Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study.

BACKGROUND: Although electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet been performed. METHODS: Patients with lung cancer, as well as healthy control and diseased control groups, were prospectively recruited from two referral centers between 2019 and 2022. Deep learning models for detecting lung cancer with eNose breathprint were developed using training cohort from one site and then tested on cohort from the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) and Noise-Shift Augmentation (NSA) methods with or without fine-tuning was applied to improve performance. RESULTS: In this study, 231 participants were enrolled, comprising a training/validation cohort of 168 individuals (90 with lung cancer, 16 healthy controls, and 62 diseased controls) and a test cohort of 63 individuals (28 with lung cancer, 10 healthy controls, and 25 diseased controls). The model has satisfactory results in the validation cohort from the same hospital while directly applying the trained model to the test cohort yielded suboptimal results (AUC, 0.61, 95% CI: 0.47─0.76). The performance improved after applying data augmentation methods in the training cohort (SDA, AUC: 0.89 [0.81─0.97]; NSA, AUC:0.90 [0.89─1.00]). Additionally, after applying fine-tuning methods, the performance further improved (SDA plus fine-tuning, AUC:0.95 [0.89─1.00]; NSA plus fine-tuning, AUC:0.95 [0.90─1.00]). CONCLUSION: Our study revealed that deep learning models developed for eNose breathprint can achieve cross-site validation with data augmentation and fine-tuning. Accordingly, eNose breathprints emerge as a convenient, non-invasive, and potentially generalizable solution for lung cancer detection. CLINICAL TRIAL REGISTRATION: This study is not a clinical trial and was therefore not registered.

Sputum bacterial microbiota signature as a surrogate for predicting disease progression of nontuberculous mycobacterial lung disease.

OBJECTIVES: Predicting progression of nontuberculous mycobacterial lung disease (NTM-LD) remains challenging. This study evaluated whether sputum bacterial microbiome diversity can be the biomarker and provide novel insights into related phenotypes and treatment timing. METHODS: We analyzed 126 sputum microbiomes of 126 patients with newly diagnosed NTM-LD due to Mycobacterium avium complex, M. abscessus complex, and M. kansasii between May 2020 and December 2021. Patients were followed for 2 years to determine their disease progression status. We identified consistently representative genera that differentiated the progressor and nonprogressor by using six methodologies. These genera were used to construct a prediction model using random forest with 5-fold cross validation. RESULTS: Disease progression occurred in 49 (38.6%) patients. Compared with nonprogressors, α-diversity was lower in the progressors. Significant compositional differences existed in the ß-diversity between groups (p=0.001). The prediction model for NTM-LD progression constructed using seven genera (Burkholderia, Pseudomonas, Sphingomonas, Candidatus Saccharibacteria, Phocaeicola, Pelomonas, and Phascolarctobacterium) with significantly differential abundance achieved an area under curve of 0.871. CONCLUSIONS: Identification of the composition of sputum bacterial microbiome facilitates prediction of the course of NTM-LD, and maybe used to develop precision treatment involving modulating the respiratory microbiome composition to ameliorate NTM-LD.

Deep Learning-based Diagnosis of Pulmonary Tuberculosis on Chest X-ray in the Emergency Department: A Retrospective Study.

Prompt and correct detection of pulmonary tuberculosis (PTB) is critical in preventing its spread. We aimed to develop a deep learning-based algorithm for detecting PTB on chest X-ray (CXRs) in the emergency department. This retrospective study included 3498 CXRs acquired from the National Taiwan University Hospital (NTUH). The images were chronologically split into a training dataset, NTUH-1519 (images acquired during the years 2015 to 2019; n = 2144), and a testing dataset, NTUH-20 (images acquired during the year 2020; n = 1354). Public databases, including the NIH ChestX-ray14 dataset (model training; 112,120 images), Montgomery County (model testing; 138 images), and Shenzhen (model testing; 662 images), were also used in model development. EfficientNetV2 was the basic architecture of the algorithm. Images from ChestX-ray14 were employed for pseudo-labelling to perform semi-supervised learning. The algorithm demonstrated excellent performance in detecting PTB (area under the receiver operating characteristic curve [AUC] 0.878, 95% confidence interval [CI] 0.854-0.900) in NTUH-20. The algorithm showed significantly better performance in posterior-anterior (PA) CXR (AUC 0.940, 95% CI 0.912-0.965, p-value < 0.001) compared with anterior-posterior (AUC 0.782, 95% CI 0.644-0.897) or portable anterior-posterior (AUC 0.869, 95% CI 0.814-0.918) CXR. The algorithm accurately detected cases of bacteriologically confirmed PTB (AUC 0.854, 95% CI 0.823-0.883). Finally, the algorithm tested favourably in Montgomery County (AUC 0.838, 95% CI 0.765-0.904) and Shenzhen (AUC 0.806, 95% CI 0.771-0.839). A deep learning-based algorithm could detect PTB on CXR with excellent performance, which may help shorten the interval between detection and airborne isolation for patients with PTB.

Quantifying the contribution of smear-negative, culture-positive pulmonary tuberculosis to nosocomial transmission.

BACKGROUND: Despite current guidelines for tuberculosis (TB) control in health care settings, which focused on smear-positive cases, prevention of nosocomial TB transmission continues to be a challenge. Here, we report the results of the first hospital-wide prospective study applying interferon-gamma release assay to investigate the role of smear-negative, culture-positive index cases in nosocomial TB transmission. METHODS: We prospectively identified cases of culture-confirmed smear-negative pulmonary TB receiving aerosol-generating procedures (AGPs) and cases of culture-confirmed smear-positive pulmonary TB admitted at a medical center. Nosocomial transmission was evaluated by screening their close contacts for latent TB infection (LTBI) using an interferon-gamma release assay. RESULTS: A total of 93 smear-negative index receiving AGP and 122 smear-positive index were enrolled. Among them, 13 (14.0%) and 43 (35.2%) index cases, respectively, had secondary cases of LTBI (P < .001). Sputum smear negativity (adjusted odds ratio: 0.20 [0.08-0.48]) and AGP (sputum suction; adjusted odds ratio: 3.48 [1.34-9.05]) are independent factors of transmission. A similar proportion in the close contacts of the 2 index groups had LTBI (17 [15.3%] and 63 [16.0%], respectively), and the former index group contributed to 21.3% of the nosocomial transmission. CONCLUSIONS: Smear-negative, culture-positive index cases receiving AGPs could be as infectious as smear-positive index cases. Hospital TB control policy should also focus on the former group.

Deep Learning-based Diagnosis and Localization of Pneumothorax on Portable Supine Chest X-ray in Intensive and Emergency Medicine: A Retrospective Study.

PURPOSE: To develop two deep learning-based systems for diagnosing and localizing pneumothorax on portable supine chest X-rays (SCXRs). METHODS: For this retrospective study, images meeting the following inclusion criteria were included: (1) patient age ≥ 20 years; (2) portable SCXR; (3) imaging obtained in the emergency department or intensive care unit. Included images were temporally split into training (1571 images, between January 2015 and December 2019) and testing (1071 images, between January 2020 to December 2020) datasets. All images were annotated using pixel-level labels. Object detection and image segmentation were adopted to develop separate systems. For the detection-based system, EfficientNet-B2, DneseNet-121, and Inception-v3 were the architecture for the classification model; Deformable DETR, TOOD, and VFNet were the architecture for the localization model. Both classification and localization models of the segmentation-based system shared the UNet architecture. RESULTS: In diagnosing pneumothorax, performance was excellent for both detection-based (Area under receiver operating characteristics curve [AUC]: 0.940, 95% confidence interval [CI]: 0.907-0.967) and segmentation-based (AUC: 0.979, 95% CI: 0.963-0.991) systems. For images with both predicted and ground-truth pneumothorax, lesion localization was highly accurate (detection-based Dice coefficient: 0.758, 95% CI: 0.707-0.806; segmentation-based Dice coefficient: 0.681, 95% CI: 0.642-0.721). The performance of the two deep learning-based systems declined as pneumothorax size diminished. Nonetheless, both systems were similar or better than human readers in diagnosis or localization performance across all sizes of pneumothorax. CONCLUSIONS: Both deep learning-based systems excelled when tested in a temporally different dataset with differing patient or image characteristics, showing favourable potential for external generalizability.

Deep learning with test-time augmentation for radial endobronchial ultrasound image differentiation: a multicentre verification study.

PURPOSE: Despite the importance of radial endobronchial ultrasound (rEBUS) in transbronchial biopsy, researchers have yet to apply artificial intelligence to the analysis of rEBUS images. MATERIALS AND METHODS: This study developed a convolutional neural network (CNN) to differentiate between malignant and benign tumours in rEBUS images. This study retrospectively collected rEBUS images from medical centres in Taiwan, including 769 from National Taiwan University Hospital Hsin-Chu Branch, Hsinchu Hospital for model training (615 images) and internal validation (154 images) as well as 300 from National Taiwan University Hospital (NTUH-TPE) and 92 images were obtained from National Taiwan University Hospital Hsin-Chu Branch, Biomedical Park Hospital (NTUH-BIO) for external validation. Further assessments of the model were performed using image augmentation in the training phase and test-time augmentation (TTA). RESULTS: Using the internal validation dataset, the results were as follows: area under the curve (AUC) (0.88 (95% CI 0.83 to 0.92)), sensitivity (0.80 (95% CI 0.73 to 0.88)), specificity (0.75 (95% CI 0.66 to 0.83)). Using the NTUH-TPE external validation dataset, the results were as follows: AUC (0.76 (95% CI 0.71 to 0.80)), sensitivity (0.58 (95% CI 0.50 to 0.65)), specificity (0.92 (95% CI 0.88 to 0.97)). Using the NTUH-BIO external validation dataset, the results were as follows: AUC (0.72 (95% CI 0.64 to 0.82)), sensitivity (0.71 (95% CI 0.55 to 0.86)), specificity (0.76 (95% CI 0.64 to 0.87)). After fine-tuning, the AUC values for the external validation cohorts were as follows: NTUH-TPE (0.78) and NTUH-BIO (0.82). Our findings also demonstrated the feasibility of the model in differentiating between lung cancer subtypes, as indicated by the following AUC values: adenocarcinoma (0.70; 95% CI 0.64 to 0.76), squamous cell carcinoma (0.64; 95% CI 0.54 to 0.74) and small cell lung cancer (0.52; 95% CI 0.32 to 0.72). CONCLUSIONS: Our results demonstrate the feasibility of the proposed CNN-based algorithm in differentiating between malignant and benign lesions in rEBUS images.

Oral uracil-tegafur compared with intravenous chemotherapy as adjuvant therapy for resected early-stage non-small cell lung cancer patients.

BACKGROUND: Studies comparing the effectiveness of either adjuvant oral uracil-tegafur (UFT) or intravenous chemotherapy on early-stage (stage I and II) non-small cell lung cancer (NSCLC) patients treated with complete surgical treatment remain limited. METHODS: From January 2011 to December 2017, patients with early-stage NSCLC (defined as tumor size >3 cm without mediastinal lymph node involvement or any distant metastasis) receiving either adjuvant oral UFT or intravenous chemotherapy after surgical resection were identified from the Taiwan Cancer Registry. Overall survival (OS) and relapse-free survival (RFS) were the primary and secondary outcomes, respectively. Propensity matching was used for controlling confounders. RESULTS: A total of 840 patients receiving adjuvant therapy after surgery (including 595 oral UFT and 245 intravenous chemotherapy) were enrolled. Before matching, patients using oral UFT had significantly longer OS (HR: 0.69, 95% CI: 0.49-0.98, p = 0.0387) and RFS (HR: 0.79, 95% CI: 0.61-0.97, p = 0.0392) than those with intravenous chemotherapy. A matched cohort of 352 patients was created using 1:1 propensity score-matching. In the Cox regression analysis, the UFT and the matched chemotherapy groups had similar OS (HR: 0.80, 95% CI: 0.48-1.32, p = 0.3753) and RFS (HR: 0.98, 95% CI: 0.72-1.34, p = 0.9149). Among subgroup analysis, oral UFT use was associated with longer RFS among the subgroups of non-drinker (HR: 0.66, 95% CI: 0.34-0.99, p = 0.0478) and patients with stage IB disease (HR: 0.67, 95% CI: 0.42-0.97, p = 0.0341). CONCLUSIONS: This population-based study in the real-world setting of Taiwan demonstrates comparable effectiveness between oral UFT and intravenous chemotherapy in terms of clinical outcomes for early-stage NSCLC patients after surgery.

A deep learning model using chest X-ray for identifying TB and NTM-LD patients: a cross-sectional study.

BACKGROUND: Timely differentiating between pulmonary tuberculosis (TB) and nontuberculous mycobacterial lung disease (NTM-LD), which are radiographically similar, is important because infectiousness and treatment differ. This study aimed to evaluate whether artificial intelligence could distinguish between TB or NTM-LD patients by chest X-rays (CXRs) from suspects of mycobacterial lung disease. METHODS: A total of 1500 CXRs, including 500 each from patients with pulmonary TB, NTM-LD, and patients with clinical suspicion but negative mycobacterial culture (Imitator) from two hospitals, were retrospectively collected and evaluated in this study. We developed a deep neural network (DNN) and evaluated model performance using the area under the receiver operating characteristic curves (AUC) in both internal and external test sets. Furthermore, we conducted a reader study and tested our model under three scenarios of different mycobacteria prevalence. RESULTS: Among the internal and external test sets, the AUCs of our DNN model were 0.83 ± 0.005 and 0.76 ± 0.006 for pulmonary TB, 0.86 ± 0.006 and 0.64 ± 0.017 for NTM-LD, and 0.77 ± 0.007 and 0.74 ± 0.005 for Imitator. The DNN model showed higher performance on the internal test set in classification accuracy (66.5 ± 2.5%) than senior (50.8 ± 3.0%, p < 0.001) and junior pulmonologists (47.5 ± 2.8%, p < 0.001). Among different prevalence scenarios, the DNN model has stable performance in terms of AUC to detect TB and mycobacterial lung disease. CONCLUSION: DNN model had satisfactory performance and a higher accuracy than pulmonologists on classifying patients with presumptive mycobacterial lung diseases. DNN model could be a complementary first-line screening tool.

Gut microbiota composition can reflect immune responses of latent tuberculosis infection in patients with poorly controlled diabetes.

BACKGROUND: Diabetes mellitus (DM) is a major risk factor for tuberculosis (TB). Evidence has linked the DM-related dysbiosis of gut microbiota to modifiable host immunity to Mycobacterium tuberculosis infection. However, the crosslinks between gut microbiota composition and immunological effects on the development of latent TB infection (LTBI) in DM patients remain uncertain. METHODS: We prospectively obtained stool, blood samples, and medical records from 130 patients with poorly-controlled DM (pDM), defined as ever having an HbA1c > 9.0% within previous 1 year. Among them, 43 had LTBI, as determined by QuantiFERON-TB Gold in-Tube assay. The differences in the taxonomic diversity of gut microbiota between LTBI and non-LTBI groups were investigated using 16S ribosomal RNA sequencing, and a predictive algorithm was established using a random forest model. Serum cytokine levels were measured to determine their correlations with gut microbiota. RESULTS: Compared with non-LTBI group, the microbiota in LTBI group displayed a similar alpha-diversity but different beta-diversity, featuring decrease of Prevotella_9, Streptococcus, and Actinomyces and increase of Bacteroides, Alistipes, and Blautia at the genus level. The accuracy was 0.872 for the LTBI prediction model using the aforementioned 6 microbiome-based biomarkers. Compared with the non-LTBI group, the LTBI group had a significantly lower serum levels of IL-17F (p = 0.025) and TNF-α (p = 0.038), which were correlated with the abundance of the aforementioned 6 taxa. CONCLUSIONS: The study results suggest that gut microbiome composition maybe associated with host immunity relevant to TB status, and gut microbial signature might be helpful for the diagnosis of LTBI.

Toll-like receptor and matrix metalloproteinase single-nucleotide polymorphisms, haplotypes, and polygenic risk score differentiated between tuberculosis disease and infection.

OBJECTIVES: The association of toll-like receptors (TLRs) and matrix metalloproteinases (MMPs) single-nucleotide polymorphisms (SNPs) among latent tuberculosis (TB) infection and active TB remained less studied. METHODS: We recruited participants with TB disease (active TB) (n = 400) and TB infection (latent TB infection) (n = 203) in this study. We genotyped SNPs in TLR1, TLR2, TLR4, MMP1, MMP8, MMP9, MMP12, and tissue inhibitor of MMP2. Single-variant analysis and haplotype analysis were performed, and a polygenic risk score (PRS) was created. RESULTS: We found that SNPs in TLR1 (rs5743580, rs5743551), TLR2 (rs3804100), and MMP8 (rs2508383) were associated with different TB disease status risks. TLR1 rs5743580 was associated with a higher risk of TB disease status in genotypic, recessive, and additive models. TLR2 rs3804100 polymorphisms demonstrated significant association with TB disease status in genotypic, dominant, and additive models. In the haplotype analysis, the TLR1 haplotype was associated with a higher risk of TB disease, and the MMP12 haplotype was associated with a lower risk of TB disease. A PRS using 3 SNPs was associated with a higher risk of TB disease. CONCLUSION: This study revealed that SNP variants in TLR1, TLR2, and MMP8 differed among TB infection and disease. Haplotypes and PRS could potentially help predict TB disease status.

Bisphosphonate Use Is Not Associated With Tuberculosis Risk Among Patients With Osteoporosis: A Nationwide Cohort Study.

Bisphosphonates are considered an effective inhibitor of glutamine synthetase and thus can be used for treating tuberculosis (TB). However, its clinical benefit in TB remains unknown. We conducted a population-based cohort study by using the Taiwan National Health Insurance Research Database and TB databases of the Taiwan Centers for Disease Control. Patients with osteoporosis and a history of bone fracture from 2007 to 2014 were identified. Among them, bisphosphonate users and propensity score-matched nonusers were selected. A stratified multivariable Cox proportional hazard regression model was employed to investigate the independent predictors of TB. Among 218 908 patients with osteoporosis and bone fracture, 46 842 bisphosphonate users and 46 842 propensity score-matched nonusers were selected. Within the 2-year follow-up, 723 patients-348 in the user group and 375 in the nonuser group-developed TB. Bisphosphonate use was not an independent predictor of TB in the multivariable Cox proportional hazard model (adjusted hazard ratio, 0.86; 95%CI, 0.71-1.04); however, male sex, older age, being bedridden, and steroid use were independent risk factors. The real-world data revealed that bisphosphonate use did not protect patients with osteoporosis against TB.

Whole-Blood 3-Gene Signature as a Decision Aid for Rifapentine-based Tuberculosis Preventive Therapy.

BACKGROUND: Systemic drug reaction (SDR) is a major safety concern with weekly rifapentine plus isoniazid for 12 doses (3HP) for latent tuberculosis infection (LTBI). Identifying SDR predictors and at-risk participants before treatment can improve cost-effectiveness of the LTBI program. METHODS: We prospectively recruited 187 cases receiving 3HP (44 SDRs and 143 non-SDRs). A pilot cohort (8 SDRs and 12 non-SDRs) was selected for generating whole-blood transcriptomic data. By incorporating the hierarchical system biology model and therapy-biomarker pathway approach, candidate genes were selected and evaluated using reverse-transcription quantitative polymerase chain reaction (RT-qPCR). Then, interpretable machine learning models presenting as SHapley Additive exPlanations (SHAP) values were applied for SDR risk prediction. Finally, an independent cohort was used to evaluate the performance of these predictive models. RESULTS: Based on the whole-blood transcriptomic profile of the pilot cohort and the RT-qPCR results of 2 SDR and 3 non-SDR samples in the training cohort, 6 genes were selected. According to SHAP values for model construction and validation, a 3-gene model for SDR risk prediction achieved a sensitivity and specificity of 0.972 and 0.947, respectively, under a universal cutoff value for the joint of the training (28 SDRs and 104 non-SDRs) and testing (8 SDRs and 27 non-SDRs) cohorts. It also worked well across different subgroups. CONCLUSIONS: The prediction model for 3HP-related SDRs serves as a guide for establishing a safe and personalized regimen to foster the implementation of an LTBI program. Additionally, it provides a potential translational value for future studies on drug-related hypersensitivity.

Subsequent Antituberculous Treatment May Not Be Mandatory Among Surgically Resected Culture-Negative Pulmonary Granulomas: A Retrospective Nationwide Multicenter Cohort Study.

BACKGROUND: Histologic diagnosis of granuloma is often considered clinically equivalent to a definite diagnosis of pulmonary tuberculosis (TB) in endemic areas. Optimal management of surgically resected granulomatous inflammation in lung with negative mycobacterial culture results, however, remains unclear. METHODS: From 7 medical institutions in northern, middle, and southern Taiwan between January 2010 and December 2018, patients whose surgically resected pulmonary nodule(s) had histological features suggestive of TB but negative microbiological study results and who received no subsequent anti-TB treatment were identified retrospectively. All patients were followed up for 2 years until death or active TB disease was diagnosed. RESULTS: A total of 116 patients were enrolled during the study period. Among them, 61 patients (52.6%) were clinically asymptomatic, and 36 (31.0%) patients were immunocompromised. Solitary pulmonary nodule accounted for 44 (39.6%) of all cases. The lung nodules were removed by wedge resection in 95 (81.9%), lobectomy in 17 (14.7%), and segmentectomy in 4 (3.4%) patients. The most common histological feature was granulomatous inflammation (n=116 [100%]), followed by caseous necrosis (n=39 [33.6%]). During follow-up (218.4 patient-years), none of the patients developed active TB. CONCLUSIONS: In patients with surgically resected culture-negative pulmonary granulomas, the incidence rate of subsequent active TB is low. Watchful monitoring along with regular clinical, radiological, and microbiological follow-up, instead of routine anti-TB treatment, may also be a reasonable option.

Predictors of Successful Weaning from Noninvasive Ventilation in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease: A Single-Center Retrospective Cohort Study.

PURPOSE: Noninvasive ventilation (NIV) is often required for patients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD), and it can significantly reduce the need for endotracheal intubation. Currently, there is no standard method for predicting successful weaning from NIV. Therefore, we aimed to evaluate whether a weaning index can predict NIV outcomes of patients with AECOPD. METHODS: This study was conducted at a single academic public hospital in northern Taiwan from February 2019 to January 2021. Patients with AECOPD admitted to the hospital with respiratory failure who were treated with NIV were included in the study. Univariate and multivariate logistic regression analyses were used to identify independent predictors of successful weaning from NIV. Receiver operating characteristic curve methodology was used to assess the predictive capacity. RESULTS: A total of 85 patients were enrolled, 65.9% of whom were successfully weaned from NIV. The patients had a mean age of 75.8 years and were mostly men (89.4%). The rapid shallow breathing index (RSBI) (P < 0.001), maximum inspiratory pressure (P = 0.014), and maximum expiratory pressure (P = 0.004) of the successful group were significant while preparing to wean. The area under the receiver operating characteristic curve for the RSBI was 0.804, which was considered excellent discrimination. CONCLUSION: The RSBI predicted successful weaning from NIV in patients with AECOPD with hypercapnic respiratory failure. This index may be useful for selecting patients with AECOPD that are suitable for NIV weaning.

Circulatory Inflammatory Mediators in the Prediction of Anti-Tuberculous Drug-Induced Liver Injury Using RUCAM for Causality Assessment.

BACKGROUND: Anti-tuberculous (TB) medications are common causes of drug-induced liver injury (DILI). Limited data are available on systemic inflammatory mediators as biomarkers for predicting DILI before treatment. We aimed to select predictive markers among potential candidates and to formulate a predictive model of DILI for TB patients. METHODS: Adult active TB patients from a prospective cohort were enrolled, and all participants received standard anti-tuberculous treatment. Development of DILI, defined as ≥5× ULN for alanine transaminase or ≥2.6× ULN of total bilirubin with causality assessment (RUCAM, Roussel Uclaf causality assessment method), was regularly monitored. Pre-treatment plasma was assayed for 15 candidates, and a set of risk prediction scores was established using Cox regression and receiver-operating characteristic analyses. RESULTS: A total of 19 (7.9%) in 240 patients developed DILI (including six carriers of hepatitis B virus) following anti-TB treatment. Interleukin (IL)-22 binding protein (BP), interferon gamma-induced protein 1 (IP-10), soluble CD163 (sCD163), IL-6, and CD206 were significant univariable factors associated with DILI development, and the former three were backward selected as multivariable factors, with adjusted hazards of 0.20 (0.07-0.58), 3.71 (1.35-10.21), and 3.28 (1.07-10.06), respectively. A score set composed of IL-22BP, IP-10, and sCD163 had an improved area under the curve of 0.744 (p < 0.001). CONCLUSIONS: Pre-treatment IL-22BP was a protective biomarker against DILI development under anti-TB treatment, and a score set by additional risk factors of IP-10 and sCD163 employed an adequate DILI prediction.

Establishing Aspergillus-Specific IgG Cut-Off Level for Chronic Pulmonary Aspergillosis Diagnosis: Multicenter Prospective Cohort Study.

OBJECTIVES: Aspergillus-specific IgG (Asp-IgG) cut-off level in diagnosing chronic pulmonary aspergillosis (CPA) remains unknown. METHODS: We prospectively recruited participants with clinical suspicion of CPA in three centers in Taiwan during 2019 June to 2020 August. Serum Aspergillus fumigatus-specific IgG (Asp-IgG) (Phadia, Uppsala, UPPS, Sweden) was examined. Optimal cut-off level was determined by Youden's index and validated. RESULTS: A total of 373 participants were recruited. In the derivation cohort (n = 262), Asp-IgG had an area under the receiver-operating-characteristic curve (AUC) of 0.832. The optimal cut-off level was 40.5 mgA/L. While applying this cut-off level to the validation cohort (n = 111), the sensitivity and specificity were 86.7% and 80.2%. Lowering the cut-off level from 40.5 to 27 mgA/L, the sensitivity was steady (30/36, 83.3% to 31/36, 86.1%) while specificity dropped from 81.9% (276/337) to 63.5% (214/337). Restricting CPA diagnosis to only chronic cavitary pulmonary aspergillosis (CCPA) and chronic fibrosing pulmonary aspergillosis (CFPA) yielded a cut-off level of 42.3 mgA/L in the derivation cohort with a sensitivity of 100% and specificity of 84.4% in the validation cohort. CONCLUSIONS: Serum Asp-IgG performs well for CPA diagnosis and provides a low false-positive rate when using a higher cut-off level (preferably around 40 mgA/L).

Functional Status After Pulmonary Rehabilitation as a Predictor of Weaning Success and Survival in Patients Requiring Prolonged Mechanical Ventilation.

Background: Comprehensive rehabilitation programs are recommended for patients with prolonged mechanical ventilation (PMV) to facilitate functional recovery and ventilator weaning, but whether the functional status after rehabilitation influences outcome has not been clearly evaluated. This study aimed to investigate the association between post-rehabilitation functional status and weaning and survival outcome in PMV patients. Methods: We retrospectively enrolled PMV patients admitted to the respiratory care center (RCC), a post-ICU weaning facility with protocolized rehabilitation program, from January 2016 through December 2017. Functional status was measured by the de Morton Mobility Index (DEMMI), with a cut-off value set at 20 points. The primary outcomes were the weaning status at RCC discharge and hospital survival. The secondary outcomes were overall survival and survival at 3 months after RCC discharge. We followed patients until 3 months after RCC discharge or death. Logistic and Cox regressions were performed to identify significant parameters associated with weaning success and survival. Results: In total, 320 patients were enrolled. The weaning success rate was 71.6%. The survival rate at RCC discharge, hospital discharge, and 3 months after RCC discharge was 89.1, 77.5, and 66.6%, respectively. Post-rehabilitation DEMMI ≥ 20 (odds ratio [OR], 3.514; 95% confidence interval [CI], 1.436-8.598; P = 0.006) was the most significantly associated with weaning success. The weaning success and higher post-rehabilitation DEMMI were the two most significant independent factors associated with both hospital survival (weaning success, OR, 12.272; 95% CI, 5.281-28.517; P < 0.001; post-rehabilitation DEMMI ≥ 20, OR, 6.298; 95% CI, 1.302-30.477; P = 0.022) and survival at 3 months after RCC discharge (weaning success, OR, 38.788; 95% CI, 11.505-130.762; P < 0.001; post-rehabilitation DEMMI ≥ 20, OR, 4.830; 95% CI, 1.072-21.756; P = 0.040). Post-rehabilitation DEMMI ≥ 20 remained significantly association with overall survival at 3 months after RCC discharge (hazard ratio, 0.237; 95% CI, 0.072-0.785; P = 0.018). Conclusions: Post-rehabilitation functional status of PMV patients was independently associated with weaning success, as well as hospital and 3-month overall survival after RCC discharge. Post-rehabilitation, but not pre-rehabilitation, functional status was a significant parameter associated with weaning success and survival in patients requiring PMV.

Exploring Volatile Organic Compounds in Breath for High-Accuracy Prediction of Lung Cancer.

(1) Background: Lung cancer is silent in its early stages and fatal in its advanced stages. The current examinations for lung cancer are usually based on imaging. Conventional chest X-rays lack accuracy, and chest computed tomography (CT) is associated with radiation exposure and cost, limiting screening effectiveness. Breathomics, a noninvasive strategy, has recently been studied extensively. Volatile organic compounds (VOCs) derived from human breath can reflect metabolic changes caused by diseases and possibly serve as biomarkers of lung cancer. (2) Methods: The selected ion flow tube mass spectrometry (SIFT-MS) technique was used to quantitatively analyze 116 VOCs in breath samples from 148 patients with histologically confirmed lung cancers and 168 healthy volunteers. We used eXtreme Gradient Boosting (XGBoost), a machine learning method, to build a model for predicting lung cancer occurrence based on quantitative VOC measurements. (3) Results: The proposed prediction model achieved better performance than other previous approaches, with an accuracy, sensitivity, specificity, and area under the curve (AUC) of 0.89, 0.82, 0.94, and 0.95, respectively. When we further adjusted the confounding effect of environmental VOCs on the relationship between participants' exhaled VOCs and lung cancer occurrence, our model was improved to reach 0.92 accuracy, 0.96 sensitivity, 0.88 specificity, and 0.98 AUC. (4) Conclusion: A quantitative VOCs databank integrated with the application of an XGBoost classifier provides a persuasive platform for lung cancer prediction.