Assuntos
Pessoal de Saúde , Humanos , Uganda/epidemiologia , Phlebovirus/isolamento & purificação , Masculino , Feminino , AdultoRESUMO
BACKGROUND: Despite many studies evaluating lung ultrasound (LUS) for COVID-19 prognostication, the generalizability and utility across clinical settings is uncertain. METHODS: Adults (≥18 years of age) with COVID-19 were enrolled at two military hospitals, an emergency department, home visits, and a homeless shelter in the United States, and in a referral hospital in Uganda. Participants had a 12-zone LUS scan performed at time of enrollment and clips were read off-site. The primary outcome was progression to higher level of care after the ultrasound scan. We calculated the cross-validated area under the curve for the validation cohort for individual LUS features. RESULTS: We enrolled 191 participants with COVID-19 were enrolled (57.9% female, median age 45.0 years, interquartile range [IQR]: 31.5, 58.0). Nine participants clinically deteriorated. The top predictors of worsening disease in the validation cohort measured by cross-validated area under the curve (cvAUC) were B-lines (0.88, 95% confidence interval [CI]: 0.87, 0.90), discrete B-lines (0.87, 95% CI: 0.85, 0.88), oxygen saturation (0.82, 95%: CI:0.81, 0.84), and A-lines (0.80, 95% CI: 0.78, 0.81). CONCLUSIONS: In an international multisite POCUS cohort, LUS parameters had high discriminative accuracy. Ultrasound can be applied towards triage across a wide breadth of care settings during a pandemic.
RESUMO
Melioidosis is a potentially severe disease caused by the gram-negative soil-dwelling bacterium called Burkholderia pseudomallei. The true breadth of the distribution of this tropical pathogen is starting to emerge with environmental and clinical isolates frequently characterized in new countries and regions. Even so, isolates, clinical cases, and genetic data from the continent of Africa remain scant. We previously confirmed the presence of B. pseudomallei in the environment of Ghana, unmasking a new area of endemicity for this pathogen. Here, we describe the genetic characteristics of isolates obtained from that environmental survey. Twenty-one isolates were subjected to whole genome sequencing and found to represent three discrete sequence types (ST), one of which was novel, and designated ST2058. Phylogenetic analysis places this novel isolate within a B. pseudomallei clade that includes genomes derived from the Americas, although it is closely related to a sub-clade that includes isolates from Africa. Importantly, phenotypic characterization demonstrates common features including API 20NE profiles and B. pseudomallei CPS to support existing diagnostics, and susceptibility to standard of care antibiotics often used in the clinical management of melioidosis. These findings add to our knowledge about the presence and distribution of B. pseudomallei in Africa and represent the first published genomes out of Ghana.
RESUMO
At 3 severe infection cohort sites in Uganda, Orientia seropositivity was common. We identified 4 seroconversion cases and 1 PCR-positive case. These results provide serologic and molecular support for Orientia spp. circulating in sub-Saharan Africa, possibly expanding its endemic range. Orientia infections could cause severe illness and hospitalizations in this region.
Assuntos
Doenças Endêmicas , Humanos , Uganda/epidemiologia , Masculino , Feminino , Adulto , Estudos de Coortes , Pessoa de Meia-Idade , Adolescente , Adulto JovemRESUMO
BACKGROUND: Sepsis from infection is a global health priority and clinical trials have failed to deliver effective therapeutic interventions. To address complicating heterogeneity in sepsis pathobiology, and improve outcomes, promising precision medicine approaches are helping identify disease endotypes, however, they require a more complete definition of sepsis subgroups. METHODS: Here, we use RNA sequencing from peripheral blood to interrogate the host response to sepsis from participants in a global observational study carried out in West Africa, Southeast Asia, and North America (N = 494). RESULTS: We identify four sepsis subtypes differentiated by 28-day mortality. A low mortality immunocompetent group is specified by features that describe the adaptive immune system. In contrast, the three high mortality groups show elevated clinical severity consistent with multiple organ dysfunction. The immunosuppressed group members show signs of a dysfunctional immune response, the acute-inflammation group is set apart by molecular features of the innate immune response, while the immunometabolic group is characterized by metabolic pathways such as heme biosynthesis. CONCLUSIONS: Our analysis reveals details of molecular endotypes in sepsis that support immunotherapeutic interventions and identifies biomarkers that predict outcomes in these groups.
Sepsis is a life-threatening multi-organ failure caused by the body's immune response to infection. Clinical symptoms of sepsis vary from one person to another likely due to differences in host factors, infecting pathogen, and comorbidities. This difference in clinical symptoms may contribute to the lack of effective interventions for sepsis. Therefore, approaches tailored to targeting groups of patients who present similarly are of great interest. This study analysed a large group of sepsis patients with diverse symptoms using laboratory markers and mathematical analysis. We report four patient groups that differ by risk of death and immune response profile. Targeting these defined groups with tailored interventions presents an exciting opportunity to improve the health outcomes of patients with sepsis.
RESUMO
This study presented the detection and quantification of capsular polysaccharide (CPS) as a biomarker for the diagnosis of melioidosis. After successfully screening four monoclonal antibodies (mAbs) previously determined to bind CPS molecules, the team developed a portable electrochemical immunosensor based on antibody-antigen interactions. The biosensor was able to detect CPS with a wide detection range from 0.1pg/mL to 1 µg/mL. The developed biosensor achieved high sensitivity for the detection of CPS spiked into both urine and serum. The developed assay platform was successfully programmed into a Windows app, and the sensor performance was evaluated with different spiked concentrations. The rapid electro-analytical device (READ) sensor showed great unprecedented sensitivity for the detection of CPS molecules in both serum and urine, and results were cross-validated with ELISA methods.
Assuntos
Burkholderia pseudomallei , Técnicas Eletroquímicas , Melioidose , Polissacarídeos Bacterianos , Burkholderia pseudomallei/imunologia , Melioidose/diagnóstico , Melioidose/microbiologia , Melioidose/urina , Humanos , Técnicas Eletroquímicas/métodos , Imunoensaio/métodos , Polissacarídeos Bacterianos/imunologia , Técnicas Biossensoriais/métodos , Anticorpos Monoclonais/imunologia , Cápsulas Bacterianas/imunologia , Anticorpos Antibacterianos/sangue , Ensaio de Imunoadsorção Enzimática/métodos , Biomarcadores/sangue , Biomarcadores/urinaRESUMO
Our limited understanding of the pathophysiological mechanisms that operate during sepsis is an obstacle to rational treatment and clinical trial design. There is a critical lack of data from low- and middle-income countries where the sepsis burden is increased which inhibits generalized strategies for therapeutic intervention. Here we perform RNA sequencing of whole blood to investigate longitudinal host response to sepsis in a Ghanaian cohort. Data dimensional reduction reveals dynamic gene expression patterns that describe cell type-specific molecular phenotypes including a dysregulated myeloid compartment shared between sepsis and COVID-19. The gene expression signatures reported here define a landscape of host response to sepsis that supports interventions via targeting immunophenotypes to improve outcomes.
Assuntos
COVID-19 , Fenótipo , Sepse , Transcriptoma , Humanos , Sepse/genética , Sepse/sangue , Sepse/imunologia , COVID-19/imunologia , COVID-19/genética , COVID-19/sangue , COVID-19/virologia , Gana/epidemiologia , Masculino , Estudos de Coortes , SARS-CoV-2/imunologia , SARS-CoV-2/genética , Feminino , Adulto , Pessoa de Meia-Idade , Perfilação da Expressão Gênica , Análise de Sequência de RNARESUMO
Infection with either Rickettsia prowazekii or Orientia tsutsugamushi is common, yet diagnostic capabilities are limited due to the short window for positive identification. Until now, although targeted enrichment had been applied to increase sensitivity of sequencing-based detection for various microorganisms, it had not been applied to sequencing of R. prowazekii in clinical samples. Additionally, hybridization-based targeted enrichment strategies had only scarcely been applied to qPCR of any pathogens in clinical samples. Therefore, we tested a targeted enrichment technique as a proof of concept and found that it dramatically reduced the limits of detection of these organisms by both qPCR and high throughput sequencing. The enrichment methodology was first tested in contrived clinical samples with known spiked-in concentrations of R. prowazekii and O. tsutsugamushi DNA. This method was also evaluated using clinical samples, resulting in the simultaneous identification and characterization of O. tsutsugamushi directly from clinical specimens taken from sepsis patients. We demonstrated that the targeted enrichment technique is helpful by lowering the limit of detection, not only when applied to sequencing, but also when applied to qPCR, suggesting the technique could be applied more broadly to include other assays and/or microbes for which there are limited diagnostic or detection modalities.
RESUMO
Diagnostic limitations challenge management of clinically indistinguishable acute infectious illness globally. Gene expression classification models show great promise distinguishing causes of fever. We generated transcriptional data for a 294-participant (USA, Sri Lanka) discovery cohort with adjudicated viral or bacterial infections of diverse etiology or non-infectious disease mimics. We then derived and cross-validated gene expression classifiers including: 1) a single model to distinguish bacterial vs. viral (Global Fever-Bacterial/Viral [GF-B/V]) and 2) a two-model system to discriminate bacterial and viral in the context of noninfection (Global Fever-Bacterial/Viral/Non-infectious [GF-B/V/N]). We then translated to a multiplex RT-PCR assay and independent validation involved 101 participants (USA, Sri Lanka, Australia, Cambodia, Tanzania). The GF-B/V model discriminated bacterial from viral infection in the discovery cohort an area under the receiver operator curve (AUROC) of 0.93. Validation in an independent cohort demonstrated the GF-B/V model had an AUROC of 0.84 (95% CI 0.76-0.90) with overall accuracy of 81.6% (95% CI 72.7-88.5). Performance did not vary with age, demographics, or site. Host transcriptional response diagnostics distinguish bacterial and viral illness across global sites with diverse endemic pathogens.
Assuntos
Infecções Bacterianas , Viroses , Humanos , Viroses/diagnóstico , Viroses/genética , Biomarcadores , Infecções Bacterianas/diagnóstico , Infecções Bacterianas/genética , Camboja , AustráliaRESUMO
INTRODUCTION: Point-of-care ultrasound (POCUS) is a rapid, readily available, and cost-effective diagnostic and prognostic modality in a range of clinical settings. However, data to support its clinical application are limited. This project's main goal was to assess the effectiveness of standardizing lung ultrasound (LUS) training for sonographers to determine if universal LUS adoption is justified. MATERIALS AND METHODS: We describe the effectiveness of an implementation of a LUS research training program across eight international study sites in Asia, Africa, and North America as part of prospective Coronavirus Disease of 2019 (COVID-19) and sepsis study cohorts (Rapid Assessment of Infection with SONography research network). Within our network, point-of-care LUS was used to longitudinally evaluate radiographic markers of lung injury. POCUS operators were personnel from a variety of backgrounds ranging from research coordinators with no medical background to experienced clinicians. RESULTS: Following a standardized protocol, 49 study sonographers were trained and LUS images from 486 study participants were collected. After training was completed, we compared before and after image qualities for interpretation. The proportion of acceptable images improved at each site between the first 25 scans and the second 25 scans, resulting in 80% or greater acceptance at each study site. CONCLUSIONS: POCUS training and implementation proved feasible in diverse research settings among a range of providers. Standardization across ongoing cohort protocols affords opportunities for increased statistical power and generalizability of results. These results potentially support care delivery by enabling military medics to provide care at the point of injury, as well as aiding frontline clinicians in both austere and highly resourced critical care settings.
RESUMO
Rapid and accurate measurements of immune protein markers are essential for diagnosis and treatment in all clinical settings. The recent pandemic has revealed a stark need for developing new tools and assays that could be rapidly used in diverse settings and provide useful information to clinicians. Here, we describe the development and test application of a novel one-step CRP/IP-10 duplex assay for the LightDeck platform capable of delivering reproducible and accurate measurements in under eight minutes. We used the optimized assay to measure CRP and IP-10 levels in human blood and serum samples from healthy, SARS-CoV-2 (COVID-19) positive, and influenza-like illness (ILI) presenting patients. Our results agreed with previously published analyte levels and enabled us to make statistically significant comparisons relevant to multiple clinical parameters. Our duplex assay is a simple and powerful tool for aiding prognostic decision-making in diverse settings.
Assuntos
COVID-19 , Sistemas Automatizados de Assistência Junto ao Leito , Humanos , Biomarcadores , Quimiocina CXCL10/sangue , Quimiocina CXCL10/química , COVID-19/diagnóstico , SARS-CoV-2 , Proteína C-Reativa/químicaRESUMO
The inclusion of LUS with simple, point-of-care clinical parameters have potential to improve COVID-19 prognostication above that from standard clinical care delivery. https://bit.ly/3InePYK.
RESUMO
OBJECTIVES: We evaluated the performance of commonly used sepsis screening tools across prospective sepsis cohorts in the USA, Cambodia and Ghana. DESIGN: Prospective cohort studies. SETTING AND PARTICIPANTS: From 2014 to 2021, participants with two or more SIRS (Systemic Inflammatory Response Syndrome) criteria and suspected infection were enrolled in emergency departments and medical wards at hospitals in Cambodia and Ghana and hospitalised participants with suspected infection were enrolled in the USA. Cox proportional hazards regression was performed, and Harrell's C-statistic calculated to determine 28-day mortality prediction performance of the quick Sequential Organ Failure Assessment (qSOFA) score ≥2, SIRS score ≥3, National Early Warning Score (NEWS) ≥5, Modified Early Warning Score (MEWS) ≥5 or Universal Vital Assessment (UVA) score ≥2. Screening tools were compared with baseline risk (age and sex) with the Wald test. RESULTS: The cohorts included 567 participants (42.9% women) including 187 participants from Kumasi, Ghana, 200 participants from Takeo, Cambodia and 180 participants from Durham, North Carolina in the USA. The pooled mortality was 16.4% at 28 days. The mortality prediction accuracy increased from baseline risk with the MEWS (C-statistic: 0.63, 95% CI 0.58 to 0.68; p=0.002), NEWS (C-statistic: 0.68; 95% CI 0.64 to 0.73; p<0.001), qSOFA (C-statistic: 0.70, 95% CI 0.64 to 0.75; p<0.001), UVA score (C-statistic: 0.73, 95% CI 0.69 to 0.78; p<0.001), but not with SIRS (0.60; 95% CI 0.54 to 0.65; p=0.13). Within individual cohorts, only the UVA score in Ghana performed better than baseline risk (C-statistic: 0.77; 95% CI 0.71 to 0.83; p<0.001). CONCLUSIONS: Among the cohorts, MEWS, NEWS, qSOFA and UVA scores performed better than baseline risk, largely driven by accuracy improvements in Ghana, while SIRS scores did not improve prognostication accuracy. Prognostication scores should be validated within the target population prior to clinical use.
Assuntos
Sepse , Adulto , Feminino , Humanos , Masculino , Estudos Prospectivos , Sepse/diagnóstico , Síndrome de Resposta Inflamatória Sistêmica/diagnóstico , Camboja , Estudos de CoortesRESUMO
The associations between clinical phenotypes of coronavirus disease 2019 (COVID-19) and the host inflammatory response during the transition from peak illness to convalescence are not yet well understood. Blood plasma samples were collected from 129 adult SARS-CoV-2 positive inpatient and outpatient participants between April 2020 and January 2021, in a multi-center prospective cohort study at 8 military hospitals across the United States. Plasma inflammatory protein biomarkers were measured in samples from 15 to 28 days post symptom onset. Topological Data Analysis (TDA) was used to identify patterns of inflammation, and associations with peak severity (outpatient, hospitalized, ICU admission or death), Charlson Comorbidity Index (CCI), and body mass index (BMI) were evaluated using logistic regression. The study population (n = 129, 33.3% female, median 41.3 years of age) included 77 outpatient, 31 inpatient, 16 ICU-level, and 5 fatal cases. Three distinct inflammatory biomarker clusters were identified and were associated with significant differences in peak disease severity (p < 0.001), age (p < 0.001), BMI (p < 0.001), and CCI (p = 0.001). Host-biomarker profiles stratified a heterogeneous population of COVID-19 patients during the transition from peak illness to convalescence, and these distinct inflammatory patterns were associated with comorbid disease and severe illness due to COVID-19.
Assuntos
COVID-19 , Humanos , Feminino , Estados Unidos/epidemiologia , Masculino , SARS-CoV-2 , Estudos Prospectivos , Convalescença , Biomarcadores , Fenótipo , Índice de Gravidade de Doença , HospitalizaçãoRESUMO
Background: While point-of-care ultrasound (POCUS) has been used to track worsening COVID-19 disease it is unclear if there are dynamic differences between severity trajectories. Methods: We studied 12-lung zone protocol scans from 244 participants [with repeat scans obtained in 3 days (N = 114), 7 days (N = 53), and weekly (N = 9)] ≥ 18 years of age hospitalized for COVID-19 pneumonia. Differences in mean lung ultrasound (LUS) scores and percent of lung fields with A-lines over time were compared between peak severity levels (as defined by the WHO clinical progression scale) using linear mixed-effects models. Results: Mean LUS scores were elevated by 0.19 (p = 0.035) and A-lines were present in 14.7% fewer lung fields (p = 0.02) among those with ICU-level or fatal peak illness compared to less severe hospitalized illness, regardless of duration of illness. There were no differences between severity groups in the trajectories of mean LUS score 0.19 (p = 0.66) or percent A-lines (p = 0.40). Discussion: Our results do not support the use of serial LUS scans to monitor COVID-19 disease progression among hospitalized adults.
RESUMO
The use of positive blood culture bottles for direct disk diffusion susceptibility testing (dDD), together with chromogenic culture limited to groups of pathogens for antimicrobial susceptibility testing interpretation may provide a means for laboratories-in-development to introduce rapid abbreviated blood culture testing. We assessed the performance of dDD on Chromatic MH agar using contrived positive blood culture bottles and compared findings with current standard practice. Furthermore, we characterized the growth of 24 bacterial and 3 yeast species on Chromatic MH agar with the aid of rapid spot tests for same-day identification. The coefficient of variation for reproducibility of dDD of four reference strains in 4 to 10 replicates (238 data points) ranged from 0% to 16.3%. Together with an additional 10 challenge isolates, the overall categorical agreement was 91.7% (351 data points). The following bacteria were readily identifiable: cream/white Staphylococcus aureus, coagulase-negative staphylococci, Streptococcus pyogenes; turquoise Streptococcus agalactiae, enterococci, Listeria monocytogenes; mauve Escherichia coli, Shigella sonnei, Citrobacter freundii; dark-blue Klebsiella and Enterobacter; green Pseudomonas aeruginosa; and brown Proteus. Clear colonies were seen with Salmonella, Acinetobacter, Burkholderia, and Yersinia enterocolitica (turns pink). Our study suggests that Chromatic MH for dDD may show promise as a rapid, clinically useful presumptive method for overnight simultaneous identification and antimicrobial susceptibility testing. However, there is a need to optimize the medium formulation to allow the recovery of Streptococcus pneumoniae and Haemophilus influenzae.
Assuntos
Anti-Infecciosos , Hemocultura , Humanos , Ágar , Identificação Social , Reprodutibilidade dos Testes , Streptococcus pyogenes , Testes de Sensibilidade Microbiana , Antibacterianos/farmacologiaRESUMO
BACKGROUND: Venous phlebotomy performed by trained personnel is critical for patient diagnosis and monitoring of chronic disease, but has limitations in resource-constrained settings, and represents an infection control challenge during outbreaks. Self-collection devices have the potential to shift phlebotomy closer to the point of care, supporting telemedicine strategies and virtual clinical trials. Here we assess a capillary blood micro-sampling device, the Tasso Serum Separator Tube (SST), for measuring blood protein levels in healthy subjects and non-hospitalized COVID-19 patients. METHODS: 57 healthy controls and 56 participants with mild/moderate COVID-19 were recruited at two U.S. military healthcare facilities. Healthy controls donated Tasso SST capillary serum, venous plasma and venous serum samples at multiple time points, while COVID-19 patients donated a single Tasso SST serum sample at enrolment. Concentrations of 17 protein inflammatory biomarkers were measured in all biospecimens by Ella multi-analyte immune-assay. RESULTS: Tasso SST serum protein measurements in healthy control subjects were highly reproducible, but their agreements with matched venous samples varied. Most of the selected proteins, including CRP, Ferritin, IL-6 and PCT, were well-correlated between Tasso SST and venous serum with little sample type bias, but concentrations of D-dimer, IL-1B and IL-1Ra were not. Self-collection at home with delayed sample processing was associated with significant concentrations differences for several analytes compared to supervised, in-clinic collection with rapid processing. Finally, Tasso SST serum protein concentrations were significantly elevated in in non-hospitalized COVID-19 patients compared with healthy controls. CONCLUSIONS: Self-collection of capillary blood with micro-sampling devices provides an attractive alternative to routine phlebotomy. However, concentrations of certain analytes may differ significantly from those in venous samples, and factors including user proficiency, temperature control and time lags between specimen collection and processing need to be considered for their effect on sample quality and reproducibility.
Assuntos
COVID-19 , Proteínas Sanguíneas , Coleta de Amostras Sanguíneas , COVID-19/diagnóstico , Voluntários Saudáveis , Humanos , Reprodutibilidade dos Testes , Manejo de EspécimesRESUMO
The clinical utility of point-of-care lung ultrasound (LUS) among hospitalized patients with COVID-19 is unclear. DESIGN: Prospective cohort study. SETTING: A large tertiary care center in Maryland, between April 2020 and September 2021. PATIENTS: Hospitalized adults (≥ 18 yr old) with positive severe acute respiratory syndrome coronavirus 2 reverse transcriptase-polymerase chain reaction results. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: All patients were scanned using a standardized protocol including 12 lung zones and followed to determine clinical outcomes until hospital discharge and vital status at 28 days. Ultrasounds were independently reviewed for lung and pleural line artifacts and abnormalities, and the mean LUS Score (mLUSS) (ranging from 0 to 3) across lung zones was determined. The primary outcome was time to ICU-level care, defined as high-flow oxygen, noninvasive, or invasive mechanical ventilation, within 28 days of the initial ultrasound. Cox proportional hazards regression models adjusted for age and sex were fit for mLUSS and each ultrasound covariate. A total of 264 participants were enrolled in the study; the median age was 61 years and 114 participants (43.2%) were female. The median mLUSS was 1.0 (interquartile range, 0.5-1.3). Following enrollment, 27 participants (10.0%) went on to require ICU-level care, and 14 (5.3%) subsequently died by 28 days. Each increase in mLUSS at enrollment was associated with disease progression to ICU-level care (adjusted hazard ratio [aHR], 3.61; 95% CI, 1.27-10.2) and 28-day mortality (aHR, 3.10; 95% CI, 1.29-7.50). Pleural line abnormalities were independently associated with disease progression to death (aHR, 20.93; CI, 3.33-131.30). CONCLUSIONS: Participants with a mLUSS greater than or equal to 1 or pleural line changes on LUS had an increased likelihood of subsequent requirement of high-flow oxygen or greater. LUS is a promising tool for assessing risk of COVID-19 progression at the bedside.
RESUMO
Burkholderia pseudomallei is a Gram-negative soil saprophyte with the potential to cause melioidosis, an opportunistic disease with a high mortality potential. Periodic case reports of melioidosis in or imported from Africa occur in the literature dating back decades. Furthermore, statistical models suggest Western sub-Saharan Africa as a high-risk zone for the presence of B. pseudomallei. A recent case report from the United Kingdom of a returning traveler from Ghana highlights the need for environmental studies in Ghana. We examined 100 soil samples from a rice farm in south-central Ghana. Soil was subjected to selective enrichment culture for B. pseudomallei using threonine-basal salt solution with colistin (TBSS-C50) and erythritol medium, as described in the literature. Bacterial cultures were identified with standard biochemical tests, a rapid antigen detection assay, and real-time PCR specific for B. pseudomallei. Of the 100 soil samples, 55% yielded cultures consistent with B. pseudomallei on Ashdown's agar as well as by capsular polysaccharide antigen production. This is the first confirmatory report of culture-confirmed B. pseudomallei in the environment of Ghana. Our study emphasizes the need for further exploration of the burden of human melioidosis in Ghana. We recommend that local clinicians familiarize themselves with the diagnosis and clinical management of melioidosis, while laboratories develop capacity for the safe isolation and identification of B. pseudomallei. IMPORTANCE We present the first confirmation of the presence of B. pseudomallei in the environment of Ghana. This study will bring attention to a disease with the potential to cause significant morbidity and mortality in Ghana, but which has gone completely unrecognized until this point. Furthermore, this work would encourage local clinicians to familiarize themselves with the diagnosis and clinical management of melioidosis and laboratories to develop capacity for the safe isolation and identification of B. pseudomallei.
Assuntos
Burkholderia pseudomallei , Melioidose , Burkholderia pseudomallei/genética , Gana , Humanos , Melioidose/diagnóstico , Melioidose/microbiologia , Solo , Microbiologia do SoloRESUMO
Sepsis is a life-threatening condition and understanding the disease pathophysiology through the use of host immune response biomarkers is critical for patient stratification. Lack of accurate sepsis endotyping impedes clinicians from making timely decisions alongside insufficiencies in appropriate sepsis management. This work aims to demonstrate the potential feasibility of a data-driven validation model for supporting clinical decisions to predict sepsis host-immune response. Herein, we used a machine learning approach to determine the predictive potential of identifying sepsis host immune response for patient stratification by combining multiple biomarker measurements from a single plasma sample. Results were obtained using the following cytokines and chemokines IL-6, IL-8, IL-10, IP-10 and TRAIL where the test dataset was 70%. Supervised machine learning algorithm naïve Bayes and decision tree algorithm showed good accuracy of 96.64% and 94.64%. These promising findings indicate the proposed AI approach could be a valuable testing resource for promoting clinical decision making.