Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 26 appraisals
Journal of robotic surgery
Perioperative outcomes and nodal station assessment after robotic-assisted versus video-assisted thoracoscopic segmentectomy for early-stage NSCLC: a systematic review and meta-analysis
The relative benefits of Robotic-assisted thoracoscopic segmentectomy (RATS) versus video-assisted thoracoscopic segmentectomy (VATS) for early-stage NSCLC remain uncertain. This meta-analysis compared perioperative outcomes, lymph node assessment, and postoperative safety between the two approaches. PubMed, Cochrane Library, Embase, and Web of Science were searched from inception to April 2026. Comparative studies of RATS versus VATS segmentectomy for early-stage NSCLC were included. Outcomes were pooled as weighted mean differences or odds ratios with 95% confidence intervals. Random-effects models were used for substantial heterogeneity (I² >50% or P < 0.05); otherwise, fixed-effects models were applied. Leave-one-out sensitivity plots are provided in the supplementary materials. Nine retrospective comparative studies involving 19,805 patients were included. Robotic-assisted segmentectomy was associated with a greater number of lymph node stations examined (WMD = 1.16, 95% CI: 0.51, 1.81, P < 0.001) and a shorter length of hospital stay (WMD = - 0.75, 95% CI: -1.36, - 0.15, P = 0.015). No significant differences were observed in operative time (WMD = 1.86, 95% CI: -8.80, 12.52, P = 0.732), duration of drainage (WMD = - 0.37, 95% CI: -0.79, 0.06, P = 0.090), overall complications (OR = 0.94, 95% CI: 0.67, 1.34, P = 0.745), air leak (OR = 1.02, 95% CI: 0.54, 1.91, P = 0.949), pneumonia (OR = 1.33, 95% CI: 0.89, 1.99, P = 0.170), or 30-day readmission (OR = 1.09, 95% CI: 0.94, 1.26, P = 0.257). Current retrospective evidence suggests that RATS may offer more examined lymph node stations and shorter hospital stay without increased morbidity, but these findings are limited by risk of bias and should not be interpreted as evidence of oncologic superiority.
22 July 2026
Read appraisal →BMJ open
Association of wearable device-based perioperative physical activity with recovery outcomes in patients undergoing lung cancer surgery: a systematic review and meta-analysis protocol.
INTRODUCTION: Lung cancer surgery is a cornerstone of curative treatment for resectable disease, but postoperative recovery is often prolonged and may be complicated by impaired pulmonary function, reduced physical activity, symptom burden and delayed functional restoration. Wearable devices may support perioperative physical activity through objective monitoring and activity promotion; however, existing evidence remains fragmented and has not been synthesised in a focused review. This protocol describes a systematic review and meta-analysis to evaluate the association of wearable device-based perioperative physical activity with recovery outcomes in patients undergoing lung cancer surgery. METHODS AND ANALYSIS: We will include randomised controlled trials, non-randomised interventional studies and prospective or retrospective cohort studies involving adults undergoing surgery for suspected or confirmed primary lung cancer. Eligible studies must examine wearable device-based perioperative physical activity during the preoperative period, postoperative period or both. The primary outcomes will be postoperative pulmonary complications, length of hospital stay and physical function or exercise capacity. Secondary outcomes will include overall postoperative complications, pulmonary function, symptom burden, health-related quality of life, chest tube duration, readmission and postoperative mortality. We will search PubMed, EMBASE, Web of Science, CINAHL and the Cochrane Library from inception to the final search date, supplemented by reference screening, forward citation tracking, grey literature and trial registry searches. Two reviewers will independently perform study selection, data extraction and risk-of-bias assessment. Where appropriate, meta-analysis will be performed using random-effects models; otherwise, findings will be synthesised narratively. ETHICS AND DISSEMINATION: Ethical approval is not required because this review will use data from published studies and publicly accessible sources only and will not involve individual participants or identifiable personal data. The findings will be disseminated through publication in a peer-reviewed journal and presentation at relevant academic or professional conferences. PROSPERO REGISTRATION NUMBER: CRD420261375254.
11 July 2026
Read appraisal →Gene
Based on WGCNA and machine learning studies, SMURF2 drives NSCLC malignant transformation, ferroptosis, and macrophage polarization by ubiquitinating SPP1
BACKGROUND: Non-small cell lung cancer (NSCLC) is a common type of lung cancer with poor prognosis and high mortality in advanced stages. Although secreted phosphoprotein 1 (SPP1) is associated with the progression of NSCLC, its specific mechanisms remain to be explored. METHODS: Through integrated bioinformatics analysis combining weighted gene co-expression network analysis (WGCNA), differential expression analysis, gene enrichment analysis with the Kyoto Encyclopedia of Genes and Genomes (KEGG)/Gene Ontology (GO), and machine learning techniques incorporating database predictions, core genes were identified. Experimental validation was conducted using Western blot, co-immunoprecipitation (Co-IP), cycloheximide (CHX) chase assay, Ubiquitin Immunoprecipitation (Ub-IP), colony formation, flow cytometry, transwell assay, reactive oxygen species (ROS) detection, and quantitative real-time PCR (qRT-PCR). The functional impact of SPP1 on tumor growth was further confirmed through mouse models and immunohistochemistry (IHC). RESULTS: Based on WGCNA and machine learning, SPP1 was identified as a core gene. SMURF2 ubiquitinated and degraded SPP1. Rescue experiments confirmed that SMURF2 inhibited proliferation and invasion, and promoted apoptosis in NSCLC cells, which were reversed by SPP1 overexpression. Furthermore, SMURF2 enhanced ferroptosis and modulated macrophage polarization via the same ubiquitination mechanism. Animal studies verified that SMURF2-mediated ubiquitination and degradation of SPP1 suppressed tumor growth. CONCLUSION: This study aims to investigate the role of SMURF2-mediated ubiquitination of SPP1 in inhibiting malignant progression, promoting ferroptosis, and modulating macrophage polarization in NSCLC, thereby providing a theoretical foundation and new insights for understanding and targeting NSCLC.
10 June 2026
Read appraisal →Biomedical physics & engineering express
Biwt-UNet: lung nodule segmentation via wavelet transform and multi-scale feature fusion
Lung nodule segmentation is a crucial step in computer-aided diagnosis of lung diseases and is of great significance for early detection and diagnosis of lung cancer. Traditional segmentation methods face many challenges, such as blurred nodule boundaries that are difficult to distinguish effectively, and the diversity of nodule sizes and shapes, which together increases the difficulty of segmenting lung nodules. Existing approaches often fail to address these issues adequately, highlighting the need for more effective solutions. To meet these challenges, this paper proposes a hybrid lung nodule segmentation approach-Biwt-UNet that integrates improved Haar wavelet transform and multi-scale feature information from the multi-scale fusion module and bi-encoder fusion module proposed in this study. The approach enables accurate segmentation of lung nodules of varying sizes, diverse shapes and, in particular, indistinct boundaries. Experimental results on the public LIDC-IDRI dataset demonstrate that Biwt-UNet achieves excellent segmentation performance. It significantly surpasses other state-of-the-art methods with an average dice similarity coefficient of 90.18%, an average intersection over union of 82.67%, and an average normalized surface dice of 96.39%, fully validating the effectiveness and accuracy of the proposed model in CT-based lung nodule analysis. Moreover, ablation studies further confirm the individual contributions of each architectural component and show that the best performance is achieved within an acceptable parameter budget. This study provides a new technical perspective for automatic lung nodule segmentation and is expected to assist physicians in more efficient diagnosis.
29 May 2026
Read appraisal →PLoS medicine
Sequential chemo-immunotherapy followed by standard versus reduced thoracic radiotherapy for older and/or frail stage III non-small-cell lung cancer: A randomized open-label cohort trial
BACKGROUND: The appropriateness of concurrent chemoradiotherapy (cCRT) for older or clinically vulnerable stage III unresectable non-small-cell lung cancer (NSCLC) patients remains contentious. Furthermore, the survival implications of de-escalating thoracic radiotherapy (RT) intensity in this population have not been conclusively elucidated. METHODS AND FINDINGS: We conducted a phase II randomized, open-label, two-cohort (non-comparative) trial at a tertiary hospital in China (NCT05557552). Between September 30, 2022 and April 30, 2024, we enrolled 56 older and/or frail patients with stage III NSCLC who were ineligible for cCRT. The primary endpoint was the 1-year progression-free survival (PFS) rate estimated using the Kaplan-Meier method. Secondary endpoints included objective response rate (ORR), overall survival (OS), and safety. In the intention-to-treat (ITT) set, which included all 56 randomized patients who received at least one dose of study treatment, the 1-year PFS was 84.3% (95% confidence interval [CI] [70.3%, 98.3%]) in the standard RT group and 70.7% (95% CI [54.3%, 87.1%]) in the reduced RT group. In the per-protocol set (53 patients), the 1-year PFS was 82.9% (95% CI [68.9%, 98.8%]) in the standard RT group and 73.4% (95% CI [58.3%, 92.4%]), with a median follow-up of 24 months. Among 56 patients in the safety analysis set, 71.4% of patients experienced grade 3/4 adverse events (AEs) in the standard RT group and 53.6% in the reduced RT group. One patient (3.6%) in the reduced RT and three patients (10.7%) in the standardized RT experienced grade 5 AEs. The main limitations are the non-comparative design, small sample size, and lack of power to establish non-inferiority or superiority. CONCLUSION: The current study suggested that reduced RT combined with sequential chemo-immunotherapy might be feasible for older/frail patients intolerant to cCRT, showing numerically similar survival outcomes. These exploratory findings warrant confirmation in larger, adequately powered randomized trials. TRIAL REGISTRATION: The trial had been registered on ClinicalTrials.gov on Sep 30, 2022. ClinicalTrials.gov NCT05557552.
29 May 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Nonpharmacological dyspnoea-relief strategies in lung cancer: a systematic review and network meta-analysis
BACKGROUND: Dyspnoea is a common and distressing symptom in lung cancer patients. While various dyspnoea-relief strategies show promise, their comparative effectiveness remains unclear. METHODS: We conducted a systematic review and network meta-analysis of randomised controlled trials on nonpharmacological dyspnoea-relief strategies in lung cancer patients, using studies published until 12 June 2025 from the databases PubMed, Embase, Web of Science, Cochrane Library, Cumulative Index to Nursing and Allied Health Literature, ClinicalTrials.gov, and the World Health Organization International Clinical Trials Registry Platform. The primary outcome was dyspnoea score post-intervention. RESULTS: 4138 participants from 46 randomised controlled trials were included in the analysis. Among 10 nonpharmacological dyspnoea-relief strategies in lung cancer patients, acupressure (surface under the cumulative ranking curve (SUCRA) 98.7%, Hedges' g -1.96, 95% CI -2.92 to -0.99) demonstrated the highest efficacy, followed by fan (SUCRA 83.7%, Hedges' g -1.11, 95% CI -1.72 to -0.50), and multicomponent interventions (SUCRA 80.7%, Hedges' g -1.01, 95% CI -1.49 to -0.52). In post-operative lung cancer patients, multicomponent interventions (SUCRA 97.4%, Hedges' g -1.55, 95% CI -2.16 to -0.94) were the most effective, followed by cognitive behavioural therapy (SUCRA 74.8%, Hedges' g -0.90, 95% CI -1.75 to -0.05). For patients with pre-existing dyspnoea, acupressure (SUCRA 90.9%, Hedges' g -1.72, 95% CI -3.01 to -0.42) and fan therapy (SUCRA 77.3%, Hedges' g -1.18, 95% CI -2.10 to -0.27) were the top interventions. CONCLUSIONS: Acupressure is the primary strategy for alleviating dyspnoea in lung cancer patients, including those with pre-existing dyspnoea, followed by fan therapy, while multicomponent interventions are recommended for post-operative patients.
29 May 2026
Read appraisal →Acta oncologica (Stockholm, Sweden)
Prospective evaluation and clinical outcomes of adaptive radiotherapy for locally advanced non-small cell lung cancer (LA-NSCLC)
BACKGROUND AND PURPOSE: Locoregional tumor control is strongly associated with survival for non-small cell lung cancer, emphasizing the importance of precise radiotherapy delivery. This study aims to evaluate a traffic light adaptation protocol regarding target coverage, protocol performance and patient outcomes. MATERIAL AND METHODS: From 2019 to 2022, we prospectively enrolled inoperable non-small cell lung cancer patients. We acquired daily cone-beam computed tomography and traffic light registrations, classifying anatomical changes and need of action. Using repeated computed tomography (rCT) in week 1 and 3 for dosimetric evaluation, we recalculated clinical target volume (CTV) D98% and V95% with and without adaptation, and compared traffic light registrations with the actual dose distribution. Protocol performance was evaluated by the sensitivity and specificity in detecting CTV V95% < 98%. RESULTS: Among 45 patients with complete registrations, baseline shift and tumor shrinkage were most common changes, leading to corrections from bone to tumor match in 37.8% and replanning in 13.3% of patients. Among 38 patients with at least one rCT, 15.8% would have received insufficient CTV coverage without adaptation. Protocol sensitivity, specificity and balanced accuracy were 83.3, 88.6, and 85.7%, respectively. For 38 stage II-III patients, median overall survival was 43.5 months (95% confidence interval [CI]: 32.9-54.1), median time to locoregional failure 27.4 months (95% CI: 0-61.8) and median estimated time to distant failure 30.7 months (CI not estimated due to censoring). INTERPRETATION: The protocol identified relevant changes, improving target coverage without increasing organ at risk doses. With appropriate training, protocol performance was good, and clinical outcomes were consistent with international results.
28 May 2026
Read appraisal →Journal of robotic surgery
Short-term outcomes of robot-assisted versus conventional minimally invasive esophagectomy for resectable esophageal cancer: a systematic review and meta-analysis
Robot-assisted minimally invasive esophagectomy (RAMIE) has emerged as an alternative to conventional minimally invasive esophagectomy (MIE) for esophageal cancer, but its short-term perioperative advantages remain uncertain. To compare early postoperative outcomes of RAMIE and MIE in patients with resectable esophageal cancer, this systematic review and meta-analysis was conducted according to PRISMA 2020 guidelines. PubMed was searched for randomized controlled trials, propensity score-matched studies, and retrospective comparative studies published between January 2005 and December 2024. Adult patients undergoing RAMIE or conventional MIE for resectable esophageal cancer were included. Random-effects models were used to pool standardized mean differences and odds ratios with 95% confidence intervals. Study quality was assessed using the MINORS criteria and Cochrane RoB 2 tool. In addition, a post hoc GRADE assessment was carried out for key outcomes to evaluate the certainty of evidence. Forty-one studies involving 13,321 patients were included, of whom 4,327 underwent RAMIE and 8,994 underwent MIE. Compared with MIE, RAMIE was associated with lower blood loss, reduced conversion to open surgery, higher total lymph node yield, greater left recurrent laryngeal nerve lymph node harvest, fewer pulmonary complications, and lower overall postoperative morbidity. ICU stay and hospital stay were also e shorter after RAMIE, whereas operative time was longer. No significant differences were observed in R0 resection, anastomotic leak, recurrent laryngeal nerve palsy, cardiac complications, chyle leak, surgical site infection, or 30- and 90-day mortality. Post hoc GRADE assessment showed that the certainty of evidence was very low across key outcomes, mainly because of the predominance of non-randomized studies, substantial heterogeneity across several pooled analyses, and outcome-specific concerns regarding imprecision and publication bias. RAMIE is safe and may offer some short-term perioperative advantages over conventional MIE without clear evidence of increased major morbidity or short-term mortality. However, the certainty of evidence across key outcomes was very low, and the predominance of nonrandomized studies and substantial heterogeneity across several analyses warrant cautious interpretation. Further adequately powered randomized trials are required.
25 May 2026
Read appraisal →Computer assisted surgery (Abingdon, England)
An automatic detection model for spread through air spaces in postoperative pathological sections based on deep learning in NSCLC
Spread through air spaces (STAS) is recognized as an aggressive pattern of invasion in lung cancer and has been associated with poorer survival outcomes. However, STAS is frequently overlooked or misdiagnosed during routine pathological diagnosis. We analyzed 129 pathological slides from 91 STAS-positive patients with non-small cell lung cancer (NSCLC). An artificial intelligence framework consisting of a tumor region segmentation algorithm and an object detection algorithm was developed. The segmentation algorithm was first used to isolate the main tumor region, followed by STAS detection using an improved object detection model. The segmentation module achieved a Jaccard similarity of 0.846. The proposed object detection algorithm demonstrated superior performance with a precision of 0.738, recall of 0.747 and average precision (AP) of 0.784 and F1 score of 0.742, outperforming other object detection methods. Both segmentation and detection results met diagnostic requirements, with higher accuracy observed in lung adenocarcinoma (LUAD) than in lung squamous cell carcinoma (LUSC). In external validation, the model achieved a precision of 0.670, recall of 0.705 and AP of 0.732 and F1 score of 0.687. Additionally, the AI-derived STAS counts showed substantial agreement with pathologists (interclass correlation coefficient = 0.703). Kaplan-Meier survival analysis revealed that the number of STAS events was significantly associated with disease-free survival (DFS) in stage I LUAD (p < .05). We propose a deep learning-based artificial intelligence framework for automated STAS detection and quantification in digital whole-slide images of NSCLC. This model holds promising potential to assist pathologists in achieving more comprehensive and accurate diagnosis of STAS.
25 May 2026
Read appraisal →Medicine
Applying digital technologies for remote care in the real life context: A 3-year experimentation with postoperative lung cancer patients
Surgery remains the main curative treatment for lung cancer patients. However, operation has resulted in some-degree reduction in postoperative pulmonary function. The decreased pulmonary function could be rehabilitated to the preoperative level through restoring exercise, which is related to the ways and exercise time of rehabilitating. The Dignio platform is 1 digital telemedicine system and has been used maturely in Norway, however, it has not yet been widely promoted in China. In the present study, we adopted the telemedicine system, according to the formulated rehabilitation exercise program, to design a good way to recover pulmonary function for postoperative lung cancer patients, promoting early and quick recovery, and reducing the long-term postoperative complications and outpatient visits. This retrospective controlled study enrolled 250 postoperative lung cancer patients using a remote digital care platform and 250 matched controls receiving standard instructions. In the postoperative 1-week follow-up, we found that the forced expiratory volume in 1 second (FEV1), forced vital capacity (FVC), forced expiratory volume in 6 seconds, FVC25-75, peak expiratory flow had an obvious upward trend, although there were no significant differences in the measurements on postoperative day 7 compared with day 1. From the long-term data at 1 month/3 months/6 months post-operation, we found that the recovery was better to varying degrees in the experiment group using the remote care digital platform, compared with that of the control, especially the FEV1 at 3 (P = .065) and 6 months post-operation (P = .037), and forced Expiratory Flow between 25% and 75% of forced vital capacity at 3 months post-operation (P = .084). However, most pulmonary values, such as the FEV1/FVC, FVC and peak expiratory flow have no significant difference (all P > .05) in the recovery at 1 month post-operation between the experimental group and control, the second time at 3 months and the third time at 6 months after surgery. Especially in the experimental group, 2 patients with sudden pneumothorax were timely detected after discharge through the Digino platform, the patient returned to the hospital in time, and both patients were out of danger ultimately. The Digino remote care indeed has some benefit in the pulmonary function recovery in the long-term follow up, and reduces postoperative complications obviously.
24 May 2026
Read appraisal →PloS one
Double-cuff versus single-cuff bronchial blockers for video-assisted thoracoscopic lobectomy: A randomized controlled trial
BACKGROUND: Bronchial blockers (BBs) manage airways during thoracoscopic lobectomy and isolate lungs by occluding the bronchus at the surgical site. However, intraoperative malpositioning remains a concern. We compared the performance of a new double-cuff BB (DcBB) with an additional cuff near the end of a single-cuff BB (ScBB) with that of ScBBs during thoracoscopic lobectomy. METHODS: This single-center, randomized, parallel, controlled clinical study enrolled 80 patients undergoing thoracoscopic lobectomy for lung cancer at Nanpi People's Hospital. The patients were randomized into two groups (n = 40 each); DcBB (DcBB used during one-lung ventilation) and ScBB (ScBB used during one-lung ventilation). The primary outcomes were the incidence and number of BB malpositioning. Secondary outcomes time for BB placement and positioning, surgical duration, hypoxemia, incidence of adverse cardiovascular events, grades of lung collapse, surgeon satisfaction, tracheal wall damage assessed during bronchoscopy, contamination rates of the non-surgical lung lobe on the surgical site determined by bronchoscopy, radiographic incidence of pulmonary infiltration on postoperative day 1, and intraoperative blood gas values. RESULTS: The incidence of malpositioning was significantly lower in the DcBB than the ScBB group (7.5% vs. 30%, P = 0.02). The incidence of malposition was significantly lower in the DcBB cohort (P = 0.002). However, positioning the DcBB required more time (32.28 ± 5.37 vs. 19.90 ± 4.16 sec, P < 0.001). Other secondary outcomes did not differ significantly. CONCLUSIONS: In patients undergoing thoracoscopic lobectomy, the DcBB was associated with a lower incidence of malposition than the ScBB. The DcBB did not increase tracheal wall injury or cause significant adverse hemodynamic effects, and therefore may serve as a promising optional device for airway management during thoracoscopic lobectomy, particularly in clinical scenarios requiring high placement stability. TRIAL REGISTRATION: the Chinese Clinical Trial Registry ChiCTR2400086472.
22 May 2026
Read appraisal →Clinical cancer research : an official journal of the American Association for Cancer Research
PET/CT-Guided Neoadjuvant Tislelizumab plus Chemotherapy/Chemoradiotherapy for Resectable Esophageal Squamous Cell Carcinoma: RATIONALE-213 Final Analysis
PURPOSE: The aim of this study is to assess positron emission tomography/computed tomography (PET/CT)-guided neoadjuvant treatment with tislelizumab plus chemotherapy/chemoradiotherapy in patients with resectable esophageal squamous cell carcinoma (ESCC). PATIENTS AND METHODS: RATIONALE-213, a multicenter, open-label, two-cohort phase II study, enrolled 70 patients with resectable ESCC. After one induction chemotherapy cycle, patients were categorized as PET responders (PET maximum standardized uptake value decrease ≥35%) or PET nonresponders (<35%). Subsequently, all patients received three cycles of tislelizumab 200 mg intravenously. In addition, PET responders received chemotherapy and PET nonresponders received chemoradiotherapy as neoadjuvant treatment followed by surgery. The primary endpoint was the pathologic complete response (pCR) rate. RESULTS: As of October 25, 2024 (median follow-up 25.5 months), pCR rates were 30% [95% confidence interval (CI), 11.9-54.3] in PET responders and 34.4% (95% CI, 18.6-53.2) in PET nonresponders. Higher pCR rates were associated with higher baseline programmed cell death ligand 1 tumor area positivity scores in both cohorts. One-year disease-free survival rates were 79% and 74.2%, and event-free survival rates were 87.1% and 67.8%, respectively. Any-grade and grade ≥3 treatment-related adverse events (TRAE) occurred in 93.3% and 50% of PET responders and 97.5% and 82.5% of PET nonresponders, with no new safety signals. The most common grade ≥3 TRAE was decreased neutrophil count (36.7% and 70%, respectively). CONCLUSIONS: Tislelizumab with chemotherapy/chemoradiotherapy as neoadjuvant treatment for resectable ESCC yielded promising pCR rates and favorable survival outcomes with a tolerable safety profile in both PET/CT-guided responders and PET nonresponders.
18 May 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Yield and safety of different biopsy types in interstitial lung disease: a systematic review and meta-analysis
BACKGROUND: Lung biopsy remains an important consideration in the management of interstitial lung disease (ILD). Transbronchial lung cryobiopsy (TBLC) offers an alternative to traditional surgical lung biopsy (SLB) and transbronchial forceps biopsy (TBB); however, up-to-date comparisons between these methods in ILD, particularly fibrotic ILD, remain limited. METHODS: A comprehensive literature search of Medline, Embase and Evidence-Based Medicine Reviews was performed for studies published between January 2000 and September 2025 to identify all citations reporting yield and complications of the three main lung biopsy methods for ILD. RESULTS: A total of 143 studies were included. Pooled multidisciplinary yield (following multidisciplinary discussion) in TBB, TBLC and SLB was 35.3% (95% CI 21.3-52.5), 84.3% (95% CI 81.7-86.5) and 88.6% (95% CI 83.4-92.3), respectively. For fibrotic ILD, the multidisciplinary yield was 12.5% (only one eligible study), 87.6% (95% CI 83.5-90.7) and 87.3% (95%CI 80.5-92.0), respectively. Meta-regression showed an increasing multidisciplinary yield of TBLC with more recent years of patient recruitment and an increasing percentage of fibrotic ILD in each study. The multidisciplinary yield of both TBLC and SLB was 85-90%, suggesting a biopsy "ceiling effect". All evaluated complications were more frequent in TBLC compared to TBB and some were more frequent in SLB compared to TBLC. Several complications were more frequent in fibrotic ILD compared to all ILD. CONCLUSIONS: The multidisciplinary yield of TBLC and SLB is equivalent, with both offering an acceptable safety profile. TBB has low yield, particularly in fibrotic ILD. These findings support using either TBLC or SLB as an initial diagnostic tool in fibrotic ILD, mainly based on patient-physician shared decision-making.
15 May 2026
Read appraisal →Japanese journal of clinical oncology
Impact of intensity-modulated radiotherapy on survival and pulmonary toxicities for localized esophageal squamous cell carcinoma
OBJECTIVE: Definitive chemoradiotherapy (CRT) is a treatment strategy for localized esophageal squamous cell carcinoma (ESCC). Herein, we aimed to evaluate clinical outcomes of definitive CRT for ESCC. METHODS: We reviewed 127 patients who received definitive CRT for localized ESCC at our institution between January 2004 and December 2022. All patients received elective nodal irradiation with concurrent chemotherapy, primarily comprising cisplatin and 5-fluorouracil, during radiotherapy. Seventeen patients (13%) received intensity-modulated radiation therapy (IMRT) only, and 16 patients (13%) were treated with IMRT as a boost. The median total dose was 61.4 Gy. Approximately 80% of the patients had clinical stage III or higher disease. We analyzed overall survival (OS), progression-free survival (PFS), locoregional recurrence rate (LRR), prognostic factors, and adverse events. RESULTS: The median follow-up period was 13 months for all patients and 22 months for survivors. The 2-year OS, PFS, and LRR were 40.4%, 27.1%, and 30.8%, respectively. The overall complete response rate was 40.2%. On multivariate analysis, clinical stage 0-III (non-T4) (P < .001) and the use of IMRT (P = .034) were significantly associated with better OS. Pulmonary toxicity was significantly lower in the IMRT group (P = .049). CONCLUSIONS: IMRT for localized ESCC may improve prognosis and reduce pulmonary toxicity.
12 May 2026
Read appraisal →Annals of surgical oncology
CT-based Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma ≤ 3 cm: Enhancing Deep Learning Specificity by Waiving Chest Wall Information
BACKGROUND: Accurate preoperative prediction of visceral pleural invasion (VPI) in lung adenocarcinoma is essential for guiding surgical decision-making. However, existing prediction models often sacrifice specificity when optimized for high sensitivity, increasing the risk of overtreatment. This study aimed to develop a computed tomography (CT)-based deep learning (DL) model that improves specificity by excluding chest wall information. METHODS: We retrospectively enrolled 835 patients with pathologically confirmed lung adenocarcinoma who underwent complete resection at two medical centers. A VPI-DL model was developed using a four-layer convolutional neural network incorporating a novel attention mechanism trained on chest-wall-masked CT inputs. The model was trained on 692 cases and externally validated on an independent cohort of 143 patients. Performance was benchmarked against the consolidation-to-tumor ratio (CTR), a published DL model, and assessments by three thoracic surgeons. Evaluation metrics included area under the curve (AUC), sensitivity, specificity, and accuracy under a high-sensitivity operating threshold. RESULTS: In external validation, VPI-DL achieved an AUC of 0.91, sensitivity of 91%, specificity of 82%, and accuracy of 83%, outperforming the CTR (specificity 63%), the previously published model (specificity 54%), and thoracic surgeons (specificity 57%) at comparable sensitivity levels. The attention-guided architecture effectively reduced spurious correlations and improved interpretability. CONCLUSION: The proposed VPI-DL model improves the specificity of VPI prediction while preserving high sensitivity. By intentionally excluding chest wall information, the model offers a robust and interpretable tool to aid preoperative planning and minimize the risk of both under- and overtreatment in early-stage lung adenocarcinoma.
6 May 2026
Read appraisal →Journal of vascular and interventional radiology : JVIR
A Deep Learning Model for Artery of Adamkiewicz Detection in Bronchial Artery Embolization: A Multicenter Retrospective Study
PURPOSE: To evaluate the effectiveness of a deep learning model for recognizing the artery of Adamkiewicz and anterior spinal artery (ASA) to prevent spinal artery non-target embolization during bronchial artery embolization (BAE). MATERIALS AND METHODS: This multicenter, retrospective study included 2036 patients from January 2019 to December 2023 with hemoptysis who underwent de novo BAE. A deep learning-based framework was proposed for spinal artery identification, comprising region of interest (ROI) perception and target spinal artery identification. The ROI perception extracted vessel-related regions to improve the conspicuity of the spinal artery. The target spinal artery identification utilized a progressive refinement learning network, localizing the artery from the global view, and progressively refined the identification results through cross-scale information interaction. RESULTS: Seventy-eight patients (3.8%) had an identifiable artery of Adamkiewicz and ASA on right intercostal-bronchial artery angiography. The sensitivity of the proposed method was 92.1% and the specificity was 84.6%, with no statistically significant difference from a fellow radiologist interpretation. CONCLUSIONS: The deep learning system for spinal artery detection during BAE exhibited high sensitivity and performance, comparable to radiology fellows.
4 May 2026
Read appraisal →Annals of surgical oncology
Computed Tomography-Pathology Deep Learning Model for the Precise Prediction of Recurrence in Pathological Stage IA Lung Adenocarcinoma
BACKGROUND: The postoperative prognosis of pathological stage IA lung adenocarcinoma (LUAD) exhibits significant heterogeneity. While the tumor node metastasis (TNM) staging system offers limited recurrence prediction capability, this study aims to develop a precise deep learning model for prognostic stratification. PATIENTS AND METHODS: We retrospectively analyzed a consecutive cohort of patients with pathological stage IA LUAD who underwent surgical resection at Zhongshan Hospital Fudan University. Our novel ResNet 3D-Pathology Fusion (Res3D-PF) model-integrating a three-dimensional ResNet backbone with an image-pathology fusion module-was developed to predict recurrence-free survival (RFS) using preoperative computed tomography (CT) images and International Association for the Study of Lung Cancer (IASLC) grading. Model performance was evaluated through receiver operating characteristic curve analysis, with independent RFS predictors identified via multivariable Cox regression. RESULTS: Among 551 patients with stage IA LUAD (median age 61 years; 339 women) divided into training (n = 368) and validation (n = 183) sets, the CT-pathology fusion model achieved superior predictive performance. In the validation cohort, Res3D-PF significantly outperformed the 8th T-stage (AUC 0.837 vs. 0.660, p = 0.001) and IASLC grade (AUC 0.837 vs. 0.684, p = 0.015) for 5-year RFS prediction. Multivariable analysis confirmed Res3D-PF as an independent prognostic factor (HR 15.772, 95% CI 3.384-73.508; p < 0.001). Model-stratified high-risk patients demonstrated significantly reduced 5-year RFS (73.1% vs. low-risk 98.5%, p < 0.001) and shorter median RFS (74.4 vs. 96.2 months, p < 0.001). CONCLUSIONS: We developed and validated a CT-pathology deep learning model that outperforms conventional TNM staging and IASLC grading for predicting postoperative recurrence in stage IA LUAD. This approach enables individualized risk stratification to guide precision treatment strategies.
4 May 2026
Read appraisal →PloS one
Deep feature optimization using fusion of multiple self-supervised learning approaches and filter-based feature selection for lung cancer histopathology classification
One of the most deadly illnesses in the world is lung cancer, and increasing survival rates require early detection. Lung cancer diagnostics from the imaging modalities is always subjective, and this paves the way for deep learning assisted computer aided techniques. Still, the accuracy of such a technique is the major concern. This research work attempts to enhance lung cancer diagnostics from histopathological images using a previously unaddressed combination of multiple self-supervised learning techniques, filter-based feature selection, and Vision Graph Convolutional Networks. The main contribution lies in optimized feature fusion, and it brings complementary strengths of three different self-supervised learning approaches- contrastive alignment, redundancy reduction, and semantic grouping. The first step involves extracting the key features from histopathological images using a custom Convolutional Neural Network. Three complementary self-supervised learning methods - Deep Cluster, Bootstrap Your Own Latent, and Simple Framework for Contrastive Learning of Visual Representations - are then used to refine each of these features separately. Following optimization, the improved features are combined, and the most significant features from the combined set are found and preserved using a filter-based feature selection technique called Minimum Redundancy Maximum Relevance. Vision Graph Convolutional Neural Network is used as a classifier. Initial experiments are carried out on the 691 histopathological images extracted from the publicly available LungHist700 dataset. This dataset contains histopathological images under three categories: 151 normal subjects, 280 lung adenocarcinoma subjects, and 260 lung squamous cell carcinoma subjects. The proposed approach provided a balanced accuracy of 97% while the plain Vision Graph Convolution Neural Network offers only an 86% balanced accuracy score. Further validation is performed using two more publicly available datasets, namely LC25000 and TCGA UT datasets. The experimental results demonstrate the enhanced lung cancer prediction performance of the proposed approach in all three datasets.
2 May 2026
Read appraisal →The Cochrane database of systematic reviews
Lung transplant in people with cystic fibrosis and nontuberculous mycobacteria infection
RATIONALE: Cystic fibrosis (CF) is an inherited multi-organ disorder. People with CF (pwCF) experience recurrent and chronic lung infections and a progressive loss of lung function. PwCF with poor and rapidly declining lung function may be considered for lung transplantation (LTx), which may improve their quality of life and survival. Nontuberculous mycobacteria (NTM) can cause pulmonary disease in pwCF, and NTM infection is a poor prognostic factor in LTx. Guidelines recommend NTM infection should not automatically preclude LTx. It is important to evaluate the evidence base for LTx in pwCF and NTM pulmonary disease. OBJECTIVES: To evaluate clinical outcomes in pwCF and with NTM infection (NTM infection alone or with NTM pulmonary disease) who undergo LTx by comparing: 1. pwCF with current NTM lung infection who undergo LTx versus those with NTM infection who do not undergo LTX; 2. pwCF with current NTM lung infection who undergo LTx versus those without NTM undergoing LTx. SEARCH METHODS: We searched the Cochrane Cystic Fibrosis Trials Register, CENTRAL, MEDLINE, Embase, and PubMed as well as two ongoing trials registries. We checked references. The latest search date was 17 February 2026. ELIGIBILITY CRITERIA: We considered non-randomised studies of pwCF (any age) with or without NTM lung infection or disease being considered for LTx as well as studies of pwCF and NTM who either did or did not undergo LTx. OUTCOMES: Our critical outcomes were mortality, disseminated NTM infection post-LTx, time to chronic lung allograft dysfunction (CLAD), and quality of life at any time points reported. We additionally planned to report lung function, hospitalisations for pulmonary exacerbations, and nutritional parameters in the review. RISK OF BIAS: We assessed the risk of bias in three studies using ROBINS-I and in one study using the Joanna Briggs Institute checklist for case series. SYNTHESIS METHODS: We could only report results narratively. We used GRADE to assess the certainty of the evidence. INCLUDED STUDIES: We included four single-centre retrospective studies (388 adults). Sample sizes ranged from nine to 177 participants. Mycobacteria abscessus was the most common NTM species identified, and all studies reported infection with other pathogens. All studies compared pwCF and NTM infection to pwCF without NTM infection, all undergoing LTx. Each study reported mortality and disseminated NTM infection post-LTx; two studies recorded CLAD. No study reported quality of life, specific lung function measures (although one study commented briefly on lung function in general), hospitalisations for pulmonary exacerbations, or nutritional parameters. SYNTHESIS OF RESULTS: We analysed all NTM infections together for practical reasons and were not able to undertake a planned subgroup analysis by subspecies, but acknowledge that the prognosis and clinical trajectory of pwCF infected with different NTM may not be similar. We downgraded the certainty of the evidence due to non-randomised study design and serious risk of bias across all studies. We assessed all identified evidence as of very low certainty, such that lung transplant may have little to no effect on any of the outcomes listed below, but the evidence is very uncertain. Mortality Two studies (18 participants with NTM) reported similar survival data between NTM-positive LTx recipients and matched controls without NTM. Another study (9 participants) reported that two of five participants NTM-positive at LTx died within a few months post-LTx, whilst one of four NTM-negative participants died three years post-LTx due to chronic rejection. One study (177 participants) found that pwCF who had positive NTM cultures pre-LTx had a longer median survival duration than those who had negative cultures. This study additionally reported on survival of participants with post-LTx NTM infection, finding that the five participants who had post-LTx NTM disease had a longer mean survival duration than the 141 participants without post-LTx NTM disease. Disseminated NTM infection post-LTx In the largest study, of the 18 pwCF with NTM at the time of LTx, seven had at least one positive NTM culture, and four developed NTM disease post-LTx. Conversely, 79 of the 89 pwCF without NTM remained so post-LTx; 10 participants recorded a positive NTM culture, but none developed NTM disease. For the 39 participants without a baseline NTM culture, three participants recorded positive NTM cultures post-LTx, and one developed NTM disease. Of the remaining small studies, one reported that NTM was isolated in four of 13 participants at LTx and in three of these post-LTx. A second study reported that one out of five pwCF had NTM infection post-LTx (all were positive at LTx). The third study reported that five out of nine participants had NTM disease at LTx, and two of these five remained NTM-positive post-LTx. CLAD Two studies assessed CLAD. One study reported that none of the five NTM-positive LTx recipients developed CLAD, stating that the risk of CLAD appeared to be similar between the NTM and the comparator group. The second study stated that three out of nine LTx recipients with NTM disease developed chronic rejection or graft dysfunction. AUTHORS' CONCLUSIONS: There are no randomised trials to guide clinicians and patients or their families when making decisions regarding LTx in pwCF with NTM. The available data come from observational studies and registry data, often with few people with NTM reported. It has not been possible to pool the available data in meta-analysis, and we are very uncertain of the effect of NTM on pwCF undergoing LTx on the risk of developing NTM disease post-LTx, survival after LTx, and the development of CLAD. The studies were small and at times contradictory. In the era of highly effective modulator treatments, as some centres do not offer LTx to people with a history of NTM, there is an urgent need for more data to guide decision-making. FUNDING: This review is part of a suite of reviews on NTM funded jointly by the CF Foundation and the CF Trust. REGISTRATION: Protocol registration (2024): www.crd.york.ac.uk/PROSPERO/view/562682.
23 Apr 2026
Read appraisal →Thorax
Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning.
RATIONALE: Despite significant advances in patient care and outcomes, criteria for cardiopulmonary exercise testing (CPET) in risk stratification guidelines for lung resection have not been updated in over a decade. We hypothesised that CPET no longer holds additional predictive value for postoperative complications. METHODS: In this secondary analysis, we included lung resection candidates from two prospective, multicentre studies eligible for CPET and assessed with preoperative pulmonary function tests (PFTs) and arterial blood gas analysis. Postoperative pulmonary (PPCs) and cardiovascular complications (PCCs) were documented during hospitalisation. We trained five types of machine learning models applying nested cross-validation to predict complications and compared predictive performance based on four metrics, including area under the receiver operating characteristic curve (AUC-ROC). RESULTS: A total of 497 patients were included. PPCs developed in 71 (14%) patients. Adding CPET parameters to PFTs and baseline clinical data did not improve the ability of models to predict PPCs in unselected patients (AUC-ROC=0.72-0.78; p=0.47), nor in those meeting American College of Chest Physicians (ACCPs) (n=236; AUC-ROC=0.64-0.78; p=0.70) or European Respiratory Society/European Society of Thoracic Surgery (ERS/ESTS) criteria (n=168; AUC-ROC=0.59-0.76; p=0.92). PCCs developed in 90 (18%) patients. CPET parameters likewise did not improve model performance for the prediction of PCCs in unselected patients (AUC-ROC=0.65-0.73; p=0.96), nor in the ACCP (AUC-ROC=0.61-0.73; p=0.82) or ERS/ESTS subgroups (AUC-ROC=0.62-0.69; p=0.87). CONCLUSIONS: In contemporary surgical practice, CPET did not improve the predictive performance of machine learning models for PPCs or PCCs in patients with an indication based on established guidelines or in those without. The role of CPET in preoperative risk stratification for lung resection should be re-evaluated. TRIAL REGISTRATION NUMBER: NCT03498352, NCT04826575.
17 Apr 2026
Read appraisal →PloS one
LungNet: Leveraging state-space models with SE-enhanced skip connections for precise CT-based lung lesion segmentation
Lung cancer, which accounted for 2.48 million new cases and 1.82 million deaths worldwide in 2022, continues to be the most lethal cancer across the globe, underscoring the urgent demand for more advanced diagnostic tools. Although computed tomography (CT) imaging has long been central to lung cancer detection, the heterogeneous and complex characteristics of lung lesions make accurate segmentation particularly challenging. Current deep learning methods face a critical bottleneck: convolutional neural networks (CNNs) often struggle to capture long-range dependencies due to limited receptive fields, while Transformer-based architectures incur prohibitive computational costs when processing high-resolution CT volumes. Furthermore, standard skip connections in traditional UNet models frequently introduce redundant noise, leading to the dilution of subtle lesion features. To address these specific technical gaps, we introduce a novel deep learning framework that integrates Mamba state-space models with an improved UNet architecture. In this design, to mitigate feature redundancy, Squeeze-and-Excitation networks are embedded into skip connections, while auxiliary losses are introduced to address the degradation of shallow features and capture fine-grained lesion features across varied morphologies. Such a framework not only accommodates the intricate differences in lesion size, shape, and spatial distribution but also achieves a balance between global context modeling and linear computational efficiency. By uniting the local feature extraction strengths of convolutional layers with the long-range dependency modeling power of state-space models, our approach achieves more precise delineation of lung lesion boundaries. Extensive experiments conducted on multiple datasets provide compelling evidence of the method's effectiveness: it attains state-of-the-art segmentation accuracy and demonstrates significant promise for enhancing early detection, ongoing disease monitoring, and treatment planning in lung cancer patients. This advancement delivers a robust solution for the inherently complex task of lung lesion segmentation. Moreover, because lung cancer treatment is costly and insurance coverage plays a decisive role in distributing expenses, the study's outcomes also carry considerable implications for the insurance sector.
17 Apr 2026
Read appraisal →Scientific reports
Research on lung nodule detection in X-ray plain films based on improved YOLOv12 model
To improve automatic lung nodule detection in chest X-ray images, this study proposes an improved YOLOv12-based detection framework by integrating space-to-depth convolution (SPDConv), a dynamic upsampling module (DySample), and a lightweight feature aggregation module (VoVGSCSP). SPDConv enhances spatial information preservation during feature extraction, DySample replaces conventional upsampling to improve multi-scale feature fusion, and VoVGSCSP strengthens feature representation while reducing computational redundancy. The optimized YOLOv12-DSV model was trained and evaluated using a publicly available chest X-ray dataset with annotated lung nodules from the Roboflow platform, with performance assessed through five-fold cross-validation and external testing. Experimental results show that the proposed model achieved an mAP50 of 0.735 and an mAP50-95 of 0.426, outperforming the original YOLOv12 model (mAP50: 0.704; mAP50-95: 0.411). In addition, the proposed model reduced the number of parameters from 2.52 to 2.21 M, decreased FLOPs from 6.0 to 5.2 G, and increased inference speed from 97.6 to 107.8 FPS. These results indicate that the proposed YOLOv12-DSV model improves detection accuracy while reducing computational cost, achieving a more favorable balance between detection performance and model complexity for lung nodule localization in chest X-ray images.
10 Apr 2026
Read appraisal →BMJ open respiratory research
Associations between respiratory diseases and lung cancer risk: a secondary analysis of the large-scale prospective UK biobank cohort
INTRODUCTION: Respiratory diseases are significant risk factors for lung cancer; however, the association between acute respiratory infections and lung cancer incidence requires further exploration. METHODS: We performed a secondary analysis of the prospective UK Biobank cohort, including participants aged 37-73 years recruited from 22 assessment centres across the UK between 2006 and 2010. Cox proportional hazards models estimated HRs for incident lung cancer according to respiratory disease status, which was defined based on linked hospital inpatient records. Mediation analysis explored potential biomarkers, and Mendelian randomisation assessed causal relationships. RESULTS: During a mean follow-up of 10.44 years (4 790 738 person-years), 2189 participants developed lung cancer. Among 107 007 individuals with respiratory diseases, 1322 cases occurred (incidence rate 27.6 per 10 000 person-years), compared with 867 cases among 351 876 participants without respiratory diseases (7.9 per 10 000 person-years). Overall, respiratory diseases were associated with increased lung cancer risk (HR 2.97, 95% CI 2.75 to 3.21). Acute respiratory infections, including acute nasopharyngitis (HR 3.41; 95% CI 1.83 to 6.34), influenza (HR 3.90; 95% CI 2.53 to 6.01), viral pneumonia (HR 9.86; 95% CI 6.55 to 14.85) and bacterial pneumonia (HR 6.28; 95% CI 4.40 to 8.96), showed strong associations with lung cancer incidence. In subtype analyses, squamous cell carcinoma exhibited the highest risk elevation (HR 3.65; 95% CI 3.06 to 4.36). Mediation analysis indicated that neutrophil counts partially mediated these associations (proportion mediated up to 8%). CONCLUSION: Acute respiratory infections were associated with higher lung cancer incidence, providing hypothesis-generating evidence that may inform future risk stratification research.
5 Apr 2026
Read appraisal →Medicine
Effectiveness of mindfulness-based stress reduction in managing fatigue, anxiety, and depression among non-small cell lung cancer patients receiving surgery and adjuvant chemotherapy: A randomized controlled trial
BACKGROUND: Non-small cell lung cancer (NSCLC) patients undergoing surgery and adjuvant chemotherapy often experience debilitating physical and psychological symptoms, including cancer-related fatigue, anxiety, and depression. Mindfulness-based stress reduction (MBSR) has emerged as a complementary intervention to alleviate these burdens and enhance quality of life, but evidence in NSCLC populations remains limited. METHODS: This randomized controlled trial enrolled 80 NSCLC patients, evenly divided into an MBSR group and a Control group. The MBSR group underwent an 8-week mindfulness program, while the Control group received standard care. Outcomes, including fatigue (Piper Fatigue Scale), anxiety (Self-Rating Anxiety Scale), depression (Self-Rating Depression Scale), self-efficacy (General Self-Efficacy Scale), and mindfulness awareness (Mindful Attention Awareness Scale), were assessed at 4 time points: baseline (before surgery), at the fourth week (before chemotherapy), and at 1 and 3 months post-intervention. Statistical analyses included repeated-measures ANOVA and t tests to evaluate group differences. RESULTS: The MBSR group demonstrated significant improvements across all outcomes compared to the Control group. Fatigue levels in the MBSR group peaked at the fourth week but returned close to baseline levels by 3 months post-intervention, while the Control group maintained elevated fatigue scores (P < .05). Anxiety (Self-Rating Anxiety Scale) and depression (Self-Rating Depression Scale) scores significantly decreased in the MBSR group by the fourth week and continued to improve at subsequent time points (P < .01). Self-efficacy (General Self-Efficacy Scale) and mindfulness awareness (Mindful Attention Awareness Scale) showed consistent improvements in the MBSR group, with significant differences evident at 1 and 3 months post-intervention (P < .01). CONCLUSIONS: Mindfulness-based stress reduction effectively reduced fatigue, anxiety, and depression while enhancing self-efficacy and mindfulness awareness in NSCLC patients undergoing surgery and chemotherapy. These findings support the integration of mindfulness-based interventions into routine care to improve patient well-being during and after treatment.
5 Apr 2026
Read appraisal →The European respiratory journal
A European multicentre, randomised controlled trial of pirfenidone in bronchiolitis obliterans syndrome after bilateral lung transplantation
BACKGROUND: Chronic lung allograft dysfunction (CLAD) is a major obstacle to improving outcomes after lung transplantation. Bronchiolitis obliterans syndrome (BOS), characterised by progressive decline in forced expiratory volume in 1 s (FEV1) due to fibrotic scarring of the small airways, accounts for most CLAD cases. Pirfenidone, an antifibrotic agent used for idiopathic pulmonary fibrosis, was assessed for treating progressive BOS. METHODS: An investigator-initiated, international, multicentre, randomised, double-blind, placebo-controlled phase II trial was conducted in nine European lung transplant centres. Adults with bilateral lung transplants and progressive BOS were randomised (1:1) to receive pirfenidone 2403 mg·day-1 or placebo with standard care for 26 weeks. The primary end-point was change in FEV1 from baseline to week 26, with imputation for missing values. FINDINGS: From 1 May 2015 to 1 December 2019, 477 patients were screened, and 90 were randomised to pirfenidone (n=48) or placebo (n=42). Both groups showed continued decline in FEV1 from baseline to week 26, with no significant difference in intention to treat (ITT), ITT with imputation, or per-protocol analyses. Secondary end-points (graft loss, death, re-transplantation) were similar between groups. Treatment-related serious adverse events were distributed equally. INTERPRETATION: Pirfenidone did not show superiority over placebo and standard care in this exploratory trial. It cannot be recommended for treating BOS. Further research is needed to explore other treatments for CLAD to improve long-term outcomes after lung transplantation.
4 Apr 2026
Read appraisal →European radiology
Predictive value of artificial intelligence-based quantitative CT feature analysis for diagnosing the pathological types of pulmonary nodules
OBJECTIVES: Accurate preoperative classification of pulmonary nodules (PNs) is critical for guiding clinical decision-making and preventing overtreatment. This study aims to evaluate the predictive performance of artificial intelligence (AI)-based quantitative computed tomography (CT) feature analysis in differentiating among four pathological types of PNs: atypical adenomatous hyperplasia and adenocarcinoma in situ (AAH + AIS), minimally invasive adenocarcinoma (MIA), invasive adenocarcinoma (IAC), and lung inflammatory nodules (IN). MATERIALS AND METHODS: A total of 462 pathologically confirmed PNs were analyzed. Radiomic features, including CT attenuation metrics, 3D morphometrics, and texture parameters such as entropy and skewness, were extracted using a deep learning-based AI platform. Logistic regression models were constructed using both single- and multi-variable strategies to evaluate the classification accuracy of these features. Moreover, the inclusion of IN as a separate category significantly enhanced the clinical utility of AI in differentiating benign mimickers from malignant nodules. The combined model, which integrated AI-derived features with traditional CT signs, was used to assess the diagnostic performance of the radiomic features in differentiating the four pathological types of nodules. RESULTS: The combined model demonstrated superior diagnostic performance, with area under the curve (AUC) values of 0.936 for IAC, 0.884 for AAH + AIS, and 0.865 for IN. Although MIA showed lower classification accuracy (AUC = 0.707), key features such as entropy, solid component ratio, and total volume effectively distinguished invasive from non-invasive lesions. CONCLUSION: These findings highlight the potential of AI-enhanced radiomics for supporting non-invasive, objective, and individualized diagnosis of PNs. KEY POINTS: Question Can artificial intelligence (AI)-based quantitative CT analysis reliably differentiate benign inflammatory nodules from the spectrum of lung adenocarcinoma subtypes, a common diagnostic challenge? Findings An integrated model combining AI-driven radiomic features and traditional CT signs demonstrated high accuracy in differentiating invasive adenocarcinoma (AUC = 0.936), pre-invasive lesions (AUC = 0.884), and inflammatory nodules (AUC = 0.865). Clinical relevance AI-enhanced radiomics provides a non-invasive, objective tool to improve preoperative risk stratification of pulmonary nodules, potentially guiding personalized management and reducing unnecessary surgeries for benign inflammatory lesions that mimic malignancy.
4 Apr 2026
Read appraisal →