近藤 征史

OBJECTIVES: To develop a comprehensive machine learning model incorporating various clinical factors, including frailty and comorbidities, to predict 30-day readmission and mortality risk in patients with chronic obstructive pulmonary disease (COPD). METHODS: This retrospective cohort study used electronic health records (EHR) from Fujita Health University Hospital (2004-2019) for 1294 patients with COPD and 3499 hospitalization or death events. The EHR contained longitudinal patient data (demographics, diagnoses, test results, clinical records). We developed two eXtreme Gradient Boosting models, the comprehensive Top64 and practical 11-feature models. We compared these with the Comorbidity, Obstruction, Dyspnea, and Previous Exacerbations index (CODEX) model, a widely used tool for predicting hospital readmission or death in patients with COPD. The area under the receiver operating characteristic curve (AUC) with 95% confidence interval (CI), sensitivity, and specificity were used to evaluate the model performance. RESULTS: The Top64 (AUC: 0.769, 95% CI: 0.747-0.791) and practical 11-feature (AUC: 0.746, 95% CI: 0.730-0.762) models performed better than the CODEX model (AUC: 0.587, 95% CI: 0.563-0.611). The Top64 model showed 0.978 sensitivity and 0.341 specificity, and the practical 11-feature model achieved 0.955 sensitivity and 0.361 specificity. The calibration curves showed good agreement between the observed and predicted results for both models. CONCLUSIONS: A machine learning approach based on clinical data readily available from the EHR performed better than existing models in predicting 30-day readmission and mortality risks in patients with COPD. A comprehensive risk prediction tool may enhance individualized care strategies and improve patient outcomes in COPD management.

BACKGROUND: Immune checkpoint inhibitors (ICIs) play a central role in cancer immunotherapy. However, the occurrence of immune-related adverse events, especially ICI-induced interstitial lung disease (ICI-ILD), is life-threatening and affects the effectiveness of ICI treatment. This study aimed to explore potential drugs to mitigate ICI-ILD occurrence using data from the Japanese Adverse Drug Event Report (JADER) and the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS [JAPIC AERS]). RESEARCH DESIGN AND METHODS: We investigated concomitant drugs that reduce ILD associated with four ICIs - nivolumab, pembrolizumab, atezolizumab, and durvalumab - across the JADER and FAERS databases. Subsequently, the identified common concomitant drugs that reduce the occurrence of ICI-ILD were detected and analyzed. RESULTS: We found omega-3 fatty acids, loperamide, and amlodipine as common concomitant drugs that reduced ICI-ILD occurrence in both the JADER and FAERS databases. Omega-3 fatty acids reportedly have many effects in animal models of drug-induced ILD, including their association with ILD in humans and anti-inflammatory effects against ICI-ILD. However, loperamide and amlodipine reportedly have minimal effects against ILD, thereby necessitating further evaluation. CONCLUSION: Omega-3 fatty acids have emerged as potential agents for reducing ICI-ILD occurrence, as evidenced by findings from two different pharmacovigilance databases.

Despite innovative advances in molecular targeted therapy, treatment strategies using immune checkpoint inhibitors (ICIs) for epidermal growth factor receptor (EGFR)-mutant non-small cell lung cancer (NSCLC) have not progressed significantly. Accumulating evidence suggests that ICI chemotherapy is inadequate in this population. Biomarkers of ICI therapy, such as programmed cell death ligand 1 (PD-L1) and tumor-infiltrating lymphocytes (TILs), are not biomarkers in patients with EGFR mutations, and the specificity of the tumor microenvironment has been suggested as the reason for this. Combination therapy with PD-L1 and cytotoxic T-lymphocyte-associated protein 4 (CTLA-4) inhibitors is a concern because of its severe toxicity and limited efficacy. However, early-stage NSCLC may differ from advanced-stage NSCLC. In this review, we comprehensively review the current evidence and summarize the potential of ICI therapy in patients with EGFR mutations after acquiring resistance to treatment with EGFR-tyrosine kinase inhibitors (TKIs) with no T790M mutation or whose disease has progressed on osimertinib.