Guido Marchi

Dr. Guido Marchi

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 April 2025 in European Respiratory Review
Verified
Journal Article
Open access
Guido MarchiGuido Marchi
Guido Marchi
MMMattia Mercier
Mattia Mercier
JCJacopo Cefalo
Jacopo Cefalo
CSCarmine Salerni
Carmine Salerni
MFMartina Ferioli
Martina Ferioli
MMMichele Mondoni
Michele Mondoni
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.

1 January 2026 in Breathe
Verified
Journal Article
Open access
Guido MarchiGuido Marchi
Guido Marchi
Artificial intelligence (AI) is increasingly applied in respiratory medicine, offering potential advances in diagnostics, treatment guidance and patient monitoring. However, widespread clinical adoption remains limited due to the opaque “black-box” nature of many algorithms, which challenges clinicians’ trust and hinders integration into routine practice. Explainable AI (XAI; methods and frameworks that render AI outputs interpretable and transparent) has emerged as a promising approach. By providing insights into algorithmic reasoning alongside predictive performance, XAI can support clinician evaluation, facilitate informed decision-making, and enhance accountability in patient care. This Viewpoint discusses the potential applications of XAI across respiratory medicine, highlighting its role in improving transparency, fostering clinician engagement and supporting integration of AI into clinical workflows. Beyond technical considerations, successful adoption of XAI requires cultural and educational shifts, including training programmes, interdisciplinary collaboration, patient engagement, and adherence to ethical and regulatory standards. XAI also holds potential in supporting shared decision-making, translating complex algorithmic outputs into understandable information for patients. By bridging advanced computational tools with clinical reasoning, XAI may help respiratory medicine move towards responsible, patient-centred and transparent AI implementation. Continued research, education, and collaboration are essential to realise its potential and ensure AI serves as a reliable partner in delivering high-quality respiratory care.

18 March 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
Guido MarchiGuido Marchi
Guido Marchi
FCFederico Cucchiara
Federico Cucchiara
AGAlessio Gregori
Alessio Gregori
GBGiulia Biondi
Giulia Biondi
GGGiacomo Guglielmi
Giacomo Guglielmi
Laura CarrozziLaura Carrozzi
Laura Carrozzi
Non-expandable lung (NEL) occurs when the lung fails to fully re-expand after pleural fluid drainage, complicating management and limiting therapeutic options. Diagnosis, based on clinical symptoms, pleural manometry, and traditional imaging, is often delayed to the peri- or post-procedural stages, leading to improper management, complications, and higher healthcare costs. Therefore, early, pre-procedural diagnostic methods are needed. Thoracic ultrasound (TUS) has emerged as a non-invasive tool with the potential to enhance diagnostic accuracy and guide clinical decisions, yet, it remains inadequately studied within the context of NEL. We conducted a non-systematic narrative review using a structured methodology, including a comprehensive database search, predefined inclusion criteria, and QUADAS-2 quality assessment. This approach ensured a rigorous synthesis of evidence on TUS in NEL, with the aim of identifying knowledge gaps and guiding future studies. Non-invasive, real-time, bedside M-mode TUS has demonstrated efficacy in predicting NEL prior to thoracentesis by detecting an absent sinusoidal sign and reduced atelectatic lung movement. Emerging experimental techniques, including 2D shear wave elastography (SWE), speckle tracking imaging (STI) strain analysis, the lung/liver echogenicity (LLE) ratio, TUS assessment of dynamic air bronchograms, and pleural thickening evaluation, show additional potential to enhance pre-procedural NEL detection. However, all these methods have significant limitations that require further comprehensive investigation. Despite their significant promise, TUS modalities for early NEL detection still require rigorous validation and standardization before broad clinical use. A multimodal diagnostic approach, combining clinical manifestations, pleural manometry, radiologic and ultrasonographic findings, along with emerging techniques (once fully validated), may provide the most extensive framework for NEL. Regardless of advancements, patient-centered care and shared decision-making remain essential. Further research is needed to improve outcomes, reduce healthcare costs, and enhance long-term treatment strategies.

27 November 2025 in ERJ Open Research
Verified
Journal Article
Open access
Guido MarchiGuido Marchi
Guido Marchi
Salvatore Claudio FanniSalvatore Claudio Fanni
Salvatore Claudio Fanni
MMMattia Mercier
Mattia Mercier
JCJacopo Cefalo
Jacopo Cefalo
CSCarmine Salerni
Carmine Salerni
MMMichele Mondoni
Michele Mondoni
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.

1 July 2025 in Breathe
Verified
Journal Article
Open access
Guido MarchiGuido Marchi
Guido Marchi
Malignant pleural effusion (MPE) affects up to 15% of cancer patients, with nearly 30% of symptomatic cases developing non-expandable lung (NEL), a condition characterised by the lung's failure to fully re-expand post-drainage, thereby impeding proper pleural apposition and leading to several adverse outcomes. Inadequate diagnostic certainty leads to prolonged hospitalisation, repeated invasive procedures, drainage complications, high pleurodesis failure rates, increased healthcare costs and diminished patient quality of life. Conventional diagnostic methods, predominantly based on post-procedural chest radiography and computed tomography, frequently delay accurate diagnosis, underscoring the need for noninvasive pre-procedural techniques. Emerging evidence supports thoracic ultrasound, particularly the application of M-mode during breath-hold, as a promising modality for early NEL detection by identifying the absent sinusoidal sign and reduced lung movement. Experimental approaches, including speckle tracking imaging, two-dimensional shear wave elastography and quantitative ultrasound assessments via the lung/liver echogenicity ratio, also show potential, albeit with limitations that warrant further validation. Integration of artificial intelligence into multimodal imaging workflows may enhance diagnostic precision and predictive modelling, ultimately facilitating personalised therapeutic strategies and transforming the management of NEL in MPE. These innovations promise to reduce invasive diagnostics and healthcare costs while improving patient outcomes and quality of life in MPE-associated NEL.

1 October 2025 in Breathe
Verified
Journal Article
Open access
CCCarla Carvalho
Carla Carvalho
SHSaskia van Heumen
Saskia van Heumen
FFFaustina Funke
Faustina Funke
MHMarjolein A. Heuvelmans
Marjolein A. Heuvelmans
MSMariana Serino
Mariana Serino
MCMaria Joana Catarata
Maria Joana Catarata
The implementation of lung cancer screening with low-dose computed tomography has significantly increased the detection of pulmonary nodules, most of which are peripherally located and difficult to access. Effectively addressing these findings remains a clinical challenge, particularly in balancing diagnostic accuracy with procedural risk. Advances in interventional pulmonology have enabled minimally invasive approaches that may support both diagnosis and treatment, especially in selected patients with peripherally located nodules or limited surgical options. However, evidence on their effectiveness, accessibility and integration into screening workflows remains variable. In this review, we discuss the current role of interventional pulmonology in the context of lung cancer screening, outlining its potential benefits, limitations, and areas requiring further research to define its place within multidisciplinary care.