The intensive care unit (ICU) is a highly equipment-intensive area with a wide variety of medical devices, and the accuracy and timeliness of medical equipment data collection are highly demanded. The integration of the Internet of Things (IoT) into ICU medical devices is of great significance for enhancing the quality of medical care and nursing, as well as for the advancement of digital and intelligent ICUs. This study focuses on the construction of the IOT for ICU medical devices and proposes innovative solutions, including the overall architecture design, devices connection, data collection, data standardization, platform construction and application implementation. The overall architecture was designed according to the perception layer, network layer, platform layer and application layer; three modes of device connection and data acquisition were proposed; data standardization based on Integrating the Healthcare Enterprise-Patient Care Device (IHE-PCD) was proposed. This study was practically verified in the Chinese People's Liberation Army General Hospital, a total of 122 devices in four ICU wards were connected to the IoT, storing 21.76 billion data items, with a data volume of 12.5 TB, which solved the problem of difficult systematic medical equipment data collection and data integration in ICUs. The remarkable results achieved proved the feasibility and reliability of this study. The research results of this paper provide a solution reference for the construction of hospital ICU IoT, offer more abundant data for medical big data analysis research, which can support the improvement of ICU medical services and promote the development of ICU to digitalization and intelligence.
Intensive Care Units ; Internet of Things ; Humans ; Internet ; Data Collection

Objective:In order to meet the needs of building Internet of Things(IoT)of medical equipment for mobile deployment,rapid deployment,high-speed and stable data transmission,a wireless IoT acquisition terminal for medical equipment on the basis of Wi-Fi 6 was developed.Methods:Wi-Fi 6 technique was adopted to construct IoT of medical equipment,and the data acquisition terminal included Wi-Fi 6-based customer premises equipment(CPE)and intelligent wireless access point(AP).The CPE adopted a domestic main control chip and Wi-Fi chips,which included two 2.4G and 5G antennas,and was compatible with multiple interfaces such as RS232 and RJ45.The data of medical equipment were converted into wireless transmission through wired communication interfaces.The security access and data traceability of medical equipment were supported through secure secondary authentication with security control enhanced by"white list plus certificate".The intelligent wireless AP was compatible with various RF devices such as Wi-Fi,bluetooth,radio frequency identification,etc.(included 2.4G and 5G antennas).CPE and AP jointly apply dual-transmitter selection technique to ensure stable data transmission.Results:The key performance of wireless IoT acquisition terminals has been tested,and the results indicated that the integrity of acquisition data of intelligent acquisition terminal was consistent with that of output data,with a maximum latency of 9 ms and an average latency of 2 ms.The tested results can meet the expected requirements.Conclusion:The wireless IoT data of medical equipment that based on the acquisition terminal can stably and quickly collect data of equipment to IoT platform,providing paradigm for the construction of wireless IoT of medical equipment.

Bladder paraganglioma is a rare neuroendocrine tumor, accounting for only 0.05% of all bladder tumors. This article reports the diagnosis and treatment of a 16-year-old male patient with acute hemorrhage secondary to a giant bladder paraganglioma(approximately 10 cm in maximum diameter). Preoperative imaging evaluation suggested locally advanced disease, and the patient subsequently received three cycles of neoadjuvant chemotherapy with temozolomide. He patient's blood tests revealed hemorrhagic shock. During the waiting period of surgery, hemostasis was successfully achieved through emergency transarterial embolization. Subsequently, the patient underwent emergency radical cystectomy combined with orthotopic ileal neobladder reconstruction under general anesthesia and recovered well after surgery. Postoperative pathological examination confirmed the diagnosis of bladder paraganglioma, with positive immunohistochemical staining for succinate dehydrogenase subunit B and a Ki-67 proliferation index of 3%. At the 6-week follow-up, the patient's blood pressure and endocrine parameters had returned to normal, with a satisfactory quality of life. This case demonstrates that a multidisciplinary team approach can effectively integrate expertise from various specialties to formulate comprehensive and systematic treatment plans, which is crucial for ensuring successful management of such complex cases.

Objective To construct a risk prediction model for post-stroke dysphagia(PSD)based on clinical and laboratory indicators of elderly stroke patients with explainable machine learning.Methods A retrospective analysis was conducted on 3994 stroke patients hospitalized in Depart-ment of Neurology of First Medical Center of Chinese PLA General Hospital from October 2010 to December 2021.Among them,the 1390 cases admitted during January 2019 and December 2021 were assigned into an external validation set,and the 2604 cases admitted during October 2010 to January 2019 were into a training group.Those from the training group were further divided into a training set(1823 cases)and an internal validation set(781 cases)in a 7∶3 ratio,and also grouped into a PSD subgroup(773 cases)and a non-PSD group(1831 cases).With occurrence of swallowing difficulties as an endpoint,risk prediction models were constructed using random for-est(RF),eXtreme Gradient Boosting(XGBoost),Support Vector Machine(SVM),and logistic regression.ROC curve analysis was employed to evaluate the performance of our models.After the optimal model was selected,SHAP was employed to interpret feature contributions.Results There were significant differences in muscle strength,right/left-sided stroke,and area of brain in-jury between the PSD and the non-PSD groups(P＜0.01).The PSD group had obviously larger proportions of hypertension,diabetes,and drinking history,increased neutrophil counts,and de-creased levels of potassium and albumin when compared with the non-PSD group(P＜0.05,P＜0.01).Multivariate logistic regression analysis showed that age,drinking history,diabetes,hyper-tension,muscle strength grade,area of brain injury,hemispheric stroke,neutrophil count,and al-bumin and potassium levels were risk factors for PSD(P＜0.05,P＜0.01).The external validation results showed that the area under curve value of the RF model,XGBoost model,SVM model,and our logistic model was 0.883,0.902,0.877,and 0.868,respectively.The distribution of SHAP value showed that drinking history,hypertension and diabetes were positively correlated with PSD risk;Muscle strength was negatively correlated with the risk;Age growth was positively correlated with the risk;Subtentorial lesions showed stronger predictive efficacy than supratentorial lesions and entire lesions;The bilateral and right-sided stroke had higher risk for PSD than the left-sided stroke.Conclusion The model based on the XGBoost model shows best performance in predicting the risk for swallowing disorders in elderly patients after stroke.

Objective To construct a risk prediction model for post-stroke dysphagia(PSD)based on clinical and laboratory indicators of elderly stroke patients with explainable machine learning.Methods A retrospective analysis was conducted on 3994 stroke patients hospitalized in Depart-ment of Neurology of First Medical Center of Chinese PLA General Hospital from October 2010 to December 2021.Among them,the 1390 cases admitted during January 2019 and December 2021 were assigned into an external validation set,and the 2604 cases admitted during October 2010 to January 2019 were into a training group.Those from the training group were further divided into a training set(1823 cases)and an internal validation set(781 cases)in a 7∶3 ratio,and also grouped into a PSD subgroup(773 cases)and a non-PSD group(1831 cases).With occurrence of swallowing difficulties as an endpoint,risk prediction models were constructed using random for-est(RF),eXtreme Gradient Boosting(XGBoost),Support Vector Machine(SVM),and logistic regression.ROC curve analysis was employed to evaluate the performance of our models.After the optimal model was selected,SHAP was employed to interpret feature contributions.Results There were significant differences in muscle strength,right/left-sided stroke,and area of brain in-jury between the PSD and the non-PSD groups(P＜0.01).The PSD group had obviously larger proportions of hypertension,diabetes,and drinking history,increased neutrophil counts,and de-creased levels of potassium and albumin when compared with the non-PSD group(P＜0.05,P＜0.01).Multivariate logistic regression analysis showed that age,drinking history,diabetes,hyper-tension,muscle strength grade,area of brain injury,hemispheric stroke,neutrophil count,and al-bumin and potassium levels were risk factors for PSD(P＜0.05,P＜0.01).The external validation results showed that the area under curve value of the RF model,XGBoost model,SVM model,and our logistic model was 0.883,0.902,0.877,and 0.868,respectively.The distribution of SHAP value showed that drinking history,hypertension and diabetes were positively correlated with PSD risk;Muscle strength was negatively correlated with the risk;Age growth was positively correlated with the risk;Subtentorial lesions showed stronger predictive efficacy than supratentorial lesions and entire lesions;The bilateral and right-sided stroke had higher risk for PSD than the left-sided stroke.Conclusion The model based on the XGBoost model shows best performance in predicting the risk for swallowing disorders in elderly patients after stroke.

Objective:In order to meet the needs of building Internet of Things(IoT)of medical equipment for mobile deployment,rapid deployment,high-speed and stable data transmission,a wireless IoT acquisition terminal for medical equipment on the basis of Wi-Fi 6 was developed.Methods:Wi-Fi 6 technique was adopted to construct IoT of medical equipment,and the data acquisition terminal included Wi-Fi 6-based customer premises equipment(CPE)and intelligent wireless access point(AP).The CPE adopted a domestic main control chip and Wi-Fi chips,which included two 2.4G and 5G antennas,and was compatible with multiple interfaces such as RS232 and RJ45.The data of medical equipment were converted into wireless transmission through wired communication interfaces.The security access and data traceability of medical equipment were supported through secure secondary authentication with security control enhanced by"white list plus certificate".The intelligent wireless AP was compatible with various RF devices such as Wi-Fi,bluetooth,radio frequency identification,etc.(included 2.4G and 5G antennas).CPE and AP jointly apply dual-transmitter selection technique to ensure stable data transmission.Results:The key performance of wireless IoT acquisition terminals has been tested,and the results indicated that the integrity of acquisition data of intelligent acquisition terminal was consistent with that of output data,with a maximum latency of 9 ms and an average latency of 2 ms.The tested results can meet the expected requirements.Conclusion:The wireless IoT data of medical equipment that based on the acquisition terminal can stably and quickly collect data of equipment to IoT platform,providing paradigm for the construction of wireless IoT of medical equipment.

Intelligent medical devices are flourishing with the deep integration of modern information and artificial intelligence technologies into healthcare.Testing is an important means of performance evaluation and quality control for intelligent medical devices.Compared with traditional medical devices,the testing methods and technologies of intelligent medical devices are still immature,and need active research to promote the progress in this area.Intelligent medical devices are classified according to their characteristics as artificial intelligence medical devices in the form of software and medical robots based on a general discussion of their development.The medical-device Internet of Things(IoT)system has also been included due to its close relation to the construction of smart hospitals.For each type of intelligent medical device,testing indexes and testing plans are discussed.It is suggested that specific test rules should be further developed for various specific devices.Besides,the evaluation method of complex intelligent systems should be introduced and real-world data should be used for evaluation.This paper aims to accelerate the development of intelligent medical device testing,laying the foundation for quality control and performance evaluation of intelligent medical devices.

Objective:To Compare perioperative indicators of open pancreaticoduodenectomy (OPD), laparoscopic pancreaticoduodenectomy (LPD), and robotic pancreaticoduodenectomy (RPD) using propensity score matching (PSM).Methods:A retrospective analysis of the clinical data of 167 patients with periampullary lesions who underwent pancreaticoduodenectomy at the First Affiliated Hospital of Zhengzhou University from January 2018 to March 2022. The cohort included 100 males and 67 females, with age of (58.92±11.47) years. Based on the surgical approach, patients were divided into three groups: OPD group ( n=67), LPD group ( n=58), and RPD group ( n=42). Clinical data such as gender, age, operation time, and postoperative complications were collected. PSM was employed to eliminate confounding factors and evaluate the effect of different surgical methods on perioperative outcomes. Results:After PSM, there were 42 cases in the OPD group, 29 cases in the LPD group, and 25 cases in the RPD group. The baseline characteristics of the three groups were compared, and no statistically significant differences were found (all P>0.05). The operation time in the LPD group was longer than that in the OPD group [6.0 (5.1, 7.1) h vs. 4.8 (4.1, 5.3) h, Z=221.50, P<0.001] and the RPD group [6.0 (5.1, 7.1) h vs. 5.3 (4.5, 6.0) h, Z=222.00, P=0.015], with statistically significant differences. The intraoperative blood transfusion volume in the OPD group was higher than that in the RPD group [0 (0, 600.0) ml vs. 0 ml], with a statistically significant difference ( Z=368.50, P=0.011). The length of hospital stay in the OPD group was longer than that in the LPD group [15.5(12.8, 22.3) d vs. 11.0(9.5, 16.0) d, Z=354.50, P=0.003] and the RPD group [15.5(12.8, 22.3) d vs. 11.0(8.5, 15.5) d, Z=289.00, P=0.002], with statistically significant differences. The duration of intravenous analgesic use in the OPD group was longer than that in the RPD group [1.5(0, 3.0) d vs. 0(0, 1.0) d], with a statistically significant difference ( Z=310.50, P=0.004). Additionally, the time to gastric tube removal after surgery in the OPD group was longer than that in the LPD group [3.0(2.0, 4.0) d vs. 2.0(2.0, 3.0) d, Z=392.50, P=0.009] and the RPD group [3.0(2.0, 4.0) d vs. 2.0(1.0, 3.5) d, Z=297.50, P=0.003], with statistically significant differences. There were no statistically significant differences in postoperative complications among the three groups. Conclusion:Compared with LPD, RPD had a shorter operation time; compared with OPD, both LPD and RPD were able to reduce hospital stay and intravenous analgesic use, and decrease intraoperative blood transfusion.

Objective:To Compare perioperative indicators of open pancreaticoduodenectomy (OPD), laparoscopic pancreaticoduodenectomy (LPD), and robotic pancreaticoduodenectomy (RPD) using propensity score matching (PSM).Methods:A retrospective analysis of the clinical data of 167 patients with periampullary lesions who underwent pancreaticoduodenectomy at the First Affiliated Hospital of Zhengzhou University from January 2018 to March 2022. The cohort included 100 males and 67 females, with age of (58.92±11.47) years. Based on the surgical approach, patients were divided into three groups: OPD group ( n=67), LPD group ( n=58), and RPD group ( n=42). Clinical data such as gender, age, operation time, and postoperative complications were collected. PSM was employed to eliminate confounding factors and evaluate the effect of different surgical methods on perioperative outcomes. Results:After PSM, there were 42 cases in the OPD group, 29 cases in the LPD group, and 25 cases in the RPD group. The baseline characteristics of the three groups were compared, and no statistically significant differences were found (all P>0.05). The operation time in the LPD group was longer than that in the OPD group [6.0 (5.1, 7.1) h vs. 4.8 (4.1, 5.3) h, Z=221.50, P<0.001] and the RPD group [6.0 (5.1, 7.1) h vs. 5.3 (4.5, 6.0) h, Z=222.00, P=0.015], with statistically significant differences. The intraoperative blood transfusion volume in the OPD group was higher than that in the RPD group [0 (0, 600.0) ml vs. 0 ml], with a statistically significant difference ( Z=368.50, P=0.011). The length of hospital stay in the OPD group was longer than that in the LPD group [15.5(12.8, 22.3) d vs. 11.0(9.5, 16.0) d, Z=354.50, P=0.003] and the RPD group [15.5(12.8, 22.3) d vs. 11.0(8.5, 15.5) d, Z=289.00, P=0.002], with statistically significant differences. The duration of intravenous analgesic use in the OPD group was longer than that in the RPD group [1.5(0, 3.0) d vs. 0(0, 1.0) d], with a statistically significant difference ( Z=310.50, P=0.004). Additionally, the time to gastric tube removal after surgery in the OPD group was longer than that in the LPD group [3.0(2.0, 4.0) d vs. 2.0(2.0, 3.0) d, Z=392.50, P=0.009] and the RPD group [3.0(2.0, 4.0) d vs. 2.0(1.0, 3.5) d, Z=297.50, P=0.003], with statistically significant differences. There were no statistically significant differences in postoperative complications among the three groups. Conclusion:Compared with LPD, RPD had a shorter operation time; compared with OPD, both LPD and RPD were able to reduce hospital stay and intravenous analgesic use, and decrease intraoperative blood transfusion.

With the progress of science and technology and the increase of clinical demand, medical robots have developed rapidly and played a important role in promoting the medical cause. Service robot is a branch of medical robot, which is mainly oriented to medical service and assistance needs, and has been applied in many medical scenarios and achieved demonstration effects. This research first describes the development of medical service robots, and then summarizes the key technologies and clinical applications of robots. Finally, it points out the challenges and directions that medical service robots face at present, and puts forward prospects for their further development in the medical field.
Robotics ; Technology