Deep learning to estimate lung disease mortality from chest radiographs

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Май 16, 2023

Abstract Prevention and management of chronic lung diseases (asthma, cancer, etc.) are great importance. While tests available for reliable diagnosis, accurate identification those who will develop severe morbidity/mortality is currently limited. Here, we developed a deep learning model, CXR Lung-Risk, to predict the risk disease mortality from chest x-ray. The model was trained using 147,497 x-ray images 40,643 individuals tested in three independent cohorts comprising 15,976 individuals. We found that Lung-Risk showed graded association with after adjustment factors, including age, smoking, radiologic findings (Hazard ratios up 11.86 [8.64–16.27]; p < 0.001). Adding multivariable improved estimates all cohorts. Our results demonstrate can identify at on easily obtainable x-rays, which may improve personalized prevention treatment strategies.

Язык: Английский

---

Advances in CAR T Cell Therapy for Non-Small Cell Lung Cancer

Current Issues in Molecular Biology, Год журнала: 2023, Номер 45(11), С. 9019 - 9038

Опубликована: Ноя. 12, 2023

Since its first approval by the FDA in 2017, tremendous progress has been made chimeric antigen receptor (CAR) T cell therapy, adoptive transfer of engineered, CAR-expressing lymphocyte. CAR cells are all composed three main elements: an extracellular antigen-binding domain, intracellular signaling domain responsible for activation, and a hinge that joins these two domains. Continuous improvement CARs, now their fifth generation, particularly activation. therapy revolutionized treatment hematologic malignancies. Nonetheless, use solid tumors not attained comparable levels success. Here we review challenges achieving effective tumors, emerging have shown great promise non-small lung cancer (NSCLC). A growing number clinical trials conducted to study effect on NSCLC, targeting different types surface antigens. They include epidermal growth factor (EGFR), mesothelin (MSLN), prostate stem (PSCA), mucin 1 (MUC1). Potential new targets such as erythropoietin-producing hepatocellular carcinoma A2 (EphA2), tissue (TF), protein tyrosine kinase 7 (PTK7) currently under investigation trials. The developing NSCLC other approaches enhancing efficacy discussed. Finally, provide our perspective imaging action reviewing radionuclide-based techniques, direct labeling or indirect via reporter gene.

Язык: Английский

---

5-Year Real-World Outcomes With Frontline Pembrolizumab Monotherapy in PD-L1 Expression ≥ 50% Advanced NSCLC

Clinical Lung Cancer, Год журнала: 2024, Номер 25(6), С. 502 - 508.e3

Опубликована: Май 16, 2024

Язык: Английский

---

Non-small cell lung cancer with MET amplification: review of epidemiology, associated disease characteristics, testing procedures, burden, and treatments

Frontiers in Oncology, Год журнала: 2024, Номер 13

Опубликована: Янв. 11, 2024

Introduction Mesenchymal-epidermal transition factor gene amplification ( MET amp) is being investigated as a therapeutic target in advanced non-small cell lung cancer (NSCLC). We reviewed the epidemiology and disease characteristics associated with primary secondary amp, well testing procedures used to identify NSCLC. Economic humanistic burdens, practice patterns treatments under investigation for amp were also examined. Methods Embase Medline (via ProQuest), ClinicalTrials.gov, Cochrane Controlled Register of Trials (2015–2022) systematically searched. Conference abstracts searched via conference proceedings websites (2020–2022). The review focused on evidence from United States; global was included identified gaps. Results median rate NSCLC across references 4.8% (n=4 studies) (epidermal growth receptor [ EGFR ]-mutant NSCLC) 15% (n=10). Next-generation sequencing (NGS; n=12) and/or fluorescence situ hybridization (FISH; n=11) most frequently real-world studies FISH clinical trials (n=9/10). definitions varied among using ISH/FISH (MET chromosome 7 centromere ratio ≥1.8 ≥3.0; or copy number [GCN] ≥5 ≥10) NGS (tissue testing: GCN ≥6; liquid biopsy: ≥2.1 &gt;5). Limited no data economic treatment Promising preliminary results enrolling patients -mutated, progressing an EGFR-tyrosine kinase inhibitor (TKI) observed MET-TKIs (i.e., tepotinib, savolitinib, capmatinib) combination EGFR-TKIs gefitinib osimertinib). For metastatic high-level monotherapy capmatinib, crizotinib, tepotinib are recommended 2022 published NCCN Guidelines. Conclusion Primary occurs approximately 5% cases, cases previously treated inhibitor. Variability methods (including NGS) observed. Several promising treating Additional evaluating clinical, economic, burdens needed.

Язык: Английский

---

Could the underlying biological basis of prognostic radiomics and deep learning signatures be explored in patients with lung cancer? A systematic review

European Journal of Radiology, Год журнала: 2024, Номер 171, С. 111314 - 111314

Опубликована: Янв. 13, 2024

To summarize the underlying biological correlation of prognostic radiomics and deep learning signatures in patients with lung cancer evaluate quality available studies.

Язык: Английский

---