Adherence to medical therapies is a growing issue, so much so that the World Health Organization defined it as “a new pharmacological problem”. The main factors affecting compliance are: frequency of administration, rapid onset of action, role of device. The most severe consequence of non-adherence is the increased risk of poor clinical outcome, associated with worsening of the quality of life and increase in health-care expenditure. It appears crucial to identify those COPD patients who are “poorly or not at all compliant with their treatment”. In order to evaluate adherence to the medical therapy, several methods were proposed, the most effective of which turned out to be self-reports, i.e. simple, brief questionnaires (e.g. Morisky test). To increase the likelihood of quickly identifying non-compliant patients, it may be useful to administer a simple questionnaire to naïve subjects (for example, in the waiting room before an examination) including six specific items allowing to identify the patient’s key characteristics. Depending on the answers, patients who do not comply with their pharmacological treatment may be classified as belonging to 6 phenotypes. For patients who are already under treatment it might be useful to administer another short questionnaire during follow up examination. Once the risk of non-compliance is identified, four possible types of measures can be taken: prescription-related, educational, behavioral and complex combined measures (combination of two or more actions). Therefore, while it is clear that adherence in COPD is a critical issue, it is also obvious that raising awareness on the disease and improving cooperation among specialists, general practitioners, health-care professionals, and patients is the starting point at which this evolution should immediately begin. Each medication is able to foster good compliance with the therapy, and consequently to maximize the efficacy, by virtue of its specific inhaler and its own active ingredient.

Background: Pleural diseases represent a significant healthcare burden, affecting over 350 000 patients annually in the US alone and requiring accurate diagnostic approaches for optimal management. Traditional imaging techniques have limitations in differentiating various pleural disorders and invasive procedures are usually required for definitive diagnosis.Methods: We conducted a nonsystematic, narrative literature review aimed at describing the latest advances in imaging techniques and artificial intelligence (AI) applications in pleural diseases.Results: Novel ultrasound-based techniques, such as elastography and contrast-enhanced ultrasound, are described for their promising diagnostic accuracy in differentiating malignant from benign pleural lesions. Quantitative imaging techniques utilising pixel-density measurements to noninvasively distinguish exudative from transudative effusions are highlighted. AI algorithms, which have shown remarkable performance in pleural abnormality detection, malignant effusion characterisation and automated pleural fluid volume quantification, are also described. Finally, the role of deep-learning models in early complication detection and automated analysis of follow-up imaging studies is examined.Conclusions: Advanced imaging techniques and AI applications show promise in the management and follow-up of pleural diseases, improving diagnostic accuracy and reducing the need for invasive procedures. However, larger prospective studies are needed for validation. The integration of AI-driven imaging analysis with molecular and genomic data offers potential for personalised therapeutic strategies, although challenges in data privacy, algorithm transparency and clinical validation persist. This comprehensive approach may revolutionise pleural disease management, enhancing patient outcomes through more accurate, noninvasive diagnostic strategies.

Endobronchial ultrasound (EBUS) has revolutionized the field of bronchoscopy because it allows to observe peribronchial structures and distal peripheral lung lesions. The use of EBUS was first described by Hurte and Hanrath in 1992. EBUS technology exists in two forms: radial and convex transducer probes. The radial EBUS probe has a 20-MHZ (12-30 MHz available) rotating transducer that can be inserted together with or without a guide sheath through the working channel (2.0-2.8 mm) of a standard flexible bronchoscope. The transducer rotates and produces a 360-degree circular image around the central position of the probe. There are two types of radial EBUS probes: "peripheral" probes, used to identify parenchymal lung lesions, and "central" probes, with balloon sheaths, used for the assessment of airway walls and peribronchial lymph nodes.

Background: Drug-induced interstitial lung disease (DI-ILD) encompasses a heterogeneous spectrum of potentially severe pulmonary toxicities associated with various pharmacological agents. Diagnosis is often delayed due to nonspecific symptoms and imaging findings that can mimic other ILDs or infections, particularly in patients receiving oncological or immunomodulatory therapies. Novel approaches are needed to improve early recognition and management. Methods: We conducted a non-systematic, narrative literature review across major biomedical databases up to June 2025, aimed at describing current and emerging applications of artificial intelligence (AI) and radiomics in the early diagnosis, risk stratification, and personalised management of DI-ILD. Results: Radiomics applied to computed tomography and positron emission tomography/computed tomography enables extraction of high-dimensional quantitative features capturing subclinical alterations undetectable by visual assessment. In DI-ILD (particularly immune checkpoint inhibitor-related pneumonitis), radiomic models show potential diagnostic utility in distinguishing overlapping imaging patterns and predicting fibrotic progression. Integration with clinical, radiological and pharmacogenomic data has improved model performance in several studies. Additionally, AI approaches, including convolutional neural networks and ensemble learning methods, demonstrate promise in enhancing pattern recognition and risk stratification. Conclusions: Radiomics and AI are emerging complementary tools in multidisciplinary management of DI-ILD, offering objective imaging biomarkers and facilitating multimodal data integration to improve diagnostic precision and personalised therapeutic decisions. Nonetheless, reproducibility remains limited by variability in imaging protocols and lack of large-scale prospective multicentre validation. Clinical implementation requires standardised protocols to ensure consistency and reliability. The development of transparent, interpretable models seamlessly integrated into healthcare workflows is essential to fully leverage their real-world potential in proactive patient care.

Background/Objectives. To evaluate T&N-staging diagnostic performance of [68Ga]Ga-FAPI-46 PET/CT (FAPI) in a suspected/confirmed lung cancer surgical cohort. Methods: Patients were enrolled in a prospective monocentric trial (EudraCT: 2021-006570-23) to perform FAPI, in addition to conventional-staging-flow-chart (including [18F]F-FDG PET/CT-FDG). For the current purpose, only surgical patients were included. PET-semiquantitative parameters were measured for T&N: SUVmax, target-to-background-ratios (using mediastinal blood pool-MBP, liver-L and pulmonary-parenchyma-P). Visual and semiquantitative T&N PET/CT performances were analysed per patient and per region for both tracers, with surgical histopathology as standard-of-truth. Results: 63 FAPI scans were performed in 64 patients enrolled (26 May 2022–30 November 2023). A total of 50/63 patients underwent surgery and were included. Agreement (%) with histopathological-T&N-StagingAJCC8thEdition was slightly in favour of FAPI (T-66% vs. 58%, N-78% vs. 70%), increasing when T&N dichotomised (T-92% vs. 80%, N-78% vs. 72%). The performance of Visual-Criteria for T-per patient (n = 50) resulted higher FAPI than FDG. For N-per patient (n = 46), sensitivity and NPV were slightly lower with FAPI. Among 59 T-regions surgically examined, malignancy was excluded in 6/59 (10%). FAPI showed (vs. FDG): sensitivity 85% (vs. 72%), specificity 67% (vs. 50%), PPV 96% (vs. 93%), NPV 33% (vs. 17%), accuracy 83% (vs. 69%). Among 217 N-stations surgically assessed (overall 746 ln removed), only 15/217 (7%) resulted malignant; FAPI showed (vs. FDG): sensitivity 53% (vs. 60%), PPV 53% (vs. 26%), NPV 97% (vs. 97%), and significantly higher specificity (97% vs. 88%, p = 0.001) and accuracy (94% vs. 86%, p = 0.018). Semiquantitative-PET parameters performed similarly, better for N (p < 0.001) than for T, slightly in favour (although not significantly) of FAPI over FDG. Conclusions: In a suspected/confirmed lung cancer surgical cohort, PET/CT performances for preoperative T&Nstaging were slightly in favour of FAPI than FDG (except for suboptimal N-sensitivity), significantly better only for N (region-based) specificity and accuracy using visual assessment. The trial’s conventional follow-up is still ongoing; future analyses are pending, including non-surgical findings and theoretical impact on patient management.

The ability of high-definition (HD) videobronchoscopy to detect airway involvement in sarcoidosis has not been evaluated previously. What is the role of HD videobronchoscopy in the identification of sarcoidosis-associated airway abnormalities (AAs)? What are the patterns of AAs more commonly observed and more frequently associated with the detection of granulomas in endobronchial biopsy (EBB)? In this prospective international multicenter cohort study, consecutive patients with suspected sarcoidosis underwent airway inspection with an HD videobronchoscope and EBB using a standardized workflow. AAs were classified according to six patterns defined a priori: nodularity, cobblestoning, thickening, plaque, increased vascularity, and miscellaneous. We assessed diagnostic yield of EBB, prevalence of AAs, and interobserver agreement for different patterns of AAs. AAs were identified in 64 of 134 patients with sarcoidosis (47.8%), with nodularity (n = 23 [17.2%]), plaque (n = 19 [14.2%]), and increased vascularity (n = 19 [14.2%]) being the most prevalent. The diagnostic yield of EBB was 36.6%. AAs were significantly more prevalent in patients with than in those without nonnecrotizing granulomas on EBB (67.4% vs 36.5%; P = .001). Likewise, parenchymal disease on CT scan imaging was significantly more common in patients with than in those without nonnecrotizing granulomas on EBB (79.6% vs 54.1%; P = .003). On a per-lesion analysis, nonnecrotizing granulomas were seen especially in EBB samples obtained from areas of cobblestoning (9/10 [90%]) and nodularity (17/29 [58.6%]). The overall diagnostic yield of random EBB was low (31/134 [23.1%]). The interobserver agreement for the different patterns of AA was fair (Fleiss κ = 0.34). In a population with a large prevalence of White Europeans, HD videobronchoscopy detected AAs in approximately one-half of patients with sarcoidosis. The diagnostic yield of EBB was higher in patients with parenchymal involvement on CT scan imaging and in those with AAs, especially if manifesting as cobblestoning and nodularity. ClinicalTrials.gov; No.: NCT4743596; URL: www. gov.