Welcome to the ISPPD 2022 Meeting Calendar

To check the meeting times in your local time zone Click Here

             

Displaying One Session

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Session Description
Please note: Each presentation is followed by about 3 minutes of Q&A. The audience is encouraged to send questions to the speakers from the beginning of their presentations. Q&A time is included in each speaker’s presentation duration, accounting for at least 25% active learning for the maximum registrants anticipated.

Introduction (ID 61)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
15:05 - 15:07

O059 - CHANGES IN THE GLOBAL INCIDENCE OF INVASIVE PNEUMOCOCCAL DISEASE DURING THE COVID-19 PANDEMIC: DATA FROM THE INVASIVE RESPIRATORY INFECTION SURVEILLANCE (IRIS) INITIATIVE (ID 865)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
15:17 - 15:25

Abstract

Background

IRIS was established to analyse the impact of the COVID-19 pandemic on invasive diseases among all age groups caused by four major bacterial pathogens, Streptococcus pneumoniae, Haemophilus influenzae, Neisseria meningitidis and Streptococcus agalactiae. We previously demonstrated a significant association between the stringency of COVID-19 containment measures and reduced bacterial invasive disease early in the pandemic (https://doi.org/10.1016/S2589-7500(21)00077-7). Here, we focus on the reduction in invasive pneumococcal disease (IPD) cases through 2021.

Methods

Reference laboratories in 29 countries submitted invasive disease data to a private project in PubMLST. We performed interrupted time series analyses to quantify the impact of pandemic-related response measures on IPD rates. Autoregressive integrated moving average (ARIMA) models were used to estimate effect sizes and forecast counterfactual trends for each country, 2018-2021.

Results

Nearly 90,000 IPD cases (75,465 and 14,228 cases in the Northern and Southern hemispheres, respectively) occurred from 2018-2021 among participating countries. Overall, the risk of IPD was reduced by 55% after the pandemic was officially declared in week 11 of 2020 (relative risk: 0.45; 95% confidence interval [CI], 0.39-0.52). The reduction was similar in the Northern (57%; CI, 40-66%) and Southern (54%; CI, 45-60%) hemispheres. Overall, nearly 30,000 IPD cases (n=29,811; CI, 16,157-43,465) were estimated to have been averted since the beginning of the pandemic.

Conclusions

COVID-19 pandemic response measures were associated with a significant decrease in IPD across all countries participating in IRIS. IPD cases have started returning to pre-pandemic levels in some countries as pandemic restrictions are lifting and the IRIS members are closely monitoring these changes.

Hide

O060 - POPULATION IMMUNITY TO PNEUMOCOCCAL SEROTYPES IN KILIFI, KENYA, BEFORE AND 5 YEARS AFTER THE INTRODUCTION OF PCV10 WITH A CATCH-UP CAMPAIGN (ID 870)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
15:35 - 15:43

Abstract

Background

In Kilifi, PCV10 was introduced in 2011 with a catch-up campaign in 1-4 year olds. Carriage of vaccine serotypes declined by 64% in children aged <5 years within 6 months of introduction. We aimed to measure the effect of PCV on population immunity.

Methods

Cross-sectional serosurveys were conducted in independent random samples of 500 individuals aged <15 years in 2009, 2011, 2013, 2015 and 2017. Anti-capsular IgG against vaccine serotypes 1, 4, 5, 6B, 7F, 9V, 14, 18C, 19F, 23F and serotypes 6A and 19A, was assayed by ELISA at a WHO reference laboratory. The GMCs and the proportion with an antibody concentration >0.35mcg/ml were examined. Age-specific immunity profiles were constructed by plotting GMCs by birth-year and age.

Results

Vaccine introduction with catch-up increased the proportion of infants and young children with protective levels of IgG. As the vaccination programme matured, GMCs among infants remained high. However, among those vaccinated in infancy, GMCs for 7 of the 10 vaccine serotypes waned rapidly after vaccination, between 1-3 years of age. GMCs rise again later in childhood; there was no change in the GMCs in the oldest age group, 10–14-year-olds, over time.

Conclusions

After PCV10 vaccination in infancy there was relatively rapid waning of IgG for most vaccine serotypes in the first two years of life. However, antibody concentrations remained high in older children throughout the study, despite hypothesised reduced natural boosting in this age group. Continued exposure to vaccine serotypes, e.g., as sub-dominant carriage, or memory responses to cross-reactive antigens could explain this phenomenon.

Hide

O061 - SEROTYPE-1 POPULATION IN BANGLADESH: CHANGES IN THE POST-VACCINATION PERIOD AND THEIR GENOMIC BACKGROUND (ID 866)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
15:53 - 16:01

Abstract

Background

Serotype-1, a major cause of invasive pneumococcal diseases (IPD), is a part of PCV10 and PCV13 formulations. Multiple countries have reported a positive impact on serotype-1 after vaccine introduction. This study aims to observe the trend of serotype-1 in Bangladesh, their sequence types (ST), and GPSCs using whole-genome sequence (WGS), from 2004 to 2021, following the introduction of PCV10 in 2015.

Methods

Child Health Research Foundation has been conducting IPD surveillance since 1993 at four different hospitals in Bangladesh and identified 164 serotype-1 cases since. WGS was done for all culture-positive isolates (n=94) and analyzed to detect serotypes, GPSCs and STs; also reference mapped to generate a phylogenetic tree.

Results

Since 2004, we identified overall 9% (112/1,280) serotype-1 among all IPD cases. However, this ratio increased in the post-PCV period, from a yearly average of 10.2% to 10.8%. The affected age group has also changed, from 82% to 43% cases (pre- vs post) among <5y children (Figure 1).

figure_01.png

Remarkably, the change was reflected in the phylogenetic tree, showing specific clusters for pre- and post-PCV cases (Figure 2), suggesting some changes in their genomic background, although the dominance of GPSC-2 (100%) and ST303 (94%) remains.

figure_02.png

Conclusions

Our results suggest changes in the serotype-1 population of Bangladesh since the PCV10 introduction. Both the burden and age group have changed, along with some indicative genomic changes. Further, we will explore the evolutionary background (using BEAST), relate with clinical and epidemiological data, and the possible role of vaccines – to present at ISPPD, Toronto.

Hide

O062 - MOLECULAR MECHANISMS OF NEURONAL DAMAGE CAUSED BY PNEUMOCOCCAL INFECTION (ID 818)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
16:11 - 16:19

Abstract

Background

Streptococcus pneumoniae (the pneumococcus) is the main etiological cause of bacterial meningitis globally. 50% of survivors suffer from permanent neurological dysfunctions, such as cognitive and motor delay, hearing loss, and psychiatric disorders, due to a neuronal injury caused by the bacterial infection.

Methods

Through cell-culture assays, we have investigated the cytotoxicity inflicted by pneumococci to human neurons, and the capacity of pneumococci to interact (adhesion/invasion) with neurons. In vitro assays using purified proteins were performed to investigate pneumococcal-neuron interaction. Results were confirmed with our in vivo meningitis mouse model combined with ex vivo high-resolution immunofluorescence microscopy analysis.

Results

Thanks to their elasticity and motility, neurons present some cytoskeleton β-actin filaments exposed on their plasma membrane. S. pneumoniae can invade and kill neurons through interaction with the pneumococcal pilus-1 adhesin RrgA and pneumolysin with the neuronal β-actin filaments exposed on the neuronal plasma membrane. S. pneumoniae can then exploit the interaction with neuronal β-actin to invade neurons causing disruption of the cytoskeleton. Importantly, when the surface-exposed β-actin filaments are blocked with specific antibodies, pneumococcal adhesion to neurons is prevented and neurons in vitro survive from pneumococcal infection.

Conclusions

For the first time in literature, our study published in 2021 in PLOS Pathogens has shed light into important aspects of pneumococcal-neuron interactions: 1. Pneumococci adhere to and invade neurons through interaction of the pilus-1 tip-protein RrgA and pneumolysin with β-actin exposed on neuronal plasma membrane 2. Blockade of this interaction can prevent neuronal death during a pneumococcal infection in vitro opening new avenues for new therapeutic approaches.

Hide

O070 - EXTRAPULMONARY SYNERGISM: INFLUENZA PROMOTES STREPTOCOCCUS PNEUMONIAE CARDIAC PATHOGENESIS (ID 823)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
16:19 - 16:27

Abstract

Background

It has been extensively reported that primary influenza infection promotes the development of a lethal form of Streptococcus pneumoniae (Spn) pulmonary disease. Recently, pneumonia events caused by both viruses and bacteria have been directly associated with cardiac damage. It is not known whether viral-bacterial synergy extends to extrapulmonary organs such as the heart.

Methods

Here we used a mouse model of secondary infection (SI) were mice are infected with pandemic influenza A virus (IAV) and then challenged with Spn. Using label-free quantitative proteomics we assessed the effects of SI to cardiac biology. We determined cardiac bacterial titers, and used immunoblots and isogenic deletion bacterial mutants to validate proteomic observations. We used mice deficient in necroptosis to discern the requirement of this pathway in vitro and in vivo.

Results

We report that primary infection with pandemic IAV leads to increased Spn translocation to the myocardium. We also observed that each infection alone led to proteomic changes in the heart, and these were exacerbated in the SI model. Gene ontology analysis of significantly upregulated proteins showed increased innate immune activity, oxidative processes, and changes to ion homeostasis during SI. Immunoblots confirmed increase complement, antioxidants and ACE2. Using an in vitro model of SI, we observed that influenza enhances Spn cell cytotoxicity and bacterial adhesion to cardiomyocytes. Mice deficient in necroptosis showed enhanced innate immune responses and mitochondrial function, and decreased virus-associated pathways.

Conclusions

The presented results provide the first in vivo evidence that influenza infection promotes Spn infiltration, necrotic damage, and proteomic remodeling of the heart.

Hide

O063 - EVALUATION OF REDUCED DOSE PCV SCHEDULES IN A NAIVE POPULATION IN VIETNAM (ID 838)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
16:47 - 16:55

Abstract

Background

We investigated whether a mature Pneumococcal Conjugate Vaccine (PCV) schedule with a single priming and a booster dose (1p+1) offers non-inferior protection compared to 3 dose schedules (2p+1 and 3p+0).

Methods

Between October 2016 and October 2020 we conducted a cRCT with four arms using PCV10 in a 1p+1, 0p+1, 2p+1 or 3p+0 schedule, in 24 communes in Nha Trang, Vietnam, a PCV-naïve population. A catch-up campaign was offered to all <3y olds at the start of vaccination in February 2017. Annual carriage surveys in 1440 infants, 1440 toddlers and their mothers were conducted. Vaccine type (VT) carriage was determined by lytA RT-PCR positivity, culture and microarray serotyping. The primary endpoint was non-inferiority of VT carriage in infants in 1p+1 vs 2p+1 and 3p+0 arms; non-inferiority was defined as an absolute difference of less than 5%.

Results

VT carriage in infants before PCV was 11.6% (161/1383). In 2020, VT carriage in infants had reduced to 2.0% (7/353) vs 1.5% (5/343) and 1.2% (4/331) in 1p+1, 2p+1, and 3p+0 arms respectively: a non-inferior difference of 0.5% (-1.4, 2.5%) and 0.8% (-1.1, 2.7%). Vaccine cross reactive ST6A prevalence in infants was 6.4% (89/1383) before PCV use and reduced to 3.3% (12/353) vs 2.9% (10/343) and 0.9% (3/331) in 1p+1, 2p+1, and 3p+0 arms in 2020. Reductions were similar for toddlers and marginally lower for the 0p+1 arm.

Conclusions

The 1p+1 was non-inferior to 3 dose PCV10 schedules in sustaining combined direct and indirect protection against carriage in infants.

Hide

O064 - IMMUNOGENICITY AND SAFETY OF A 10-VALENT PNEUMOCOCCAL CONJUGATE VACCINE (PCV) ADMINISTERED AS A 2+1 SCHEDULE TO HEALTHY INFANTS IN THE GAMBIA (ID 859)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:05 - 17:13

Abstract

Background

SIIPL-PCV (Pneumosil®) is a new, low-cost, WHO prequalified 10-valent PCV manufactured by the Serum Institute of India Pvt. Ltd. This study was designed to describe how SIIPL-PCV compares to the other two WHO prequalified PCVs: 10-valent pneumococcal polysaccharide protein D-conjugate vaccine (PHiD-CV [Synflorix™], GlaxoSmithKline); and the 13-valent PCV (PCV13 [Prevenar 13®], Pfizer), when given as a 2+1 schedule.

Methods

Vaccines were administered in a 1:1:1 ratio to 660 infants at 6 and 14 weeks of age with the booster at 9 months. The primary immunogenicity objective, measured four weeks after the booster, was to compare the serotype-specific immunoglobulin G geometric mean concentrations (GMCs) generated by SIIPL-PCV with those generated by PHiD-CV and PCV13.

Results

For SIIPL-PCV compared to PHiD-CV, GMC ratios for the shared serotypes ranged from 0.64 (95% CI 0.52 to 0.79) for serotype 19F to 2.91 (95% CI 2.47 to 3.44) for serotype 1. For SIIPL-PCV compared to PCV13, GMC ratios ranged from 0.72 (95% CI 0.60 to 0.87) for serotype 19A to 1.44 (95% CI 1.23 to 1.69) for serotype 1. Sixteen (7.3%) infants experienced a mild or moderate systemic rash following vaccination with SIIPL-PCV compared to seven (3.2%) and six (2.7%) following PHiD-CV and PCV13, respectively. No other notable differences in solicited adverse event rates occurred.

Conclusions

SIIPL-PCV generates robust immune responses following administration to infants according to a 2+1 schedule. The serotype-specific immune responses are of the same order as those generated by PHiD-CV and PCV13 for which effectiveness data are available.

Hide

O065 - INCREASE OF INVASIVE PNEUMOCOCCAL DISEASE IN CHILDREN TEMPORALLY ASSOCIATED WITH RSV OUTBREAK: A TIME SERIES ANALYSIS (ID 860)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:23 - 17:31

Abstract

Background

Background. Following the start of the COVID-19 pandemic, IPD incidence markedly decreased in all age groups from spring of 2020 to the summer of 2021, concomitantly with a quasi-disappearance of respiratory viruses. During fall 2021, a surge of IPD was observed among children in Quebec. We aimed to assess the temporal association of this increase with respiratory viruses’ dynamics.

Methods

Methods. We conducted an interrupted time-series analysis using IPD and respiratory viruses surveillance data from January 2013 to January 2022 in Quebec, focusing on epidemiological changes occurring since 2020. Monthly IPD rates were analyzed by segmented quasi-Poisson regression adjusted for seasonality, using monthly number of positive tests for RSV, influenza, parainfluenza 1 to 4, adenovirus, metapneumovirus and coronavirus as explanatory variables. A sensitivity analysis considering the proportion of positive tests for the different respiratory viruses was also conducted.

Results

Results. We included 7,669 IPD cases. In children < 5 years of age, the IPD increase in the fall 2021 was temporally associated with a major RSV outbreak. The fraction of the IPD increase in 2021 attributable to RSV dynamics was 77% (95%CI [33; 100]). Sensitivity analysis provided similar respults. By contrast in adults, the monthly IPD incidence, which remained low over the same period, was temporally associated with influenza dynamics.capture d’écran 2022-04-12 à 18.55.02.png

Conclusions

Conclusion. Respiratory viral infections may trigger invasive pneumococcal disease (IPD). Our results suggest a differential role of RSV and influenza on IPD risk in children and adults. Besides pneumococcal vaccines, influenza and future RSV vaccines could play a role in IPD prevention.

Hide

O066 - IMPACT OF PCV13 INTRODUCTION ON SEVERE LOWER RESPIRATORY TRACT INFECTIONS ASSOCIATED WITH RESPIRATORY SYNCYTIAL VIRUS OR INFLUENZA IN HOSPITALISED CHILDREN IN ULAANBAATAR, MONGOLIA (ID 869)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:31 - 17:39

Abstract

Background

PCV13 was introduced in Mongolia in a phased manner, from June 2016. We aimed to evaluate the impact of PCV13 introduction on the incidence of severe lower respiratory tract infections (LRTIs) and those associated with RSV or influenza among hospitalised children <2 years in 4 districts of Ulaanbaatar (SK:Songinokhairkhan, SB:Sukhbataar, BZ:Bayanzurkh and CHD:Chingeltei) for the period April 2015-March 2020.

Methods

This study is nested in a pneumonia surveillance project which enrolled hospitalised children aged 2-59 months who met an adapted WHO pneumonia case definition. We included children <2 years with arterial O2 saturation<93%, and children with radiological confirmed pneumonia. We tested nasopharyngeal swabs for RSV and influenza using qRT-PCR. Incidence rate ratios (IRR) comparing pre- and post-vaccine periods were estimated using negative binomial models with PCV13 introduction, district and time, as covariates.

Results

In total 5,680 children were enrolled; 1,977 (34.8%) and 360 (6.3%) were positive for RSV and influenza, respectively. The RSV and influenza peaks coincided with the peak of LRTIs cases from the surveillance project (Figure 1). No significant reductions in incidences of LRTIs [IRR 0.97 (95% confidence interval (CI) 0.78-1.21)], nor LRTIs associated with RSV [IRR 0.90 (95%CI 0.64-1.25)] or influenza [IRR 0.87 (95%CI 0.52-1.46)] were observed after PCV introduction.

Figure 1-LRTIs and LRTIs associated with RSV and influenza cases

figure 1-abstract isppd 2022.png

Conclusions

PCV13 introduction does not have a clear impact on reducing the incidence of all LRTIs as well as LRTIs associated with RSV or with influenza. Separate models exploring impact by district for different endpoints will also be presented.

Hide

O067 - SEASONAL PATTERN OF INVASIVE PNEUMOCOCCAL DISEASE [IPD] IN MASSACHUSETTS’ CHILDREN DISRUPTED BY COVID19 (ID 889)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:39 - 17:47

Abstract

Background

IPD in children in Massachusetts traditionally follows a seasonal pattern with peak disease between October-April and a nadir during June-September (Figure 1). To further understand the decline in IPD observed in 2020 and 2021, we evaluated the seasonal pattern of IPD during the multiple COVID-19 surges in Massachusetts and compared with the seasonality observed in 2002-2019

Methods

A statewide, population-based surveillance for IPD in children <18-year-old was initiated in October/2001 and has been ongoing. IPD is defined as isolation of S. pneumoniae from a normally sterile site. Microbiology laboratories submit isolates of S. pneumoniae from normally sterile body fluids to MDPH, demographic data is confirmed with follow-up phone interviews. Isolates are serotyping using antisera from Staten's Serum Institute.

Results

Forty-five cases of IPD were identified in Massachusetts’ children in 2020/21 representing a decline of 39% in annual cases compared to 2013-2019 period. Notable was the near absence of IPD cases between April/2020 and June/2021 during the peak COVID-19 activity (October/2020 to June/2021)Despite high COVID-19 activity in September-December 2021, we observed frequent IPD cases. The difference between the two period of high COVID-19 activity was the return of RSV to the community during September–December 2021.ipd isppd22 figure.jpg

Conclusions

The disruption impact of COVID-19 on IPD in Massachusetts during 2020-2021 was manifest by a 40% decline in cases in children and a disruption of the traditional seasonal pattern. The return of IPD during fourth quarter 2021 despite a COVID-19 surge was associated with a return of RSV to the community.

Hide

O068 - REDUCTIONS IN LABORATORY-CONFIRMED INVASIVE PNEUMOCOCCAL DISEASE DURING SARS-COV-2 PANDEMIC, 2020-2021, SOUTH AFRICA (ID 893)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:47 - 17:55

Abstract

Background

The first laboratory-confirmed SARS-CoV-2 case in South Africa was reported 5 March 2020. Followed by the implementation of varying SARS-CoV-2 containment measures, resulting in a lack of the typical seasonal influenza in 2020 and 2021, on a background of four SARS-COV-2 infection waves. We determined the change in invasive pneumococcal disease (IPD) cases during this time.

Methods

National, laboratory-based IPD data from an established surveillance system was used to perform interrupted time series analysis to compare IPD diagnoses pre-(2012-2019) and during the SARS-CoV-2 pandemic (2020-2021) overall, by PCV13 serotype and age group.

Results

During 2012-2021 we enrolled 23,759 IPD cases, ranging from 3,223 in 2012 to 1,241 in 2020. Compared to 2012-2019 trends, IPD diagnoses in South Africa reduced by 42% (95%CI 40%-44%) in 2020 and 23% (95%CI 22%-25%) in 2021. Except for children aged 2-4 years in 2021, all age groups saw a reduction of IPD diagnoses. The highest reductions were seen in adults aged ≥65 years (53% [95%CI 46%-58%] in 2020 and 50% [95%CI 45%-54%] in 2021). There were similar reductions in PCV13 and non-PCV13 serotype IPD (41%, [95%CI 38%-44%] vs 46%, [95%CI 43%-48%]).

plot_saipd_2022-04-12.jpg

Figure. Observed IPD cases (grey), trend (black) and predicted (red)

Conclusions

We observed a marked reduction in IPD diagnoses during the SARS-CoV-2 pandemic, with larger reductions in the first year of the pandemic where restrictions were more stringent compared to the second. Reductions may be attributed to the introduction of non-pharmaceutical interventions that reduced transmission of pneumococcus, reduced healthcare-seeking behaviour, or reduced sample collection for diagnosis.

Hide

O069 - REAL-TIME COMPUTERIZED ANALYSIS OF AUSCULTATION FOR POINT-OF-CARE PEDIATRIC PNEUMONIA DIAGNOSIS IN FRONTLINE CLINICAL ENVIRONMENTS (ID 897)

Session Type
Parallel Session
Date
Wed, 22.06.2022
Session Time
15:05 - 16:50
Room
Grand Ballroom Centre
Lecture Time
17:55 - 18:03

Abstract

Background

Frontline workers use World Health Organization guidelines for child pneumonia care in resource-limited settings, which prioritize sensitivity over specificity and result in antibiotic overtreatment. Chest radiography (CXR) and other imaging tools are not available in many clinical contexts, and without standardized training, have high variability. Chest auscultation offers a non-invasive and low-cost tool for improving pneumonia diagnosis but is undermined by the need for trained listeners, inter-listener variability, subjectivity, and vulnerability to noise.

Methods

Feelix, a digital auscultation tool with onboard algorithms, is presented to improve the accuracy and speed of pneumonia diagnosis. Lung sounds are captured at various positions on a patient, using real-time noise suppression schemes to eliminate ambient sounds and sensor motion artifacts. High-quality signals are then mapped onto a rich spectrotemporal feature space before undergoing classification of the presence/lack of pneumonia using a novel lightweight deep learning model. The model is trained and benchmarked against a dataset sourced from a pneumococcal vaccine effectiveness study of children aged 3-35 months in Sylhet, Bangladesh, with 97 patients diagnosed with primary endpoint pneumonia (PEP) and 355 without PEP (normal or other infiltrates), based on a CXR adjudication panel.

Results

The classification of auscultation signals is shown to achieve an accuracy of 90.9% in differentiating PEP from non-PEP cases, with a sensitivity of 100% and specificity of 88.46%.

Conclusions

This process is designed to run in real-time, can be widely deployed in any clinical setting, can provide a classification in seconds, and would dramatically improve the diagnostic accuracy and speed of frontline health care workers.

Hide