Chronic neuropathic pain affects 7–10% of the global population and imposes a substantial socioeconomic burden, yet existing pharmacological options remain inadequate in efficacy and burdened by systemic toxicity. Antibody-drug conjugates (ADCs) — engineered to deliver neuromodulatory payloads selectively to peripheral nociceptors — represent a compelling but unexplored therapeutic modality; no clinical-stage pain ADC currently exists. To the best of our knowledge based on a structured literature search (January 2000–March 2025) and targeted updates through 6 June 2026, this review provides a systematic and comprehensive conceptual framework mapping AI methodologies validated in oncology ADC development onto the unique challenges of chronic neuropathic pain. The framework spans five pipeline stages: multi-omics integration and graph neural networks for nociceptor-selective target prioritization (Nav1.7, TRPV1, P2X3, TrkA, CGRP receptor, ASIC3); structure prediction and protein language models for antibody engineering against transmembrane pain targets; generative AI for neuromodulatory payload design; deep learning for neural tissue pharmacokinetics and neurotoxicity prediction; and AI-driven patient stratification for precision clinical trial design. A unique three-layer optimization challenge — neural selectivity, analgesic potency, and systemic safety — distinguishes pain ADC AI from oncology ADC AI and defines the core design constraints of this review. Clinical precedent from FDA-approved anti-CGRP pathway antibodies (erenumab, fremanezumab, galcanezumab, eptinezumab) and Phase III anti-NGF antibody trials establishes that peripheral nociceptor-targeting biologics are both feasible and clinically active, providing the biological foundation for the pain-ADC concept. Realizing this framework requires curated pain-ADC datasets, interpretable AI, and closed-loop platforms incorporating dorsal root ganglion (DRG) organoids.

Recent increases in overweight and obesity have established Metabolic–Bariatric Surgery (MBS) as a principal intervention for durable weight reduction and metabolic improvement. Given the elevated perioperative complication risk among patients with obesity, there is a growing imperative to enhance the precision of preoperative management. This review synthesizes evidence from 2020–2025 on the application of artificial intelligence (AI) to bariatric surgery preoperative assessment, focusing on machine learning (ML), deep learning (DL), and large language models (LLMs). We summarize AI applications across three domains: preoperative risk prediction and individual assessment, patient stratification and procedure selection, and preoperative education and surgical training. The evidence suggests that integrating AI into routine preoperative workflows enables individualized, quantitative estimation of high-risk complications and weight-loss prognosis, thereby optimizing risk management; it can also support patient stratification and procedure matching to facilitate patient-centered shared decision-making; and NLP- and vision-based tools promote standardization and visualization of knowledge for patients and surgeons. Overall, AI is driving preoperative assessment toward greater individualization, interpretability, and multidisciplinary coordination, but its clinical generalizability requires validation in multicenter, prospective studies.

The rapid advancement of artificial intelligence (AI) in healthcare has significantly enhanced diagnostic accuracy and clinical decision-making processes. This review examines four pivotal studies that highlight the integration of large language models (LLMs) and multimodal systems in medical diagnostics. BioBERT demonstrates the efficacy of domain-specific pretraining on biomedical texts, improving performance in tasks such as named entity recognition, relation extraction, and question answering. Med-PaLM, a large-scale language model tailored for clinical question answering, leverages instruction prompt tuning to enhance accuracy and reduce harmful outputs, validated through the MultiMedQA benchmark. DR.KNOWS integrates medical knowledge graphs with LLMs, enhancing diagnostic reasoning and interpretability by grounding model predictions in structured medical knowledge. Medical Multimodal Foundation Models (MMFMs) combine textual and imaging data to improve tasks like segmentation, lesion detection, and automated report generation. These studies demonstrate the importance of domain adaptation, structured knowledge integration, and multimodal data fusion in developing robust and interpretable AI-driven diagnostic tools.

Renal cell carcinoma (RCC) is distinguished by a highly inflamed tumor microenvironment (TME) that offers both opportunities and challenges for immunotherapy. This review synthesizes current insights into the immunological landscape of RCC, highlighting robust cluster of differentiation 8‑positiv (CD8⁺) T-cell infiltration, unconventional antigen sources such as endogenous retroviruses and frameshift neoantigens, and the heterogeneity of immune niches revealed by single-cell and spatial profiling. We then examine the clinical impact and mechanisms of immune checkpoint inhibitors —including programmed cell death protein 1 (PD‑1), programmed death‑ligand 1 (PD‑L1), and cytotoxic T‑lymphocyte‑associated protein 4 (CTLA‑4)—tumor vaccines, cellular therapies such as chimeric antigen receptor T cell (CAR‑T) therapy and tumor‑infiltrating lymphocytes (TILs) and bispecific antibody constructs, emphasizing advances in dosing, engineering, and combination regimens. Combination strategies—including dual checkpoint blockade, integration with anti-angiogenic tyrosine kinase inhibitors, radiotherapy, metabolism-targeted agents such as adenosine and poly (ADP‑ribose) polymerase (PARP) inhibitors, and hypoxia modulators—are reviewed for their capacity to overcome resistance and remodel the microenvironment. We further explore intrinsic and acquired resistance mechanisms, the immunosuppressive roles of myeloid and stromal elements, and emerging biomarker approaches spanning genomic, transcriptomic, spatial, and circulating analytes. Finally, we discuss current limitations—such as variable clinical response, toxicities, and biomarker gaps—and outline future prospects, including personalized combination regimens, next-generation engineered cell products, and artificial intelligence (AI)-driven precision monitoring. Together, these insights chart a path toward more effective, individualized immunotherapy in RCC.