OBJECTIVE: Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality.
METHODS: We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction.
RESULTS: We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889.
CONCLUSIONS: The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE .

Mycobacterium abscessus pulmonary infections are increasingly problematic, especially for immunocompromised individuals and those with underlying lung conditions. Currently, there is no reliable standardized treatment, underscoring the need for improved preclinical drug testing. We present a simplified immunosuppressed mouse model using only four injections of cyclophosphamide, which allows for sustained M. abscessus lung burden for up to 16 days. This model proved effective for antibiotic efficacy evaluation, as demonstrated with imipenem or amikacin.

Aim: Torquetenovirus (TTV) was a promising biomarker for immunity, while lung regional TTV for evaluating the opportunistic infection among immunocompromised hosts (ICH) was unclear. Materials & methods: In the ICH and non-ICH populations, we compared the susceptibility to opportunistic infections, clinical severity and the prognosis between subgroups, respectively. Results: ICH with detectable bronchoalveolar lavage fluid (BALF)-TTV were more susceptible to lung aspergillosis and Mycobacterium infections. Furthermore, our data demonstrated that the ICH cohort with detectable BALF-TTV represented a higher clinical severity and a worse prognosis, while the above findings were not found in the non-ICH population. Conclusion: Our findings demonstrated that the BALF-TTV could act as an effective predictor for opportunistic infection for ICH that complemented the CD4+ T cell counts.
[Box: see text].

OBJECTIVE: To predict the risk of in-hospital death in patients with chronic heart failure (CHF) complicated by lung infections using interpretable machine learning.
METHODS: The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database. According to the pathogen type, the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups, and their risks of in-hospital death were compared using Kaplan-Meier survival curves. Univariate analysis and LASSO regression were used to select the features for constructing LR, AdaBoost, XGBoost, and LightGBM models, and their performance was compared in terms of accuracy, precision, F1 value, and AUC. External validation of the models was performed using the data from eICU-CRD database. SHAP algorithm was applied for interpretive analysis of XGBoost model.
RESULTS: Among the 4 constructed models, the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set. In the external test set, the XGBoost model had an AUC of 0.691 (95% CI: 0.654-0.720) in bacterial pneumonia group and an AUC of 0.725 (95% CI: 0.577-0.782) in non-bacterial pneumonia group, and showed better predictive ability and stability than the other models.
CONCLUSIONS: The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections. The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Airway microbiota are known to contribute to lung diseases, such as cystic fibrosis (CF), but their contributions to pathogenesis are still unclear. To improve our understanding of host-microbe interactions, we have developed an integrated analytical and bioinformatic mass spectrometry (MS)-based metaproteomics workflow to analyze clinical bronchoalveolar lavage (BAL) samples from people with airway disease. Proteins from BAL cellular pellets were processed and pooled together in groups categorized by disease status (CF vs. non-CF) and bacterial diversity, based on previously performed small subunit rRNA sequencing data. Proteins from each pooled sample group were digested and subjected to liquid chromatography tandem mass spectrometry (MS/MS). MS/MS spectra were matched to human and bacterial peptide sequences leveraging a bioinformatic workflow using a metagenomics-guided protein sequence database and rigorous evaluation. Label-free quantification revealed differentially abundant human peptides from proteins with known roles in CF, like neutrophil elastase and collagenase, and proteins with lesser-known roles in CF, including apolipoproteins. Differentially abundant bacterial peptides were identified from known CF pathogens (e.g., Pseudomonas), as well as other taxa with potentially novel roles in CF. We used this host-microbe peptide panel for targeted parallel-reaction monitoring validation, demonstrating for the first time an MS-based assay effective for quantifying host-microbe protein dynamics within BAL cells from individual CF patients. Our integrated bioinformatic and analytical workflow combining discovery, verification, and validation should prove useful for diverse studies to characterize microbial contributors in airway diseases. Furthermore, we describe a promising preliminary panel of differentially abundant microbe and host peptide sequences for further study as potential markers of host-microbe relationships in CF disease pathogenesis.IMPORTANCEIdentifying microbial pathogenic contributors and dysregulated human responses in airway disease, such as CF, is critical to understanding disease progression and developing more effective treatments. To this end, characterizing the proteins expressed from bacterial microbes and human host cells during disease progression can provide valuable new insights. We describe here a new method to confidently detect and monitor abundance changes of both microbe and host proteins from challenging BAL samples commonly collected from CF patients. Our method uses both state-of-the art mass spectrometry-based instrumentation to detect proteins present in these samples and customized bioinformatic software tools to analyze the data and characterize detected proteins and their association with CF. We demonstrate the use of this method to characterize microbe and host proteins from individual BAL samples, paving the way for a new approach to understand molecular contributors to CF and other diseases of the airway.

OBJECTIVE: Slow-growing nontuberculous mycobacteria (NTMs) are highly prevalent and routinely cause opportunistic intracellular infectious disease in immunocompromised hosts.
METHODS: The activity of the triple combination of antibiotics, clarithromycin (CLR), rifabutin (RFB), and clofazimine (CFZ), was evaluated and compared with the activity of single antibiotics as well as with double combinations in an in vitro biofilm assay and an in vivo murine model of Mycobacterium avium subsp. hominissuis (M. avium) lung infection.
RESULTS: Treatment of 1-week-old biofilms with the triple combination exerted the strongest effect of all (0.12 ± 0.5 × 107 CFU/mL) in reducing bacterial growth as compared to the untreated (5.20 ± 0.5 × 107/mL) or any other combination (≥0.75 ± 0.6 × 107/mL) by 7 days. The treatment of mice intranasally infected with M. avium with either CLR and CFZ or the triple combination provided the greatest reduction in CLR-sensitive M. avium bacterial counts in both the lung and spleen compared to any single antibiotic or remaining double combination by 4 weeks posttreatment. After 4 weeks of treatment with the triple combination, there were no resistant colonies detected in mice infected with a CLR-resistant strain. No clear relationships between treatment and spleen or lung organ weights were apparent after triple combination treatment.
CONCLUSIONS: The biofilm assay data and mouse disease model efficacy results support the further investigation of the triple-antibiotic combination.

With the increasing resistance of Acinetobacter baumannii (A. baumannii) to antibiotics, researchers have turned their attention to the development of new antimicrobial agents. Among them, coumarin-based heterocycles have attracted much attention due to their unique biological activities, especially in the field of antibacterial infection. In this study, a series of coumarin derivatives were synthesized and screened for their bactericidal activities (Ren et al. 2018; Salehian et al. 2021). The inhibitory activities of these compounds on bacterial strains were evaluated, and the related mechanism of the new compounds was explored. Firstly, the MIC values and bacterial growth curves were measured after compound treatment to evaluate the antibacterial activity in vitro. Then, the in vivo antibacterial activities of the new compounds were assessed on A. baumannii-infected mice by determining the mice survival rates, counting bacterial CFU numbers, measuring inflammatory cytokine levels, and histopathology analysis. In addition, the ROS levels in the bacterial cells were measured with DCFH-DA detection kit. Furthermore, the potential target and detailed mechanism of the new compounds during infection disease therapy were predicted and evidenced with molecular docking. After that, ADMET characteristic prediction was completed, and novel, synthesizable, drug-effective molecules were optimized with reinforcement learning study based on the probed compound as a training template. The interaction between the selected structures and target proteins was further evidenced with molecular docking. This series of innovative studies provides important theoretical and experimental data for the development of new anti-A. baumannii infection drugs.

Diagnosing lung infections is often challenging because of the lack of a high-quality specimen from the diseased lung. Since persons with cystic fibrosis are subject to chronic lung infection, there is frequently a need for a lung specimen. In this small, proof of principle study, we determined that PneumoniaCheckTM, a non-invasive device that captures coughed droplets from the lung on a filter, might help meet this need. We obtained 10 PneumoniaCheckTM coughed specimens and 2 sputum specimens from adult CF patients hospitalized with an exacerbation of their illness. We detected amylase (upper respiratory tract) with an enzymatic assay, surfactant A (lower respiratory tract) with an immunoassay, pathogenic bacteria by PCR, and markers of inflammation by a Luminex multiplex immunoassay. The amylase and surfactant A levels suggested that 9/10 coughed specimens were from lower respiratory tract with minimal upper respiratory contamination. The PCR assays detected pathogenic bacteria in 7 of 9 specimens and multiplex Luminex assay detected a variety of cytokines or chemokines. These data indicate that the PneumoniaCheckTM coughed specimens can capture good quality lower respiratory tract specimens that have the potential to help in diagnosis, management and understanding of CF exacerbations and other lung disease.

Objective: To analyze the comprehensive blood inflammation index of the patients with stage I pneumoconiosis complicated with pulmonary infection, and to explore its value in predicting the patients\' disease. Methods: In September 2023, 83 patients with stage I pneumoconiosis who were treated in Tianjin Occupational Diseases Precaution and Therapeutic Hospital from November 2021 to August 2023 were selected and divided into non-infected group (56 cases) and infected group (27 cases) according to whether they were combined with lung infection. Workers with a history of dust exposure but diagnosed without pneumoconiosis during the same period were selected as the control group (65 cases) . By referring to medical records and collecting clinical data such as gender, age, occupational history, past medical history, hematology testing, the differences in the comprehensive blood inflammation indexes among the three groups were compared, ROC curve was drawn, and the relationship between comprehensive blood inflammation indexes and stage I pneumoconiosis and its combined lung infection was analyzed. Results: There were significtant differences in the number of neutrophils (N) , the number of lymphocytes (L) , the number of monocytes (M) , C-reactive protein (CRP) , the neutrophil to lymphocyte ratio (NLR) , the monocyte to lymphocyte ratio (MLR) , the platelet to lymphocyte ratio (PLR) , the systemic immune-inflammatory index (SII) , the systemic inflammation response index (SIRI) , the aggregate index of systemic inflammation (AISI) , the derived neutrophil to lymphocyte ratio (dNLR) , the neutrophil to lymphocyte and platelet ratio (NLPR) , and the C-reactive protein to lymphocyte ratio (CLR) (P<0.05) . Compared with the control group, MLR, SIRI and AISI in the non-infected group were significantly increased (P<0.05) . NLR, MLR, PLR, SII, SIRI, AISI, dNLR, NLPR, CLR were significantly increased (P<0.05) . Compared with the non-infected group, NLR, PLR, SII, SIRI, AISI, dNLR, NLPR and CLR were significantly increased in the infected group (P<0.05) . ROC analysis showed that NLR, MLR, PLR, SII, SIRI and AISI had a certain predictive capability for stage I pneumoconiosis (P<0.05) , among which MLR had the highest efficacy, with an AUC of 0.791 (95% CI: 0.710-0.873) , the cut-off value was 0.18, the sensitivity was 71.4%, and the specificity was 78.5%. NLR, MLR, PLR, SII, SIRI, AISI, dNLR, NLPR and CLR all had a certain predictive capability forstage I pneumoconiosis combined lung infection (P<0.05) , among which CLR had the highest efficacy, with an AUC of 0.904 (95%CI: 0.824~0.985) , the cut-off value was 5.33, sensitivity was 77.8%, specificity was 98.2%. Conclusion: The comprehensive blood inflammation index may be an auxiliary predictor of stage I pneumoconiosis and its combined lung infections.
目的： 分析壹期尘肺病合并肺部感染患者的综合血液炎症指数，探讨其对患者病情的预测价值。 方法： 于2023年9月，选取2021年11月至2023年8月在天津市职业病防治院就诊的83例壹期尘肺病患者，根据是否合并肺部感染分为非感染组（56例）和感染组（27例），选取同期有接尘史但未诊断为尘肺病的65例工人为对照组。通过查阅病案，收集性别、年龄、职业史、既往病史、血液学化验检测等临床资料，比较各组人员综合血液炎症指数的差异，绘制ROC曲线，分析综合血液炎症指数与壹期尘肺病及其合并肺部感染的关系。 结果： 各组患者的中性粒细胞数目（N）、淋巴细胞数目（L）、单核细胞数目（M）、C反应蛋白（CRP）、中性粒细胞/淋巴细胞比值（NLR）、单核细胞/淋巴细胞比值（MLR）、血小板/淋巴细胞比值（PLR）、全身免疫炎症反应指数（SII）、全身炎症反应指数（SIRI）、系统炎症综合指数（AISI）、衍生中性粒细胞与淋巴细胞比值（dNLR）、中性粒细胞与淋巴细胞和血小板比值（NLPR）、C反应蛋白与淋巴细胞比值（CLR）差异均有统计学意义（P<0.05），与对照组比较，非感染组患者MLR、SIRI、AISI均明显升高（P<0.05），感染组NLR、MLR、PLR、SII、SIRI、AISI、dNLR、NLPR、CLR均明显升高（P<0.05）；与非感染组比较，感染组患者NLR、PLR、SII、SIRI、AISI、dNLR、NLPR、CLR明显升高（P<0.05）。ROC分析显示，NLR、MLR、PLR、SII、SIRI、AISI对壹期尘肺有一定预测能力（P<0.05），其中MLR的效能最高，其AUC为0.791（95%CI：0.710~0.873），截断值为0.18，灵敏度为71.4%，特异度为78.5%；NLR、MLR、PLR、SII、SIRI、AISI、dNLR、NLPR、CLR对壹期尘肺病合并肺部感染均有一定预测能力（P<0.05），其中CLR的效能最高，其AUC为0.904（95%CI：0.824~0.985），截断值为5.33，灵敏度为77.8%，特异度为98.2%。 结论： 壹期尘肺病患者的综合血液炎症指数可能是其合并肺部感染的辅助预测指标。.

Mycobacterium abscessus, a rapidly growing nontuberculous mycobacterium, is increasingly recognized as an important pathogen of the human lung, disproportionally affecting people with cystic fibrosis (CF) and other susceptible individuals with non-CF bronchiectasis and compromised immune functions. M. abscessus infections are extremely difficult to treat due to intrinsic resistance to many antibiotics, including most anti-tuberculous drugs. Current standard-of-care chemotherapy is long, includes multiple oral and parenteral repurposed drugs, and is associated with significant toxicity. The development of more effective oral antibiotics to treat M. abscessus infections has thus emerged as a high priority. While murine models have proven instrumental in predicting the efficacy of therapeutic treatments for M. tuberculosis infections, the preclinical evaluation of drugs against M. abscessus infections has proven more challenging due to the difficulty of establishing a progressive, sustained, pulmonary infection with this pathogen in mice. To address this issue, a series of three workshops were hosted in 2023 by the Cystic Fibrosis Foundation (CFF) and the National Institute of Allergy and Infectious Diseases (NIAID) to review the current murine models of M. abscessus infections, discuss current challenges and identify priorities toward establishing validated and globally harmonized preclinical models. This paper summarizes the key points from these workshops. The hope is that the recommendations that emerged from this exercise will facilitate the implementation of informative murine models of therapeutic efficacy testing across laboratories, improve reproducibility from lab-to-lab and accelerate preclinical-to-clinical translation.