trial RegistrationClinicalTrials.gov, NCT03235193, retrospectively registered on July 27th 2017.

scholarly journals A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study (Preprint)

2020 ◽  
Author(s):  
Angier Allen ◽  
Samson Mataraso ◽  
Anna Siefkas ◽  
Hoyt Burdick ◽  
Gregory Braden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Intensive Care ◽  
Racial Disparities ◽  
Equal Opportunity ◽  
Racial Bias ◽  
Learning Algorithm ◽  
Early Warning Score ◽  
Machine Learning Algorithm ◽  
Saps Ii

BACKGROUND Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, <i>P</i>=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, <i>P</i>=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, <i>P</i>=.006 and equal opportunity difference 0.074, <i>P</i><.001, respectively). CONCLUSIONS This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

scholarly journals Effective and efficient network anomaly detection system using machine learning algorithm

2019 ◽  
Vol 8 (1) ◽  
pp. 46-51 ◽  
Author(s):  
Mukrimah Nawir ◽  
Amiza Amir ◽  
Naimah Yaakob ◽  
Ong Bi Lynn
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Processing Time ◽  
Learning Algorithm ◽  
Detection System ◽  
Malicious Code ◽  
Supervised Machine Learning ◽  
Machine Learning Algorithm ◽  
Network Anomaly Detection ◽  
Anomaly Detection System

Network anomaly detection system enables to monitor computer network that behaves differently from the network protocol and it is many implemented in various domains. Yet, the problem arises where different application domains have different defining anomalies in their environment. These make a difficulty to choose the best algorithms that suit and fulfill the requirements of certain domains and it is not straightforward. Additionally, the issue of centralization that cause fatal destruction of network system when powerful malicious code injects in the system. Therefore, in this paper we want to conduct experiment using supervised Machine Learning (ML) for network anomaly detection system that low communication cost and network bandwidth minimized by using UNSW-NB15 dataset to compare their performance in term of their accuracy (effective) and processing time (efficient) for a classifier to build a model. Supervised machine learning taking account the important features by labelling it from the datasets. The best machine learning algorithm for network dataset is AODE with a comparable accuracy is 97.26% and time taken approximately 7 seconds. Also, distributed algorithm solves the issue of centralization with the accuracy and processing time still a considerable compared to a centralized algorithm even though a little drop of the accuracy and a bit longer time needed.

A Survey on Intrusion Detection in Wired and Wireless Network for Future IoT Deployment

2020 ◽  
pp. 119-144
Author(s):  
Vasaki Ponnusamy ◽  
Said Bakhshad ◽  
Bobby Sharma ◽  
Robithoh Annur ◽  
Teh Boon Seong
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Computer System ◽  
Wireless Network ◽  
Learning Algorithm ◽  
Detection System ◽  
Machine Learning Algorithm ◽  
Problem Statement ◽  
Malicious Activity ◽  
Alarm Message

An intrusion detection system (IDS) works as an alarm mechanism for computer systems. It detects any malicious activity that happened to the computer system and it alerts an alarm message to notify the user there is malicious activity. There are IDS that are able to take action when malicious or anomalous networks are detected, which include suspending the traffic sent from suspicious IP addresses. The problem statement for this project is to find out the most accurate machine learning algorithm and the types of IDS with different placement strategies. When it comes to the deployment of a wireless network, IDS is not as easy a task as deploying a traditional network IDS. There are many unexpected complexities of the problem of reliable intrusion detection in a wireless network. The motivation of this research is to find the most suitable classification techniques that are able to increase the accuracy of an IDS. Machine learning is useful for the upcoming trend; it provides better accuracy in the detection of malicious traffic.

scholarly journals Intensive care unit admission protocol controlled by intensivists can reduce transfer delays from the emergency department in critically ill patients

2018 ◽  
Vol 26 (2) ◽  
pp. 84-90 ◽  
Author(s):  
Ji Eun Kim ◽  
Seul Lee ◽  
Jinwoo Jeong ◽  
Dong Hyun Lee ◽  
Jin-Heon Jeong
Keyword(s):  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Length Of Stay ◽  
Intensive Care Unit Admission ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Unit Length ◽  
Intensive Care Unit Length ◽  
Before And After

Background: Delayed transfer of patients from the emergency department to the intensive care unit is associated with adverse clinical outcomes. Critically ill patients with delayed admission to the intensive care unit had higher in-hospital mortality and increased hospital length of stay. Objectives: We investigated the effects of an intensive care unit admission protocol controlled by intensivists on the emergency department length of stay among critically ill patients. Methods: We designed the intensive care unit admission protocol to reduce the emergency department length of stay in critically ill patients. Full-time intensivists determined intensive care unit admission priorities based on the severity of illness. Data were gathered from patients who were admitted from the emergency department to the intensive care unit between 1 April 2016 and 30 November 2016. We retrospectively analyzed the clinical data and compared the emergency department length of stay between patients admitted from the emergency department to the intensive care unit before and after intervention. Results: We included 292 patients, 120 and 172 were admitted before and after application of the intensive care unit admission protocol, respectively. The demographic characteristics did not differ significantly between the groups. After intervention, the overall emergency department length of stay decreased significantly from 1045.5 (425.3–1665.3) min to 392.0 (279.3–686.8) min (p < 0.001). Intensive care unit length of stay also significantly decreased from 6.0 (4.0–11.8) days to 5.0 (3.0–10.0) days (p = 0.015). Conclusion: Our findings suggest that introduction of the intensive care unit admission protocol controlled by intensivists successfully decreased the emergency department length of stay and intensive care unit length of stay among critically ill patients at our institution.

Sign in / Sign up

Export Citation Format

Share Document