To address the current issues of data imbalance and scarcity in photoplethysmography (PPG) data for type 2 diabetes mellitus (T2DM) prediction, this study proposes an improved conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP). The algorithm integrated gated recurrent unit (GRU) networks and self-attention mechanisms to construct a generator, aiming to produce high-quality PPG signals. Various data augmentation methods, including the improved CWGAN-GP, were employed to expand the PPG dataset, and multiple classifiers were applied for T2DM prediction analysis. Experimental results showed that the model trained on data generated by the improved CWGAN-GP achieved the optimal prediction performance. The highest accuracy reached 0.895 0, and compared with other data enhancement methods, this approach exhibited significant advantages in terms of precision and F1-score. The generated data notably enhances the accuracy and generalization ability of T2DM prediction models, providing a more reliable technical basis for non-invasive early T2DM screening based on PPG signals.
Photoplethysmography/methods* ; Diabetes Mellitus, Type 2/diagnosis* ; Humans ; Algorithms ; Neural Networks, Computer ; Signal Processing, Computer-Assisted ; Prediction Algorithms

Objective To investigate the clinical advantages and safety of an acupoint auto-positioning moxibustion robot combined with massage techniques in the treatment of lumbar disc herniation.Methods Totally 114 patients with lumbar disc herniation treated between June 2021 and December 2023 at Yueyang Hospital of Integrated Traditional Chinese and Western Medicine,Shanghai University of Traditional Chinese Medicine,the Outpatient Department of Rehabilitation Medicine,Changhai Hospital and Shanghai Third Rehabilitation Hospital were divided into control group and experimental group with random number table method,with 57 cases in each group.The control group received conventional moxibustion combined with massage techniques,while the experimental group was treated using an acupoint auto-positioning moxibustion robot combined with massage techniques.Both groups underwent treatment once every three days,totaling 10 sessions over one month.Clinical efficacy was observed between the two groups by comparing pre-treatment and post-treatment(after 3,6 and 10 sessions)scores on the visual analogue scale(VAS)for pain,the Japanese Orthopaedic Association(JOA)lower back pain score,and lumbar range of motion(LROM).Adverse reactions during the intervention were recorded.Satisfaction with the moxibustion robot in the experimental group was assessed using a Likert scale.Additionally,20 healthy subjects were recruited to evaluate the accuracy of the robot's acupoint auto-positioning function.Results The overall effective rate was 91.23%(52/57)in the experimental group and 94.74%(54/57)in the control group,without statistical significance between the two groups(P>0.05).Compared to pre-treatment,both groups showed significant improvements in VAS scores,JOA scores and LROM across all measured directions after 3,6,and 10 treatment sessions(P<0.001).In the Likert scale assessment,86.96%of subjects agreed that the device was convenient to use,87.72%agreed that the device was safer than conventional moxibustion therapy,and 94.74%were willing to recommend the device to other patients.The accuracy evaluation of the acupoint auto-positioning moxibustion robot demonstrated that the average deviation between robot-positioned acupoints and standard acupoints was(1.68±0.46)mm,achieving a positioning accuracy rate exceeding 95%.No adverse reactions were reported during the intervention.Conclusion The combination of an acupoint auto-positioning moxibustion robot with massage techniques is as effective as conventional moxibustion combined with massage techniques in improving clinical symptoms,alleviating pains,enhancing lumbar function and increasing lumbar mobility in patients with lumbar disc herniation.Participants have exhibited a high willingness to use the device,and the robot achieved a high accuracy rate in acupoint positioning.

Objective:To compare the short- and long-term outcomes of robotic versus laparoscopic gastrectomy in patients with locally advanced gastric cancer after neoadjuvant chemotherapy.Methods:Data from 321 patients with locally advanced gastric cancer undergoing neoadjuvant chemotherapy followed by robotic ( n=109) and laparoscopic ( n=212) radical gastrectomy at our center between May 2017 and Sep 2022 was collected. After 1∶1 propensity score matching, 106 patients from each group were included in the final analysis to compare short-term clinical outcomes and long-term prognostic indicators. Results:The robotic group had a significantly lower overall complication rate (13.2% vs. 28.3%, χ2=6.453, P=0.007) and surgery-related complication rate (8.5% vs. 17.9%, χ2=3.333, P=0.043) than the laparoscopic group. The robotic group also retrieved more total lymph nodes (35.3±4.9 vs. 31.4±6.3, t=4.863, P<0.001) and supra-pancreatic lymph nodes (13.1±3.4 vs. 10.1±2.1, t=5.258, P<0.001). Additionally, the robotic group had a shorter operative time [(218±47) min vs. (267±71) min, t=-6.001, P<0.001], less intraoperative blood loss [(47±12) ml vs. (71±17) ml, t=-5.424, P<0.001], and faster postoperative recovery. The 3-year recurrence-free survival rate was significantly higher in the robotic group compared to the laparoscopic group (75.5% vs. 62.3%, P=0.017). Conclusion:Compared with laparoscopic gastrectomy, robotic gastrectomy allows for a more lymph nodes harvest, significantly reduces intraoperative blood loss and complication rates and significantly improves recurrence-free survival.

Robot-assisted surgery with its advantages such as three-dimensional high-definition vision, dexterous robotic arms, and tremor filtration, is increasingly being applied to complex radical gastrectomy. However, the role of the surgical assistant remains crucial during the procedure. The assistant is responsible for tasks outside the console, including adjusting robotic arms, changing instruments, exposing the surgical field, and addressing unexpected situations. The technical proficiency of the assistant and their collaboration efficiency with the primary surgeon directly impact the smoothness of surgery and patients' outcomes. With the expansion of robot-assisted surgical indications, the establishment of a standardized training system and the optimization of team collaboration models have become urgent challenges to address. This article draws on the author's practical experience as an assistant in robot-assisted gastric cancer surgeries, conducting an in-depth analysis of the responsibilities and operational skills of surgical assistants in robot-assisted procedures. The aim is to develop a relatively comprehensive set of operational guidelines for surgical assistants in robot-assisted radical gastrectomy, providing valuable references for enhancing the overall efficiency of surgical teams and improving surgical outcomes.

Robot-assisted surgery with its advantages such as three-dimensional high-definition vision, dexterous robotic arms, and tremor filtration, is increasingly being applied to complex radical gastrectomy. However, the role of the surgical assistant remains crucial during the procedure. The assistant is responsible for tasks outside the console, including adjusting robotic arms, changing instruments, exposing the surgical field, and addressing unexpected situations. The technical proficiency of the assistant and their collaboration efficiency with the primary surgeon directly impact the smoothness of surgery and patients' outcomes. With the expansion of robot-assisted surgical indications, the establishment of a standardized training system and the optimization of team collaboration models have become urgent challenges to address. This article draws on the author's practical experience as an assistant in robot-assisted gastric cancer surgeries, conducting an in-depth analysis of the responsibilities and operational skills of surgical assistants in robot-assisted procedures. The aim is to develop a relatively comprehensive set of operational guidelines for surgical assistants in robot-assisted radical gastrectomy, providing valuable references for enhancing the overall efficiency of surgical teams and improving surgical outcomes.

Objective To investigate the clinical advantages and safety of an acupoint auto-positioning moxibustion robot combined with massage techniques in the treatment of lumbar disc herniation.Methods Totally 114 patients with lumbar disc herniation treated between June 2021 and December 2023 at Yueyang Hospital of Integrated Traditional Chinese and Western Medicine,Shanghai University of Traditional Chinese Medicine,the Outpatient Department of Rehabilitation Medicine,Changhai Hospital and Shanghai Third Rehabilitation Hospital were divided into control group and experimental group with random number table method,with 57 cases in each group.The control group received conventional moxibustion combined with massage techniques,while the experimental group was treated using an acupoint auto-positioning moxibustion robot combined with massage techniques.Both groups underwent treatment once every three days,totaling 10 sessions over one month.Clinical efficacy was observed between the two groups by comparing pre-treatment and post-treatment(after 3,6 and 10 sessions)scores on the visual analogue scale(VAS)for pain,the Japanese Orthopaedic Association(JOA)lower back pain score,and lumbar range of motion(LROM).Adverse reactions during the intervention were recorded.Satisfaction with the moxibustion robot in the experimental group was assessed using a Likert scale.Additionally,20 healthy subjects were recruited to evaluate the accuracy of the robot's acupoint auto-positioning function.Results The overall effective rate was 91.23%(52/57)in the experimental group and 94.74%(54/57)in the control group,without statistical significance between the two groups(P>0.05).Compared to pre-treatment,both groups showed significant improvements in VAS scores,JOA scores and LROM across all measured directions after 3,6,and 10 treatment sessions(P<0.001).In the Likert scale assessment,86.96%of subjects agreed that the device was convenient to use,87.72%agreed that the device was safer than conventional moxibustion therapy,and 94.74%were willing to recommend the device to other patients.The accuracy evaluation of the acupoint auto-positioning moxibustion robot demonstrated that the average deviation between robot-positioned acupoints and standard acupoints was(1.68±0.46)mm,achieving a positioning accuracy rate exceeding 95%.No adverse reactions were reported during the intervention.Conclusion The combination of an acupoint auto-positioning moxibustion robot with massage techniques is as effective as conventional moxibustion combined with massage techniques in improving clinical symptoms,alleviating pains,enhancing lumbar function and increasing lumbar mobility in patients with lumbar disc herniation.Participants have exhibited a high willingness to use the device,and the robot achieved a high accuracy rate in acupoint positioning.

Objective:To compare the short- and long-term outcomes of robotic versus laparoscopic gastrectomy in patients with locally advanced gastric cancer after neoadjuvant chemotherapy.Methods:Data from 321 patients with locally advanced gastric cancer undergoing neoadjuvant chemotherapy followed by robotic ( n=109) and laparoscopic ( n=212) radical gastrectomy at our center between May 2017 and Sep 2022 was collected. After 1∶1 propensity score matching, 106 patients from each group were included in the final analysis to compare short-term clinical outcomes and long-term prognostic indicators. Results:The robotic group had a significantly lower overall complication rate (13.2% vs. 28.3%, χ2=6.453, P=0.007) and surgery-related complication rate (8.5% vs. 17.9%, χ2=3.333, P=0.043) than the laparoscopic group. The robotic group also retrieved more total lymph nodes (35.3±4.9 vs. 31.4±6.3, t=4.863, P<0.001) and supra-pancreatic lymph nodes (13.1±3.4 vs. 10.1±2.1, t=5.258, P<0.001). Additionally, the robotic group had a shorter operative time [(218±47) min vs. (267±71) min, t=-6.001, P<0.001], less intraoperative blood loss [(47±12) ml vs. (71±17) ml, t=-5.424, P<0.001], and faster postoperative recovery. The 3-year recurrence-free survival rate was significantly higher in the robotic group compared to the laparoscopic group (75.5% vs. 62.3%, P=0.017). Conclusion:Compared with laparoscopic gastrectomy, robotic gastrectomy allows for a more lymph nodes harvest, significantly reduces intraoperative blood loss and complication rates and significantly improves recurrence-free survival.

To establish a disease risk prediction model based on genetic susceptibility genes and environmental risk factors， which can target high-risk population as early as possible， and intervene in the environmental risk factors in this population. Moreover， accurate screening of genetically susceptible populations can enhance the efficiency of health system. In recent years， with the maturation and cost reduction of high-throughput gene testing， gene testing has been widely used in individual clinical decision-making and will play a more important role in medical and health decision-making. The correlation between genetic testing and disease risk prediction is increasing， making it a prominent research topic in this field. This review summarizes the approaches for establishing and evaluating risk prediction models and discusses potential future challenges and opportunities.

When facing two or more choices， sound decision-making is critical. In the field of clinical medical practice and public health， more and more researchers use decision-making analysis as an important tool to assist in making the optimal choices. Public health emergencies have the characteristics of group cases， sudden and uncertain. In addition to causing serious damage to public health， they may also have varying degrees of impact on socio-economic， psychological and even social stability. At present， we have not seen the application of mature and sound decision analysis in public health emergency response. This paper reviewed the development of decision analysis in the medical field and the application of common decision-making models in clinical practice. Combined with the current situation of global infectious disease outbreaks and prevention and control， this paper puts forward the concepts and prospects of establishing an auxiliary decision-making system for public health emergencies， aiming to provide a scientific method for medical and health workers to respond to public health emergencies.

Statistics plays an important role in medical research， and the selection of appropriate statistical methods is crucial for drawing reliable and valuable conclusions. This paper provides a brief introduction to commonly used statistical analysis methods for medical data， covering descriptive analysis， parametric test， nonparametric test， correlation analysis， regression analysis， and analysis of survival data. It focuses on discussing the assumptions of multiple linear regression， logistic regression and Cox proportional risk regression， as well as how to choose the appropriate statistical methods for analyzing and interpreting medical data based on different research objectives and data types.