OBJECTIVE: To screen the risk factors for death in patients with nasopharyngeal carcinoma (NPC) using artificial intelligence (AI) technology and establish a risk prediction model. METHODS: The clinical data of NPC patients obtained from SEER database (1973-2015). The patients were randomly divided into model building and verification group at a 7∶3 ratio. Based on the data in the model building group, R software was used to identify the risk factors for death in NPC patients using 4 AI algorithms, namely eXtreme Gradient Boosting (XGBoost), Decision Tree (DT), Least absolute shrinkage and selection operator (LASSO) and random forest (RF), and a risk prediction model was constructed based on the risk factor identified. The C-Index, decision curve analysis (DCA), receiver operating characteristic (ROC) curve and calibration curve (CC) were used for internal validation of the model; the data in the validation group and clinical data of 96 NPC patients (collected from First Affiliated Hospital of Bengbu Medical College) were used for internal and external validation of the model. RESULTS: The clinical data of a total of 2116 NPC patients were included (1484 in model building group and 632 in verification group). Risk factor screening showed that age, race, gender, stage M, stage T, and stage N were all risk factors of death in NPC patients. The risk prediction model for NPC-related death constructed based on these factors had a C-index of 0.76 for internal evaluation, an AUC of 0.74 and a net benefit rate of DCA of 9%-93%. The C-index of the model in internal verification was 0.740 with an AUC of 0.749 and a net benefit rate of DCA of 3%-89%, suggesting a high consistency of the two calibration curves. In external verification, the C-index of this model was 0.943 with a net benefit rate of DCA of 3%-97% and an AUC of 0.851, and the predicted value was consistent with the actual value. CONCLUSIONS Gender, age, race and TNM stage are risk factors of death of NPC patients, and the risk prediction model based on these factors can accurately predict the risks of death in NPC patients.
Humans ; Nasopharyngeal Neoplasms ; Nasopharyngeal Carcinoma ; Artificial Intelligence ; Algorithms ; Software

OBJECTIVES: This study aimed to compare the effects of virtual adjustment on occlusal interferences in mandibular posterior single crown and three-unit bridge restorations by using the mandibular movement track and the movement parameters of a virtual articulator. METHODS: Twenty-two participants were recruited. Digital casts of the maxillary and mandibular arches were obtained using an intraoral scanner, and the jaw registration system was used to record the data of the mandibular movement track and the movement parameters of the articulator. Four kinds of restorations with 0.3 mm occlusal interferences were designed with dental design software. In particular, single crowns were designed for teeth 44 and 46, whereas three-unit bridges were designed for teeth 44-46 and 45-47, and the corresponding natural teeth were virtually extracted. Virtual adjustment of the restorations was performed using two dynamic occlusal recordings, namely, the mandibular movement track and the movement parameters of the virtual articulator. A reverse-engineering software was used to measure the root-mean-square of the three-dimensional deviation of the occlusal surfaces between natural teeth and the adjusted restorations. The differences between the two methods of virtual-occlusion adjustment were compared and analyzed. RESULTS: For the same group of restorations, the three-dimensional deviation of the mandibular movement track group were lower than those of the virtual articulator group, and the differences were statistically significant (P<0.05). For the four groups of restorations adjusted by the same method, the three-dimensional deviation of the 46-tooth single crown was the largest and the smallest three-dimensional deviation was that of the 44-tooth single crown. Statistical differences existed between the 44-tooth single crown and the other groups (P<0.05). CONCLUSIONS For the occlusal design of posterior single crown and three-unit bridge, the mandibular movement track could be a more effective approach to virtual occlusal adjustment than the movement parameters of the virtual articulator.
Humans ; Mouth, Edentulous ; Occlusal Adjustment ; Jaw Relation Record ; Dental Articulators ; Software

As one of the standard electrophysiological signals in the human body, the photoplethysmography contains detailed information about the blood microcirculation and has been commonly used in various medical scenarios, where the accurate detection of the pulse waveform and quantification of its morphological characteristics are essential steps. In this paper, a modular pulse wave preprocessing and analysis system is developed based on the principles of design patterns. The system designs each part of the preprocessing and analysis process as independent functional modules to be compatible and reusable. In addition, the detection process of the pulse waveform is improved, and a new waveform detection algorithm composed of screening-checking-deciding is proposed. It is verified that the algorithm has a practical design for each module, high accuracy of waveform recognition and high anti-interference capability. The modular pulse wave preprocessing and analysis software system developed in this paper can meet the individual preprocessing requirements for various pulse wave application studies under different platforms. The proposed novel algorithm with high accuracy also provides a new idea for the pulse wave analysis process.
Humans ; Systems Analysis ; Algorithms ; Software ; Heart Rate ; Microcirculation

Advanced radiotherapy technology enables the dose to more accurately conform to the tumor target area of the patient, providing accurate treatment for the patient, but the gradient of the patient's radiation dose at the tumor edge is getting larger, which putting forward higher requirements for radiotherapy dose verification. The dose verification system software KylinRay-Dose4D can verify the patient's pre-treatment plan and the in vivo/on-line dose during the patient's treatment, providing important reference for the physicist to modify the radiotherapy plan and ensuring that the patient receives accurate treatment. This study introduces the overall design and key technologies of KylinRay-Dose4D, and tests the pre-treatment plan dose checking calculation and 2D/3D dose verification through clinical cases. The test results showed that the 2D/3D gamma pass rate (3 mm/3%) of KylinRay-Dose4D reconstructed dose compared with TPS plan dose and measured dose is larger than 95%, which indicating that the reconstructed dose of KylinRay-Dose4D meets the requirement of clinical application.
Humans ; Radiotherapy Dosage ; Radiotherapy Planning, Computer-Assisted/methods* ; Radiotherapy, Intensity-Modulated/methods* ; Software ; Neoplasms ; Phantoms, Imaging ; Radiometry/methods*

The proton treatment control system is the supporting software of the proton therapy device, which specifically coordinates and controls the status and work of each subsystem. In this study, the software architecture and hardware implementation of the proton treatment control system was developed and built a foundation for the overall debugging. Using C# programming language and WPF programming techniques, TCP network communication protocol specified by the proton treatment technical document and MVVM pattern in Windows system, the logic design and implementation of each level were studied. Meanwhile, the communication interface between the subsystems under TCP communication protocol was agreed. The logic design and research of the setup field and treatment field were carried out. And the User Interface was designed and developed using the above technology. The program realizes the communication and interaction between the proton treatment control system and each subsystem, so as to control and monitor the whole treatment process. The proton treatment control system provides a software basis for the remote overall debugging and on-line monitor and control of proton treatment device.
Protons ; User-Computer Interface ; Software ; Computers ; Logic

OBJECTIVE: In order to record the whole life process information of medical equipment and improve the management efficiency, this study proposes an informatization scheme for the whole life cycle management of medical equipment. METHODS: Relying on cloud-native, based on the software architecture of front-end and back-end separation, a mode of sub-account and sub-authority management of medical equipment was designed to integrate maintenance work orders, operation reports and other functions, and manage medical equipment data in a structured and platform-based manner. RESULTS: Comparing the equipment failure rate, maintenance response time, and average inventory time per device before and after the system operation, the differences are statistically significant (P<0.05). CONCLUSIONS The system can realize the work collaboration of maintenance engineers, equipment users, and equipment management personnel, and can trace the information of the whole life cycle of the equipment.
Software ; Information Systems

OBJECTIVES: To realize the dynamic visualization of forensic odontology based on the bibliometrics methods, and capture the research hotspots and identify the future development trend. METHODS: Literature articles published from January 1995 to December 2020 were searched according to specific subject words in the core data set of Web of Science. The visualization analysis of publishing country, institution, discipline, author, co-cited journal and keywords was performed by CiteSpace 5.7.R5W software. RESULTS: The annual analysis of publications showed an upward trend of forensic odontology research literature year by year, with the number of annual publications more than 110 in the last five years. Developed countries were the main source of contributions and the average centrality was greater than 0.2. The research of forensic odontology involved multiple disciplines, including stomatology, biology, computer science and medical imaging, with a distinct interdisciplinary feature. A total of 115 nodes were obtained by keyword cluster analysis. The principal line of forensic odontology mainly included individual identification and age estimation and the emergence of hotspots was closely related to new technologies. Population-based odontology investigation, improvement of traditional dental age estimation method and dental age estimation based on new technology were popular research in forensic odontology. CONCLUSIONS Developing countries urgently need to increase the focus on related research. It may be an important direction for the development of forensic odontology to establish and enrich the regional dental database, develop new odontology identification technology combined with frontier and high-end technology, and develop the identification program based on advanced information technology.
Forensic Medicine ; Software ; Bibliometrics

Humans ; Child ; Caregivers ; Singapore ; Software

Objective: To analyze the trend of epidemiological characteristics and spatiotemporal distribution of pulmonary tuberculosis (PTB) among smear-positive or other types of students in Guizhou Province from 2011 to 2020, and to provide a reference for improving prevention and control measures. Methods: Data were collected from the Chinese Information System's Notifiable Disease and Tuberculosis Management Information System for disease control and prevention, the Joinpoint 4.9.1.0 software was used to analyze the trend of registration rate; the ArcGIS 10.6 software was used to construct a ring map and to perform spatial autocorrelation analysis; the SaTScan 9.7 software was used for spatial-temporal scan statistics. Results: A total of 32 682 student PTB cases were reported in Guizhou Province from 2011 to 2020, including 5 949 (18.20%) smear-positive cases. Most cases occurred from high school students of 16 to 18 years old (43.99%, 14 376/32 682); the annual average registered rate was 36.22/100 000, the highest in 2018 (52.90/100 000), and the registration rate showed an increasing trend. Meanwhile, a similar trend of registration rate was observed among smear-positive or other types of students. The spatialtemporal heterogeneity was found that the "high-high" clustering patterns of smear-positive or other types were aggregated in Bijie City. Six spatialtemporal clusters with statistically significant (all P<0.001) were detected among smear-positive or other cases, respectively. Conclusions: Upward trend with spatial- temporal clusters of PTB cases reported in students from Guizhou Province from 2011 to 2020. Surveillance should be strengthened for high school students, and regular screening should be conducted in high-risk areas to control the source of infection and reduce the risk of transmission.
Humans ; Adolescent ; Tuberculosis, Pulmonary/epidemiology* ; Asian People ; Cluster Analysis ; Software ; Students

Objective: To explore an automatic landmarking method for anatomical landmarks in the three-dimensional (3D) data of the maxillary complex and preliminarily evaluate its reproducibility and accuracy. Methods: From June 2021 to December 2022, spiral CT data of 31 patients with relatively normal craniofacial morphology were selected from those who visited the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology. The sample included 15 males and 16 females, with the age of (33.3±8.3) years. The maxillary complex was reconstructed in 3D using Mimics software, and the resulting 3D data of the maxillary complex was mesh-refined using Geomagic software. Two attending physicians and one associate chief physician manually landmarked the 31 maxillary complex datasets, determining 24 anatomical landmarks. The average values of the three expert landmarking results were used as the expert-defined landmarks. One case that conformed to the average 3D morphological characteristics of healthy individuals' craniofacial bones was selected as the template data, while the remaining 30 cases were used as target data. The open-source MeshMonk program (a non-rigid registration algorithm) was used to perform an initial alignment of the template and target data based on 4 landmarks (nasion, left and right zygomatic arch prominence, and anterior nasal spine). The template data was then deformed to the shape of the target data using a non-rigid registration algorithm, resulting in the deformed template data. Based on the unchanged index property of homonymous landmarks before and after deformation of the template data, the coordinates of each landmark in the deformed template data were automatically retrieved as the automatic landmarking coordinates of the homonymous landmarks in the target data, thus completing the automatic landmarking process. The automatic landmarking process for the 30 target data was repeated three times. The root-mean-square distance (RMSD) of the dense corresponding point pairs (approximately 25 000 pairs) between the deformed template data and the target data was calculated as the deformation error of the non-rigid registration algorithm, and the intra-class correlation coefficient (ICC) of the deformation error in the three repetitions was analyzed. The linear distances between the automatic landmarking results and the expert-defined landmarks for the 24 anatomical landmarks were calculated as the automatic landmarking errors, and the ICC values of the 3D coordinates in the three automatic landmarking repetitions were analyzed. Results: The average three-dimensional deviation (RMSD) between the deformed template data and the corresponding target data for the 30 cases was (0.70±0.09) mm, with an ICC value of 1.00 for the deformation error in the three repetitions of the non-rigid registration algorithm. The average automatic landmarking error for the 24 anatomical landmarks was (1.86±0.30) mm, with the smallest error at the anterior nasal spine (0.65±0.24) mm and the largest error at the left oribital (3.27±2.28) mm. The ICC values for the 3D coordinates in the three automatic landmarking repetitions were all 1.00. Conclusions: This study established an automatic landmarking method for three-dimensional data of the maxillary complex based on a non-rigid registration algorithm. The accuracy and repeatability of this method for landmarking normal maxillary complex 3D data were relatively good.
Male ; Female ; Humans ; Adult ; Imaging, Three-Dimensional/methods* ; Reproducibility of Results ; Algorithms ; Software ; Tomography, Spiral Computed ; Anatomic Landmarks/anatomy & histology*