scholarly journals Artificial Intelligence-based tools to control healthcare associated infections: where do we stand

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
A Scardoni ◽  
F Balzarini ◽  
F Cabitza ◽  
A Odone
Keyword(s):  
Public Health ◽  
Artificial Intelligence ◽  
Performance Measures ◽  
Performance Outcomes ◽  
Health Concern ◽  
Surveillance Systems ◽  
Healthcare Associated Infections ◽  
Public Health Action ◽  
Practice Performance ◽  
Healthcare Associated

Abstract Background Control of Healthcare associated infections (HAI) is a key public health concern in Europe. Current HAI surveillance systems are based on manual medical records review, vulnerable to misclassification and expensive. Artificial intelligence (AI) offers great potential to public health action and, specifically, to HAI control. Still, scant evidence is available on both its practice and impact. Methods As part of a broader multidisciplinary project, we conducted a systematic review to retrieve, pool and critically apprize all the available evidence on practice, performance and impact of AI-based HAI control programmes. We followed PRISMA guidelines and searched the Medline and Embase databases for relevant studies. Included studies were stratified by HAI type and outcomes of interest, including all possible performance measures, clinical, organizational and economic outcomes. Results We screened 2873 records, resulting in 27 papers included in the review. Studies were carried out in 9 countries, the majority in the US (56%), 18.5% in EU countries, 25.9% published in 2018. Two thirds of studies focused on selected types of infections. Study designs were very diverse and performance observed for HAI detection were very heterogeneous, precluding pooled calculation of summary diagnostic accuracy estimates in most instances, but generally higher than non AI-based models. The highest performance outcomes were Specificity and Negative Predictive Value. Overall performance measures of AI algorithms were: sensitivity range 19%-92%, specificity range 64%-96%, accuracy 70.2%-96.1%. Conclusions Use of AI algorithms for HAI surveillance of HAI has increased reliability compared to traditional surveillance or to automated surveillance models. With ongoing improvements in information technology, implementation of AI models will improve the quality and capacity of surveillance will support hospital HAI surveillance. Key messages Artificial Intelligence (AI) offer great potential to healthcare associated infections (HAI) control. Preliminary evidence show AI-based models have perform better than manual or automated models for HAIs detection.

scholarly journals Artificial Intelligence-based tools to control healthcare associated infections: where do we stand

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
A Scardoni ◽  
A Odone
Keyword(s):  
Artificial Intelligence ◽  
Performance Measures ◽  
Technology Implementation ◽  
Preliminary Evidence ◽  
Health Concern ◽  
Surveillance Systems ◽  
Healthcare Associated Infections ◽  
Digital Tool ◽  
Practice Performance ◽  
Healthcare Associated

Abstract Background Control of Healthcare associated infections (HAI) is a key public health concern in Europe. Current HAI surveillance systems are based on manual medical records review, vulnerable to misclassification & expensive. Artificial intelligence (AI), as a digital tool, offers great potential to HAI control. Still, scant evidence is available on both its practice and impact. Methods As part of a broader multidisciplinary project, we conducted a systematic review to retrieve, pool and critically apprize all the available evidence on practice, performance and impact of AI-based HAI control programmes. We followed PRISMA and searched the Medline and Embase databases for relevant studies. Included studies were stratified by HAI type and outcomes of interest, including all possible performance measures, clinical, organizational and economic outcomes. Results We screened 2873 records, resulting in 27 papers included in the review. Studies were carried out in 9 countries, the majority in the US (56%), 18.5% in EU countries, 25.9% published in 2018. Two thirds of studies focused on selected types of infections. Study designs were very diverse and performance observed for HAI detection were very heterogeneous, precluding pooled calculation of summary diagnostic accuracy estimates in most instances, but generally higher than non AI-based models. Overall performance measures of AI algorithms were: sensitivity range 19%-92%, accuracy 70.2%-96.1%. Conclusions Use of AI for HAI surveillance of HAI has increased reliability compared to traditional surveillance or to automated surveillance models. With ongoing improvements in information technology, implementation of AI models will improve the quality and capacity of surveillance will support hospital HAI surveillance. Main messages AI offer great potential to healthcare associated infections control. Preliminary evidence show AI-based models have perform better than manual or automated models for HAIs detection.

Surveillance for Healthcare associated Infections in Indian NICUs: Researchable Issues

2009 ◽  
Vol 23 (4) ◽  
pp. 331-336
Author(s):  
Ashwani Kumar ◽  
Praveen Kumar
Keyword(s):  
Developed Countries ◽  
Control Measures ◽  
Surveillance Systems ◽  
Healthcare Associated Infections ◽  
Infection Control Measures ◽  
Infection Surveillance ◽  
Healthcare Associated ◽  
Symptoms And Signs ◽  
Local Research ◽  
Underlying Risk

Systematic surveillance is the first and integral step of all infection control measures, especially in intensive care settings. Surveillance systems started evolving in developed countries nearly 40 years ago. With experience and wisdom gained, the surveillance methods have improved and become more standardized. It is now clearly recognized that all patients are not at equal risk. For fair comparisons over time within an unit and in between units, the denominator must take the underlying risk into account. Infection surveillance in the NICU presents a number of unique challenges regarding definitions and differing symptoms and signs in the neonate. Although the importance of surveillance is being increasingly recognized in our country and the methods of developed countries are being adopted, there are numerous issues which need local research. This is in view of the limited manpower and financial resources and different profile of organisms and their epidemiology.

scholarly journals Modeling Carbapenemase-producing Enterobacteriaceae episodes’ evolution in France over 2010-2020

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
J Roux ◽  
N Nekkab ◽  
P Astagneau ◽  
P Crépey
Keyword(s):  
Public Health ◽  
Time Series ◽  
Patient Safety ◽  
Healthcare Associated Infections ◽  
Time Series Modeling ◽  
National Healthcare ◽  
Response System ◽  
Health Authorities ◽  
Public Health Authorities ◽  
Healthcare Associated

Abstract Background Incidence of Carbapenemase-Producing Enterobacteriaceae (CPE) episodes within hospitals is rising at an alarming rate and threaten health systems and patient safety worldwide. Their number is growing in France since 2009 associated with inter-regional dissemination and importation of international cases. This study aimed at describing the dynamics of CPE episodes in France over 2010-2016 and forecasting their evolution for 2017-2020. Methods Surveillance data of CPE episodes (imported and non-imported) from August 2010 to November 2016 were issued from the French national Healthcare-Associated Infections Early Warning and Response System. Impact of seasonality on the number of CPE episodes was analyzed using seasonal-to-irregular ratios. Seven models issued from time series analysis and three ensemble stacking models (average, convex and linear stacking) were used to describe and forecast CPE episodes. The model with the best forecasting’s quality was then trained on all available data (2010-2016) and used to predict CPE episodes over 2017-2020. Results Over 2010-2016, 3,559 CPE episodes were observed in France. Compared to the average yearly trend, we observed a 30% increase in the number of CPE episodes in September and October. On the opposite, a decrease of 20% was noticed in February compared to other months. We also noticed a 1-month lagged seasonality of non-imported episodes compared to imported ones. The number of non-imported episodes appeared to grow faster than imported ones starting from 2014. Average stacking gave the best forecasts and predicted an increase over 2017-2020 with a peak up to 345 CPE episodes (95% PI [124-1,158], 80% PI [171-742]) in September 2020. Conclusions The number of CPE episodes is predicted to rise in the next years in France because of non-imported episodes. These results could help public health authorities in the definition and evaluation of new containment strategies. Key messages Time series modeling predicts an increase in the number of CPE episodes in France in the next few years with a quicker rise of non-imported episodes. An increase of 30% in the number of CPE episodes was observed in September and October with a 1-month lagged seasonality impact of non-imported episodes compared to imported one.

scholarly journals An overview of antimicrobial resistance surveillance among healthcare-associated pathogens in South Africa

2018 ◽  
Vol 7 (2) ◽  
Author(s):  
Ashika Singh-Moodley ◽  
Husna Ismail ◽  
Olga Perovic
Keyword(s):  
Antimicrobial Resistance ◽  
Treatment Guidelines ◽  
Resistance Mechanisms ◽  
Health Concern ◽  
Infection Prevention And Control ◽  
Surveillance Systems ◽  
African Countries ◽  
Lack Of Information ◽  
Healthcare Associated ◽  
And Control

Healthcare-associated infections are a serious public health concern resulting in morbidity and mortality particularly in developing countries. The lack of information from Africa, the increasing rates of antimicrobial resistance and the emergence of new resistance mechanisms intensifies this concern warranting the need for vigorous standardised surveillance platforms that produce reliable and accurate data which can be used for addressing these concerns. The implementation of national treatment guidelines, policies, antimicrobial stewardship programmes and infection prevention and control practices within healthcare institutions require a platform from which it can draw information and direct its approach. In this review, the importance of standardised surveillance systems, the challenges faced in the application of a surveillance system and the condition (existence and nonexistence) of such systems in African countries is discussed. This review also reports on some South African data.

Maximizing Infection Prevention in the Next Decade: Defining the Unacceptable

2010 ◽  
Vol 31 (S1) ◽  
pp. S1-S3 ◽  
Author(s):  
Thomas R. Frieden
Keyword(s):  
Public Health ◽  
Infection Prevention ◽  
Healthcare Associated Infections ◽  
New Normal ◽  
Public Health Agencies ◽  
Health Agencies ◽  
Healthcare Associated

An important role of public health agencies is to define the unacceptable. This concept has particular relevance for healthcare-associated infections. Evidence indicates that, with focused efforts, these once-formidable infections can be greatly reduced in number, leading to a new normal for healthcare-associated infections as rare, unacceptable events.

scholarly journals Revealing COVID-19 Transmission by SARS-CoV-2 Genome Sequencing and Agent Based Modelling

2020 ◽  
Author(s):  
Rebecca J Rockett ◽  
Alicia Arnott ◽  
Connie Lam ◽  
Rosemarie Sadsad ◽  
Verlaine Timms ◽  
...  
Keyword(s):  
Public Health ◽  
Genome Sequencing ◽  
New South ◽  
Control Measures ◽  
Health Concern ◽  
Public Health Action ◽  
Agent Based ◽  
South Wales ◽  
Health Action ◽  
Community Transmission

ABSTRACTCommunity transmission of the new coronavirus SARS-CoV-2 is a major public health concern that remains difficult to assess. We present a genomic survey of SARS-CoV-2 from a during the first 10 weeks of COVID-19 activity in New South Wales, Australia. Transmission events were monitored prospectively during the critical period of implementation of national control measures. SARS-CoV-2 genomes were sequenced from 209 patients diagnosed with COVID-19 infection between January and March 2020. Only a quarter of cases appeared to be locally acquired and genomic-based estimates of local transmission rates were concordant with predictions from a computational agent-based model. This convergent assessment indicates that genome sequencing provides key information to inform public health action and has improved our understanding of the COVID-19 evolution from outbreak to epidemic.

scholarly journals Klebsiella pneumoniae acquisition in ICUs: patient-based and laboratory-based surveillance

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
M Barchitta ◽  
A Maugeri ◽  
C La Mastra ◽  
MC La Rosa ◽  
L Sessa ◽  
...  
Keyword(s):  
Public Health ◽  
Intensive Care ◽  
High Risk ◽  
Klebsiella Pneumoniae ◽  
Intensive Care Units ◽  
Multidrug Resistant ◽  
Trauma Patients ◽  
Healthcare Associated Infections ◽  
Global Threat ◽  
Healthcare Associated

Abstract Klebsiella pneumoniae - and especially multidrug-resistant K. pneumoniae - represents a global threat for Public Health, due to its high dissemination in Intensive Care Units (ICUs) and its association with mortality. Here, we investigated the molecular epidemiology of multidrug-resistant K. pneumoniae strains in ICUs from Catania, Italy. We used data and samples from the Italian Nosocomial Infections Surveillance in ICUs - SPIN-UTI project, which has been surveying the epidemiology and the risk of Healthcare-associated infections (HAIs) in Italian ICUs. The SPIN-UTI network adopted the ECDC protocols for patient-based HAI surveillance. In a sample of ICUs the patient-based surveillance was integrated with a laboratory-based surveillance of MDR K. pneumoniae isolates. K. pneumoniae isolates were genotyped by multilocus sequence typing (MLST), and patterns of K. pneumoniae acquisition (i.e. carriage, colonization and infection) were identified using standard definitions. Our analysis included 155 patients who stayed in two ICUs for a total of 2254 days, from October 2016 to March 2017. Trauma patients were more likely to be infected with K. pneumoniae than other patients (OR = 5.9; 95%CI=2.4-14.8; p = 0.004). A total of 109 K. pneumoniae strains were isolated from different sites of 39 patients, which in turn were defined as 45.2% colonization, 25.8% infection, and 29% carriage. 79.3% K. pneumoniae isolates resistant to carbapenems and 100% resistant to penicillins and cephalosporins. The MLST identified two major clonal groups: the ST395 and the ST37, which represented respectively the 65.6% and the 21.3% of typed isolates. Surveillance of colonization and infection by high-risk clones might help in implementing appropriate strategies, which are crucial to reduce the spread of K. pneumoniae in ICUs. *Study Group AOU 'Policlinico-Vittorio Emanuele', Catania, Italy: Patrizia Bellocchi, Giacomo Castiglione, Alida Imbriani, Marinella Astuto, Giuseppa La Camera, Agata Sciacca Key messages Multidrug-resistant K. pneumoniae still represents a threat for Public Health in Italy and globally, due to its high dissemination in intensive care units. Surveillance of colonization and infection by high-risk clones might help in reducing the spread of Klebsiella pneumoniae.

scholarly journals Electronically assisted surveillance systems of healthcare-associated infections: a systematic review

2020 ◽  
Vol 25 (2) ◽  
Author(s):  
H Roel A Streefkerk ◽  
Roel PAJ Verkooijen ◽  
Wichor M Bramer ◽  
Henri A Verbrugh
Keyword(s):  
Systematic Review ◽  
Control Programme ◽  
Mature Stage ◽  
Surveillance Systems ◽  
Healthcare Associated Infections ◽  
Medical Specialties ◽  
Specificity And Sensitivity ◽  
Healthcare Associated ◽  
Traditional Surveillance

Background Surveillance of healthcare-associated infections (HAI) is the basis of each infection control programme and, in case of acute care hospitals, should ideally include all hospital wards, medical specialties as well as all types of HAI. Traditional surveillance is labour intensive and electronically assisted surveillance systems (EASS) hold the promise to increase efficiency. Objectives To give insight in the performance characteristics of different approaches to EASS and the quality of the studies designed to evaluate them. Methods In this systematic review, online databases were searched and studies that compared an EASS with a traditional surveillance method were included. Two different indicators were extracted from each study, one regarding the quality of design (including reporting efficiency) and one based on the performance (e.g. specificity and sensitivity) of the EASS presented. Results A total of 78 studies were included. The majority of EASS (n = 72) consisted of an algorithm-based selection step followed by confirmatory assessment. The algorithms used different sets of variables. Only a minority (n = 7) of EASS were hospital-wide and designed to detect all types of HAI. Sensitivity of EASS was generally high (> 0.8), but specificity varied (0.37–1). Less than 20% (n = 14) of the studies presented data on the efficiency gains achieved. Conclusions Electronically assisted surveillance of HAI has yet to reach a mature stage and to be used routinely in healthcare settings. We recommend that future studies on the development and implementation of EASS of HAI focus on thorough validation, reproducibility, standardised datasets and detailed information on efficiency.

Sign in / Sign up

Export Citation Format

Share Document