A groundbreaking milestone in oncology has been the recognition and targeted elimination of malignant cells through cancer immunotherapy, which harnesses the body’s immune system to attack cancer

McNeil Valencia, Sung Rae Kim, Yeseul Jang and Sung Hoon Lee. Biomolecules & Therapeutics 2021;29:605-14. https://doi.org/10.4062/biomolther.2021.012

Background/Objective: Chronic kidney disease (CKD) is a major global health concern associated with significant morbidity, mortality, and healthcare burden. This study aimed to develop an explainable machine learning framework that integrates lifestyle, sociodemographic, and biochemical factors for early CKD risk prediction among middle-aged men using public health survey data. Methods: Data from 968 male participants were preprocessed by removing missing values, deriving eGFR and ACR, and labeling CKD status. Five machine learning algorithms, (i.e., Random Forest, AdaBoost, Naïve Bayes, SVM, and XGBoost) were trained and evaluated using accuracy, precision, recall, and F1-score. Model interpretability was assessed using SHAP, LIME, Boruta, and Pearson’s correlation analyses. Results: AdaBoost yielded the best performance (accuracy = 0.7258, F1 = 0.6457, recall = 0.6923), with robust generalization confirmed by the precision–recall curve (AP = 0.715). SHAP and LIME revealed that serum creatinine, blood urea nitrogen, urinary creatinine, and age were major predictors, whereas lifestyle and metabolic indicators such as BMI, sodium and sugar intake, and sleep duration emerged as secondary factors for CKD. Conclusions: This study demonstrates the effectiveness of an explainable machine learning model that integrates lifestyle, sociodemographic and biochemical data for early CKD prediction among middle-aged men. The AdaBoost-based framework shows strong potential for implementation as a clinical decision-support tool within EHR systems and may contribute to personalized and preventive interventions. It emphasizes the growing importance of modifiable behaviors in kidney disease development and supports future work involving multiple cohorts and temporal model expansion to improve risk stratification for individuals at risk of kidney disease.

In recent years, immune checkpoint inhibitors (ICIs) have changed the landscape of cancer treatment by harnessing their efficacy in treating malignancies. These cancer therapies have shown remarkable result and efficacy across multiple cancer types. However, this review specifically focuses on non-small cell lung cancer (NSCLC) and gastric cancer (GC) due to their high incidence rates in Korea and Japan, ranking first to second in both sexes, as well as the availability of real-world data assessing ICI efficacy in these populations. In NSCLC, ICI treatment demonstrated better objective response rate and disease control rate, with overall survival (OS) ranging from 8.4 to 12.6 months in different studies. Nivolumab and atezolizumab exhibited efficacy in disease management in lung lesions. In GC, ICI showed promising efficacy in biomarker-positive patients, including those with programmed death-ligand 1 positive tumors, human epidermal growth factor receptor 2 (HER2) positive tumors, and microsatellite instability-high/mismatch repair (MSI-H/MMR)-deficient tumors, indicating that ICIs are beneficial for patients with favorable biomarker profiles. The median OS was significantly longer in patients with GC who were treated with ICI (16.9 months vs. 13.9 months). Immunotherapy leads to a durable response and improves the survival rates of patients with advanced or metastatic cancers. However, the success of ICI is affected by mild to severe immune-related adverse events, which are potentially life-threatening. Given the expanding ICIs application across different cancer, further studies are warranted to explores its broader implications and limitations. Therefore, this review explored the impacts of ICIs and their potential drawbacks in cancer treatment in Korea and Japan using real-world data and clinical trials.

The coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), primarily affects the respiratory system but can also involve multiple organs, including the often-overlooked ocular system. An increasing number of population-based and retrospective case series studies have reported that ocular and neuro-ophthalmic complications are temporally associated with COVID-19 infection and vaccination. Furthermore, some data suggest a modest increase in ocular adverse events (OAEs) following infection or vaccination, particularly among individuals with autoimmune or pre-existing ocular conditions. The proposed immune-mediated mechanisms include immune responses following vaccination that may contribute to demyelination through molecular mimicry, a phenomenon in which antigens share structural or functional similarities with host self-antigens. In this review, we summarize studies published between 2019 and June 2025, retrieved from PubMed and Google Scholar databases. Studies were selected based on their clinical relevance and contribution to the understanding of OAEs in the context of SARS-CoV-2 infection and COVID-19 vaccination. Thematic tables highlight the clinical spectrum of reported ocular manifestations, ranging from common conditions such as uveitis, optic neuritis, retinal vascular occlusions, and cranial nerve palsies to rarer entities, including acute macular neuroretinopathy, thyroid eye disease, and papillophlebitis. This review presents recent evidence on the proposed pathophysiological mechanisms and risk profiles of COVID-19-related OAEs, with the aim of improving awareness, promoting timely ophthalmic evaluation, and supporting surveillance and future research to clarify causality and inform preventive strategies.