The histopathological diagnosis of mycobacterial infection may be improved by a comprehensive analysis using artificial intelligence. Two autopsy cases of pulmonary tuberculosis, and forty biopsy cases of undetected acid-fast bacilli (AFB) were used to train AI (convolutional neural network), and construct an AI to support AFB detection. Forty-two patients underwent bronchoscopy, and were evaluated using AI-supported pathology to detect AFB. The AI-supported pathology diagnosis was compared with bacteriology diagnosis from bronchial lavage fluid and the final definitive diagnosis of mycobacteriosis. Among the 16 patients with mycobacteriosis, bacteriology was positive in 9 patients (56%). Two patients (13%) were positive for AFB without AI assistance, whereas AI-supported pathology identified eleven positive patients (69%). When limited to tuberculosis, AI-supported pathology had significantly higher sensitivity compared with bacteriology (86% vs. 29%, p = 0.046). Seven patients diagnosed with mycobacteriosis had no consolidation or cavitary shadows in computed tomography; the sensitivity of bacteriology and AI-supported pathology was 29% and 86%, respectively (p = 0.046). The specificity of AI-supported pathology was 100% in this study. AI-supported pathology may be more sensitive than bacteriological tests for detecting AFB in samples collected via bronchoscopy.

Background and Objective: The diagnosis of interstitial lung diseases (ILDs) often relies on the integration of various clinical, radiological, and histopathological data. Achieving high diagnostic accuracy in ILDs, particularly for distinguishing usual interstitial pneumonia (UIP), is challenging and requires a multidisciplinary approach. Therefore, this study aimed to develop a multimodal artificial intelligence (AI) algorithm that combines computed tomography (CT) and histopathological images to improve the accuracy and consistency of UIP diagnosis.Methods: A dataset of CT and pathological images from 324 patients with ILD between 2009 and 2021 was collected. The CT component of the model was trained to identify 28 different radiological features. The pathological counterpart was developed in our previous study. A total of 114 samples were selected and used for testing the multimodal AI model. The performance of the multimodal AI was assessed through comparisons with expert pathologists and general pathologists.Results: The developed multimodal AI demonstrated a substantial improvement in distinguishing UIP from non‐UIP, achieving an AUC of 0.92. When applied by general pathologists, the diagnostic agreement rate improved significantly, with a post‐model κ score of 0.737 compared to 0.273 pre‐model integration. Additionally, the diagnostic consensus rate with expert pulmonary pathologists increased from κ scores of 0.278–0.53 to 0.474–0.602 post‐model integration. The model also increased diagnostic confidence among general pathologists.Conclusion: Combining CT and histopathological images, the multimodal AI algorithm enhances pathologists' diagnostic accuracy, consistency, and confidence in identifying UIP, even in cases where specialised expertise is limited. image

Patients with fibrosing interstitial lung disease (FILD) have poor health-related quality of life (HRQOL). We analyzed predictors of short-term improvement of HRQOL after starting pulmonary rehabilitation (PR) in moderate to severe FILD patients. This study involved 28 consecutive patients with FILD (20 males, median age of 77.5 years), who participated in PR program of our hospital for >6 weeks. The St. George’s Respiratory Questionnaire (SGRQ) score and the 6-min walk distance (6MWD) were evaluated before and after PR, and the predictors of efficacy of PR were analyzed. The duration from diagnosis of FILD to start of PR showed a positive correlation with the increase in the SGRQ score, and the baseline SGRQ score showed a negative correlation with increase in the 6MWD. The FILD subtype, modified Medical Research Council score, and treatment history were not associated with the endpoints. According to the receiver operating characteristic curve (ROC) analyses, starting PR within 514 days after diagnosis of FILD was a significant favorable predictor of improvement in the SGRQ total score more than a minimal clinically important difference of 4. In this study, early intervention of PR and lower SGRQ score were associated with the favorable response to PR. PR for FILD should be initiated early before the disease becomes severe.

Periostin was investigated as a biomarker for rheumatoid arthritis-associated interstitial lung disease (RA-ILD). This prospective study measured serum monomeric and total periostin, Klebs von den Lungen-6 (KL-6), surfactant protein D (SP-D), and lactate dehydrogenase (LDH) in 19 patients with RA-ILD, 20 RA without ILD, and 137 healthy controls (HC). All biomarkers were higher in RA-ILD than HC or RA without ILD. KL-6 accurately detected ILD in RA patients (area under curve [AUC] = 0.939) and moderately detected SP-D and monomeric and total periostin (AUC = 0.803, =0.767, =0.767, respectively). Monomeric and total periostin were negatively correlated with normal lung area and positively correlated with honeycombing, reticulation, fibrosis score, and the traction bronchiectasis grade but not inflammatory areas. Serum levels of SP-D, KL-6, and LDH did not correlate with the extent of those fibrotic areas on high-resolution CT. Serum monomeric and total periostin were higher in patients with RA-ILD with definite usual interstitial pneumonia pattern compared with other ILD patterns. Immunohistochemical analyses of biopsy or autopsy lung tissues from RA-ILD during the chronic phase and acute exacerbation showed that periostin was expressed in fibroblastic foci but not inflammatory or dense fibrosis lesions. Periostin is a potential biomarker for diagnosis, evaluating fibrosis, and deciding therapeutic strategies for patients with RA-ILD.

Insufficient evidence exists regarding the efficacy of Janus kinase inhibitors (JAKis), a class of targeted synthetic disease-modifying anti-rheumatic drugs (tsDMARDs), in the treatment of rheumatoid arthritis (RA)-associated interstitial lung disease (ILD). Herein, we present a case of RA-ILD refractory to previous treatments that exhibited favorable response to upadacitinib. A 69-year-old man, former smoker, was diagnosed with RA-ILD based on persistent symmetric polyarthritis, elevated C-reactive protein levels and erythrocyte sedimentation rate, reduced diffusing capacity for carbon monoxide/alveolar volume (D_LCO 69.9%), and bilateral ground-glass attenuation with traction bronchiectasis, predominantly in the lower lung lobe. Initial treatment with oral prednisolone and methotrexate was started; however, the patient showed worsening dyspnea, chest high-resolution computed tomography abnormalities, and decreased pulmonary function. The dose of prednisolone was increased, and methotrexate was shifted to tacrolimus; however, tacrolimus was eventually discontinued because of renal dysfunction. Subsequent treatment changes included abatacept followed by intravenous cyclophosphamide, but ILD activity continued to worsen and met the criteria of progressive pulmonary fibrosis. Approximately 4.5 years after the RA diagnosis, dyspnea, radiological abnormalities, and D_LCO improved following treatment switch to upadacitinib, one of JAKis. JAKi therapy may have potential as a treatment option for refractory RA-ILD.