Intravitreal anti-vascular endothelial growth factor(anti-VEGF)therapy has been widely used, but the variability in its therapeutic efficacy limits individualized treatment. In recent years, the application of artificial intelligence(AI)has opened up new avenues for personalized treatment response prediction, and its core branches include machine learning(ML)and deep learning(DL). This review systematically retrieved and analyzed 41 relevant studies published up to April 2025. Comprehensive analysis reveals that AI predictive models are evolving from forecasting single endpoints(such as visual acuity or central retinal thickness)to integrating multi-dimensional endpoints(encompassing anatomical, functional, and treatment demand parameters)and generating predictive imaging outputs. In terms of technical approaches, DL models(28 studies, accounting for 68.3%)dominate this field due to their robust image interpretation capabilities, while ML models(10 studies, 24.4%)retain significant value in the analysis of structured clinical data. Cross-disease comparisons indicate that research efforts are most concentrated on age-related macular degeneration(ARMD)and diabetic macular edema(DME), with shared conceptual frameworks for model construction, yet distinct anatomical and functional indicators are prioritized for each disease. Currently, the field confronts several key challenges, including insufficient prospective clinical validation, limited model interpretability(the “black box problem”), and a scarcity of high-quality multi-center datasets. Moving forward, it is imperative to advance real-world validation and develop explainable AI techniques to expedite the clinical translation of these predictive models.

OBJECTIVE To assess the correlation between the steady-state minimal concentration （cmin） and 24 h area under the drug concentration-time curve （AUC24）/minimal inhibitory concentration （MIC） ratio （AUC24/MIC） of vancomycin in pediatric patients， and analyze independent risk factors for treatment failure. METHODS Data of hospitalized children treated with vancomycin and receiving therapeutic drug monitoring in our hospital from January 2021 to July 2024 were retrospectively collected and divided into success group and failure group according to whether the treatment was successful or not. Spearman correlation analysis was used to analyze the correlation between cmin and AUC24/MIC of vancomycin， and one-way and multifactorial Logistic regression analyses were used to screen the independent risk factors for vancomycin treatment failure. RESULTS A total of 59 children were included， with 41 in the success group and 18 in the failure group. Compared with the failure group， AUC24/MIC of vancomycin was significantly higher in the success group （P＝0.038）， but there was no statistically significant difference in the cmin of the two groups （P＞0.05）； cmin of vancomycin was significantly positively correlated with AUC24/MIC （r＝0.499， P＜0.001）， but it has a certain efficacy in predicting the achievement of the AUC24/MIC standard （≥400） （area under the receiver operator characteristic curve＝0.696）， with an optimal cutoff value of 6.05 mg/L determined by the Youden index. The efficacy of AUC24/ MIC in predicting treatment failure was superior to cmin （areas under the receiver operator characteristic curve were 0.671 vs. 0.523， P were 0.038 vs. 0.684）， with higher sensitivity （83.3% vs. 66.7%）. Hypoproteinemia and AUC24/MIC≤369.1 were independent risk factors for vancomycin treatment failure （P＜0.05）. The incidence of nephrotoxicity was 3.4%. CONCLUSIONS There is a significant positive correlation between cmin and AUC24/MIC of vancomycin in pediatric patients； hypoproteinemia and AUC24/MIC≤369.1 are independent risk factors for vancomycin treatment failure in children.

Mycophenolic acid (MPA), the active moiety of both mycophenolate mofetil (MMF) and enteric-coated mycophenolate sodium (EC-MPS), serves as a primary immunosuppressant for maintaining solid organ transplants. Therapeutic drug monitoring (TDM) enhances treatment outcomes through tailored approaches. This study aimed to develop an evidence-based guideline for MPA TDM, facilitating its rational application in clinical settings. The guideline plan was drawn from the Institute of Medicine and World Health Organization (WHO) guidelines. Using the Delphi method, clinical questions and outcome indicators were generated. Systematic reviews, Grading of Recommendations Assessment, Development, and Evaluation (GRADE) evidence quality evaluations, expert opinions, and patient values guided evidence-based suggestions for the guideline. External reviews further refined the recommendations. The guideline for the TDM of MPA (IPGRP-2020CN099) consists of four sections and 16 recommendations encompassing target populations, monitoring strategies, dosage regimens, and influencing factors. High-risk populations, timing of TDM, area under the curve (AUC) versus trough concentration (C₀), target concentration ranges, monitoring frequency, and analytical methods are addressed. Formulation-specific recommendations, initial dosage regimens, populations with unique considerations, pharmacokinetic-informed dosing, body weight factors, pharmacogenetics, and drug‍-‍drug interactions are covered. The evidence-based guideline offers a comprehensive recommendation for solid organ transplant recipients undergoing MPA therapy, promoting standardization of MPA TDM, and enhancing treatment efficacy and safety.
Mycophenolic Acid/administration & dosage* ; Drug Monitoring/methods* ; Humans ; Organ Transplantation ; Immunosuppressive Agents/administration & dosage* ; Delphi Technique

Iron overload is strongly associated with heart disease. Ferroptosis is a new form of regulated cell death indicated in cardiac ischemia-reperfusion (I/R) injury. However, the specific molecular mechanism of myocardial injury caused by iron overload in the heart is still unclear, and the involvement of ferroptosis in iron overload-induced myocardial injury is not fully understood. In this study, we observed that ferroptosis participated in developing of iron overload and I/R-induced cardiomyopathy. Mechanistically, we discovered that Parkin inhibited iron overload-induced ferroptosis in cardiomyocytes by promoting the ubiquitination of long-chain acyl-CoA synthetase 4 (ACSL4), a crucial protein involved in ferroptosis-related lipid metabolism pathways. Additionally, we identified p53 as a transcription factor that transcriptionally suppressed Parkin expression in iron-overloaded cardiomyocytes, thereby regulating iron overload-induced ferroptosis. In animal studies, cardiac-specific Parkin knockout mice (Myh6-CreER ^T2 /Parkin ^fl/fl ) fed a high-iron diet presented more severe myocardial damage, and the high iron levels exacerbated myocardial I/R injury. However, the ferroptosis inhibitor Fer-1 significantly suppressed iron overload-induced ferroptosis and myocardial I/R injury. Moreover, Parkin effectively protected against impaired mitochondrial function and prevented iron overload-induced mitochondrial lipid peroxidation. These findings unveil a novel regulatory pathway involving p53-Parkin-ACSL4 in heart disease by inhibiting of ferroptosis.

Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Multi-Dimensional Feature Fusion model named MDFF, which integrates one-dimensional simplified molecular input line entry system sequence features, two-dimensional molecular graph features, and three-dimensional geometric features to enhance drug representations for predicting DDIs. MDFF was trained and validated on two DDI datasets, evaluated across three distinct scenarios, and compared with advanced DDI prediction models using accuracy, precision, recall, area under the curve, and F1 score metrics. MDFF achieved state-of-the-art performance across all metrics. Ablation experiments showed that integrating multi-dimensional drug features yielded the best results. More importantly, we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs. Among 12 real-world adverse drug reaction reports, the predictions of 9 reports were supported by relevant evidence. Additionally, MDFF demonstrated the ability to explain adverse DDI mechanisms, providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.

Objective To explore the differences in neck and lumbar spine injuries among different types of aircraft pilots and the correlation between body surface temperature and the severity of injury.Methods Data were collected by questionnaire surveys and medical examinations.Forty male pilots were selected as research objects,including 14 fighter pilots and 26 helicopter pilots,aged between 28 and 39 years,with a height range of 168 to 178 cm,and a total flight time of 600 to 2 000 h.Infrared thermal imaging was employed for skin temperature.A questionnaire survey was conducted for the assessment of the common site and degree of pain.The relationship between body surface temperature and pain was investigated.Results Fighter pilots mainly complained of discomfort in the neck and scapular region,while helicopter pilots were more likely to experience lower back pain.The skin temperature in the affected regions was significantly higher than that in the surrounding normal regions in both fighter pilots and helicopter pilots(P<0.05).The pain score was positively related with elevated temperature in the affected areas(P<0.05).Conclusion It is found that fighter pilots are more prone to neck and scapular pain,while helicopter pilots are more likely to experience lower back pain.The severity of pain is positively related with increased temperature in the affected areas.Infrared thermal imaging can be used to assess temperature variation at injured sites and the location of training injuries among pilots.

Objective To investigate the risk factors influencing the prolonged length of hospital stay after transjugular intrahepatic portosystemic shunt(TIPS)in patients with ruptured esophagogastric variceal bleeding(EGVB)and to construct a risk prediction model.Methods The clinical data of 215 patients with EGVB,who received TIPS at a certain grade ⅢA hospital in Nanjing of China from January 1,2020 to January 30,2023,were retrospectively analyzed.According to whether the postoperative hospitalization stay was prolonged or not,the patients were divided into prolonged group(n=67)and normal group(n=148).Multivariate logistic regression analysis was sued to analyze the independent risk factors for prolonged postoperative hospitalization stay,and the risk factors were used as predictors for constructing the nomogram model.Results Multivariate logistic regression analysis showed that history of splenectomy,early TIPS performance,NRS 2002 Nutritional Risk Screening Score ≥3 points,and Barthel index score≤40 points were the independent risk factors for prolonged postoperative hospitalization stay in patients with cirrhotic EGVB after receiving TIPS(P＜0.05).The area under receiver operating characteristic(ROC)curve of the model constructed on the basis of independent risk factors was 0.743,which was higher than that of early TIPS performance,history of splenectomy,NRS 2002 score,and Barthel index score.The Hosmer-Lemeshow test obtained P=0.723,indicating that this model had a good fit degree.Conclusion The prediction model established in this study can be used for cirrhotic EGVB patients to predict the risk of prolonged postoperative hospitalization stay,and this model has good discrimination and calibration,besides,it can bring some clinical benefits to patients.

To investigate the impact of preoperative serum follicle-stimulating hormone (FSH) levels on the probability of testicular sperm retrieval, we conducted a study of nonobstructive azoospermic (NOA) men with different testicular volumes (TVs) who underwent microdissection testicular sperm extraction (micro-TESE). A total of 177 NOA patients undergoing micro-TESE for the first time from April 2019 to November 2022 in Shenzhen Zhongshan Obstetrics and Gynecology Hospital (formerly Shenzhen Zhongshan Urology Hospital, Shenzhen, China) were retrospectively reviewed. The subjects were divided into four groups based on average TV quartiles. Serum hormone levels in each TV group were compared between positive and negative sperm retrieval subgroups. Overall sperm retrieval rate was 57.6%. FSH levels (median [interquartile range]) were higher in the positive sperm retrieval subgroup compared with the negative outcome subgroup when average TV was <5 ml (first quartile [Q1: TV <3 ml]: 43.32 [17.92] IU l -1 vs 32.95 [18.56] IU l -1 , P = 0.048; second quartile [Q2: 3 ml ≤ TV <5 ml]: 31.31 [15.37] IU l -1 vs 25.59 [18.40] IU l -1 , P = 0.042). Elevated serum FSH levels were associated with successful micro-TESE sperm retrieval in NOA men whose average TVs were <5 ml (adjusted odds ratio [OR]: 1.06 per unit increase; 95% confidence interval [CI]: 1.01-1.11; P = 0.011). In men with TVs ≥5 ml, larger TVs were associated with lower odds of sperm retrieval (adjusted OR: 0.84 per 1 ml increase; 95% CI: 0.71-0.98; P = 0.029). In conclusion, elevated serum FSH levels were associated with positive sperm retrieval in micro-TESE in NOA men with TVs <5 ml. In men with TV ≥5 ml, increases in average TVs were associated with lower odds of sperm retrieval.
Humans ; Male ; Azoospermia/surgery* ; Sperm Retrieval/statistics & numerical data* ; Adult ; Follicle Stimulating Hormone/blood* ; Retrospective Studies ; Testis/pathology* ; Microdissection ; Organ Size

This study investigated the impact of metabolic syndrome (MetS) and its components on prostate volume (PV) in the general Chinese population. In total, 43 455 participants in The First Medical Center of the Chinese PLA General Hospital (Beijing, China) from January 1, 2012, to December 31, 2022, undergoing health examinations were included in the study. Participants were categorized into four groups according to PV quartiles: Q1 (PV ≤24.94 ml), Q2 (PV >24.94 ml and ≤28.78 ml), Q3 (PV >28.78 ml and ≤34.07 ml), and Q4 (PV >34.07 ml), with Q1 serving as the reference group. Logistic regression analyses were used to examine the association between MetS and PV, with subgroup analyses conducted by age. Among the participants, 18 787 (43.2%) were diagnosed with MetS. In the multivariate analysis model, a significant correlation between MetS and PV was observed, with odds ratios (ORs) increasing as PV increased (Q2, OR = 1.203, 95% confidence interval [CI]: 1.139-1.271; Q3, OR = 1.300, 95% CI: 1.230-1.373; and Q4, OR = 1.556, 95% CI: 1.469-1.648). Analysis of MetS components revealed that all components were positively associated with PV, with abdominal obesity showing the most significant effect. The number of MetS components was identified as a dose-dependent risk factor for elevated PV. The impact of MetS, its components, and component count on PV exhibited a decreasing trend with advancing age. Overall, the influence of MetS, its components, and component count on PV was predominantly observed in the age groups of 40-49 years and 50-59 years. Early intervention targeting MetS can significantly alleviate the increase in PV, particularly benefiting individuals aged 40-59 years who have abdominal obesity.
Humans ; Male ; Metabolic Syndrome/complications* ; Middle Aged ; Cross-Sectional Studies ; Aged ; Prostate/diagnostic imaging* ; Adult ; Age Factors ; Organ Size ; China/epidemiology* ; Obesity, Abdominal ; Risk Factors