Bladder cancer, when diagnosed at an advanced stage, often necessitates inevitable invasive intervention. Consequently, non-invasive biosensor-based cancer detection and AI-based precision screening are being actively employed. However, the misclassification of cancer patients as normal-referred to as false negatives-remains a significant concern, as it could lead to fatal outcomes in lifespan. Moreover, while ensemble techniques such as soft voting and other methods can improve model accuracy and reduce misclassification, their effectiveness is limited and not applicable to all diagnostic tasks. Here, we developed a double stage cancer screening system that utilizes a sensitive urinary electrical biosensor implemented with an AI model and XAI interpretation tools. This system is designed for screening bladder cancer, well-known for its notable recurrence and high tendency to advance from non-invasive muscle tumors to muscle-invasive tumors. Four urinary biomarkers (CK8, CK18, PD-1, PD-L1) were measured by a field-effect transistor biosensor, and along with gender and age information, patients underwent initial screening by the CatBoost classification model. Patients initially classified as normal were reclassified using local explanations from neural networks offering a different perspective than CatBoost. After the second-stage screening, all of the false negatives from the initial screening could be correctly reclassified as cancer patients. Furthermore, global explanation guides the improvement of the AI model to be trained on an appropriate set of biomarker features to achieve high accuracy.
Purpose: Metastatic bladder cancer has historically been treated with platinum-based chemotherapy as the standard firstline therapy. Since the introduction of cisplatin-based regimens, advancements in treatment strategies have been limited. However, the recent emergence of immune checkpoint inhibitors (ICIs) and antibody-drug conjugates (ADCs) has significantly transformed the treatment landscape. Notably, the combination of enfortumab vedotin (EV) and pembrolizumab has demonstrated considerable clinical benefits, challenging traditional chemotherapy. This review aims to provide an overview of recent advancements in the treatment of metastatic bladder cancer.Current Concepts: Recent phase III clinical trials, notably EV-302/KEYNOTE-A39 and CheckMate 901, have reshaped the first-line management. EV combined with pembrolizumab has shown superior progression-free survival and overall survival compared to platinum-based chemotherapy, establishing it as a new standard of care. Patients ineligible for this regimen due to underlying comorbidities or toxicity may still benefit from alternative options. Such alternatives include platinum-based chemotherapy with ICI maintenance therapy, including avelumab or nivolumab. The selection of treatments should be individualized, taking into account specific patient factors, particularly platinum eligibility, renal function, and performance status.Discussion and Conclusion: The incorporation of ICIs and ADCs into the therapeutic landscape for metastatic bladder cancer has significantly improved patient outcomes. EV plus pembrolizumab has demonstrated substantial survival benefits, establishing it as a preferred first-line regimen for eligible patients. However, not all patients are candidates for this combination, emphasizing the necessity of individualized treatment strategies. Future research should focus on managing treatment-related adverse events and developing personalized therapies to maximizing efficacy while minimizing toxicity.