Search

Objectives: This study explored the clinical utility of CT radiomics-driven machine learning as a predictive marker for chemotherapy response in colorectal liver metastasis (CRLM) patients., Methods: We included 150 CRLM patients who underwent first-line doublet chemotherapy, dividing them into a training cohort (n=112) and a test cohort (n=38). We manually delineated three-dimensional tumor volumes, selecting the largest liver metastasis for measurement, using pretreatment portal-phase CT images and extracted 107 radiomics features. Treatment response was classified as responder (complete or partial response) or non-responder (stable or progressive disease), based on the best overall response according to RECIST criteria, version 1.1. Employing Random Forest and Boruta algorithms, we identified significant features for responder-non-responder differentiation. Radiomics signatures were developed and validated in the training cohort using five-fold cross-validation, and performance was assessed using the area under the curve (AUC)., Results: Among the patients, 91 (61%) were responders and 59 (39%) were non-responders. Variable selection with Boruta revealed three key parameters ("DependenceVariance," "ClusterShade," and "RunVariance"). In the training cohort, individual CT texture parameter AUCs ranged from 0.4 to 0.65, while the machine learning analysis incorporating all valid parameters exhibited a significantly higher AUC of 0.94 (p<0.01). The validation cohort also demonstrated strong predictive accuracy, with an AUC of 0.87 for treatment response., Conclusions: This study highlights the potential of CT radiomics-driven machine learning in predicting chemotherapy responses among CRLM patients., Competing Interests: Conflicts of Interest There are no conflicts of interest., (Copyright © 2025 The Japan Society of Coloproctology.)

Background: Asthma involves variable airflow limitation and persistent airway inflammation. Eosinophilic asthma, characterized by cytokine-mediated type 2 inflammation, is generally treated with inhaled corticosteroids. However, patients with severe asthma may require biologics, such as mepolizumab, which targets IL-5 and can manage uncontrolled eosinophilic asthma., Objective: We investigated the relationship between serum mepolizumab concentrations and treatment response in patients with severe asthma., Methods: Patients with mepolizumab-treated severe asthma were enrolled onto this prospective cohort study. Baseline assessments were conducted and repeated at 3, 6, and 12 months. Those with response were categorized on the basis of improvements in asthma control test score, lung function, and asthma exacerbations. We quantified the serum concentration of mepolizumab at 3, 6, and 12 months after treatment by liquid chromatography coupled with tandem mass spectrometry., Results: Twenty-five adult patients aged 20 years and older with severe asthma were included in the analysis. Serum mepolizumab concentrations significantly increased at 6 and 12 months compared with those at 3 months, particularly in those with disease that responded to therapy. Furthermore, the relative change in mepolizumab concentration was significantly higher in those with response than in those with no response. Body size parameters were negatively correlated with mepolizumab concentration. In those with response, there were inverse correlations between mepolizumab concentration and baseline body size parameters., Conclusions: The study observed a yearlong increase in mepolizumab concentrations, particularly in those with response, indicating a potential mepolizumab surplus. Correlations between mepolizumab concentrations and baseline characteristics suggested differing mepolizumab requirements between those with response and those with no response. Further research is needed to validate these findings and optimize treatment strategies for patients with severe asthma., Competing Interests: Supported in part by 10.13039/501100001691Japan Society for the Promotion of Science Grants-in-Aid for Scientific Research (grant 20K08549) and by a Grant-in-Aid for Special Research in Subsidies for ordinary expenses of private schools from the 10.13039/501100012359Promotion and Mutual Aid Corporation for Private Schools of Japan to the Atopy (Allergy) Research Center. Disclosure of potential conflict of interest: N. Harada reports personal fees from AstraZeneca, GlaxoSmithKline, Kyorin, Novartis, and Sanofi; and grants from AstraZeneca, Daikin, Kao, Sanofi, and TOSOH outside the submitted work. S. Yagishita reports personal fees from LSI Medience outside the submitted work. A. Hamada reports grants from CIMIC Pharma Science, TOSOH, Chordia Therapeutics, LSI Medience, Chugai, Eli Lilly, Sysmex, Healios, Konica Minolta, Boehringer Inhelheim, Eisai, Daiichi Sankyo, AstraZeneca, Mitsubishi Tanabe Pharma, and Novartis outside the submitted work. K. Takahashi reports grants from Asahi Kasei Pharma Corporation, Bayer Yakuhin, Chugai, Daiichi Sankyo, Eli Lilly, Kyorin, Kyowa, Nippon Boehringer Ingelheim, Nippon Kayaku, Nippon Shinyaku, Nipro, Novartis, Ono, Pfizer, Sanofi, Shionogi, Taiho, Takeda, Teijin, and Tsumura; and personal fees from Abbott Japan, AstraZeneca, Bristol-Myers, Chugai, Eli Lilly, Janssen, Kyorin, Meiji Seika, Merck, MSD, Nippon Boehringer Ingelheim, Nippon Kayaku, Novartis, Ono, Pfizer, Sumitomo Dainippon Pharma, Taiho, Takeda, Thermo Fisher Scientific, and Viatris outside the submitted work. Furthermore, K. Takahashi has a patent (P6840330) for detecting cells, managed by Juntendo University in Japan. The rest of the authors declare that they have no relevant conflicts of interest., (© 2025 The Author(s).)