Enhancing pneumonia prognosis in the emergency department: a novel machine learning approach using complete blood count and differential leukocyte count combined with CURB-65 score.

BACKGROUND: Pneumonia poses a major global health challenge, necessitating accurate severity assessment tools. However, conventional scoring systems such as CURB-65 have inherent limitations. Machine learning (ML) offers a promising approach for prediction. We previously introduced the Blood Culture Prediction Index (BCPI) model, leveraging solely on complete blood count (CBC) and differential leukocyte count (DC), demonstrating its effectiveness in predicting bacteremia. Nevertheless, its potential in assessing pneumonia remains unexplored. Therefore, this study aims to compare the effectiveness of BCPI and CURB-65 in assessing pneumonia severity in an emergency department (ED) setting and develop an integrated ML model to enhance efficiency. METHODS: This retrospective study was conducted at a 3400-bed tertiary medical center in Taiwan. Data from 9,352 patients with pneumonia in the ED between 2019 and 2021 were analyzed in this study. We utilized the BCPI model, which was trained on CBC/DC data, and computed CURB-65 scores for each patient to compare their prognosis prediction capabilities. Subsequently, we developed a novel Cox regression model to predict in-hospital mortality, integrating the BCPI model and CURB-65 scores, aiming to assess whether this integration enhances predictive performance. RESULTS: The predictive performance of the BCPI model and CURB-65 score for the 30-day mortality rate in ED patients and the in-hospital mortality rate among admitted patients was comparable across all risk categories. However, the Cox regression model demonstrated an improved area under the ROC curve (AUC) of 0.713 than that of CURB-65 (0.668) for in-hospital mortality (p<0.001). In the lowest risk group (CURB-65=0), the Cox regression model outperformed CURB-65, with a significantly lower mortality rate (2.9% vs. 7.7%, p<0.001). CONCLUSIONS: The BCPI model, constructed using CBC/DC data and ML techniques, performs comparably to the widely utilized CURB-65 in predicting outcomes for patients with pneumonia in the ED. Furthermore, by integrating the CURB-65 score and BCPI model into a Cox regression model, we demonstrated improved prediction capabilities, particularly for low-risk patients. Given its simple parameters and easy training process, the Cox regression model may be a more effective prediction tool for classifying patients with pneumonia in the emergency room.

A simplified pneumonia severity index (PSI) for clinical outcome prediction in COVID-19.

BACKGROUND: The Pneumonia Score Index (PSI) was developed to estimate the risk of dying within 30 days of presentation for community-acquired pneumonia patients and is a strong predictor of 30-day mortality after COVID-19. However, three of its required 20 variables (skilled nursing home, altered mental status and pleural effusion) are not discreetly available in the electronic medical record (EMR), resulting in manual chart review for these 3 factors. The goal of this study is to compare a simplified 17-factor version (PSI-17) to the original (denoted PSI-20) in terms of prediction of 30-day mortality in COVID-19. METHODS: In this retrospective cohort study, the hospitalized patients with confirmed SARS-CoV-2 infection between 2/28/20-5/28/20 were identified to compare the predictive performance between PSI-17 and PSI-20. Correlation was assessed between PSI-17 and PSI-20, and logistic regressions were performed for 30-day mortality. The predictive abilities were compared by discrimination, calibration, and overall performance. RESULTS: Based on 1,138 COVID-19 patients, the correlation between PSI-17 and PSI-20 was 0.95. Univariate logistic regression showed that PSI-17 had performance similar to PSI-20, based on AUC, ICI and Brier Score. After adjusting for confounding variables by multivariable logistic regression, PSI-17 and PSI-20 had AUCs (95% CI) of 0.85 (0.83-0.88) and 0.86 (0.84-0.89), respectively, indicating no significant difference in AUC at significance level of 0.05. CONCLUSION: PSI-17 and PSI-20 are equally effective predictors of 30-day mortality in terms of several performance metrics. PSI-17 can be obtained without the manual chart review, which allows for automated risk calculations within an EMR. PSI-17 can be easily obtained and may be a comparable alternative to PSI-20.

Community-acquired pneumonia: a US perspective on the guideline gap.

Community-acquired pneumonia continues to be one of the most common causes of morbidity and mortality due to infectious disease. The aetiologies, clinical presentations, diagnostic modalities and therapeutic options are changing and outpacing the creation of management guidelines. This educational article summarizes a roundtable activity sponsored by an unrestricted educational grant by Paratek that included US experts discussing these changes and identifying gaps in the current guidelines.

Anasarca as the first presentation of anti-synthetase syndrome.

A woman in her 70s presented with anasarca and exertional dyspnoea. Investigation showed severe hypoalbuminaemia with no urinary or gastrointestinal protein losses. CT thorax reported lung consolidations, and transbronchial lung biopsy demonstrated organising pneumonia. Autoimmune myositis serology was positive for anti-Jo-1, anti-Ro-52, and anti-PM/Scl-100 antibodies. She was diagnosed with anti-synthetase syndrome with organising pneumonia. She was treated with oral prednisolone and oral mycophenolate mofetil with a good clinical response.

Expression and significance of procalcitonin, leukotriene B4, serum amyloid A, and C-reactive protein in children with different types of pneumonia: An observational study.

This study aimed to investigate the expression and significance of serum procalcitonin (PCT), leukotriene B4 (LTB4), Serum amyloid A (SAA), and C-reactive protein (CRP) in children with different types of pneumonia caused by different pathogenic infections. One hundred and one children with pneumonia admitted to The Fifth People Hospital of Zhuhai from July 2019 to June 2020 were enrolled and divided into 38 cases in the bacterial group, 30 cases in the mycoplasma group, and 33 cases in the virus group according to the different types of pathogens. The patients were divided into 42 cases in the noncritical group, 33 cases in the critical group, and 26 cases in the very critical group according to the pediatric clinical illness score (PCIS), and 30 healthy children were selected as the control group during the same period. Comparison of serum PCT, SAA: bacterial group > mycoplasma group > viral group > control group with significant differences (P < .05). Receiver operator characteristic (ROC) analysis showed that the area under the curves (AUCs) of serum PCT, LTB4, SAA, and CRP for the diagnosis of bacterial pneumonia were 1.000, 0.531, 0.969, and 0.833, respectively, and the AUCs for the diagnosis of mycoplasma pneumonia were 0.653, 0.609, 0.547, and 0.652, respectively, and the AUCs for the diagnosis of viral pneumonia were 0.888, 0.570, 0.955, and 1.000, respectively. Comparison of serum PCT, LTB4, SAA: very critical group > critical group > noncritical group > control group, with significant differences (P < .05). Serum PCT, LTB4, and SAA were negatively correlated with PCIS score by Pearson analysis (P < .05). Serum PCT and SAA showed diagnostic value for bacterial pneumonia, and serum SAA and CRP showed diagnostic value for viral pneumonia; serum PCT, LTB4, and SAA correlate with severity of disease and show higher expression with worsening of the condition.

Weil's disease with multiple organ dysfunction, community-acquired pneumonia and septic shock: The role of rapid diagnosis and management.

Leptospirosis is an uncommon infectious illness - a spirochetal zoonosis - caused by Leptospira species and the primary cause of human leptospirosis is exposure to the urine of infected rodents. Clinical manifestations of human leptospirosis are diverse, ranging from asymptomatic infection to severe life-threatening with multiorgan dysfunction. The severe condition is known as Weil's disease, which is characterized by feverish illness with jaundice, acute kidney damage, and bleeding. The aim of this case report was to present a Weil's disease which occurred simultaneously with a community-acquired pneumonia (CAP) resulting in serious complications. A 41-year-old man with Weil's disease, as well as CAP caused by Streptococcus pneumoniae, and septic shock was presented. The patient was treated accordingly after establishing the diagnosis through history taking, physical examination, and laboratory tests. In this instance, the score for diagnosing leptospirosis based on Modified Faine's Criteria was calculated resulting possible diagnoses; and therefore, therapeutic management was initiated. Despite presenting with severe symptoms, the patient recovered completely after receiving antibiotics and supportive care. This study highlights that when a patient has Weil's disease and a CAP infection, which could cause unfavorable consequence, a prompt diagnosis and proper treatment could result satisfied patient recovery.

Impacts of environmental factors on the aetiological diagnosis and disease severity of community-acquired pneumonia in China: a multicentre, hospital-based, observational study.

Environmental exposures are known to be associated with pathogen transmission and immune impairment, but the association of exposures with aetiology and severity of community-acquired pneumonia (CAP) are unclear. A retrospective observational study was conducted at nine hospitals in eight provinces in China from 2014 to 2019. CAP patients were recruited according to inclusion criteria, and respiratory samples were screened for 33 respiratory pathogens using molecular test methods. Sociodemographic, environmental and clinical factors were used to analyze the association with pathogen detection and disease severity by logistic regression models combined with distributed lag nonlinear models. A total of 3323 CAP patients were included, with 709 (21.3%) having severe illness. 2064 (62.1%) patients were positive for at least one pathogen. More severe patients were found in positive group. After adjusting for confounders, particulate matter (PM) 2.5 and 8-h ozone (O3-8h) were significant association at specific lag periods with detection of influenza viruses and Klebsiella pneumoniae respectively. PM10 and carbon monoxide (CO) showed cumulative effect with severe CAP. Pollutants exposures, especially PM, O3-8h, and CO should be considered in pathogen detection and severity of CAP to improve the clinical aetiological and disease severity diagnosis.

Myeloid-derived suppressor cells in pleural effusion as a diagnostic marker for early discrimination of pulmonary tuberculosis from pneumonia.

Introduction: Tuberculous pleural effusion (TPE) stands as one of the primary forms of extrapulmonary tuberculosis (TB) and frequently manifests in regions with a high prevalence of TB, consequently being a notable cause of pleural effusion in such areas. However, the differentiation between TPE and parapneumonic pleural effusion (PPE) presents diagnostic complexities. This study aimed to evaluate the potential of myeloid-derived suppressor cells (MDSCs) in the pleural fluid as a potential diagnostic marker for distinguishing between TPE and PPE. Methods: Adult patients, aged 18 years or older, who presented to the emergency room of a tertiary referral hospital and received a first-time diagnosis of pleural effusion, were prospectively enrolled in the study. Various immune cell populations, including T cells, B cells, natural killer (NK) cells, and MDSCs, were analyzed in both pleural fluid and peripheral blood samples. Results: In pleural fluid, the frequency of lymphocytes, including T, B, and NK cells, was notably higher in TPE compared to PPE. Conversely, the frequency of polymorphonuclear (PMN)-MDSCs was significantly higher in PPE. Notably, compared to traditional markers such as the neutrophil-to-lymphocyte ratio and adenosine deaminase level, the frequency of PMN-MDSCs emerged as a more effective discriminator between PPE and TPE. PMN-MDSCs demonstrated superior positive and negative predictive values and exhibited a higher area under the curve in the receiver operating characteristic curve analysis. PMN-MDSCs in pleural effusion increased the levels of reactive oxygen species and suppressed the production of interferon-gamma from T cells following nonspecific stimulation. These findings suggest that MDSC-mediated immune suppression may contribute to the pathology of both TPE and PPE. Discussion: The frequency of PMN-MDSCs in pleural fluid is a clinically useful indicator for distinguishing between TPE and PPE.

Clinical characteristics of persistent or recurrent pneumonia combined with airway malacia in children.

OBJECTIVE: The aim of this study is to investigate the clinical characteristics and pathogens involved in persistent or recurrent pneumonia combined with airway malacia in children. METHODS: We retrospectively reviewed the information of children hospitalised with persistent or recurrent pneumonia, including clinical presentations, laboratory examination results and pathogens. RESULTS: A total of 554 patients were admitted, 285 (51.44%) of whom were found to have airway malacia. There were 78 (27.37%), 166 (58.25%) and 41 (14.39%) patients with mild, moderate and severe malacia, respectively. Patients with airway malacia were younger than those without malacia (6.0 vs. 12.0 months, p < 0.01) and were more likely to present with wheezing (75.07%), fever (34.39%), dyspnoea (28.77%), cyanosis (13.68%) and wheezing in the lungs (78.95%). The incidence of preterm delivery, oxygen therapy, paediatric intensive care unit (PICU) admission and mechanical ventilation was higher, and the hospital stay (11.0 vs. 10.0 days, p = 0.04) was longer in these patients than in those without malacia. Patients with severe airway malacia were more likely to undergo oxygen therapy, PICU admission, mechanical ventilation and have multiple malacia than were those with mild or moderate malacia. Mycoplasma pneumoniae (30.18%) was the most common pathogen. CONCLUSION: Severe airway malacia likely aggravates conditions combined with pneumonia. The proportion of multisite malacia was greater in severe airway malacia patients.

Time to Clinical Stability in Children With Community-Acquired Pneumonia.

BACKGROUND AND OBJECTIVES: Time to clinical stability (TCS) is a commonly used outcome in adults with community-acquired pneumonia (CAP), yet few studies have evaluated TCS in children. Our objective was to determine the association between TCS and disease severity in children with suspected CAP, as well as factors associated with reaching early stability. METHODS: This is a prospective cohort study of children (aged 3 months to 18 years) hospitalized with suspected CAP. TCS parameters included temperature, heart rate, respiratory rate, and hypoxemia with the use of supplemental oxygen. TCS was defined as time from admission to parameter normalization. The association of TCS with severity and clinical factors associated with earlier TCS were evaluated. RESULTS: Of 571 children, 187 (32.7%) had at least 1 abnormal parameter at discharge, and none had ≥3 abnormal discharge parameters. A greater proportion of infants (90 [93%]) had all 4 parameters stable at discharge compared with 12- to 18-year-old youths (21 [49%]). The median TCS for each parameter was <24 hours. Younger age, absence of vomiting, diffusely decreased breath sounds, and normal capillary refill were associated with earlier TCS. Children who did not reach stability were not more likely to revisit after discharge. CONCLUSIONS: A TCS outcome consisting of physiologic variables may be useful for objectively assessing disease recovery and clinical readiness for discharge among children hospitalized with CAP. TCS may decrease length of stay if implemented to guide discharge decisions. Clinicians can consider factors associated with earlier TCS for management decisions.

The clinical value of mNGS of bronchoalveolar lavage fluid versus traditional microbiological tests for pathogen identification and prognosis of severe pneumonia (NT-BALF):study protocol for a prospective multi-center randomized clinical trial.

BACKGROUND: Early, rapid, and accurate pathogen diagnosis can help clinicians select targeted treatment options, thus improving prognosis and reducing mortality rates of severe pneumonia. Metagenomic next-generation sequencing (mNGS) has a higher sensitivity and broader pathogen spectrum than traditional microbiological tests. However, the effects of mNGS-based antimicrobial treatment procedures on clinical outcomes and cost-effectiveness in patients with severe pneumonia have not been evaluated. METHODS: This is a regional, multi-center, open, prospective, randomized controlled trial to evaluate that whether the combination of mNGS and traditional testing methods could decrease 28-day call-cause mortality with moderate cost-effectiveness. A total of 192 patients with severe pneumonia will be recruited from four large tertiary hospitals in China. Bronchoalveolar lavage fluid will be obtained in all patients and randomly assigned to the study group (mNGS combined with traditional microbiological tests) or the control group (traditional microbiological tests only) in a 1:1 ratio. Individualized antimicrobial treatment and strategy will be selected according to the analysis results. The primary outcome is 28-day all-cause mortality. The secondary outcomes are ICU and hospital length of stay (LOS), ventilator-free days and ICU-free days, consistency between mNGS and traditional microbiological tests, detective rate of mNGS and traditional microbiological tests, turn-out time, time from group allocation to start of treatment, duration of vasopressor support, types and duration of anti-infective regimens, source of drug-resistant bacteria or fungi, and ICU cost. DISCUSSION: The clinical benefits of mNGS are potentially significant, but its limitations should also be considered. TRIAL REGISTRATION: ChineseClinicalTrialRegistry.org, ChiCTR2300076853. Registered on 22 October 2023.

Acute primary CMV infection complicated by pneumonitis and ITP in young immunocompetent woman in a regional Queensland Hospital.

We present the first published case of simultaneous pneumonitis and immune thrombocytopenic purpura secondary to primary cytomegalovirus (CMV) infection in an immunocompetent patient. Treatment with oral valganciclovir for 2 weeks successfully led to complete clinical recovery. CMV is traditionally associated with infection in immunocompromised patients and neonates; however, evidence of severe CMV infections in immunocompetent hosts is emerging. It is important to highlight the broad range of clinical presentations of CMV infections to prevent diagnostic delay and associated morbidity and expense.

Alveolar-arterial oxygen gradient: An early marker to predict the severity of community-acquired pneumonia in children.

To study the clinical significance of alveolar-arterial oxygen gradient (PA-aO2) for children with community-acquired pneumonia (CAP). A prospective study was carried out from January 2020 to June 2023, Overall, 100 patients were included in the study, 35 had severe pneumonia, whereas, 65 had non-severe pneumonia. Clinical and laboratory data were retrospectively collected at the time of hospital admission and during hospitalization. Patients were divided into severe and non-severe groups. PA-aO2 was significantly higher among children with severe pneumonia, as determined by WHO, PRESS (P < .001). PA-aO2 was significantly higher among children with mechanical ventilation, shock, sepsis, and mortality. Receiver operating characteristic curve (ROC) analysis for PA-aO2 showed that the area under the curve was 0.76 (P value < .05), with a sensitivity of 84.3% and a specificity of 67.9%. Our study suggests that PA-aO2 level has a predictive value for detecting community-acquired pneumonia severity in children.

Microbial aetiology of community-acquired pneumonia in hospitalised adults: A prospective study utilising comprehensive molecular testing.

OBJECTIVES: This study aimed to describe the microbial aetiology of community-acquired pneumonia (CAP) in adults admitted to a tertiary care hospital and assess the impact of syndromic polymerase chain reaction (PCR) panels on pathogen detection. METHODS: Conducted at Haukeland University Hospital, Norway, from September 2020 to April 2023, this prospective study enrolled adults with suspected CAP. We analysed lower respiratory tract samples using both standard-of-care tests and the BIOFIRE® FILMARRAY® Pneumonia Plus Panel (FAP plus). The added value of FAP Plus in enhancing the detection of clinically relevant pathogens, alongside standard-of-care diagnostics, was assessed. RESULTS: Of the 3238 patients screened, 640 met the inclusion criteria, with 384 confirmed to have CAP at discharge. In these patients, pathogens with proven or probable clinical significance were identified in 312 (81.3%) patients. Haemophilus influenzae was the most prevalent pathogen, found in 118 patients (30.7%), followed by SARS-CoV-2 in 74 (19.3%), and Streptococcus pneumoniae in 64 (16.7%). Respiratory viruses were detected in 186 (48.4%) patients. The use of FAP plus improved the pathogen detection rate from 62.8% with standard-of-care methods to 81.3%. CONCLUSIONS: Pathogens were identified in 81% of CAP patients, with Haemophilus influenzae and respiratory viruses being the most frequently detected pathogens. The addition of the FAP plus panel, markedly improved pathogen detection rates compared to standard-of-care diagnostics alone.

Assessing the utility of natural language processing for detecting postoperative complications from free medical text.

BACKGROUND: Postoperative complication rates are often assessed through administrative data, although this method has proven to be imprecise. Recently, new developments in natural language processing have shown promise in detecting specific phenotypes from free medical text. Using the clinical challenge of extracting four specific and frequently undercoded postoperative complications (pneumonia, urinary tract infection, sepsis, and septic shock), it was hypothesized that natural language processing would capture postoperative complications on a par with human-level curation from electronic health record free medical text. METHODS: Electronic health record data were extracted for surgical cases (across 11 surgical sub-specialties) from 18 hospitals in the Capital and Zealand regions of Denmark that were performed between May 2016 and November 2021. The data set was split into training/validation/test sets (30.0%/48.0%/22.0%). Model performance was compared with administrative data and manual extraction of the test data set. RESULTS: Data were obtained for 17 486 surgical cases. Natural language processing achieved a receiver operating characteristic area under the curve of 0.989 for urinary tract infection, 0.993 for pneumonia, 0.992 for sepsis, and 0.998 for septic shock, whereas administrative data achieved a receiver operating characteristic area under the curve of 0.595 for urinary tract infection, 0.624 for pneumonia, 0.571 for sepsis, and 0.625 for septic shock. CONCLUSION: The natural language processing approach was able to capture complications with acceptable performance, which was superior to administrative data. In addition, the model performance approached that of manual curation and thereby offers a potential pathway for complete real-time coverage of postoperative complications across surgical procedures based on natural language processing assessment of electronic health record free medical text.