Metabolic dysfunction-associated fatty liver disease （MAFLD） has become one of the most prevalent chronic liver diseases worldwide， posing a serious challenge to public health. In this context， the integration of artificial intelligence （AI）， especially intelligent diagnosis and treatment and digital health interventions based on machine learning， can break through the limitations of traditional methods， realize efficient screening of multi-dimensional data such as key genes， biomarkers， and biochemical metabolites， and achieve revolutionary breakthroughs in risk prediction， subtype identification， and therapeutic effect assessment for MAFLD. This article systematically reviews the ground-breaking application of machine learning models in driving the innovation of clinical diagnosis and precise risk prediction of MAFLD， conducts a comprehensive comparative analysis of digital health practice cases of MAFLD in China and globally， and deeply analyzes their advantages and limitations in terms of research subjects， interventions， and management team. Studies have shown that the deep integration of digital health and long-term management of MAFLD is becoming the key engine driving the transformation of disease management modes towards an intelligent， individualized， and precise era， but there are various ethical and technical issues that need to be addressed urgently.

Objective To explore the diagnosis and treatment experience of malignant peritoneal mesothelioma by analyzing the clinical characteristics of patients with single center peritoneal mesothelioma.Methods Retrospec-tively analyze the clinical data,including age and treatment regimens,of 99 patients with malignant peritoneal mes-othelioma admitted to Peking Union Medical College Hospital from June 2012 to July 2023.Kaplan-Meier for surviv-al analysis and Logistic and Cox regression were applied to assess the impact of factors like age and treatment regi-mens on survival time.Results The median age of diagnosis for 99 patients with peritoneal mesothelioma was 56 years,of which 82 were pathologically diagnosed.Among them,38 cases(51.4%)underwent tumor cell reduction surgery,and 57 cases(77.0%)underwent systemic or local treatment.The median survival time for all patients was 43 years.The age of diagnosis may affect the prognosis of patients with malignant mesothelioma,and those aged≥65 at the time of diagnosis have a worse prognosis.Conclusions Malignant peritoneal mesothelioma is a rare but invasive malignant tumor with a poor prognosis.There is still a need to develop novo drugs and comprehensive treat-ment strategies.

Objective To evaluate the clinical application of CT-guided coaxial needle biopsy in pancreatic puncture-cutting biopsy via adipose tissue space.Methods The clinical data of 30 patients,who received CT-guided pancreatic coaxial needle biopsy via adipose tissue space at the Pingdu Hospital Area of Affiliated Hospital of Qingdao University of China from June 2021 to April 2024,were retrospectively analyzed.The patients included 20 males and 10 females with a mean age of(65.1±8.7)years.The lesions were located in the pancreatic head(n=7),pancreatic neck(n=4),pancreatic body(n=7),pancreatic tail(n=10)and uncinate process(n=2).Under CT guidance,a 17 G co-axial guiding needle was inserted to establish a puncture pass through adipose tissue space,then an 18 G biopsy needle was used to make tissue sampling.A total of 32 procedures of pancreatic puncture-cutting biopsy were performed,two of these patients received two times of biopsy.After sampling,a self-made blocking agent(a mixed liquid of gelatin sponge particles and snake venom hemagglutinin),was used to occlude the puncture channel so as to prevent complications such as bleeding,pancreatic leakage,needle tract implantation metastasis,etc.Results A total of 32 procedures of pancreatic puncture-cutting biopsy with coaxial guiding needle via adipose tissue space were performed,including two patients who received two times of biopsy.The success rate of puncturing was 100％(32/32),the success rate of sampling was 93.8％(30/32),and the accuracy of sampling was 93.8％(30/32).No serious puncture-related complications occurred in all patients.Conclusion CT-guided pancreatic coaxial needle biopsy via adipose tissue space is clinically safe,accurate in sampling and minimally-invasive.This interventional diagnostic technique is worth applying in clinical practice.

OBJECTIVE: To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. METHODS: Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. RESULTS: The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. CONCLUSION The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.
Humans ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Adult ; Male ; Female

OBJECTIVE: To investigate the effect of manual acupuncture manipulations (MAMs) on subcutaneous muscle tissue, by developing quantitative models of "lifting and thrusting" and "twisting and rotating", based on machine learning techniques. METHODS: A depth camera was used to capture the acupuncture operator's hand movements during "lifting and thrusting" and "twisting and rotating" of needle. Simultaneously, the ultrasound imaging was employed to record the muscle tissue responses of the participants. Amplitude and angular features were extracted from the movement data of operators, and muscle fascicle slope features were derived from the data of ultrasound images. The dynamic time warping barycenter averaging algorithm was adopted to align the dual-source data. Various machine learning techniques were applied to build quantitative models, and the performance of each model was compared. The most optimal model was further analyzed for its interpretability. RESULTS: Among the quantitative models built for the two types of MAMs, the random forest model demonstrated the best performance. For the quantitative model of the "lifting and thrusting" technique, the coefficient of determination (R²) was 0.825. For the "twisting and rotating" technique, R² reached 0.872. CONCLUSION Machine learning can be used to effectively develop the models and quantify the effects of MAMs on subcutaneous muscle tissue. It provides a new perspective to understand the mechanism of acupuncture therapy and lays a foundation for optimizing acupuncture technology and designing personalized treatment regimen in the future.
Humans ; Acupuncture Therapy/methods* ; Machine Learning ; Male ; Adult ; Female ; Subcutaneous Tissue/diagnostic imaging* ; Young Adult

Traditional Chinese medicine (TCM) features complex compatibility mechanisms involving multi-component, multi-target, and multi-pathway interactions. This study presents an interpretable graph artificial intelligence (GraphAI) framework to quantify such mechanisms in Chinese herbal formulas (CHFs). A multidimensional TCM knowledge graph (TCM-MKG; https://zenodo.org/records/13763953) was constructed, integrating seven standardized modules: TCM terminology, Chinese patent medicines (CPMs), Chinese herbal pieces (CHPs), pharmacognostic origins (POs), chemical compounds, biological targets, and diseases. A neighbor-diffusion strategy was used to address the sparsity of compound-target associations, increasing target coverage from 12.0% to 98.7%. Graph neural networks (GNNs) with attention mechanisms were applied to 6,080 CHFs, modeled as graphs with CHPs as nodes. To embed domain-specific semantics, virtual nodes medicinal properties, i.e., therapeutic nature, flavor, and meridian tropism, were introduced, enabling interpretable modeling of inter-CHP relationships. The model quantitatively captured classical compatibility roles such as "monarch-minister-assistant-guide," and uncovered TCM etiological types derived from diagnostic and efficacy patterns. Model validation using 215 CHFs used for coronavirus disease 2019 (COVID-19) management highlighted Radix Astragali-Rhizoma Phragmitis as a high-attention herb pair. Mass spectrometry (MS) and target prediction identified three active compounds, i.e., methylinissolin-3-O-glucoside, corydalin, and pingbeinine, which converge on pathways such as neuroactive ligand-receptor interaction, xenobiotic response, and neuronal function, supporting their neuroimmune and detoxification potential. Given their high safety and dietary compatibility, this herb pair may offer therapeutic value for managing long COVID-19. All data and code are openly available (https://github.com/ZENGJingqi/GraphAI-for-TCM), providing a scalable and interpretable platform for TCM mechanism research and discovery of bioactive herbal constituents.

Objective To explore the difference in terahertz signal characteristics between rat skin scar and normal skin using terahertz time-domain spectroscopy technology,thereby providing a novel non-invasive detection technique for the pathological examination of skin scars.Methods A rat model of whole-layer skin defect was prepared,and a reflectance terahertz time-domain spectroscopy system was used to obtain the terahertz signal maps of normal skin and scarred area.Results The terahertz signals of normal skin showed two obvious reflection time-domain signal peaks,and the characteristics of the reflection peaks at different reflection points were relatively regular.The terahertz signals of skin scar also had two obvious reflection time-domain signal peaks,but the highest peak was lower than that of normal skin.In addition,principal component analysis revealed that skin scar signals and normal skin signals were clustered together separately.The terahertz signal at different sites differed significantly(P<0.05).Conclusion Terahertz time-domain spectroscopy technology can be applied to the non-invasive detection of skin scarring,exhibiting a good application prospect in biomedicine.

Traditional Chinese medicine(TCM)features complex compatibility mechanisms involving multi-component,multi-target,and multi-pathway interactions.This study presents an interpretable graph artificial intelligence(GraphAI)framework to quantify such mechanisms in Chinese herbal formulas(CHFs).A multidimensional TCM knowledge graph(TCM-MKG;https://zenodo.org/records/13763953)was constructed,integrating seven standardized modules:TCM terminology,Chinese patent medicines(CPMs),Chinese herbal pieces(CHPs),pharmacognostic origins(POs),chemical compounds,biological targets,and diseases.A neighbor-diffusion strategy was used to address the sparsity of compound-target associations,increasing target coverage from 12.0％to 98.7％.Graph neural networks(GNNs)with attention mechanisms were applied to 6,080 CHFs,modeled as graphs with CHPs as nodes.To embed domain-specific semantics,virtual nodes medicinal properties,i.e.,therapeutic nature,flavor,and me-ridian tropism,were introduced,enabling interpretable modeling of inter-CHP relationships.The model quantitatively captured classical compatibility roles such as"monarch-minister-assistant-guide",and uncovered TCM etiological types derived from diagnostic and efficacy patterns.Model validation using 215 CHFs used for coronavirus disease 2019(COVID-19)management highlighted Radix Astragali-Rhi-zoma Phragmitis as a high-attention herb pair.Mass spectrometry(MS)and target prediction identified three active compounds,i.e.,methylinissolin-3-O-glucoside,corydalin,and pingbeinine,which converge on pathways such as neuroactive ligand-receptor interaction,xenobiotic response,and neuronal func-tion,supporting their neuroimmune and detoxification potential.Given their high safety and dietary compatibility,this herb pair may offer therapeutic value for managing long COVID-19.All data and code are openly available(https://github.com/ZENGJingqi/GraphAI-for-TCM),providing a scalable and inter-pretable platform for TCM mechanism research and discovery of bioactive herbal constituents.

Objective To explore the effect of SGLT2 inhibitor(SGLT2i)Dagaglipzin(Dap)on mitochondrial autophagy in cardiomyocytes in diabetic cardiomyopathy(DCM)by regulating mitochondrial membrane transporter TOM20.Methods H9C2 cardiomyocytes cultured in vitro were divided into normal control(Con)group,HG+PA group,knockout TOM20(HG+PA+siTOM20)group,knockout control(HG+PA+siNC)group,Dap intervention(HG+PA+Dap)group,and solvent control(HG+PA+DMSO)group.The expression of TOM20 was predicted by RNA-seq second-generation sequencing in HG+PA group.The expression of TOM20 and mitochondrial autophagy related proteins was detected by Western blot,the mitochondrial membrane potential was measured by immunofluorescence staining,and the mitochondrial autophagy level was evaluated by transmission electron microscopy.Results Compared with Con group,protein expressions of TOM20 and P62 were increased(P<0.05),while protein expressions of ULK1,Parkin,Beclin1 and LC3-B were decreased(P<0.05),mitochondrial membrane potential was destroyed,the number of mitochondrial autophagosomes was reduced,and autophagy activity was inhibited in HG+PA group.Compared with HG+PA+siNC group and HG+PA+DMSO group,the protein expressions of TOM20 and P62 were decreased(P<0.05),while the protein expressions of ULK1,Parkin,Beclin1 and LC3-B were increased(P<0.05),the damage of mitochondrial membrane potential decreased,the number of mitochondrial autophagosomes increased,and the inhibition of autophagy activity reversed in HG+PA+siTOM20 and HG+PA+DAPA groups.Conclusions SGLT2 inhibitors appear to partially restore mitochondrial function in diabetic cardiomyopathy by suppressing TOM20 expression,potentially through activation of mitochondrial autophagy.

With the popularization of 5G communication technology and the continuous upgrade of robot-assisted surgery system,telesurgery has developed rapidly.However,there are few of reports about this technique in single-port laparoscopic gynecological surgery.On April 19,2024,the surgeons at the Second Affiliated Hospital of Naval Medical University in Shanghai successfully implemented robot-assisted single-port laparoscopic bilateral adnexectomy for a patient who was admitted to the Naval Hospital of the Eastern Theater Command in Zhoushan,Zhejiang Province through 5G communication technology.The operation time was 90 min,intraoperative bleeding was 20 ml,and no intraoperative complications occurred.There were no adverse events caused by robots such as robot system failure and instrument failure,or adverse events caused by remote communication such as network interruption and network attack.Intraoperative user datagram protocol(UDP)real-time monitoring data showed an average delay of 108 ms(range,105-111 ms)and a packet loss rate of 0.04%.The surgeons had a slight sense of delay when the operation amplitude was too large.There was no obvious stalling which affected the process of the operation.The patient was able to move around on the first day after surgery,and the catheter was removed.No postoperative complications occurred.The patient was discharged from the hospital on the second day after surgery.Postoperative pathological results revealed left fallopian tube ovarian serous cystadenofibroma,fallopian tubal tissue;right fallopian tube ovarian,sent for examination as ovarian and fallopian tube tissue.There were no complaints of discomfort during reexamination one month after surgery,and the umbilical incision healed well.This case is an attempt of telesurgery in the field of gynecology,and provides experiences for the further development of this technique.