Objectives: To develop and test machine learning-based CT radiomics models for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection. Design: Cross-sectional Setting: Multicenter Participants: A total of 52 patients with laboratory-confirmed SARS-CoV-2 infection and their initial CT images were enrolled from 5 designated hospitals in Ankang, Lishui, Zhenjiang, Lanzhou, and Linxia between January 23, 2020 and February 8, 2020. As of February 20, patients remained in hospital or with non-findings in CT were excluded. Therefore, 31 patients with 72 lesion segments were included in the final analysis. Intervention: CT radiomics models based on logistic regression (LR) and random forest (RF) were developed on features extracted from pneumonia lesions in training and inter-validation datasets. The predictive performance was further evaluated in test dataset on lung lobe- and patients-level. Main outcomes: Short-term hospital stay (≤10 days) and long-term hospital stay (>10 days). Results: The CT radiomics models based on 6 second-order features were effective in discriminating short- and long-term hospital stay in patients with pneumonia associated with SARS-CoV-2 infection, with areas under the curves of 0.97 (95%CI 0.83-1.0) and 0.92 (95%CI 0.67-1.0) by LR and RF, respectively, in the test dataset. The LR model showed a sensitivity and specificity of 1.0 and 0.89, and the RF model showed similar performance with sensitivity and specificity of 0.75 and 1.0 in test dataset. Conclusions: The machine learning-based CT radiomics models showed feasibility and accuracy for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection.

Background: The inflammation indexes in blood routine play an essential role in evaluating the prognosis of patients with hepatocellular carcinoma, but the effect on early recurrence has not been clarified. The study aimed to investigate the risk factors of early recurrence (within 2 years) and recurrence-free survival after curative hepatectomy and explore the role of inflammatory indexes in predicting early recurrence. Methods: The baseline data of 161 patients with hepatocellular carcinoma were analyzed retrospectively. The optimal cut-off value of the inflammatory index was determined according to the Youden index. Its predictive performance was compared by the area under the receiver operating characteristic curve. Logistic and Cox regression analyses were used to determine the risk factors of early recurrence and recurrence-free survival. Results: The area under the curve of monocyte to lymphocyte ratio (MLR) for predicting early recurrence was 0.700, which was better than systemic inflammatory response index (SIRI), neutrophil to lymphocyte ratio (NLR), platelet to lymphocyte ratio (PLR) and systemic immune-inflammatory index (SII). MLR, tumour size, tumour differentiation and BCLC stage are all risk factors for early recurrence and recurrence-free survival of HCC. Combining the above four risk factors to construct a joint index, the area under the curve for predicting early recurrence was 0.829, which was better than single MLR, tumour size, tumour differentiation and BCLC stage. Furthermore, with the increase of risk factors, the recurrence-free survival of patients is worse. Conclusion: The combination of MLR and clinical risk factors is helpful for clinicians to identify high-risk patients with early recurrence and carry out active postoperative adjuvant therapy to improve the prognosis of patients.

Cancer nanomedicine has evolved from the 1995 landmark approval of Doxil® into a programmable platform of precision oncology. The field now progresses along a coherent continuum that begins with passive enhanced permeability and retention (EPR)-mediated tumor accumulation, advances to active ligand–receptor targeting, and culminates in stimuli-responsive carriers whose cargo is liberated only when triggered by endogenous (acidic pH, redox imbalance, elevated GSH, dysregulated enzymes, ROS) or exogenous (light, magnetic, ultrasound, X-ray, electric) cues intrinsic to the tumor microenvironment (TME). This review maps this continuum, highlighting how the integration of patient-specific multi-omics data with artificial intelligence (AI) is converting tumor heterogeneity into quantitative design rules for nanocarrier optimization, validated in patient-derived organoids. Despite over 15 FDA-approved cancer nanomedicines and a robust clinical pipeline, translation is impeded by biological barriers, protein corona-mediated toxicity, manufacturing scalability issues, and a fragmented regulatory landscape. To bridge this bench-to-bedside chasm, we propose a convergent roadmap: safe-by-design engineering, quality-by-design modular manufacturing, and AI-guided digital twins coupled with micro/nano-robotic delivery for real-time, adaptive dosing. Realizing this vision will transform nanomedicine from an empirical carrier technology into a patient-calibrated, closed-loop therapeutic engine, cementing its role as the frontline of precision oncology.

Non-alcoholic fatty liver disease (NAFLD) and depression represent two highly prevalent medical conditions often presenting concurrently. However, currently available pharmacological treatments rarely target both disorders simultaneously. Xiaoyao San (XYS), a traditional herbal formulation from Chinese medicine, has been clinically effective in addressing NAFLD and depressive symptoms, although its precise therapeutic mechanisms remain poorly understood. This study aimed to investigate the underlying mechanisms of XYS in managing comorbid NAFLD and depression by employing network pharmacology (NP) and multi-omics methodologies. A chronic restraint stress (CRS)-induced NAFLD rat model was constructed to simulate the disease conditions. The efficacy of XYS treatment was evaluated through behavioral assessments, histopathological liver examination, biochemical analyses, and measurements of inflammatory and oxidative stress (OS) biomarkers. Further, NP combined with metabolomic and proteomic techniques was applied to uncover pivotal targets and pathways, with subsequent validation via Western blotting (WB). XYS improved depression-like behaviors, reduced hepatic lipid deposition, and lowered levels of hepatic enzymes, blood lipids, and blood glucose. It also attenuated inflammatory and OS responses. Multi-omics analysis identified the PPARα/HMOX1/GPX4 axis as a key target. XYS modulated this pathway to inhibit ferroptosis and reduce hepatic iron accumulation. Specifically, XYS upregulated PPARα and GPX4 expression, downregulated HMOX1 expression, and decreased hepatic iron levels, alleviating both NAFLD and depression. XYS exerts therapeutic effects on NAFLD and depression through multi-target regulation, primarily by modulating the PPARα/HMOX1/GPX4 axis to inhibit ferroptosis. This study provides a novel mechanistic basis for the dual therapeutic efficacy of XYS.