ABSTRACT
Medical Artificial Intelligence (AI) makes the traditional doctor-patient relationship present a new pattern, but also highlights many ethical problems: inability to protect the rights and interests of patients, weakening the main responsibility of medical personnel, weakening the practical ability of medical personnel, and challenging the main status of medical personnel, etc.. It is necessary to improve relevant laws, regulations and regulatory system, adhere to the main status of medical personnel, improve the public awareness and acceptance of medical AI, and strengthen the construction of ethical system of AI, so as to deal with the ethical anomie caused by intelligent medical treatment and promote the harmonious development of doctor-patient relationship. It is expected that through the combination of AI and professional ethics principles, AI will be brought into daily clinical practice responsibly, to provide patients with better medical services.
ABSTRACT
This paper provides a comprehensive analysis of the current state of intelligent ophthalmology in China, including technological advancements, academic exchange platforms, policy support, future challenges, and potential solutions. Technologically, remarkable progress have been made in various areas of intelligent ophthalmology in China, including diabetic retinopathy, fundus image analysis, and crucial aspects such as quality assessment of medical artificial intelligence products, clinical research methods, technological evaluation, and industrial standards. Researchers are constantly improving the safety and standardization of intelligent ophthalmology technology by formulating clinical application guidelines and standards. Academic exchange platforms have been established to provide extensive collaboration opportunities for professionals across diverse fields, and various academic journals serve as publication platforms for intelligent ophthalmology research. Regarding public policy, the Chinese government has not only established a supportive policy environment for the advancement of intelligent ophthalmology through various documents and regulations, but provided a legal basis and management framework. However, there are still challenges to overcome, such as technological innovation, data privacy and security, outdated regulations, and talent shortages. To tackle these issues, there is a requirement for increased technological research and development, the establishment of regulatory frameworks, talent cultivation, and greater awareness and acceptance of new technologies among patients. By comprehensively addressing these challenges, intelligent ophthalmology in China is expected to continue leading the industry's global development, bringing more innovation and convenience to the field of ophthalmic healthcare.
ABSTRACT
@#The biomedicine industry is a strategic emerging industry that is related to the national economy,people's livelihood,and national security. As a new generation of digital production technology,the intelligent manufacturing of biopharmaceuticals has been proposed by policies such as the“14th Five Year Plan”for the development of the bioeconomy,and has become an important direction for the transformation and upgrading of the biopharmaceutical industry. This paper started with the background and significance of studying the intelligent transformation of the biopharmaceutical industry,analyzed the goals of the intelligent transformation of biopharmaceutical enterprises,and proposed relevant countermeasures and suggestions to accelerate the promotion of high-end intelligent transformation of the domestic biopharmaceutical industry.
ABSTRACT
Objective@#To research the effectiveness of deep learning techniques in intelligently diagnosing dental caries and periapical periodontitis and to explore the preliminary application value of deep learning in the diagnosis of oral diseases@*Methods@#A dataset containing 2 298 periapical films, including healthy teeth, dental caries, and periapical periodontitis, was used for the study. The dataset was randomly divided into 1 573 training images, 233 validation images, and 492 test images. By comparing various neural network models, the MobileNetV3 network model with better performance was selected for dental disease diagnosis, and the model was optimized by tuning the network hyperparameters. The accuracy, precision, recall, and F1 score were used to evaluate the model's ability to recognize dental caries and periapical periodontitis. Class activation map was used to visualization analyze the performance of the network model@*Results@#The algorithm achieved a relatively ideal intelligent diagnostic effect with precision, recall, and accuracy of 99.42%, 99.73%, and 99.60%, respectively, and the F1 score was 99.57% for classifying healthy teeth, dental caries, and periapical periodontitis. The visualization of the class activation maps also showed that the network model can accurately extract features of dental diseases.@*Conclusion@#The tooth lesion detection algorithm based on the MobileNetV3 network model can eliminate interference from image quality and human factors and has high diagnostic accuracy, which can meet the needs of dental medicine teaching and clinical applications.
ABSTRACT
In this Paper With the aid of AI techniques, this study aims to predict the early detection of chronic kidney disease, also known as chronic renal disease, in diabetic patients. It then suggests a decision tree to reach specific conclusions with desired accuracy by evaluating its performance in relation to its specification and sensitivity. Methods: The behaviour of learning algorithms based on a set of data mining indicators affects the models that are produced proportionately. Predicting the future is no longer a difficult task thanks to the promises of predictive analytics in big data and the use of machine learning algorithms, especially for the health sector, which has undergone significant evolution as a result of the development of new computer technologies that gave rise to numerous fields of study research. Many initiatives are made to deal with the explosion of medical data on the one hand, and to learn meaningful information from it, forecast diseases, and anticipate treatments on the other. To extract meaningful information and aid in decision-making, researchers used all the technological advancements, including big data analytics, predictive analytics, machine learning, and learning algorithms.
ABSTRACT
Artificial intelligence algorithms play an important role in the medical field with their unique technological advantages and operational logic. However, due to the " black box" nature and security flaws of artificial intelligence algorithms, there were problems in the application of intelligent medical algorithms, such as the alienation of medical personnel′s subject status, the alienation of right to informed consent for diagnosis and treatment, the alienation of health fairness, and the alienation of health information security. At the same time, there were some practical difficulties in the process of regulating risks, such as the difficulty in determining the responsibility of the legal person, the incompleteness of the causal chain, the lag of the scene regulation of laws and regulations, and the increasing difficulty in protecting health information. In order to prevent the alienation of power in medical intelligent algorithms and promote the healthy development of intelligent medicine, the author suggested to adhere to the embedding of tool attributes in the underlying logic of medical algorithms, enhance the interpretability of medical algorithms, improve relevant laws and regulations, and strengthen the risk supervision mechanism of intelligent medical algorithms.
ABSTRACT
Day surgery can effectively improve the utilization of medical resources. In October 2015, an obstetrics and gynecology hospital established a gynecological day surgery center to centrally manage gynecological day surgery and continuously optimize the management process. In July 2019, the hospital established an intelligent information platform for gynecological daytime surgery managemen. Based on this platform, the " evaluation-appointment-hospitalization-follow-up-chronic disease management" information management process was implemented, the " pre hospital-in hospital-post hospital" full process medical quality and safety monitoring was carried out to form a centralized closed-loop management mode for gynecological day surgery led by gynecologists. Under this management mode, the number of gynecological day surgeries in the hospital has increased from 2 866 cases in 2019 to 4 065 cases in 2021, providing convenient medical services and personalized chronic disease management services, and ensuring the quality and safety of gynecological day medical care, for reference for promoting the high-quality development of day surgeries in specialized hospitals.
ABSTRACT
Percutaneous nephrolithotripsy is the first line treatment for complete staghorn calculi, but there are risks such as renal function damage, bleeding, and infection. A case of complete staghorn calculi 8.3 cm×4.5 cm and mean CT value of 1 321 HU was reported. Urine culture suggested proteus mirabilis infection. The patient was given sensitive antibiotics for 3 days, and was treated with one session of natural orifice transluminal endoscopic lithotripsy with intelligent control of renal pelvic pressure. KUB on the first postoperative day showed residual stones of 1.0 cm×0.5 cm. There were no complications.
ABSTRACT
Objective:To investigate the necessity and feasibility of the virtual simulation teaching experiment software of the bronchoscopy intelligent navigation-based fiducial marker implantation technology in the clinical application of radiotherapy.Methods:This study developed a 3D virtual operation and interactive system using the Unity3D engine, tools including 3Dmax and Maya, and the SQL database. The scenes in the system were produced using the currently popular next-generation production process. Targeting the priorities and difficulties in the implantation of fiducial markers, the system developed in this study allowed for simulated demonstration and training based on 12 steps and 10 knowledge points. Internal tests and remote evaluation tests were adopted in this system to obtain the test result of each subject. Then, the application value of the system was analyzed based on the test result.Results:As of May 1, 2022, the system had received 2 409 views and 425 test participants, with an test completion rate of 100% and an experiment pass rate of 96.5%. Moreover, this system won unanimous praise from 167 users, primarily including the students majoring in multilevel medical imaging technology and medical imaging science from the Fujian Medical University, as well as the radiotherapy-related staff of this university.Conclusions:The virtual simulation teaching experiment software of the bronchoscopy intelligent navigation-based fiducial marker implantation technology can be applied to the teaching of students and the training of related professionals.
ABSTRACT
Objective:To evaluate the effectiveness and feasibility of 3D ResSE-Unet-based intelligent delineation of clinical target volume (CTV) in postoperative adjuvant radiotherapy for breast cancer.Methods:A total of 974 cases of breast cancer treated in the Cancer Diagnosis and Treatment Center of the Fourth Affiliated Hospital of Guangxi Medical University from September 2018 to June 2022 were enrolled in this study, including 614 cases receiving total mastectomy and 360 cases treated with breast-conserving surgery. They were divided into a training set, a validation set, and a testing set. The training set consisted of 874 cases and was used to build a model of 3D ResSE-Unet-based intelligent CTV delineation. The validation set comprised 40 cases and was used to evaluate the feasibility and effectiveness of the clinical application of AI-based CTV design in the radiotherapy for breast cancer. The testing set was composed of 60 cases and was used to test the accuracy of intelligent CTV. The Wilcoxon rank test was used to compare the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) obtained using the intelligent delineation model.Results:The intelligent delineation model showed high precision. The CTV of cases treated with total mastectomy (CTV cw) and the CTV of cases treated with breast-conserving surgery (CTV b) had DSCs greater than 0.80 and greater than 0.88, respectively. Therefore, compared with CTV cw, CTV b had a higher DSC (0.91 ± 0.03 vs.0.83 ± 0.05, t = 7.11, P < 0.05). Both CTV cw and CTV b had lower HD 95 [(7.56 ± 3.42) mm vs.(8.77 ± 5.89) mm] and ASD [(1.85 ± 0.71) mm vs.(1.86 ± 0.83)mm], without statistically significant difference ( P > 0.05). The left/right supraclavicular and infraclavicular CTV (CTV2) had DSCs greater than 0.8. CTV2 also had low average HD95 and ASD, without statistically significant difference ( P > 0.05). Conclusions:The 3D ResSE-Unet-based intelligent CTV delineation has better consistency and feasibility in postoperative adjuvant radiotherapy for breast cancer, especially the CTVs after breast-conserving surgery.
ABSTRACT
Objective:To evaluate the role of virtual bronchoscopy intelligent system in improving the theory and operation level of bronchoscopy in pulmonary and critical care medicine (PCCM) teaching for standardized training specialists.Methods:A total of 50 PCCM physicians who had participated in virtual bronchoscopy training in Xijing Hospital, Air Force Medical University from 2018 to 2021 were selected as research subjects. In this study, self-controlled method was adopted to evaluate the change of assessment indicators after 1 week and 2 weeks of training. Questionnaire survey was also used to evaluate the training effect. SPSS 23.0 software was used for paired t-test and Chi-square test. Results:All the 50 PCCM physicians successfully completed the training of virtual bronchoscopy operation. The theoretical score was significantly improved after the training [(80.0±5.2) points vs. (92.4±3.8) points]. The basic operation time [(1 050.9±103.3) s vs. (386.4±47.7) s], and the number of hitting the bronchial wall [(88.3±12.7) times vs. (27.0±5.3) times] were significantly reduced. The recovery rate of alveolar lavage fluid [(27.6±7.4)% vs. (58.0±8.2)%] and the positive rate of biopsy [(19.2±13.1)% vs. (86.8±10.8)%] were significantly increased. The learning curve of the final score indicated that the score improved more rapidly in the first week of training, and the score improved more slowly in the second week of training. Questionnaires before and after the training indicated that virtual intelligent training could significantly improve the confidence and proficiency of students in bronchoscopy.Conclusion:Through the systematic training of virtual bronchoscopy intelligent system, the PCCM physicians have significantly improved their theoretical knowledge and operational proficiency. Therefore, the virtual bronchoscopy training system has practical significance for improving the overall training effect of clinical bronchoscopy for PCCM trainees, which is worthy of promotion.
ABSTRACT
Objective:To investigate the application effect of the blended teaching model of "intelligent teaching" and "wisdom learning" in the practice teaching of integrated traditional Chinese and Western medicine in internal medicine.Methods:According to the principle of randomization, 54 interns in Class 1 of integrated traditional Chinese and Western medicine in the grade of 2019 were selected as control group and received traditional teaching, and 56 interns in Class 2 were selected as observation group and received blended teaching with "intelligent teaching" and "wisdom learning". After 6 months of internship, the two groups were compared in terms of the scores of theoretical assessment (basic theoretical knowledge and professional theoretical knowledge), clinical practice ability [Leicester Assessment Package (LAP)], and degree of satisfaction with teaching. SPSS 17.0 was used to perform the t-test and the chi-square test. Results:At the end of internship, compared with the control group, the observation group had significantly higher score of basic theoretical knowledge (41.53±3.42 vs. 38.71±3.38, P<0.05), score of professional theoretical knowledge (39.49±3.14 vs. 37.85±3.07, P<0.05), LAP score (84.32±6.65 vs. 78.46±6.17, P<0.05), and degree of satisfaction with teaching ( P<0.05). Conclusion:For interns majoring in integrated traditional Chinese and Western medicine, the blended teaching model of "intelligent teaching" and "wisdom learning" can strengthen their mastery of theoretical knowledge, enhance their clinical practice ability, and improve their degree of satisfaction with teaching.
ABSTRACT
Clinical laboratory instrumentation is a practical course. In order to change the limitations of the experimental site and the lack of large automatic testing instruments in the current teaching, this paper puts forward the idea of virtual simulation teaching of clinical laboratory instrument. Based on the training objective of medical laboratory application-oriented talents, the design and management of virtual simulation teaching of single instrument and comprehensive project training are formed. The teaching effect evaluation and quality control method are constructed, which significantly improves the students' autonomous learning ability and the comprehensive practical ability. It further promotes the connotation construction of medical laboratory experiment teaching with the help of Internet sharing advantages.
ABSTRACT
In order to improve the effectiveness of private class inquiry with the development of information teaching, the smart teaching platform has been established, with instructional management, curriculum setting, teacher preparation, classroom application, supervision and monitoring modules. Taking the platform as the medium, the small class inquiry learning community of entity curriculum is constructed between students and the teachers. In the eight-year medical teaching, the content of learning cycle is designed according to the entity curriculum, which is issued on cloud platform before class, in class and after class. Students learn basic concepts by themselves in the learning community, explore the application of knowledge under the guidance of teachers, and expand knowledge in class or after class. After having test in teaching procedure, the small class learning community based on smart teaching cloud platform has a submission rate, interaction rate and score rate of more than 90%. It can not only make full use of the advantages of information-based teaching resources, but also build face-to-face learning community in the course teaching, reflecting the emotional interaction of personalized teaching. It's suggested that new approaches to teaching should be student-centered and activity-based, engaging students actively in the learning process, which can promote students' autonomous learning ability and innovative thinking ability.
ABSTRACT
Objective:To explore the application effect of the intelligent ward combined with DMAIC in improving the procedure and shortening the time of operation, so as to provide a reasonable basis for optimizing and improving the operation process.Methods:This was a prospective study. A total of 240 patients with gynecological surgery hospitalized in Shengjing Hospital of China Medical University from August to November 2021 were selected as the research object. From August to September 2021, the routine management mode of staff in the operating room and ward was adopted as the control group, with a total of 120 cases. From October to November 2021, the intelligent ward combined with DMAIC mode of staff in the operating room and ward was adopted as the observation group, with a total of 120 cases. The time of receiving operation notice, preoperative preparation time, preparation time of transfer personnel, waiting time after the arrival of transfer personnel and the total time of receiving operation were compared between the two groups.Results:The time of receiving operation notice was (1.42 ± 0.61) min in the observation group, which was less than that in the control group (3.53 ± 1.12) min, the difference was statistically significant ( t=18.14, P<0.05). The preoperative preparation time was (8.43 ± 1.80) min in the observation group,which was less than that in the control group (11.36 ± 2.01) min, the difference was statistically significant ( t=11.89, P<0.05). There was no significant difference in the preparation time of transfer personnel between the two groups ( P>0.05). The waiting time after the arrival of transfer personnel was 2.33(1.75, 2.93) min in the observation group, which was less than that in the control group 5.19(3.46, 8.42) min, the difference was statistically significant ( t=-10.06, P<0.05). The total time of receiving operation was (23.90 ± 4.94) min in the observation group, which was less than that in the control group (28.84 ± 4.75) min, the difference was statistically significant ( t=7.90, P<0.05). Conclusions:The intelligent ward combined with DMAIC improves the operation receiving process of the ward, shortens the total time for receiving the operation, and effectively improves the work quality and efficiency of the medical staff.
ABSTRACT
Acupuncture has been proved to be safe and effective by large-scale and authoritative clinical observation at home and abroad. However, in recent years, the results of some randomized controlled trials of acupuncture in JAMA showed no significant difference between acupuncture effect and sham acupuncture effect. Acupuncture and moxibustion in clinical practice is a summary of academic and clinical rules. Different from chemical drugs, the amount of stimulation, methods of operation and techniques vary. At present, sham acupuncture in clinical trials at home and abroad has been questioned by many scholars, who believe that sham acupuncture is not fake, and call for "fake targeted research" to be stopped. In order to improve the sham acupuncture control design, 5G + VR technology and the principle elements of sham acupuncture should be combined. We also discussed and analyzed advantages and prospects of modern intelligent medical technology of 5G + VR technology in the sham acupuncture RCT. We hope to promote standardization of acupuncture clinical trials, and the development, innovation and application of acupuncture research at home and abroad.
ABSTRACT
Objective:To explore the application effect of an intelligent teaching robot system of lifting manipulation in cervical spine manipulation teaching.Methods:60 doctors were randomly divided into an experimental group ( n = 30) and a control group ( n = 30). The control group was taught by a certified chief physician using a combination of "PowerPoint presentations, video demonstrations, and operation demonstrations" . Each part is 5 min. The experimental group was taught by the intelligent teaching robot system with a spinning technique. The teaching time is 15 min for both groups. At the end of the two teaching sessions, the two groups were trained five times under different BMIs and passed the system assessment. The qualified rates of pre-traction force, lifting and pulling force, maximum force, pre-traction time, lifting and pulling time, rotation amplitude, and pitch amplitude were compared between the two groups. Results:In normal, there was significant differences between the qualified rates of pre-traction force, lifting and pulling force, maximum force, pre-traction time, lifting and pulling time, rotation amplitude, and pitch amplitude in two groups (all P<0.05). For overweight people, there were significant differences in pre-traction force, pulling force, maximum force, and rotation amplitude (all P <0.05), while there were no significant differences in pre-traction time, pulling time, or pitching amplitude (all P >0.05). In obesity, there were significant differences in pre-traction force, lifting and pulling force, maximum force, and pitch amplitude (all P <0.05), but no significant differences in pre-traction time, lifting and pulling time, or rotation amplitude (all P >0.05). Conclusions:The proposed system can improve the pass rate of spinning manipulation, especially by effectively controlling the pre-traction force, pulling force, and maximum force.
ABSTRACT
Objective:To investigate the effect of smart air cell mattresses on sleep quality.Methods:Twenty healthy young people were enrolled as subjects, and each subject underwent a four-night polysomnographic monitoring experiment, including two nights each on a smart air cell mattress and a general mattress. The differences in sleep quality were compared by self-assessment of sleep quality, objective sleep indicators, and electroencephalogram (EEG) spectral analysis.Results:In the comparison between the smart air cell mattress and the general mattress, the differences in self-assessment of sleep quality and objective sleep indicators were not statistically significant (all P > 0.05), but the smart air cell mattress had a slight overall advantage. The relative power of EEG in the low-frequency band and the relative power of EEG in the high-frequency band were higher in the subjects with the smart air cell mattress. Conclusions:For the healthy young population, the smart air cell mattress can positively influence sleep quality to some extent, and the change in EEG relative power indicates an increase in sleep depth.
ABSTRACT
OBJECTIVE To build an “integration of drug storage and dispensing” intelligent drug validity management system in outpatient pharmacy， and to evaluate the effect of this system. METHODS The information technology was used to connect the drug information in the primary storage， the intelligent secondary storage and the rapid dispensing machine； an “integration of drug storage and dispensing” intelligent drug validity management system was constructed. At the same time， the implementation effects of drug validity management system in outpatient pharmacy of our hospital were evaluated one year before and after the construction of the system. RESULTS By using information technology， intelligent closed-loop management of batch number and expiration date information throughout the entire process of drug circulation in outpatient pharmacy of our hospital had been achieved， making it easy to track and trace drug information. After the establishment of the intelligent system， the time spent on managing drug validity every month was reduced from 103 people·h to 8 people·h； the number of near-expired drugs per month had decreased from （30.67±1.10）types to （17.67±1.17）types（P＜0.05）. CONCLUSIONS The intelligent drug validity management system in outpatient pharmacy based on the mode of “integration of drug storage and dispensing” makes the drug validity management in the outpatient pharmacy more scientific， reasonable and efficient.
ABSTRACT
This paper presents a nuclear radiation environment monitoring scheme based on the Internet of Things technology. The scheme primarily utilizes ZigBee wireless communication protocol, dedicated line network topology, and cloud-based processing techniques to achieve the entire process of acquisition, localization, transmission, tracking, monitoring, and management of X, γ, α, β, and neutron radiation data at nuclear radiation monitoring sites. Through initial application, the system demonstrates favorable characteristics such as good portability, strong scalability, secure information transmission, and deep data mining.