Search Results (381)

Objectives: This study evaluated the utility of complex morphometric analyses for predicting radiation pneumonitis (RP) and proposed a quantitative prognostic framework for patients with non-small cell lung cancer (NSCLC) undergoing curative-intent radiotherapy (RT). Imaging biomarkers, including box-counting fractal dimension (BoxFD), lacunarity, and minimum spanning tree fractal dimension (MSTFD), were assessed for their prognostic significance. Materials and Methods: We retrospectively analyzed 166 NSCLC patients who received curative-intent RT and had both pre-treatment and follow-up chest CT scans. Among them, 85 received RT alone and 81 underwent concurrent chemoradiotherapy (CCRT). Fractal features were measured to build a Random Forest model (RFM) predicting RP of grade ≥ 2, and the most important features were used to construct a decision tree model. Results: RP of grade ≥ 2 occurred in 19 patients (22.3%) in the RT alone group and 44 patients (54.3%) in the CCRT group. Lacunarity increased significantly post-RT in both groups, while BoxFD and MSTFD showed no significant changes. In the RFM, pre-RT MSTFD and lung dose parameters (V10 in RT alone; V5–V20 in CCRT) were identified as key predictors. Decision tree models based on these features achieved high predictive performance, with AUROC of 0.83 and 0.85, and F1 scores of 0.92 and 0.76 for RT alone and CCRT groups, respectively. Conclusions: Fractal imaging biomarkers demonstrated promising prognostic value for predicting grade ≥ 2 RP in NSCLC patients. The proposed decision tree model may serve as a practical tool for early identification of high-risk patients, facilitating personalized treatment strategies and informing future research. Full article

Alterations in the human epidermal growth factor receptor 2 (HER2) gene are well-recognized oncogenic drivers and therapeutic targets in non-small cell lung cancer (NSCLC). The first anti-HER2 inhibitor, trastuzumab-deruxtecan, was approved for previously treated advanced NSCLC with HER2 mutations, which accounts for 2–4% of NSCLC. The first anti-HER2 antibody, trastuzumab, was approved for HER2-positive metastatic breast cancer in 1998, and a combination therapy comprising trastuzumab, pertuzumab, and docetaxel demonstrated efficacy in the first-line setting. Some EGFR-tyrosine kinase inhibitors (TKIs) have been evaluated as pan-HER TKIs but have shown limited benefits in HER2-altered NSCLC. However, HER2-specific TKIs, such as zongertinib and BAY2927088, have demonstrated encouraging results. Zongertinib was the first HER2-specific TKI to be approved by the FDA in 2025 for previously treated ERBB2-mutated advanced NSCLC. In this narrative review, we have summarized the latest research on the biology of HER2 signaling, HER2 alterations, HER2-targeting therapies, and challenges of treating HER2-overexpressing or -mutated NSCLC. Despite different targets of HER2 mutations in NSCLC and HER2 amplification/overexpression in breast cancer, the development of HER2-targeting agents has been more advanced in breast cancer than in NSCLC. Therefore, pivotal clinical studies in breast cancer may help in identifying more effective therapies for NSCLC. Full article

Noninvasive liquid biopsy for monitoring circulating tumor cells offers valuable insights for predicting therapeutic responses. We developed TelomeScan^® (OBP-401), based on the detection of telomerase activity as a universal cancer cell marker and an indicator of the presence of viable circulating tumor cells (CTCs) for patients with advanced non-small cell lung cancer (NSCLC). This system evaluated CTC subtypes characterized by programmed death ligand 1 (PD-L1), an immune checkpoint molecule, and vimentin, an epithelial–mesenchymal transition (EMT) marker, using a multi-fluorescent color microscope reader. The prognostic value and therapeutic responses were predicted by dynamically monitoring CTC counts in 79 patients with advanced NSCLC. The sensitivity and specificity values of TelomeScan^® for PD-L1⁽⁺⁾ cells (≥1 cell) were 75% and 100%, respectively, indicating high diagnostic accuracy. PD-L1⁽⁺⁾ and EMT⁽⁺⁾ in CTCs were detected in 75% and 12% of patients, respectively. Detection of PD-L1⁽⁺⁾CTCs and PD-L1⁽⁺⁾EMT⁽⁺⁾ CTCs before treatment was associated with poor prognosis (p < 0.05). Monitoring of reducing and increasing PD-L1⁽⁺⁾ CTC counts in two sequential samples (baseline, cycle 2 treatment) correlated significantly with partial response (p = 0.032) and progressive disease (p = 0.023), respectively. Monitoring PD-L1⁽⁺⁾CTCs by TelomeScan^® will aid in anticipating responses or resistance to frontline treatments, optimizing precision medicine choices in patients with NSCLC. Full article

Objectives: To determine the prescribing prevalence of epidermal growth factor receptor (EGFR)- and anaplastic lymphoma kinase (ALK)-positive non-small cell lung cancer (NSCLC) patients in Greece and examine patterns of first-line tyrosine kinase inhibitor (TKI) utilization and associated treatment costs using nationwide real-world data. Methods: A retrospective analysis of the national e-prescription database was performed, identifying patients initiating first-line treatment (FLT) for EGFR- or ALK-positive NSCLC between 1 January 2020 and 31 December 2022. Demographic characteristics, prescribing prevalence data, drug utilization patterns, total annual drug expenditures, and per patient treatment costs were assessed. All statistical analyses were performed using the statistical software SPSS-v.29. Results: Overall, 1188 EGFR-positive (mean age of 70.93 ± 11.6) and 246 (mean age of 64.26 ± 12.6) ALK-positive NSCLC patients initiated FLT during the three-year study period. EGFR mutations were slightly more common in females (53%), peaking in the 70–79 age group (35%). ALK mutations were also more common among females (52%), particularly within the 60–79 age group. In EGFR-positive patients, osimertinib usage markedly increased from 41% in 2020 to 63% in 2022, primarily displacing afatinib (from 32% to 22%) and erlotinib (from 24% to 14%), with gefitinib prescriptions falling below 2%. Among ALK-positive patients, crizotinib utilization declined significantly from 60% to 16%, whereas alectinib increased to 59% by 2022. Annual EGFR-related total drug expenditures remained stable (€11.5 million in 2020 vs. €11.9 million in 2022), driven primarily by increasing osimertinib usage. Similarly, ALK-related annual drug expenditures showed stability, with costs predominantly attributed to rising alectinib utilization. Conclusions: This nationwide analysis highlights the rapid adoption of second- and third-generation TKIs for EGFR- and ALK-positive NSCLC in Greece, reflecting evolving clinical practice patterns. Although the target patient populations are relatively small, the associated economic burden is considerable. To ensure long-term sustainability of the Greek healthcare system, policymakers should critically assess the cost-effectiveness of these innovative therapies and align resource allocation with value-based care principles. Full article

Background: The advent of immunotherapy has significantly improved survival outcomes in advanced non-small cell lung cancer (NSCLC). In this evolving context, salvage surgery has emerged as a potential curative strategy, despite the risk of serious complications. This study aimed to evaluate the safety and efficacy of surgical resection following chemo-immunotherapy in patients with initially unresectable NSCLC. Methods: We retrospectively analyzed patients with stage III–IVB NSCLC who underwent salvage surgery at our institution between January 2019 and June 2024. All cases were initially deemed unresectable by a multidisciplinary tumor board. Perioperative complications, complete (R0) resection rate, major pathologic response (MPR), complete pathologic response (pCR), progression-free survival (PFS), and overall survival (OS) were analyzed. Results: Twenty-one patients (thirteen males, eight females; median age: 68 years [IQR: 9]) were included. Reasons for initial unresectability were metastatic disease (28.6%), N2 bulky disease (14.3%), local invasiveness (33.3%), or a combination of factors (23.7%). Chemo-immunotherapy was administered in 19 patients (90.5%), while 2 (9.5%) received immunotherapy alone, with a median of four treatment cycles (IQR: 1). Complete (R0) resection was achieved in all patients (100%). Anatomical resections were performed in 17 patients (81%), predominantly lobectomies (66.7%). There were no intraoperative or major postoperative complications, and 30-day mortality was zero. Median hospital stay was 7 days (IQR: 4). pCR and MPR were achieved in 33.3% and 14.3% of patients, respectively. After a median follow-up of 17 months (IQR: 19), the estimated 3-year PFS and OS were 50.9% and 66.3%, respectively. Recurrences included locoregional (4.8%), distant (14.3%), and combined (14.3%). Cox regression analysis identified stage III at diagnosis (OR: 0.292; 95% CI: 0.093–0.912; p = 0.034) and achieved pCR or MPR (OR: 0.113; 95% CI: 0.013–0.959; p = 0.046) as independent predictors of improved PFS. Conclusions: Salvage surgery after chemo-immunotherapy in initially unresectable NSCLC appears to be a safe and effective strategy in selected patients, offering favorable pathological responses and encouraging mid-term oncologic outcomes. Full article

Background: Single-agent pembrolizumab represents a standard of care in the first-line treatment of patients with metastatic non-small cell lung cancer (mNSCLC) with a programmed death-ligand 1 (PD-L1) tumor proportion score (TPS) of ≥50%. Real-world evidence is of increasing importance in oncology, as clinical trial inclusion criteria may not be truly reflective of the patient population seen in daily clinical practice. Methods: We performed a prospective–retrospective single-center study including 121 patients who received pembrolizumab as a first-line therapy for mNSCLC with a PD-L1 TPS ≥ 50%. Our aims were to make a comparison with published clinical trial results by assessing the efficacy and safety of pembrolizumab monotherapy in our population. We collected patient demographics, clinical characteristics of the disease, and treatment outcomes, including efficacy and safety. Results: A total of 121 patients were included, with a median follow-up of 40.77 months. The median progression-free survival in the real world (rwPFS) was 20.73 months (95% CI 12.24–29.22), and the median overall survival (OS) was 29.30 months (95% CI 16.57–42.04). Immune-mediated adverse events (irAEs) occurred in 42% of patients, with serious events (grade 3 or more) occurring in 12%. ECOG PS 2, male gender, squamous histology, pleural and visceral metastases, and treatment with corticosteroids prior to initiation of pembrolizumab were found to be negative predictors for overall survival, while the occurrence of irAEs was the predictor of longer survival. Conclusions: This study provides further real-world insights into the efficacy of pembrolizumab in a heterogeneous patient population with advanced NSCLC in a single center in Serbia. It also confirmed the value of good ECOS PS and the occurrence of irAEs as predictors of favorable outcomes. Full article

Background/Objectives: KRAS mutations are among the most prevalent oncogenic drivers in non-small cell lung cancer (NSCLC), with their impact on survival influenced by co-mutations. SMARCA4 mutations are increasingly associated with poor prognosis and can be classified as class 1 or class 2 mutations. This study evaluates the prognostic implications of KRAS and SMARCA4 mutations, including their co-mutations and their impact on NSCLC patients by utilizing real-world evidence. Methods: A retrospective analysis was conducted using the AACR GENIE Biopharma Collaborative (BPC) NSCLC 2.0 dataset. NSCLC patients with KRAS mutations, SMARCA4 mutations, or KRAS/SMARCA4 co-mutations were identified. Survival outcomes were assessed using univariate and multivariate Cox proportional hazards models, incorporating key clinical variables such as sex, race, smoking history, and stage. Results: Among 659 NSCLC patients with KRAS or SMARCA4 mutations analyzed, KRAS mutations were the most prevalent (79%, n = 518). SMARCA4 mutations were identified in 14% of cases (n = 95) across two classes. Six percent (n = 41) with class 1 mutations and 8% (n = 54) with class 2. Neither SMARCA4 class was associated with worse survival outcomes compared to KRAS-mutated patients (p = 0.438 & 0.720). Patients harboring KRAS/SMARCA4 class 1 co-mutations (3%, n = 18) had significantly worse overall survival compared to those with KRAS mutations alone (hazard ratio [HR] = 3.23, p < 0.001). In contrast, KRAS/SMARCA4 class 2 co-mutations (4%, n = 28) did not significantly impact survival compared to KRAS-mutated patients (HR = 1.34, p = 0.205). Conclusions: KRAS/SMARCA4 class 1 co-mutations are associated with significantly worse overall survival compared to KRAS-mutated NSCLC patients. Our multivariate analysis demonstrates the critical need to incorporate routine next-generation sequencing (NGS) testing in managing NSCLC patients at the time of metastatic diagnosis, with particular emphasis on identifying SMARCA4 mutation class as a potential prognostic biomarker in those with KRAS co-mutations. Full article

Background: Advances in screening programs have led to increased detection of early-stage non-small cell lung cancer (NSCLC), including synchronous or metachronous nodules amenable to surgical resection. Patients requiring contralateral anatomical lung resections present a unique surgical challenge due to potential impairments in lung function and the complexities of one-lung ventilation. This study evaluates the feasibility, safety, and perioperative outcomes of robotic-assisted thoracic surgery (RATS) for contralateral anatomical lung resections in patients with NSCLC. Methods: A retrospective analysis was conducted on 20 patients who underwent RATS contralateral anatomical resection between January 2019 and June 2024. Preoperative pulmonary function, perioperative characteristics, and oncological outcomes were assessed. Operative parameters, including conversion rates, intraoperative oxygenation, need for extracorporeal membrane oxygenation (ECMO), and postoperative complications, were recorded. Results: Seventy percent of the patients underwent surgery for metachronous tumors. The median forced expiratory volume in 1 s (FEV1) was 75.94% (66.62–89.24). The most common resection was segmentectomy (65.0%). The median operative time was 148.0 min (108.0–194.75). There were no conversions to open surgery or ECMO requirements. Intraoperative parameters remained stable (median FiO₂: 0.8; lowest SaO₂: 92.0%). Complications occurred in 25% of the patients, mostly Clavien–Dindo grade 2. No in-hospital, 30-day, or 90-day mortality was observed. Conclusions: Robotic-assisted contralateral anatomical lung resection is a feasible and safe approach for patients with previous contralateral surgery, supporting its role as a minimally invasive alternative for complex surgical cases. Full article

Background and Objectives: Non-small-cell lung cancer (NSCLC) often has epidermal growth factor receptor (EGFR) mutations, which are key targets for therapy. EGFR mutation subtypes, especially exon 19 deletions and exon 21 L858R mutations, influence responses to EGFR tyrosine kinase inhibitors (TKIs) and patient survival. Despite progress in TKI treatments, resistance and different responses remain challenges. This study explores the relationship between EGFR mutation subtypes, PD-L1 expression, and patient outcomes after anti-EGFR therapy. Materials and Methods: We studied 176 cases of EGFR mutation-positive NSCLC. Next-generation sequencing was used to analyze EGFR and other mutations, while PD-L1 expression was evaluated through immunohistochemistry. We analyzed EGFR mutation subtypes, PD-L1 status, treatments, and survival outcomes. Results: Among 176 cases, 88.6% were adenocarcinomas. Within the EGFR mutation spectrum, exon 19 deletions were the most common subtype, accounting for 40.9% of cases, followed by the point mutation in exon 21, which occurred in 35.8% of cases. Less frequent alterations, making up 23.3% of all detected mutations, included mutations in exon 18, insertions, and point mutations such as S768I and T790M in exon 20, as well as changes in exon 2, exon 7, and other less frequently affected regions. Exon 19 mutations were associated with older age, female sex, adenocarcinoma, and bone metastasis (p < 0.05). TP53 was the most common concurrent mutation (44.3%). PD-L1 positivity (TPS ≥ 1%) was observed in 48.3%, with high expression (TPS ≥ 50%) in 25.9%. Exon 21 mutations were significantly linked to PD-L1 negativity (p = 0.008). The median overall survival was longest with TKI therapy (51 months), and this was also observed in PD-L1-positive patients, although the difference was not statistically significant. The median progression-free survival for patients treated with TKIs and those with EGFR mutations was 14 months. PD-L1-positive patients receiving TKIs had significantly longer survival than those who did not (51 vs. 17 months, p = 0.003). Conclusions: EGFR mutation subtypes and PD-L1 expression seem to affect treatment outcomes and survival in NSCLC. The observed links emphasize the potential value of combining molecular and immunological markers to guide therapy choices. Full article

The efficacy of immune checkpoint inhibitors (ICIs) in non-small-cell lung cancer (NSCLC) varies widely across patients. Growing evidence indicates that the gut microbiome, through its interaction with the tumor microenvironment, may influence the response to immunotherapy. To investigate this, we analyzed fecal and tumor samples from 63 patients with inoperable NSCLC undergoing ICI therapy. Based on microbiome profiling using 16S rRNA sequencing, patients were grouped according to treatment benefit, defined as progression-free survival (PFS) of six months or longer. Associations between α-diversity indices, microbial composition at the genus and phylum levels, and a composite Sum Index of Binary Abundance (SIBA) were examined in relation to clinical outcomes. Higher microbial α-diversity was linked to improved response to ICIs (p-value = 0.0078 for the Chao1 index). Multiple specific taxa, such as Ruminococcus gauvreauii (p-value = 2 × 10⁻⁴), Ruminiclostridium 9 (p-value = 8 × 10⁻⁴), and [Eubacterium] ventriosum (p-value = 9 × 10⁻⁴), were enriched in patients with favorable outcomes, whereas Oscillibacter and the Eubacterium hallii group were associated with disease progression (p-value = 2 × 10⁻³ and 9 × 10⁻³, respectively). The SIBA index, which reflects the absence of multiple beneficial bacterial taxa, proved to be a stronger predictor of treatment response than individual taxa alone. Median SIBA values were 18 vs. 24 in patients benefiting from IO therapy compared to non-responders (p-value = 9 × 10⁻⁷). These findings suggest that gut microbiome diversity and composition are closely tied to immunotherapy outcomes in NSCLC. Composite microbial metrics like SIBA may enhance predictive accuracy and inform personalized treatment approaches. Full article

Background: Mediastinal staging plays a critical role in guiding treatment decisions for non-small cell lung cancer (NSCLC). While mediastinoscopy has been the gold standard for assessing mediastinal lymph node involvement, endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) has emerged as a minimally invasive alternative with comparable diagnostic accuracy. This systematic review evaluates the diagnostic performance, safety, cost-effectiveness, and feasibility of EBUS-TBNA versus mediastinoscopy for mediastinal staging. Methods: A systematic literature review was conducted in accordance with PRISMA guidelines, including searches in Medline, Scopus, EMBASE, and Cochrane databases for studies published from 2010 onwards. A total of 1542 studies were identified, and after removing duplicates and applying eligibility criteria, 100 studies were included for detailed analysis. The extracted data focused on sensitivity, specificity, complications, economic impact, and patient outcomes. Results: EBUS-TBNA demonstrated high sensitivity (85–94%) and specificity (~100%), making it an effective first-line modality for NSCLC staging. Mediastinoscopy remained highly specific (~100%) but exhibited slightly lower sensitivity (86–90%). EBUS-TBNA had a lower complication rate (~2%) and was more cost-effective, while mediastinoscopy provided larger biopsy samples, essential for molecular and histological analyses. The need for general anaesthesia, longer hospital stays, and increased procedural costs make mediastinoscopy less favourable as an initial approach. Combining both techniques in select cases enhanced overall staging accuracy, reducing false negatives and improving diagnostic confidence. Conclusions: EBUS-TBNA has become the preferred first-line mediastinal staging method due to its minimally invasive approach, high diagnostic accuracy, and lower cost. However, mediastinoscopy remains crucial in cases requiring posterior mediastinal node assessment or larger tissue samples. The integration of both techniques in a stepwise diagnostic strategy offers the highest accuracy while minimizing risks and costs. Given the lower hospitalization rates and economic benefits associated with EBUS-TBNA, its widespread adoption may contribute to more efficient resource utilization in healthcare systems. Full article

Background and Purpose: Stratification based on specific image biomarkers applicable in clinical settings could help optimize treatment outcomes for recurrent non-small cell lung cancer patients. For this purpose, we aimed to determine the clinical impact of positive delta changes (any difference above zero > 0) between baseline [¹⁸F]FDG PET/CT metrics before the first treatment course and reirradiation. Material/Methods: Forty-seven patients who underwent thoracic reirradiation with curative intent at our institute between 2013 and 2021 met the inclusion criteria. All patients had histologically verified NSCLC, ECOG (Eastern Cooperative Oncology Group) ≤ 2, and underwent [¹⁸F]FDG PET/CT for initial staging and re-staging before primary radiotherapy and reirradiation, respectively. The time interval between radiation treatments was at least nine months. Quantitative metabolic volume and intensity parameters were measured before first irradiation and before reirradiation, and the difference above zero (>0; delta change) between them was statistically correlated to locoregional control (LRC), progression-free survival (PFS), and overall survival (OS). Results: Patients were followed for a median time of 33 months after reirradiation. The median OS was 21.8 months (95%-CI: 16.3–27.3), the median PFS was 12 months (95%-CI: 6.7–17.3), and the median LRC was 13 months (95%-CI: 9.0–17.0). Multivariate analysis revealed that the delta changes in SULpeak, SUVmax, and SULmax of the lymph nodes significantly impacted OS (SULpeak p = 0.017; SUVmax p = 0.006; SULmax p = 0.006), PFS (SULpeak p = 0.010; SUVmax p = 0.009; SULmax p = 0.009), and LRC (SULpeak p < 0.001; SUVmax p = 0.003; SULmax p = 0.003). Conclusions: Delta changes in SULpeak, SUVmax, and SULmax of the metastatic lymph nodes significantly impacted all clinical endpoints (OS, PFS and LRC) in recurrent NSCLC patients treated with reirradiation. Hence, these imaging biomarkers could be helpful with regard to patient selection in this challenging clinical situation. Full article

Background: Consolidation therapy with durvalumab after definitive chemoradiotherapy (CRT) has become the standard care for patients with stage III non-small-cell lung cancer (NSCLC) following the PACIFIC trial. However, real-world data evaluating outcomes under routine clinical conditions remain limited, particularly in European cohorts. Methods: In this retrospective single-center study, we analyzed clinical data from 72 patients with stage III NSCLC treated with definitive CRT between 2017 and 2022. The patients were stratified by receipt of durvalumab consolidation. Univariable and multivariable Cox regression models were used to assess overall survival (OS) and progression-free survival (PFS). Stepwise variable selection based on the Akaike Information Criterion (AIC) was used to construct an optimized multivariable model. A sensitivity analysis with adjustment for treatment period (2017–2018 vs. 2019–2022) was conducted to account for the introduction of durvalumab into routine clinical practice. Results: Among 72 patients, 35 received durvalumab and 37 did not. The median OS was 2.08 years; the 3- and 5-year OS rates were 38.6% and 30.3%, respectively. Multivariable regression revealed significantly improved OS associated with Karnofsky performance status (KPS) > 80% (HR 0.29, p = 0.003), Charlson Comorbidity Index (CCI) ≤ 2 (HR 0.39, p = 0.009), and durvalumab treatment (HR 3.99, p = 0.008). PD-L1 expression ≥ 1% showed a trend toward improved OS (HR 3.72, p = 0.063). The median progression-free survival (PFS) for the total cohort was 1.17 years. The estimated 3- and 5-year PFS rates were 31.1% and 26.3%, respectively. Patients treated with durvalumab had a longer median PFS (20.5 months) compared to those without durvalumab (12.0 months). In the multivariable analysis, KPS > 80% (HR 0.29, p < 0.001), CCI ≤ 2 (HR 0.53, p = 0.048), and durvalumab treatment (HR 2.81, p = 0.023) were significantly associated with improved PFS. A sensitivity analysis adjusting for treatment period—reflecting the introduction of durvalumab into routine clinical practice from 2019—confirmed the robustness of these findings. Conclusions: Our findings support the clinical benefit of durvalumab consolidation following CRT in a real-world population, especially in patients with good performance status and low comorbidity burden. These results confirm and extend the PACIFIC trial findings into routine clinical practice, highlighting the prognostic value of functional status and comorbidity alongside PD-L1 expression. Full article

Introduction: Radiomics is the extraction of non-invasive and reproducible quantitative imaging features, which may yield mineable information for clinical practice implementation. Quantification of lung function through radiomics could play a role in the management of patients with pulmonary lesions. The aim of this study is to test the capability of radiomic features to predict pulmonary function parameters, focusing on the diffusing capacity of lungs to carbon monoxide (DL_CO). Methods: Retrospective data were retrieved from electronical medical records of patients treated with Stereotactic Body Radiation Therapy (SBRT) at a single institution. Inclusion criteria were as follows: (1) SBRT treatment performed for primary early-stage non-small cell lung cancer (ES-NSCLC) or oligometastatic lung nodules, (2) availability of simulation four-dimensional computed tomography (4DCT) scan, (3) baseline spirometry data availability, (4) availability of baseline clinical data, and (5) written informed consent for the anonymized use of data. The gross tumor volume (GTV) was segmented on 4DCT reconstructed phases representing the moment of maximum inhalation and maximum exhalation (Phase 0 and Phase 50, respectively), and radiomic features were extracted from the lung parenchyma subtracting the lesion/s. An iterative algorithm was clustered based on correlation, while keeping only those most associated with baseline and post-treatment DL_CO. Three models were built to predict DL_CO abnormality: the clinical model—containing clinical information; the radiomic model—containing the radiomic score; the clinical-radiomic model—containing clinical information and the radiomic score. For the models just described, the following were constructed: Model 1 based on the features in Phase 0; Model 2 based on the features in Phase 50; Model 3 based on the difference between the two phases. The AUC was used to compare their performances. Results: A total of 98 patients met the inclusion criteria. The Charlson Comorbidity Index (CCI) scored as the clinical variable most associated with baseline DL_CO (p = 0.014), while the most associated features were mainly texture features and similar among the two phases. Clinical-radiomic models were the best at predicting both baseline and post-treatment abnormal DL_CO. In particular, the performances for the three clinical-radiomic models at predicting baseline abnormal DL_CO were AUC₁ = 0.72, AUC₂ = 0.72, and AUC₃ = 0.75, for Model 1, Model 2, and Model 3, respectively. Regarding the prediction of post-treatment abnormal DL_CO, the performances of the three clinical-radiomic models were AUC₁ = 0.91, AUC₂ = 0.91, and AUC₃ = 0.95, for Model 1, Model 2, and Model 3, respectively. Conclusions: This study demonstrates that radiomic features extracted from healthy lung parenchyma on a 4DCT scan are associated with baseline pulmonary function parameters, showing that radiomics can add a layer of information in surrogate models for lung function assessment. Preliminary results suggest the potential applicability of these models for predicting post-SBRT lung function, warranting validation in larger, prospective cohorts. Full article

Background: This study aimed to develop a nomogram based on the most relevant clinical, CT, and radiomic features comprising 11 key signatures (2 clinical, 2 CT-based, and 7 radiomic) for the non-invasive prediction of the EGFR mutation status and to support the timely initiation of tyrosine kinase inhibitor (TKI) therapy in patients with non-small cell lung cancer (NSCLC) adenocarcinoma. Methods: Retrospective real-world data were collected from 521 patients with histologically confirmed NSCLC adenocarcinoma who underwent CT imaging and either surgical resection or pathological biopsy for EGFR mutation testing. Five Random Forest classification models were developed and trained on various datasets constructed by combining clinical, CT, and radiomic features extracted from CT image regions of interest (ROIs), with and without feature preselection. Results: The model trained exclusively on the most relevant clinical, CT, and radiomic features demonstrated superior predictive performance compared to the other models, with strong discrimination between EGFR-mutant and wild-type cases (AUC = 0.88; macro-average = 0.90; micro-average = 0.89; precision = 0.90; recall = 0.94; F1-score = 0.91; and accuracy = 0.87). Conclusions: A nomogram constructed using a Random Forest model trained solely on the most informative clinical, CT, and radiomic features outperformed alternative approaches in the non-invasive prediction of the EGFR mutation status, offering a promising decision-support tool for precision treatment planning in NSCLC. Full article