A Computed Tomography Radiomics-Based Prediction Model on Interstitial Lung Disease in Anti-MDA5-Positive Dermatomyositis

Severe interstitial lung disease risk prediction in anti-melanoma differentiation-associated protein 5 positive dermatomyositis: the STRAD-Ro52 model

OBJECTIVE

Anti-melanoma differentiation-associated gene 5-positive dermatomyositis-associated interstitial lung disease (MDA5+DM-ILD) often leads to acute respiratory failure and endangers lives. This study quantitatively analysed chest high-resolution computed tomography (HRCT) images to assess MDA5+DM-ILD and establish a risk prediction model for severe ILD within six months.

METHODS

We developed a 'Standardized Threshold Ratio Analysis & Distribution' (STRAD) to analyse lung HRCT images. In this retrospective study, 51 patients with MDA5+DM-ILD were included and divided into severe-ILD and non-severe-ILD groups based on the occurrence of acute respiratory failure within six months post-diagnosis of MDA5+DM. The STRAD parameters, clinical indicators and treatments were compared between the two groups. Least absolute shrinkage and selection operator (LASSO) regression was used to select the optimal STRAD parameters. Multivariate analysis selected clinical factors to be further combined with STRAD to enhance the predictive performance of the final model (STRAD-Ro52 model).

RESULTS

Significant differences were observed between the two groups in STRAD parameters, anti-Ro52 antibody titers, presence of anti-Ro52 antibodies, age, ESR, ALB, Pa/FiO2, IgM and IL-4 levels. The STRAD parameters were significantly correlated with demographic, inflammatory, organ function and immunological indicators. Lasso logistic regression analysis identified the -699 to -650 HU lung tissue proportion (%V7) as the optimal parameter for predicting severe ILD and S6·%V7, and the distribution of %V7 in the mid lungs was the optimal space parameter. Multifactorial regression of clinical indicators showed that the presence of anti-Ro52 antibodies was an independent risk factor for severe ILD, leading to the establishment of the STRAD-Ro52 model.

CONCLUSIONS

The STRAD-Ro52 model assists in identifying MDA5+DM patients at risk of developing severe ILD within six months, further optimizing precise disease management and clinical research design.

Identifying two pathways to poor prognosis in patients with anti-MDA5 antibodies: insights from prognostic factor and cytokines analysis

OBJECTIVE

To identify pathways linking cytokine abnormalities to mortality via prognostic factors in patients with anti-melanoma differentiation-associated protein 5 antibodies (anti-MDA5 Ab).

METHODS

This study included patients with anti-MDA5 Ab whose serum was available. Serum cytokine levels were measured using a multiplex bead assay. Prognostic factors were identified using Cox regression and log-rank test. Prognostic factor groups were identified using principal component analysis (PCA) and factor and cluster analyses. The association between cytokine levels and prognostic factors (groups) was examined using PCA and correlation and path analyses. A prognosis-prediction model was developed using prognostic factors from the different groups.

RESULTS

Thirty-five patients were included in this study, of whom 31 had rapidly progressive interstitial lung disease (RP-ILD), and 14 died. We identified white blood cell (WBC), gamma-glutamyl transpeptidase (γ-GTP), lactate dehydrogenase (LDH), C-reactive protein (CRP), ferritin, and ILD-related factors (Krebs von den Lungen-6 [KL-6], surfactant protein D [SP-D], and CT score) as prognostic factors, in addition to von Willebrand factor and thrombomodulin. Two prognostic factor groups were found: Group 1 included WBC, CRP, and ILD-related factors, and Group 2 included ferritin, LDH, and γ-GTP. Both groups contributed to mortality. Group 1 was associated with IL-6, and Group 2 was related to IL-6, IL-10, and IP-10, and indirectly with TNF-α. A model using CRP (Group1) and γ-GTP (Group2) achieved an area under the curve of 0.84, which was not inferior to previously reported models.

CONCLUSIONS

Two pathways leading to poor prognosis were identified in anti-MDA5-Ab-positive patients, each marked by specific cytokine abnormalities.

Computer-Aided Evaluation of Interstitial Lung Diseases

The approach for the diagnosis and treatment of interstitial lung diseases (ILDs) has changed in recent years, mainly for the identification of new entities, such as interstitial lung abnormalities (ILAs) and progressive pulmonary fibrosis (PPF). Clinicians and radiologists are facing new challenges for the screening, diagnosis, prognosis, and follow-up of ILDs. The detection and classification of ILAs or the identification of fibrosis progression at high-resolution computed tomography (HRCT) is difficult, with high inter-reader variability, particularly for non-expert radiologists. In the last few years, various software has been developed for ILD evaluation at HRCT, with excellent results, equal to or more reliable than humans. AI tools can classify ILDs, quantify the extent, analyze the features hidden from the human eye, predict prognosis, and evaluate the progression of the disease. More advanced tools can incorporate clinical and radiological data to obtain personalized prognosis, with the potential ability to steer treatment decisions. To step forward and implement in daily practice such tools, more collaboration is required to collect more homogeneous clinical and radiological data; furthermore, more robust, prospective trials, with the new AI-derived biomarkers compared with each other, are needed to demonstrate the real reliability of the computer-aided evaluation of ILDs.

A systematic review of the role of quantitative CT in the prognostication and disease monitoring of interstitial lung disease

BACKGROUND

The unpredictable trajectory and heterogeneity of interstitial lung disease (ILDs) make prognostication challenging. Current prognostic indices and outcome measures have several limitations. Quantitative computed tomography (qCT) provides automated numerical assessment of CT imaging and has shown promise when applied to the prognostication and disease monitoring of ILD. This systematic review aims to highlight the current evidence underpinning the prognostic value of qCT in predicting outcomes in ILD.

METHODS

A comprehensive search of four databases (Medline, EMCare, Embase and CINAHL (Cumulative Index to Nursing and Allied Health Literature)) was conducted for studies published up to and including 22 November 2024. A modified CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies) checklist was used for data extraction. The risk of bias was assessed using a Quality in Prognostic Studies template.

RESULTS

The search identified 1134 unique studies, of which 185 studies met inclusion and exclusion criteria. Commonly studied ILD subtypes included idiopathic pulmonary fibrosis (41%, n=75), mixed subtypes (26%, n=48) and systemic sclerosis ILD (16%, n=30). Numerous studies showed significant prognostic signals, even when adjusted for common covariates and/or significant correlation between serial qCT biomarkers and conventional outcome measures. Heterogenous and nonstandardised reporting methods meant that direct comparison or meta-analysis of studies was not possible. Studies were limited by the use of retrospective methodology without prospective validation and significant study attrition.

DISCUSSION

qCT has shown efficacy in the prognostication and disease monitoring of a range of ILDs. Hurdles exist to widespread adoption including governance concerns, appropriate algorithm anchoring and standardisation of image acquisition. International collaboration is underway to address these hurdles, paving the way for regulatory approval and ultimately patient benefit.

Integrating Radiomics Signature into Clinical Pathway for Patients with Progressive Pulmonary Fibrosis

Interstitial lung diseases (ILDs) are a heterogeneous group of pulmonary disorders characterised by variable degrees of inflammation, interstitial thickening, and fibrosis leading to distortion of the pulmonary architecture and gas exchange impairment. There are approximately 200 different entities in this category. ILDs are commonly classified based on several criteria, including causes, clinical features, and radiological patterns. Chest HRCT is the gold standard for the recognition of lung alteration patterns underlying interstitial lung diseases (ILDs), diagnosing specific patterns, and evaluating radiologic progression. Methods based on artificial intelligence (AI) may be used in computational medicine, especially in image-based specialties such as radiology. The evolving field of radiomics offers a unique and non-invasive approach to extracting quantitative information from medical images, particularly high-resolution computed tomography (HRCT) scans. This comprehensive review explores the burgeoning role of radiomics in unravelling the intricacies of interstitial lung disease. It focuses on its potential applications in diagnosis, prognostication, and treatment response evaluation.

Correlation of CT-based radiomics analysis with pathological cellular infiltration in fibrosing interstitial lung diseases

PURPOSE

We aimed to identify computed tomography (CT) radiomics features that are associated with cellular infiltration and construct CT radiomics models predictive of cellular infiltration in patients with fibrotic ILD.

MATERIALS AND METHODS

CT images of patients with ILD who underwent surgical lung biopsy (SLB) were analyzed. Radiomics features were extracted using artificial intelligence-based software and PyRadiomics. We constructed a model predicting cell counts in histological specimens, and another model predicting two classifications of higher or lower cellularity. We tested these models using external validation.

RESULTS

Overall, 100 patients (mean age: 62 ± 8.9 [standard deviation] years; 61 men) were included. The CT radiomics model used to predict cell count in 140 histological specimens predicted the actual cell count in 59 external validation specimens (root-mean-square error: 0.797). The two-classification model's accuracy was 70% and the F1 score was 0.73 in the external validation dataset including 30 patients.

CONCLUSION

The CT radiomics-based model developed in this study provided useful information regarding the cellular infiltration in the ILD with good correlation with SLB specimens.

Radiomics based on HRCT can predict RP-ILD and mortality in anti-MDA5 + dermatomyositis patients: a multi-center retrospective study

OBJECTIVES

To assess the effectiveness of HRCT-based radiomics in predicting rapidly progressive interstitial lung disease (RP-ILD) and mortality in anti-MDA5 positive dermatomyositis-related interstitial lung disease (anti-MDA5 + DM-ILD).

METHODS

From August 2014 to March 2022, 160 patients from Institution 1 were retrospectively and consecutively enrolled and were randomly divided into the training dataset (n = 119) and internal validation dataset (n = 41), while 29 patients from Institution 2 were retrospectively and consecutively enrolled as external validation dataset. We generated four Risk-scores based on radiomics features extracted from four areas of HRCT. A nomogram was established by integrating the selected clinico-radiologic variables and the Risk-score of the most discriminative radiomics model. The RP-ILD prediction performance of the models was evaluated by using the area under the receiver operating characteristic curves, calibration curves, and decision curves. Survival analysis was conducted with Kaplan-Meier curves, Mantel-Haenszel test, and Cox regression.

RESULTS

Over a median follow-up time of 31.6 months (interquartile range: 12.9-49.1 months), 24 patients lost to follow-up and 46 patients lost their lives (27.9%, 46/165). The Risk-score based on bilateral lungs performed best, attaining AUCs of 0.869 and 0.905 in the internal and external validation datasets. The nomogram outperformed clinico-radiologic model and Risk-score with AUCs of 0.882 and 0.916 in the internal and external validation datasets. Patients were classified into low- and high-risk groups with 50:50 based on nomogram. High-risk group patients demonstrated a significantly higher risk of mortality than low-risk group patients in institution 1 (HR = 4.117) and institution 2 cohorts (HR = 7.515).

CONCLUSION

For anti-MDA5 + DM-ILD, the nomogram, mainly based on radiomics, can predict RP-ILD and is an independent predictor of mortality.

Multivariate logistic regression analysis of poor prognosis of dermatomyositis and clinical value of ferritin/Kl-6 in predicting prognosis

BACKGROUND

Dermatomyositis (DM) is a rare inflammatory disease. Our research focuses on predicting poor prognosis in DM patients and evaluating the prognostic significance of ferritin and Salivary Sugar Chain Antigen-6 (KL-6) through multivariate logistic regression analysis.

METHODS

Between February 2018 and April 2020, 80 DM patients at our hospital were categorized into MDA5 positive (n = 20) and negative (n = 60) groups. We conducted multivariate logistic regression to determine DM's poor prognosis risk factors and evaluate ferritin/KL-6's predictive value for prognosis.

RESULTS

Analysis showed no gender, age, body mass index (BMI), or lifestyle (smoking, drinking) differences, nor in dyspnea, muscle weakness, skin ulcers, and acetylcysteine treatment effects (p > 0.05). Significant differences emerged in arrhythmias, interstitial pneumonia, C-reactive protein, albumin, and lactate dehydrogenase levels (p < 0.05). Before treatment, differences were negligible (p > 0.05), but post-treatment, serum KL-6 and ferritin levels dropped. MDA5 positive patients had elevated serum KL-6 and ferritin levels than survivors (p < 0.05), with a strong correlation to DM. Combined diagnosis using serum KL-6 and ferritin for DM prognosis showed area under curves of 0.716 and 0.634, significantly outperforming single-index diagnoses with an area under curve (AUC) of 0.926 (p < 0.05).

CONCLUSION

Serum KL-6 and ferritin show marked abnormalities in DM, useful as indicators for evaluating polymyositis and DM conditions. However, the study's small sample size is a drawback. Expanding the sample size is essential to monitor serum KL-6 and ferritin changes in DM patients under treatment more closely, aiming to improve clinical assessment and facilitate detailed research.

Predicting the death of patients with anti-melanoma differentiation-associated protein-5-positive dermatomyositis-associated interstitial lung disease: A systematic review and meta-analysis

OBJECTIVES

To investigate the risk factors for death in anti-melanoma differentiation-associated protein-5-positive dermatomyositis-associated interstitial lung disease (ILD).

METHODS

Studies were identified by searching PubMed, Embase, Web of Science, and Cochrane Library. We calculated pooled risk ratios (RRs) or standardized mean differences (SMDs) and 95% confidence intervals (CIs) using random-effects models.

RESULTS

Twenty studies were selected. Factors that may increase death risk included older age (SMD: 0.62, 95% CI: 0.42-0.81), elevated Krebs von den Lungen-6 (SMD: 0.66, 95% CI: 0.47-0.86), lactate dehydrogenase (SMD: 0.87, 95% CI: 0.72-1.02), C-reactive protein (SMD: 0.62, 95% CI: 0.44-0.80), ferritin (SMD: 0.93, 95% CI: 0.71-1.15), creatine kinase (SMD: 0.28, 95% CI: 0.13-0.44), neutrophil (SMD: 0.34, 95% CI: 0.04-0.64), neutrophil-to-lymphocyte ratio (SMD: 0.52, 95% CI: 0.24-0.79), aspartate aminotransferase (SMD: 0.70, 95% CI: 0.45-0.94), shorter disease duration (SMD: -0.44, 95% CI: -0.67 to -0.21), rapidly progressive ILD (RR: 4.08, 95% CI: 3.01-5.54), fever (RR: 1.98, 95% CI: 1.46-2.69), dyspnoea (RR: 1.63, 95% CI: 1.32-2.02), and anti-Ro52 antibody positive (RR: 1.28, 95% CI: 1.11-1.49). Female (RR: 0.86, 95% CI: 0.78-0.94), increased albumin (SMD: -1.20, 95% CI: -1.76 to -0.64), lymphocyte (SMD: -0.49, 95% CI: -0.67 to -0.30), and arthralgia (RR: 0.53, 95% CI: 0.37-0.78) were protective factors.

CONCLUSION

Older age, shorter disease duration, rapidly progressive ILD, fever, dyspnoea, anti-Ro52 antibody positive, and some inflammatory markers were risk factors for death in patients with anti-melanoma differentiation-associated protein-5-positive dermatomyositis-associated ILD.

A nomogram based on clinical factors and CT radiomics for predicting anti-MDA5+ DM complicated by RP-ILD

OBJECTIVES

Anti-melanoma differentiation-associated gene 5 antibody-positive (anti-MDA5+) DM complicated by rapidly progressive interstitial lung disease (RP-ILD) has a high incidence and poor prognosis. The objective of this study was to establish a model for the prediction and early diagnosis of anti-MDA5+ DM-associated RP-ILD based on clinical manifestations and imaging features.

METHODS

A total of 103 patients with anti-MDA5+ DM were included. The patients were randomly split into training and testing sets of 72 and 31 patients, respectively. After image analysis, we collected clinical, imaging and radiomics features from each patient. Feature selection was performed first with the minimum redundancy and maximum relevance algorithm and then with the best subset selection method. The final remaining features comprised the radscore. A clinical model and imaging model were then constructed with the selected independent risk factors for the prediction of non-RP-ILD and RP-ILD. We also combined these models in different ways and compared their predictive abilities. A nomogram was also established. The predictive performances of the models were assessed based on receiver operating characteristics curves, calibration curves, discriminability and clinical utility.

RESULTS

The analyses showed that two clinical factors, dyspnoea (P = 0.000) and duration of illness in months (P = 0.001), and three radiomics features (P = 0.001, 0.044 and 0.008, separately) were independent predictors of non-RP-ILD and RP-ILD. However, no imaging features were significantly different between the two groups. The radiomics model built with the three radiomics features performed worse than the clinical model and showed areas under the curve (AUCs) of 0.805 and 0.754 in the training and test sets, respectively. The clinical model demonstrated a good predictive ability for RP-ILD in MDA5+ DM patients, with an AUC, sensitivity, specificity and accuracy of 0.954, 0.931, 0.837 and 0.847 in the training set and 0.890, 0.875, 0.800 and 0.774 in the testing set, respectively. The combination model built with clinical and radiomics features performed slightly better than the clinical model, with an AUC, sensitivity, specificity and accuracy of 0.994, 0.966, 0.977 and 0.931 in the training set and 0.890, 0.812, 1.000 and 0.839 in the testing set, respectively. The calibration curve and decision curve analyses showed satisfactory consistency and clinical utility of the nomogram.

CONCLUSION

Our results suggest that the combination model built with clinical and radiomics features could reliably predict the occurrence of RP-ILD in MDA5+ DM patients.

Global trends in research of melanoma differentiation-associated gene 5: a bibliometric analysis from 2002 to 2022

BACKGROUND

Melanoma differentiation-associated gene 5 (MDA5), as a cytoplasmic sensor for viral double-stranded RNAs, has received increasing attention in recent years. Although considerable headway has been made on the functional role of MDA5 in antiviral immunity and autoimmune disease, the available literature is insufficient to assess the vast field.

METHODS

This study performed a bibliometric analysis to investigate current hotspots in the global scientific output of MDA5 over the past two decades. Related publications and recorded information from 2002 to 2022 in the Web of Science Core Collection (WoSCC) database were retrieved. VOSviewer and CiteSpace were used for quantitative evaluation and visualization.

RESULTS

A total of 2267 original articles and reviews were obtained, and the annual number of publications related to MDA5 was increasing rapidly. China has published the most papers, while the USA was the most influential country with the most citations and the highest H-index. The Chinese Academy of Sciences, the United States Department of Health and Human Services, and the Journal of Virology were the most prolific research affiliation, funding source, and journal, respectively. Fujita T (Kyoto University) was the most productive author with the highest H-index and had close cooperation with Kato H and Yoneyama M. The keywords "RIG-I," "MDA5," "innate immunity," "double-stranded-RNA," and "recognition" had the highest frequency, while "dermatomyositis" as well as "autoantibody" seemed to be the emerging hotspots.

CONCLUSION

This study comprehensively demonstrated the research frontiers of MDA5 and will provide a useful resource for scholars to conduct future decisions.

KEY POINTS

We conducted the first in-depth survey of the research frontiers on melanoma differentiation-associated gene 5 (MDA5) over the past two decades via bibliometric analysis. We found that many early breakthroughs have been made in the mechanism of MDA5-mediated antiviral immune responses, and the role of MDA5 in autoimmune and autoinflammatory diseases has raised the recent concern. We identified that the virus infection-associated pathogenesis and effective therapeutic strategy of anti-MDA5 antibody-positive dermatomyositis will remain the hotspots in the future.

Using clinical and radiomic feature-based machine learning models to predict pathological complete response in patients with esophageal squamous cell carcinoma receiving neoadjuvant chemoradiation

OBJECTIVE

This study aimed to build radiomic feature-based machine learning models to predict pathological clinical response (pCR) of neoadjuvant chemoradiation therapy (nCRT) for esophageal squamous cell carcinoma (ESCC) patients.

METHODS

A total of 112 ESCC patients who underwent nCRT followed by surgical treatment from January 2008 to December 2018 were recruited. According to pCR status (no visible cancer cells in primary cancer lesion), patients were categorized into primary cancer lesion pCR (ppCR) group (N = 65) and non-ppCR group (N = 47). Patients were also categorized into total pCR (tpCR) group (N = 48) and non-tpCR group (N = 64) according to tpCR status (no visible cancer cells in primary cancer lesion or lymph nodes). Radiomic features of pretreatment CT images were extracted, feature selection was performed, machine learning models were trained to predict ppCR and tpCR, respectively.

RESULTS

A total of 620 radiomic features were extracted. For ppCR prediction models, radiomic model had an area under the curve (AUC) of 0.817 (95% CI: 0.732-0.896) in the testing set; and the combination model that included rad-score and clinical features had a great predicting performance, with an AUC of 0.891 (95% CI: 0.823-0.950) in the testing set. For tpCR prediction models, radiomic model had an AUC of 0.713 (95% CI: 0.613-0.808) in the testing set; and the combination model also had a great predicting performance, with an AUC of 0.814 (95% CI: 0.728-0.881) in the testing set.

CONCLUSION

This study built machine learning models for predicting ppCR and tpCR of ESCC patients with favorable predicting performance respectively, which aided treatment plan optimization.

CLINICAL RELEVANCE STATEMENT

This study significantly improved the predictive value of machine learning models based on radiomic features to accurately predict response to therapy of esophageal squamous cell carcinoma patients after neoadjuvant chemoradiation therapy, providing guidance for further treatment.

KEY POINTS

• Combination model that included rad-score and clinical features had a great predicting performance. • Primary tumor pCR predicting models exhibit better predicting performance compared to corresponding total pCR predicting models.

The potential role of artificial intelligence in the clinical practice of interstitial lung disease

Artificial intelligence (AI) is being widely applied in the field of medicine, in areas such as drug discovery, diagnostic support, and assistance with medical practice. Among these, medical imaging is an area where AI is expected to make a significant contribution. In Japan, as of November 2022, 23 AI medical devices have received regulatory approval; all these devices are related to image analysis. In interstitial lung diseases, technologies have been developed that use AI to analyze high-resolution computed tomography and pathological images, and gene expression patterns in tissue taken from transbronchial lung biopsies to assist in the diagnosis of idiopathic pulmonary fibrosis. Some of these technologies are already being used in clinical practice in the United States. AI is expected to reduce the burden on physicians, improve reproducibility, and advance personalized medicine. Obtaining sufficient data for diseases with a small number of patients is difficult. Additionally, certain issues must be addressed in order for AI to be applied in healthcare. These issues include taking responsibility for the AI results output, updating software after the launch of technology, and adapting to new imaging technologies. Establishing research infrastructures such as large-scale databases and common platforms is important for the development of AI technology: their use requires an understanding of the characteristics and limitations of the systems. CLINICAL TRIAL REGISTRATION: Not applicable.

Computed Tomography Radiomics-based Prediction Model for Gender-Age-Physiology Staging of Connective Tissue Disease-associated Interstitial Lung Disease

PURPOSE

To analyze the feasibility of predicting gender-age-physiology (GAP) staging in patients with connective tissue disease-associated interstitial lung disease (CTD-ILD) by radiomics based on computed tomography (CT) of the chest.

MATERIALS AND METHODS

Chest CT images of 184 patients with CTD-ILD were retrospectively analyzed. GAP staging was performed on the basis of gender, age, and pulmonary function test results. GAP I, II, and III have 137, 36, and 11 cases, respectively. The cases in GAP Ⅱ and Ⅲ were then combined into one group, and the two groups of patients were randomly divided into the training and testing groups with a 7:3 ratio. The radiomics features were extracted using AK software. Multivariate logistic regression analysis was then conducted to establish a radiomics model. A nomogram model was established on the basis of Rad-score and clinical factors (age and gender).

RESULTS

For the radiomics model, four significant radiomics features were selected to construct the model and showed excellent ability to differentiate GAP I from GAP Ⅱ and Ⅲ in both the training group (the area under the curve [AUC] = 0.803, 95% confidence interval [CI]: 0.724-0.874) and testing group (AUC = 0.801, 95% CI:0.663-0.912). The nomogram model that combined clinical factors and radiomics features improved higher accuracy of both training (88.4% vs. 82.1%) and testing (83.3% vs. 79.2%).

CONCLUSION

The disease severity assessment of patients with CTD-ILD can be evaluated by applying the radiomics method based on CT images. The nomogram model demonstrates better performance for predicting the GAP staging.

Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease

Rationale and introduction

It is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical management by using the ILD-GAP (gender, age, and pulmonary physiology) index system.

Materials and methods

Patients with CTD-ILD were staged using the ILD-GAP index system. A clinical factor model was built by demographics and CT features, and a radiomics signature was developed using radiomics features extracted from CT images. Combined with the radiomics signature and independent clinical factors, a radiomics nomogram was constructed and evaluated by the area under the curve (AUC) from receiver operating characteristic (ROC) analyses. The models were externally validated in dataset 2 to evaluate the model generalization ability using ROC analysis.

Results

A total of 245 patients from two clinical centers (dataset 1, n = 202; dataset 2, n = 43) were screened. Pack-years of smoking, traction bronchiectasis, and nine radiomics features were used to build the radiomics nomogram, which showed favorable calibration and discrimination in the training cohort {AUC, 0.887 [95% confidence interval (CI): 0.827-0.940]}, the internal validation cohort [AUC, 0.885 (95% CI: 0.816-0.922)], and the external validation cohort [AUC, 0.85 (95% CI: 0.720-0.919)]. Decision curve analysis demonstrated that the nomogram outperformed the clinical factor model and radiomics signature in terms of clinical usefulness.

Conclusion

The CT-based radiomics nomogram showed favorable efficacy in predicting individual ILD-GAP stages.

Machine learning in radiology: the new frontier in interstitial lung diseases

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

A New Predictive Model for the Prognosis of MDA5+ DM-ILD

Purpose

The purpose of this study is to analyze clinical information and combine significant parameters to generate a predictive model and achieve a better prognosis prediction of dermatomyositis-associated interstitial lung disease with positive melanoma differentiation-associated gene 5 antibody (MDA5+ DM-ILD) and stratify patients according to prognostic risk factors appropriately.

Methods

We retrospectively reviewed 63 patients MDA5+ DM-ILD who were treated in our hospital from January 2018 to January 2021. Our study incorporated most clinical characteristics in clinical practice to explore the associations and predictive functions of clinical characteristics and prognosis. Student's t-test, Mann-Whitney U-test, chi-squared test, Pearson correlation analysis, Cox regression analysis, R, receiver operating characteristic curves (ROC curves), and Kaplan-Meier survival curves were performed to identify independent predictors for the prognosis of MDA5+DM-ILD.

Results

In all the 63 patients with MDA5+DM-ILD, 44 improved but 19 did not. Poor prognosis was found more frequently in patients who were older, clinically amyopathic variant of dermatomyositis (CADM), and/or with short duration, short interval of DM and ILD, long length of stay, fever, dyspnea, non-arthralgia, pulmonary infection, pleural effusion (PE), high total computed tomography scores (TCTs), ground-glass opacity (GGO), consolidation score, reticular score and fibrosis score, decreased forced vital capacity (FVC), forced expiratory volume in 1s (FEV1), albumin, A/G, glomerular filtration rate (GFR) and tumor necrosis factor α (TNFα), high titer of anti-MDA5, proteinuria, high levels of monocyte, lactate dehydrogenase (LDH), ferritin (FER), neuron specific enolase (NSE) and glucocorticoid, antibiotic, antiviral, and non-invasive positive pressure ventilation (NPPV). The multivariate Cox regression analysis demonstrated that duration, fever, PE, TCTs and aspartate transaminase (AST) were independent predictors of poor prognosis in patients with MDA5+DM-ILD. The nomogram model quantified the risk of 400-day death as: duration ≤ 4 months (5 points), fever (88 points), PE (21 points), TCTs ≥10 points (22 points), and AST ≥200 U/L (100 points) with high predictive accuracy and convenience. The ROC curves possessed good discriminative ability for combination of fever, PE, TCTs, and AST, as reflected by the area under curve (AUC) being.954, 95% CI 0.902-1.000, and sensitivity and specificity being 84.2 and 94.6%, respectively.

Conclusion

We demonstrated that duration, fever, PE, TCTs, and AST could be integrated together to be independent predictors of poor prognosis in MDA5+ DM-ILD with highly predictive accuracy.

A Matrix Prediction Model for the 6-Month Mortality Risk in Patients With Anti-Melanoma Differentiation-Associated Protein-5-Positive Dermatomyositis

Objectives

The purpose of this study was to investigate the baseline independent risk factors for predicting 6-month mortality of patients with anti-melanoma differentiation-associated gene 5 (anti-MDA5)-positive dermatomyositis (DM) and develop a matrix prediction model formed by these risk factors.

Methods

The hospitalized patients with DM who completed at least 6-month follow-up were recruited as a derivation cohort. The primary exposure was defined as positive anti-MDA5 at the baseline. The primary outcome was all-cause 6-month mortality after enrollment. A matrix prediction model was developed in the derivation cohort, and another published cohort was used for external validation.

Results

In derivation cohort, 82 patients with DM were enrolled (mean age of onset 50 ± 11 years and 63% women), with 40 (49%) showing positive anti-MDA5. Gottron sign/papules (OR: 5.135, 95%CI: 1.489–17.708), arthritis (OR: 5.184, 95%CI: 1.455–18.467), interstitial lung disease (OR: 7.034, 95%CI: 1.157–42.785), and higher level of C4 (OR: 1.010, 95%CI: 1.002–1.017) were the independent associators with positive anti-MDA5 in patients with DM. Patients with anti-MDA5-positive DM had significant higher 6-month all-cause mortality than those with anti-MDA5-negative (30 vs. 0%). Among the patients with anti-MDA5-positive DM, compared to the survivors, non-survivors had significantly advanced age of onset (59 ± 6 years vs. 46 ± 9 years), higher rates of fever (75 vs. 18%), positive carcinoma embryonic antigen (CEA, 75 vs. 14%), higher level of ferritin (median 2,858 ug/L vs. 619 ug/L, all p < 0.05). A stepwise multivariate Cox regression showed that ferritin ≥1,250 μg/L (HR: 10.4, 95%CI: 1.8–59.9), fever (HR: 11.2, 95%CI: 2.5–49.9), and positive CEA (HR: 5.2, 95%CI: 1.0–25.7) were the independent risk factors of 6-month mortality. A matrix prediction model was built to stratify patients with anti-MDA5-positive DM into different subgroups with various probabilities of 6-month mortality risk. In an external validation cohort, the observed 6-month all-cause mortality was 78% in high-risk group, 43% in moderate-risk group, and 25% in low-risk group, which shows good accuracy of the model.

Conclusion

Baseline characteristics such as fever, ferritin ≥1,250 μg/L, and positive CEA are the independent risk factors for 6-month all-cause mortality in patients with anti-MDA5-positive DM. A novel matrix prediction model composed of these three clinical indicators is first proposed to provide a chance for the exploration of individual treatment strategies in anti-MDA5-positive DM subgroups with various probabilities of mortality risk.