The Expert Consensus on the Deployment of DeepSeek in Medical Institutions serves as a detailed guideline for the deployment of DeepSeek in medical institutions. It was developed by experts in the fields of healthcare， hospital management， medical information， health policy， law， and medical ethics from nearly 30 leading domestic medical and academic research institutions， based on relevant domestic and international laws and regulations as well as the practices of medical institutions. It aims to provide medical institutions with a scientific， standardized， and secure deployment guideline to ensure that the application of artificial intelligence （AI） technologies in healthcare， including but not limited to DeepSeek， conforms to the unique characteristics of the healthcare industry and effectively promotes the improvement of medical service levels. From the three aspects of pre-deployment evaluation， deployment implementation， and post-deployment management and monitoring， the key factors that medical institutions should consider when introducing DeepSeek were elaborated in detail， including medical demand compatibility， technical capabilities and infrastructure， legal and ethical risks， data preparation and management， model selection and optimization， system integration and training， performance monitoring and continuous optimization， risk management and emergency response， as well as compliance review and evaluation. This provides a comprehensive deployment framework for medical institutions to ensure the safety and effectiveness of technology applications.

Purpose: Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations. Methods: Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals. Results: Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified. Conclusions DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.

Purpose: Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations. Methods: Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals. Results: Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified. Conclusions DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.

Purpose: Gold-standard urodynamic examination is widely used in the diagnosis and treatment of lower urinary tract dysfunction. The purpose of urodynamic quality control is to standardize urodynamic examination and ensure its clinical reference value. In our study, we attempted to use a deep learning (DL) algorithm model, mainly for the recognition of typical urodynamic signal, to help physicians complete high-quality urodynamic examinations. Methods: Urodynamic image data from 2 cohorts of adult patients with neurogenic bladder were used: (1) 300 patients with neurogenic bladder in our center from 2012 to 2018 (1,960 images used to train and validate the DL model); and (2) 100 patients with neurogenic bladder from 2020 to 2021 (695 images used to test the performance of the DL model). This resulted in a total of 2,655 images to train, validate and test the DL algorithm to predict the urdynamic signals. Results: Yolov5l had the best detection performance and the highest comprehensive index score (F1, 0.81; mean average precision, 0.83). Our study is a retrospective single-center study, and the generalization ability of the model has not been verified. Conclusions DL algorithms can help operators identify typical urodynamic signals in real time, improve the interpretation and quality of urodynamic examination, and benefit patients.

ObjectiveBased on ultra-high performance liquid chromatography-quadrupole-time-of-flight mass spectrometry（UPLC-Q-TOF-MS/MS）， network pharmacology and molecular docking techniques， to explore the pharmacodynamic material basis and mechanism of Renshen Wuweizi Tang in treating spleen-lung Qi deficiency syndrome. MethodsThe chemical components in the decoction of Renshen Wuweizi Tang were systematically characterized and identified by UPLC-Q-TOF-MS/MS， and network pharmacology was used to screen potential active ingredients， collect component targets and gene sets related to spleen-lung Qi deficiency syndrome， and obtain protein interaction relationships through STRING. Cytoscape 3.9.1 was used to construct a "formula-syndrome" association network and calculate topological feature values. Gene ontology（GO） function and Kyoto Encyclopedia of Genes and Genomes（KEGG） pathway enrichment analysis were performed on core genes to explore potential pharmacodynamic links， the average shortest path between the formula-drug target network and the pharmacodynamic link gene network was calculated to discover dominant pharmacodynamic links， and MCODE plugin was used to identify core gene clusters from the dominant pharmacodynamic links， which were validated using Gene Expression Omnibus（GEO）， and molecular docking was performed between key components and core targets. ResultsOne hundred and thirty-seven components were identified in the negative ion mode， and eighty components were identified in the positive ion mode. After deduplication， a total of 185 components were identified， mainly composed of triterpenoid saponins（49） and flavonoids（54）. Based on the "formula-syndrome" correlation network analysis， energy metabolism was determined to be the dominant pharmacodynamic link of Renshen Wuweizi Tang in the treatment of spleen-lung Qi deficiency syndrome. The results of molecular docking showed that 7 components（adenosine， atractylenolide Ⅱ， atractylenolide Ⅲ， ginsenoside Rg₁， glycyrrhizin B₂， glycyrrhizin E₂ and campesterol） from 4 medicinal materials（Ginseng Radix et Rhizoma， Atractylodis Macrocephalae Rhizoma， Glycyrrhizae Radix et Rhizoma and Poria） in this formula might regulate energy metabolism by acting on 6 targets， namely cyclic adenosine monophosphate-response element binding protein 1（CREB1）， glyceraldehyde-3-phosphate dehydrogenase（GAPDH）， interleukin（IL）-6， nuclear transcription factor（NF）-κB1， peroxisome proliferator-activated receptor α（PPARα）， and tumor necrosis factor（TNF）， thus improving the symptoms of diseases related to spleen-lung Qi deficiency syndrome. ConclusionThis study established a UPLC-Q-TOF-MS/MS for rapid characterization and identification of chemical components in the decoction of Renshen Wuweizi Tang， expanding the understanding of the material composition of this formula， and found that 7 components might act on the key advantageous pharmacodynamic link "energy metabolism" through 6 targets to improve the related symptoms of spleen-lung Qi deficiency syndrome. This can provide a reference for the subsequent exploration of the material benchmark and mechanism of the famous classical formula.

ObjectivePhotoacoustic pump-probe imaging can effectively eliminate the interference of blood background signal in traditional photoacoustic imaging, and realize the imaging of weak phosphorescence molecules and their triplet lifetimes in deep tissues. However, background differential noise in photoacoustic pump-probe imaging often leads to large fitting results of phosphorescent molecule concentration and triplet lifetime. Therefore, this paper proposes a novel triplet lifetime fitting method for photoacoustic pump-probe imaging. By extracting the phase of the triplet differential signal and the background noise, the fitting bias caused by the background noise can be effectively corrected. MethodsThe advantages and feasibility of the proposed algorithm are verified by numerical simulation, phantom and in vivo experiments, respectively. ResultsIn the numerical simulation, under the condition of noise intensity being 10% of the signal amplitude, the new method can optimize the fitting deviation from 48.5% to about 5%, and has a higher exclusion coefficient (0.88>0.79), which greatly improves the fitting accuracy. The high specificity imaging ability of photoacoustic pump imaging for phosphorescent molecules has been demonstrated by phantom experiments. In vivo experiments have verified the feasibility of the new fitting method proposed in this paper for fitting phosphoometric lifetime to monitor oxygen partial pressure content during photodynamic therapy of tumors in nude mice. ConclusionThis work will play an important role in promoting the application of photoacoustic pump-probe imaging in biomedicine.

ObjectiveTo investigate the infestation of bedbugs in a staff dormitory in Jiading District, Shanghai, to explore the measures to dispose Cimex lectularius linnaeus, so as to provide a scientific basis for the prevention and control of bedbugs. MethodsThe infestation of bedbugs in the dormitory of the company was determined through field investigation, accompanied by scientific guidance under the comprehensive control measures and an effect evaluation of the control results. ResultsA total of 114 rooms distributed in 3 dormitory buildings were investigated, with an average infestation rate of 42.11%, of which building B has the highest infestation rate of 51.52%. Six bedbug specimens were collected by visual inspection in the room, and all of them were identified as Cimex lectularius linnaeus. After a series of comprehensive control measures including environmental cleanup, aerosol elimination, replacement of wooden beds with iron frame beds, and purchase of all-inclusive mattress, the bedbug infestation rate dropped to 5.26%. ConclusionComprehensive control can effectively prevent the breeding and spread of bedbugs. Dissemination and education effort should be strengthened in case of the occurrence of bedbug infestation, together with an implementation of long-term and continuous surveillance and monitoring.

PURPOSE: Septic shock is associated with high mortality and poor outcomes among sepsis patients with coagulopathy. Although traditional statistical methods or machine learning (ML) algorithms have been proposed to predict septic shock, these potential approaches have never been systematically compared. The present work aimed to develop and compare models to predict septic shock among patients with sepsis. METHODS: It is a retrospective cohort study based on 484 patients with sepsis who were admitted to our intensive care units between May 2018 and November 2022. Patients from the 908th Hospital of Chinese PLA Logistical Support Force and Nanchang Hongdu Hospital of Traditional Chinese Medicine were respectively allocated to training (n=311) and validation (n=173) sets. All clinical and laboratory data of sepsis patients characterized by comprehensive coagulation indexes were collected. We developed 5 models based on ML algorithms and 1 model based on a traditional statistical method to predict septic shock in the training cohort. The performance of all models was assessed using the area under the receiver operating characteristic curve and calibration plots. Decision curve analysis was used to evaluate the net benefit of the models. The validation set was applied to verify the predictive accuracy of the models. This study also used Shapley additive explanations method to assess variable importance and explain the prediction made by a ML algorithm. RESULTS: Among all patients, 37.2% experienced septic shock. The characteristic curves of the 6 models ranged from 0.833 to 0.962 and 0.630 to 0.744 in the training and validation sets, respectively. The model with the best prediction performance was based on the support vector machine (SVM) algorithm, which was constructed by age, tissue plasminogen activator-inhibitor complex, prothrombin time, international normalized ratio, white blood cells, and platelet counts. The SVM model showed good calibration and discrimination and a greater net benefit in decision curve analysis. CONCLUSION The SVM algorithm may be superior to other ML and traditional statistical algorithms for predicting septic shock. Physicians can better understand the reliability of the predictive model by Shapley additive explanations value analysis.
Humans ; Shock, Septic/blood* ; Machine Learning ; Male ; Female ; Retrospective Studies ; Middle Aged ; Aged ; Sepsis/complications* ; ROC Curve ; Cohort Studies ; Adult ; Intensive Care Units ; Algorithms ; Blood Coagulation ; Critical Illness

Insulin-like growth factor 2 (IGF2) is a critical endocrine mediator implicated in male reproductive physiology. To investigate the correlation between IGF2 protein levels and various aspects of male infertility, specifically focusing on sperm quality, inflammation, and DNA damage, a cohort of 320 male participants was recruited from the Women's Hospital, Zhejiang University School of Medicine (Hangzhou, China) between 1 st January 2024 and 1 st March 2024. The relationship between IGF2 protein concentrations and sperm parameters was assessed, and Spearman correlation and linear regression analysis were employed to evaluate the independent associations between IGF2 protein levels and risk factors for infertility. Enzyme-linked immunosorbent assay (ELISA) was used to measure IGF2 protein levels in seminal plasma, alongside markers of inflammation (tumor necrosis factor-alpha [TNF-α] and interleukin-1β [IL-1β]). The relationship between seminal plasma IGF2 protein levels and DNA damage marker phosphorylated histone H2AX (γ-H2AX) was also explored. Our findings reveal that IGF2 protein expression decreased notably in patients with asthenospermia and teratospermia. Correlation analysis revealed nuanced associations between IGF2 protein levels and specific sperm parameters, and low IGF2 protein concentrations correlated with increased inflammation and DNA damage in sperm. The observed correlations between IGF2 protein levels and specific sperm parameters, along with its connection to inflammation and DNA damage, underscore the importance of IGF2 in the broader context of male reproductive health. These findings lay the groundwork for future research and potential therapeutic interventions targeting IGF2-related pathways to enhance male fertility.
Humans ; Male ; Insulin-Like Growth Factor II/metabolism* ; Infertility, Male/genetics* ; DNA Damage ; Adult ; Inflammation/metabolism* ; Spermatozoa/metabolism* ; Semen Analysis ; Semen/metabolism* ; Tumor Necrosis Factor-alpha/metabolism* ; Histones/metabolism* ; Interleukin-1beta/metabolism*

OBJECTIVES: To investigate the clinical sub-phenotype (SP) of pediatric acute kidney injury (AKI) and their association with clinical outcomes. METHODS: General status and initial values of laboratory markers within 24 hours after admission to the pediatric intensive care unit (PICU) were recorded for children with AKI in the derivation cohort (n=650) and the validation cohort (n=177). In the derivation cohort, a least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify death-related indicators, and a two-step cluster analysis was employed to obtain the clinical SP of AKI. A logistic regression analysis was used to develop a parsimonious classifier model with simplified metrics, and the area under the curve (AUC) was used to assess the value of this model. This model was then applied to the validation cohort and the combined derivation and validation cohort. The association between SPs and clinical outcomes was analyzed with all children with AKI as subjects. RESULTS: In the derivation cohort, two clinical SPs of AKI (SP1 and SP2) were identified by the two-step cluster analysis using the 20 variables screened by LASSO regression, namely SP_d1 group (n=536) and SP_d2 group (n=114). The simplified classifier model containing eight variables (P<0.05) had an AUC of 0.965 in identifying the two clinical SPs of AKI (P<0.001). The validation cohort was clustered into SP_v1 group (n=156) and SP_v2 group (n=21), and the combined derivation and validation cohort was clustered into SP1 group (n=694) and SP2 group (n=133). After adjustment for confounding factors, compared with the SP1 group, the SP2 group had significantly higher incidence rates of multiple organ dysfunction syndrome and death during the PICU stay (P<0.001), and SP2 was significantly associated with the risk of death within 28 days after admission to the PICU (P<0.001). CONCLUSIONS This study establishes a parsimonious classifier model and identifies two clinical SPs of AKI with different clinical features and outcomes.The SP2 group has more severe disease and worse clinical prognosis.
Humans ; Acute Kidney Injury/diagnosis* ; Prognosis ; Male ; Female ; Child ; Child, Preschool ; Phenotype ; Infant ; Logistic Models ; Adolescent