近藤 征史

BACKGROUND: Cisplatin-induced nephrotoxicity (CIN) is a major dose-limiting adverse event that can lead to both acute and chronic kidney injury. The formation of thiol-cisplatin conjugates within renal tubular cells has been implicated as a key mechanism underlying CIN. Flopropione is an inhibitor of cysteine conjugate β-lyase 1, an enzyme that catalyzes the formation of the thiol-cisplatin conjugate, which might prevent CIN. OBJECTIVE: We designed a clinical trial to evaluate the safety of flopropione in patients receiving cisplatin-based chemotherapy and explore its efficacy in preventing CIN. METHODS: This is a phase 1 and 2a, single-center, randomized, open-label trial conducted in patients undergoing cisplatin therapy. Participants are randomized in a 5:2 ratio per cohort to receive either flopropione or no treatment. On the day of cisplatin administration, the flopropione group receives oral flopropione twice daily (80 mg in cohort 1, 160 mg in cohort 2, and 240 mg in cohort 3). On the following day, all cohorts receive 3 doses of 80 mg of oral flopropione. A step-up dose escalation design is adopted, progressing from cohort 1 to 3 after confirming safety at each level. The primary end point is the safety of flopropione use in combination with cisplatin; the secondary end points include changes in the levels of urinary biomarkers of nephrotoxicity such as neutrophil gelatinase-associated lipocalin, liver-type fatty acid-binding protein, and kidney injury molecule-1. Blood and urine samples are collected within 48 hours before cisplatin administration and at 24 hours, 48 hours, and 1 week after its initiation for safety and efficacy assessments. RESULTS: The first participant was registered in July 2024. As of January 2026, participant registration is ongoing. The final participant will complete the study by March 2026. Publication of results is expected by March 2027. CONCLUSIONS: This study is expected to contribute to advances in preventive strategies for CIN by providing evidence that inhibition of cysteine conjugate β-lyase 1 by flopropione may attenuate CIN. TRIAL REGISTRATION: Japan Registry of Clinical Trials jRCTs041220021; https://jrct.mhlw.go.jp/en-latest-detail/jRCTs041220021. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/87907.

In the diagnosis of lung cancer, imaging findings of lung nodules are essential for benign and malignant classifications. Although numerous studies have investigated the classification of lung nodules, no method has been proposed for obtaining detailed imaging findings. This study aimed to develop a novel method for generating image findings and classifying benign and malignant nodules in chest computed tomography (CT) images using vision–language models. In this study, we collected chest CT images of 77 patients diagnosed with either benign or malignant tumors at Fujita Health University Hospital. For these images, we cropped the regions of interest around the nodules, and a pulmonologist provided the corresponding image findings. We used vision–language models for image captioning to generate image findings. The findings generated by these two models were grammatically correct, with no deviations in notation, as expected from the image findings. Moreover, the descriptions of benign and malignant characteristics were accurately obtained. The bootstrapping language–image pretraining (BLIP) base model achieved an accuracy of 79.2% in classifying nodules, and the bilingual evaluation understudy-4 score for agreement with physician findings was 0.561. These results suggest that the proposed method may be effective for classifying and generating lung nodule findings.

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.