Pulmonology

Explainable prediction of MDR/RR-TB in tuberculosis-diabetes mellitus multimorbidity: a machine learning model developed and validated in a dual-center study.

BACKGROUND: Tuberculosis-diabetes mellitus (TB-DM) multimorbidity significantly increases the risk of multidrug-resistant/rifampicin-resistant tuberculosis (MDR/RR-TB). Early risk stratification tools for this high-risk population remain lacking. OBJECTIVE: To develop and validate an interpretable machine learning (ML) model for predicting MDR/RR-TB in patients with TB-DM multimorbidity, and to id...

Revolutionizing lung cancer screening: the rise of artificial intelligence integrating circulating tumor markers.

Lung cancer persists as the predominant oncological cause of mortality globally, underscoring an imperative public health issue that demands effective screening methodologies to mitigate its impact. The National Lung Screening Trial (NLST) from the National Cancer Institute has established that low-dose computed tomography (LDCT) can detect lung cancer at an early stage and decrease mortality. Non...

CT-based body composition and its change through time in relation to outcomes in participants screened for lung cancer.

BACKGROUND: Computed Tomography (CT) scans allow opportunistic evaluation of body composition. We investigated whether body composition and change thr...

Early ctDNA stratifies survival in locally advanced and oligometastatic lung cancer treated with radiotherapy.

PURPOSE: Circulating tumor fraction estimate (ctFE) is a machine learning-derived composite metric of circulating tumor DNA (ctDNA) burden. We hypothe...

Choroidal vascularity across aging and the spectrum of age-related macular degeneration: an AI-based OCT study.

PURPOSE: To characterize the choroidal morphology across a spectrum of participants affected by normal aging as well as age-related macular degenerati...

Deep-learning based quantitative evaluation of postoperative atelectasis following right upper lobectomy.

Existing methods of grading atelectasis are typically subjective and not scalable. We aimed to develop an automated, deep learning-based framework to ...

Peripheral blood mononuclear cell DNA methylation signatures guide surgical decision-making in indeterminate pulmonary nodules.

BACKGROUND: Distinguishing malignant from benign pulmonary nodules remained a significant clinical challenge. Given the involvement of DNA methylation...

Integration of Single-Cell RNA Sequencing and Machine Learning to Identify and Validate Prognostic Genes With Lymph Node Metastasis and Immune Cell Signatures in Lung Adenocarcinoma.

The poor prognosis of lung adenocarcinoma (LUAD) remains unimproved. This study aimed to identify lymph node metastasis (LNM)-related and cellular imm...

Exploratory association between multimodal AI-derived digital biomarkers and in-hospital mortality in adult patients with pneumonia: A proof-of-concept study.

Pneumonia remains a leading cause of in-hospital mortality worldwide. Current prognostic tools such as the IDSA/ATS severity score have meaningful lim...

Use of the Ion Robot in the Diagnosis of Pulmonary Nodules: Fine Needle Aspiration Versus Cryobiopsy.

BACKGROUND: Robotic-assisted bronchoscopy platforms provide an innovative approach to the sampling of pulmonary nodules. As compared to other technolo...

A dynamic proteomic signature for the prediction of lung Cancer: a longitudinal analysis in the UK Biobank cohort.

BACKGROUND: To understand the molecularly obscure pre-diagnostic phase of lung cancer, we mapped the temporal evolution of the plasma proteome for new...

A novel serum metabolite classifier for identifying Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) integrating metabolomics and machine learning.

BACKGROUND: Metabolic dysfunction-associated steatotic liver disease (MASLD) presents a growing global health burden, while reliable non-invasive biom...

Artificial intelligence-assisted risk prediction of postoperative pulmonary complications in non-small cell lung cancer surgery.

BACKGROUND: Pulmonary complications are the most frequent adverse events following surgery for non-small cell lung cancer (NSCLC), influencing both sh...

Retinal imaging and supervised learning predict hospitalizations, kidney, and heart-lung damage in sickle cell disease.

Sickle cell disease (SCD) is a single-gene illness which causes painful vaso-occlusion, debilitating organ damage, and early mortality. Its clinical c...

Quantitative CT Measurements of Interstitial Lung Disease: Same-Day Variability Between Two Vendors-A Prospective Study.

BACKGROUND. Clinical application of quantitative CT (QCT) measurements of interstitial lung disease (ILD) for longitudinal monitoring of disease progr...

Repurposing Clinical Candidates for Nipah and Hendra Viruses.

Nipah virus (NiV) and Hendra virus (HeV) are bat-borne zoonotic paramyxoviruses that cause severe and often fatal respiratory and neurological disease...

[Artificial intelligence-assisted diagnostics in the pathology of internal and oncological diseases].

BACKGROUND: Artificial intelligence (AI) is increasingly being implemented in digital pathology to support the tissue classification, cell detection, ...

Clinical validation and implementation of mSTOP, a machine learning-based, longitudinal prediction model for the early identification of non-small cell lung cancer patients who not benefit from immune checkpoint inhibitor treatment.

OBJECTIVES: There has been a lot of interest in the field of laboratory medicine regarding the use of machine learning (ML)-based prediction models. T...

Perioperative hypoxaemia early warning based on high-frequency waveform fusion and deep learning.

The accurate prediction of impending intraoperative hypoxaemic events is paramount for patient safety. Current models relying on structural parameters...

Molecular characterisation of progressive pulmonary sarcoidosis: protocol for a longitudinal multi-centre study to develop peripheral blood circulating biomarkers for predicting pulmonary sarcoidosis progression.

INTRODUCTION: Sarcoidosis is a heterogeneous granulomatous disease with highly variable clinical trajectories, yet no validated biomarkers exist to di...