Ongoing advances in precision cancer therapy have increased the number of molecularly targeted and immuno-oncology agents for a variety of cancers, many of which have been associated with a risk of pulmonary complications, among the most concerning being drug-induced interstitial lung disease/pneumonitis (DI-ILD). As the number of patients undergoing treatment with novel anticancer agents continues to grow, DI-ILD is expected to become an increasingly significant clinical challenge. Trastuzumab deruxtecan (T-DXd) is an antibody–drug conjugate targeting human epidermal growth factor receptor 2 that is gaining widespread use in the metastatic breast cancer setting and is undergoing exploration for other oncologic indications. ILD/pneumonitis is an adverse event of special interest associated with T-DXd, which has potentially fatal consequences if left untreated and allowed to progress. When identified in the asymptomatic stage (grade 1), T-DXd-related ILD can be monitored and treated effectively with the possibility of treatment continuation. Delayed diagnosis and/or treatment, however, results in progression to grade 2 or higher toxicity and necessitates immediate and permanent discontinuation of this active agent. Strategies are, therefore, needed to optimize careful monitoring during treatment to ensure patient safety and optimize outcomes. Several guidance documents have been developed regarding strategies for the early identification and management of T-DXd-related ILD, although none have been within the context of the Canadian health care environment. A Canadian multidisciplinary steering committee was, therefore, convened to evaluate existing recommendations and adapt them for application in Canada. A multidisciplinary approach involving collaboration among medical oncologists, radiologists, respirologists, and allied health care professionals is needed to ensure the proactive identification and management of T-DXd-related ILD and DI-ILD associated with other agents with a similar toxicity profile.

Background: Chronic lung allograft dysfunction (CLAD) is the principal cause of graft failure in lung transplant recipients and prognosis depends on CLAD phenotype. We used a machine learning computed tomography (CT) lung texture analysis tool at CLAD diagnosis for phenotyping and prognostication compared with radiologist scoring.Methods: This retrospective study included all adult first double lung transplant patients (January 2010–December 2015) with CLAD (censored December 2019) and inspiratory CT near CLAD diagnosis. The machine learning tool quantified ground-glass opacity, reticulation, hyperlucent lung and pulmonary vessel volume (PVV). Two radiologists scored for ground-glass opacity, reticulation, consolidation, pleural effusion, air trapping and bronchiectasis. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance of machine learning and radiologist for CLAD phenotype. Multivariable Cox proportional hazards regression analysis for allograft survival controlled for age, sex, native lung disease, cytomegalovirus serostatus and CLAD phenotype.Results: 88 patients were included (57 bronchiolitis obliterans syndrome (BOS), 20 restrictive allograft syndrome (RAS)/mixed and 11 unclassified/undefined) with CT a median 9.5 days from CLAD onset. Radiologist and machine learning parameters phenotyped RAS/mixed with PVV as the strongest indicator (area under the curve (AUC) 0.85). Machine learning hyperlucent lung phenotyped BOS using only inspiratory CT (AUC 0.76). Radiologist and machine learning parameters predicted graft failure in the multivariable analysis, best with PVV (hazard ratio 1.23, 95% CI 1.05–1.44; p=0.01).Conclusions: Machine learning discriminated between CLAD phenotypes on CT. Both radiologist and machine learning scoring were associated with graft failure, independent of CLAD phenotype. PVV, unique to machine learning, was the strongest in phenotyping and prognostication.

Extent of fibrosis, defined by the amount of honeycombing and traction bronchiectasis, was consistently associated with death or lung transplant across all interstitial lung disease subtypes in a dose-dependent fashion.

Ex vivo lung perfusion (EVLP) enables advanced assessment of human lungs for transplant suitability. We developed a convolutional neural network (CNN)-based approach to analyze the largest cohort of isolated lung radiographs to date. CNNs were trained to process 1300 longitudinal radiographs from n = 650 clinical EVLP cases. Latent features were transformed into principal components (PC) and correlated with known radiographic findings. PCs were combined with physiological data to classify clinical outcomes: (1) recipient time to extubation of <72 h, (2) ≥ 72 h, and (3) lungs unsuitable for transplantation. The top PC was significantly correlated with infiltration (Spearman R: 0·72, p < 0·0001), and adding radiographic PCs significantly improved the discrimination for clinical outcomes (Accuracy: 73 vs 78%, p = 0·014). CNN-derived radiographic lung features therefore add substantial value to the current assessments. This approach can be adopted by EVLP centers worldwide to harness radiographic information without requiring real-time radiological expertise.