RESUMO
BACKGROUND: Interstitial lung abnormalities (ILAs) on CT may affect the clinical outcomes in patients with chronic obstructive pulmonary disease (COPD), but their quantification remains unestablished. This study examined whether artificial intelligence (AI)-based segmentation could be applied to identify ILAs using two COPD cohorts. METHODS: ILAs were diagnosed visually based on the Fleischner Society definition. Using an AI-based method, ground-glass opacities, reticulations, and honeycombing were segmented, and their volumes were summed to obtain the percentage ratio of interstitial lung disease-associated volume to total lung volume (ILDvol%). The optimal ILDvol% threshold for ILA detection was determined in cross-sectional data of the discovery and validation cohorts. The 5-year longitudinal changes in ILDvol% were calculated in discovery cohort patients who underwent baseline and follow-up CT scans. RESULTS: ILAs were found in 32 (14%) and 15 (10%) patients with COPD in the discovery (n = 234) and validation (n = 153) cohorts, respectively. ILDvol% was higher in patients with ILAs than in those without ILA in both cohorts. The optimal ILDvol% threshold in the discovery cohort was 1.203%, and good sensitivity and specificity (93.3% and 76.3%) were confirmed in the validation cohort. 124 patients took follow-up CT scan during 5 ± 1 years. 8 out of 124 patients (7%) developed ILAs. In a multivariable model, an increase in ILDvol% was associated with ILA development after adjusting for age, sex, BMI, and smoking exposure. CONCLUSION: AI-based CT quantification of ILDvol% may be a reproducible method for identifying and monitoring ILAs in patients with COPD.
Assuntos
Inteligência Artificial , Doenças Pulmonares Intersticiais , Doença Pulmonar Obstrutiva Crônica , Tomografia Computadorizada por Raios X , Humanos , Feminino , Masculino , Doença Pulmonar Obstrutiva Crônica/diagnóstico por imagem , Idoso , Doenças Pulmonares Intersticiais/diagnóstico por imagem , Estudos Prospectivos , Pessoa de Meia-Idade , Tomografia Computadorizada por Raios X/métodos , Estudos Longitudinais , Pulmão/diagnóstico por imagem , Estudos TransversaisRESUMO
BACKGROUND AND PURPOSE: Symptomatic radiation pneumonitis (SRP) is a complication of thoracic stereotactic body radiotherapy (SBRT). As visual assessments pose limitations, artificial intelligence-based quantitative computed tomography image analysis software (AIQCT) may help predict SRP risk. We aimed to evaluate high-resolution computed tomography (HRCT) images with AIQCT to develop a predictive model for SRP. MATERIALS AND METHODS: AIQCT automatically labelled HRCT images of patients treated with SBRT for stage I lung cancer according to lung parenchymal pattern. Quantitative data including the volume and mean dose (Dmean) were obtained for reticulation + honeycombing (Ret + HC), consolidation + ground-glass opacities, bronchi (Br), and normal lungs (NL). After associations between AIQCT's quantified metrics and SRP were investigated, we developed a predictive model using recursive partitioning analysis (RPA) for the training cohort and assessed its reproducibility with the testing cohort. RESULTS: Overall, 26 of 207 patients developed SRP. There were significant between-group differences in the Ret + HC, Br-volume, and NL-Dmean in patients with and without SRP. RPA identified the following risk groups: NL-Dmean ≥ 6.6 Gy (high-risk, n = 8), NL-Dmean < 6.6 Gy and Br-volume ≥ 2.5 % (intermediate-risk, n = 13), and NL-Dmean < 6.6 Gy and Br-volume < 2.5 % (low-risk, n = 133). The incidences of SRP in these groups within the training cohort were 62.5, 38.4, and 7.5 %; and in the testing cohort 50.0, 27.3, and 5.0 %, respectively. CONCLUSION: AIQCT identified CT features associated with SRP. A predictive model for SRP was proposed based on AI-detected Br-volume and the NL-Dmean.
Assuntos
Neoplasias Pulmonares , Pneumonite por Radiação , Radiocirurgia , Tomografia Computadorizada por Raios X , Humanos , Radiocirurgia/efeitos adversos , Pneumonite por Radiação/etiologia , Pneumonite por Radiação/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Neoplasias Pulmonares/radioterapia , Neoplasias Pulmonares/cirurgia , Feminino , Masculino , Idoso , Pessoa de Meia-Idade , Idoso de 80 Anos ou mais , Doenças Pulmonares Intersticiais/diagnóstico por imagem , Doenças Pulmonares Intersticiais/etiologia , Estudos Retrospectivos , Inteligência ArtificialRESUMO
Anti-aminoacyl-tRNA synthetase (ARS) antibodies are myositis-specific antibodies associated with anti-synthetase syndrome (ASSD). Some patients are positive for anti-ARS antibodies on enzyme-linked immunosorbent assay (ELISA) but negative on RNA-immunoprecipitation (RNA-IP) (the gold standard method). Whether these patients should be considered truly positive for anti-ARS antibodies remains unclear. Therefore, we investigated the clinical characteristics of these patients and verified the authenticity of their anti-ARS positivity. Patients who were positive for anti-ARS antibodies on ELISA were divided into the non-discrepant (positive on RNA-IP, n = 52) and discrepant (negative on RNA-IP, n = 8) groups. Patient clinical characteristics were compared between the groups. For each positive individual, the authenticity of anti-ARS antibody positivity on ELISA was cross-examined using protein-IP and western blotting. All patients in the discrepant group had lung involvement, including five (63%) with interstitial lung disease. The overall survival time was significantly lower in the discrepant group than in the non-discrepant group (p < 0.05). Validation tests confirmed the presence of anti-ARS antibodies in the sera of the discrepant group but indicated different reactivity from typical anti-ARS antibodies. In conclusion, some anti-ARS antibodies are detected by ELISA but not RNA-IP. Such anti-ARS antibody discrepancies need further elucidation to attain validation of the diagnostic process in ASSD.
RESUMO
Background: Recent guidelines discourage the use of pulmonary arterial hypertension (PAH)-targeted therapies in patients with pulmonary hypertension (PH) associated with respiratory diseases. Therefore, stratifications of the effectiveness of PAH-targeted therapies are important for this group. Objectives: The authors aimed to identify phenotypes that might benefit from initial PAH-targeted therapies in patients with PH associated with interstitial pneumonia and combined pulmonary fibrosis and emphysema. Methods: We categorized 270 patients with precapillary PH (192 interstitial pneumonia, 78 combined pulmonary fibrosis and emphysema) into severe and mild PH using a pulmonary vascular resistance of 5 WU. We investigated the prognostic factors and compared the prognoses of initial (within 2 months after diagnosis) and noninitial treatment groups, as well as responders (improvements in World Health Organization functional class, pulmonary vascular resistance, and 6-minute walk distance) and nonresponders. Results: Among 239 treatment-naive patients, 46.0% had severe PH, 51.8% had mild ventilatory impairment (VI), and 40.6% received initial treatment. In the severe PH with mild VI subgroup, the initial treatment group had a favorable prognosis compared with the noninitial treatment group. The response rate in this group was significantly higher than the others (48.2% vs 21.8%, ratio 2.21 [95% CI: 1.17-4.16]). In multivariate analysis, initial treatment was a better prognostic factor for severe PH but not for mild PH. Within the severe PH subgroup, responders had a favorable prognosis. Conclusions: This study demonstrated an increased number of responders to initial PAH-targeted therapy, with a favorable prognosis in severe PH cases with mild VI. A survival benefit was not observed in mild PH cases. (Multi-institutional Prospective Registry in Pulmonary Hypertension associated with Respiratory Disease; UMIN000011541).
RESUMO
This study investigated the utility of periostin, a matricellular protein, as a prognostic biomarker in patients with idiopathic pulmonary fibrosis (IPF) who received nintedanib. Monomeric and total periostin levels were measured by enzyme-linked immunosorbent assay in 87 eligible patients who participated in a multicenter prospective study. Forty-three antifibrotic drug-naive patients with IPF described in previous studies were set as historical controls. Monomeric and total periostin levels were not significantly associated with the change in forced vital capacity (FVC) or diffusing capacity of the lungs for carbon monoxide (DLCO) during any follow-up period. Higher monomeric and total periostin levels were independent risk factors for overall survival in the Cox proportional hazard model. In the analysis of nintedanib effectiveness, higher binarized monomeric periostin levels were associated with more favorable suppressive effects on decreased vital capacity (VC) and DLCO in the treatment group compared with historical controls. Higher binarized levels of total periostin were associated with more favorable suppressive effects on decreased DLCO but not VC. In conclusion, higher periostin levels were independently associated with survival and better therapeutic effectiveness in patients with IPF treated with nintedanib. Periostin assessments may contribute to determining therapeutic strategies for patients with IPF.
Assuntos
Fibrose Pulmonar Idiopática , Periostina , Humanos , Estudos Prospectivos , Fibrose Pulmonar Idiopática/tratamento farmacológico , Capacidade Vital , Biomarcadores , Resultado do TratamentoRESUMO
BACKGROUND: We aimed to develop and externally validate a novel machine learning model that can classify CT image findings as positive or negative for SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR). METHODS: We used 2,928 images from a wide variety of case-control type data sources for the development and internal validation of the machine learning model. A total of 633 COVID-19 cases and 2,295 non-COVID-19 cases were included in the study. We randomly divided cases into training and tuning sets at a ratio of 8:2. For external validation, we used 893 images from 740 consecutive patients at 11 acute care hospitals suspected of having COVID-19 at the time of diagnosis. The dataset included 343 COVID-19 patients. The reference standard was RT-PCR. RESULTS: In external validation, the sensitivity and specificity of the model were 0.869 and 0.432, at the low-level cutoff, 0.724 and 0.721, at the high-level cutoff. Area under the receiver operating characteristic was 0.76. CONCLUSIONS: Our machine learning model exhibited a high sensitivity in external validation datasets and may assist physicians to rule out COVID-19 diagnosis in a timely manner at emergency departments. Further studies are warranted to improve model specificity.