New augmented reality remote for virtual guidance and education of fracture surgery: a retrospective, non-inferiority, multicenter cohort study.

BACKGROUND: The demand for telesurgery is rapidly increasing. Augmented reality (AR) remote surgery is a promising alternative, fulfilling a worldwide need in fracture surgery. However, previous AR endoscopic and Google Glass remotes remain unsuitable for fracture surgery, and the application of remote fracture surgery has not been reported. We aimed to evaluated the safety and clinical effectiveness of a new AR remote in fracture surgery. MATERIALS AND METHODS: This retrospective non-inferiority cohort study was conducted at three centres. Between January 1, 2018, and March 31, 2022, 800 patients who underwent fracture surgery were eligible for participation. The study enrolled 551 patients with fractures (132 patellae, 128 elbows, 126 tibial plateaus, and 165 ankles) divided into an AR group (specialists used AR to remotely guide junior doctors to perform surgeries) and a traditional non-remote group (specialists performed the surgery themselves). RESULTS: Among 364 patients (182 per group) matched by propensity score, seven (3.8%) in the AR group and four (3%) in the non-remote group developed complications. The 0.005 risk difference (95% confidence interval: -0.033 to 0.044) was below the pre-defined non-inferiority margin of a 10% absolute increase. A similar distribution in the individual components of all complications was found between the groups. Hierarchical analysis following propensity score matching revealed no statistical difference between the two groups regarding functional results at 1-year follow-up, operative time, amount of bleeding, number of fluoroscopies, and injury surgery interval. A Likert scale questionnaire showed positive results (median scores: 4-5) for safety, efficiency, and education. CONCLUSION: This study is the first to report that AR remote surgery can be as safe and effective as that performed by a specialist in person for fracture surgery, even without the physical presence of a specialist, and is associated with improving the skills and increasing the confidence of junior surgeons. This technique is promising for remote fracture surgery and other open surgeries, offering a new strategy to address inadequate medical care in remote areas.

Deep learning assisted diagnosis system: improving the diagnostic accuracy of distal radius fractures.

Objectives: To explore an intelligent detection technology based on deep learning algorithms to assist the clinical diagnosis of distal radius fractures (DRFs), and further compare it with human performance to verify the feasibility of this method. Methods: A total of 3,240 patients (fracture: n = 1,620, normal: n = 1,620) were included in this study, with a total of 3,276 wrist joint anteroposterior (AP) X-ray films (1,639 fractured, 1,637 normal) and 3,260 wrist joint lateral X-ray films (1,623 fractured, 1,637 normal). We divided the patients into training set, validation set and test set in a ratio of 7:1.5:1.5. The deep learning models were developed using the data from the training and validation sets, and then their effectiveness were evaluated using the data from the test set. Evaluate the diagnostic performance of deep learning models using receiver operating characteristic (ROC) curves and area under the curve (AUC), accuracy, sensitivity, and specificity, and compare them with medical professionals. Results: The deep learning ensemble model had excellent accuracy (97.03%), sensitivity (95.70%), and specificity (98.37%) in detecting DRFs. Among them, the accuracy of the AP view was 97.75%, the sensitivity 97.13%, and the specificity 98.37%; the accuracy of the lateral view was 96.32%, the sensitivity 94.26%, and the specificity 98.37%. When the wrist joint is counted, the accuracy was 97.55%, the sensitivity 98.36%, and the specificity 96.73%. In terms of these variables, the performance of the ensemble model is superior to that of both the orthopedic attending physician group and the radiology attending physician group. Conclusion: This deep learning ensemble model has excellent performance in detecting DRFs on plain X-ray films. Using this artificial intelligence model as a second expert to assist clinical diagnosis is expected to improve the accuracy of diagnosing DRFs and enhance clinical work efficiency.

Deep learning system assisted detection and localization of lumbar spondylolisthesis.

Objective: Explore a new deep learning (DL) object detection algorithm for clinical auxiliary diagnosis of lumbar spondylolisthesis and compare it with doctors' evaluation to verify the effectiveness and feasibility of the DL algorithm in the diagnosis of lumbar spondylolisthesis. Methods: Lumbar lateral radiographs of 1,596 patients with lumbar spondylolisthesis from three medical institutions were collected, and senior orthopedic surgeons and radiologists jointly diagnosed and marked them to establish a database. These radiographs were randomly divided into a training set (n = 1,117), a validation set (n = 240), and a test set (n = 239) in a ratio of 0.7 : 0.15: 0.15. We trained two DL models for automatic detection of spondylolisthesis and evaluated their diagnostic performance by PR curves, areas under the curve, precision, recall, F1-score. Then we chose the model with better performance and compared its results with professionals' evaluation. Results: A total of 1,780 annotations were marked for training (1,242), validation (263), and test (275). The Faster Region-based Convolutional Neural Network (R-CNN) showed better precision (0.935), recall (0.935), and F1-score (0.935) in the detection of spondylolisthesis, which outperformed the doctor group with precision (0.927), recall (0.892), f1-score (0.910). In addition, with the assistance of the DL model, the precision of the doctor group increased by 4.8%, the recall by 8.2%, the F1-score by 6.4%, and the average diagnosis time per plain X-ray was shortened by 7.139 s. Conclusion: The DL detection algorithm is an effective method for clinical diagnosis of lumbar spondylolisthesis. It can be used as an assistant expert to improve the accuracy of lumbar spondylolisthesis diagnosis and reduce the clinical workloads.

Predicting the comprehensive geospatial pattern of two ephedrine-type alkaloids for Ephedra sinica in Inner Mongolia.

Ephedra sinica Stapf. is a shrubby plant widely used in traditional Chinese medicine due to its high level of medicinal value, thus, it is in high demand. Ephedrine (E) and pseudoephedrine (PE) are key medicinal components and quality indicators for E. sinica. These two ephedrine-type alkaloids are basic elements that exert the medicinal effect of E. sinica. Recently, indiscriminate destruction and grassland desertification have caused the quantity and quality of these pharmacological plants to degenerate. Predicting potentially suitable habitat for high-quality E. sinica is essential for its future conservation and domestication. In this study, MaxEnt software was utilized to map suitable habitats for E. sinica in Inner Mongolia based on occurrence data and a set of variables related to climate, soil, topography and human impact. The model parametrization was optimized by evaluating alternative combinations of feature classes and values of the regularization multiplier. Second, a geospatial quality model was fitted to relate E and PE contents to the same environmental variables and to predict their spatial patterns across the study area. Outputs from the two models were finally coupled to map areas predicted to have both suitable conditions for E. sinica and high alkaloid content. Our results indicate that E. sinica with high-quality E content was mainly distributed in the Horqin, Ulan Butong and Wulanchabu grasslands. E. sinica with high-quality PE content was primarily found in the Ordos, Wulanchabu and Ulan Butong grasslands. This study provides scientific information for the protection and sustainable utilization of E. sinica. It can also help to control and prevent desertification in Inner Mongolia.

Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study.

We explored a new artificial intelligence-assisted method to assist junior ultrasonographers in improving the diagnostic performance of uterine fibroids and further compared it with senior ultrasonographers to confirm the effectiveness and feasibility of the artificial intelligence method. In this retrospective study, we collected a total of 3870 ultrasound images from 667 patients with a mean age of 42.45 years ± 6.23 [SD] for those who received a pathologically confirmed diagnosis of uterine fibroids and 570 women with a mean age of 39.24 years ± 5.32 [SD] without uterine lesions from Shunde Hospital of Southern Medical University between 2015 and 2020. The DCNN model was trained and developed on the training dataset (2706 images) and internal validation dataset (676 images). To evaluate the performance of the model on the external validation dataset (488 images), we assessed the diagnostic performance of the DCNN with ultrasonographers possessing different levels of seniority. The DCNN model aided the junior ultrasonographers (Averaged) in diagnosing uterine fibroids with higher accuracy (94.72% vs. 86.63%, P < 0.001), sensitivity (92.82% vs. 83.21%, P = 0.001), specificity (97.05% vs. 90.80%, P = 0.009), positive predictive value (97.45% vs. 91.68%, P = 0.007), and negative predictive value (91.73% vs. 81.61%, P = 0.001) than they achieved alone. Their ability was comparable to that of senior ultrasonographers (Averaged) in terms of accuracy (94.72% vs. 95.24%, P = 0.66), sensitivity (92.82% vs. 93.66%, P = 0.73), specificity (97.05% vs. 97.16%, P = 0.79), positive predictive value (97.45% vs. 97.57%, P = 0.77), and negative predictive value (91.73% vs. 92.63%, P = 0.75). The DCNN-assisted strategy can considerably improve the uterine fibroid diagnosis performance of junior ultrasonographers to make them more comparable to senior ultrasonographers.

Deep learning-based algorithm improves radiologists' performance in lung cancer bone metastases detection on computed tomography.

Purpose: To develop and assess a deep convolutional neural network (DCNN) model for the automatic detection of bone metastases from lung cancer on computed tomography (CT). Methods: In this retrospective study, CT scans acquired from a single institution from June 2012 to May 2022 were included. In total, 126 patients were assigned to a training cohort (n = 76), a validation cohort (n = 12), and a testing cohort (n = 38). We trained and developed a DCNN model based on positive scans with bone metastases and negative scans without bone metastases to detect and segment the bone metastases of lung cancer on CT. We evaluated the clinical efficacy of the DCNN model in an observer study with five board-certified radiologists and three junior radiologists. The receiver operator characteristic curve was used to assess the sensitivity and false positives of the detection performance; the intersection-over-union and dice coefficient were used to evaluate the segmentation performance of predicted lung cancer bone metastases. Results: The DCNN model achieved a detection sensitivity of 0.894, with 5.24 average false positives per case, and a segmentation dice coefficient of 0.856 in the testing cohort. Through the radiologists-DCNN model collaboration, the detection accuracy of the three junior radiologists improved from 0.617 to 0.879 and the sensitivity from 0.680 to 0.902. Furthermore, the mean interpretation time per case of the junior radiologists was reduced by 228 s (p = 0.045). Conclusions: The proposed DCNN model for automatic lung cancer bone metastases detection can improve diagnostic efficiency and reduce the diagnosis time and workload of junior radiologists.

Priority planting area planning for cash crops under heavy metal pollution and climate change: A case study of Ligusticum chuanxiong Hort.

Introduction: Soil pollution by heavy metals and climate change pose substantial threats to the habitat suitability of cash crops. Discussing the suitability of cash crops in this context is necessary for the conservation and management of species. We developed a comprehensive evaluation system that is universally applicable to all plants stressed by heavy metal pollution. Methods: The MaxEnt model was used to simulate the spatial distribution of Ligusticum chuanxiong Hort within the study area (Sichuan, Shaanxi, and Chongqing) based on current and future climate conditions (RCP2.6, RCP4.5, RCP6.0, and RCP8.5 scenarios). We established the current Cd pollution status in the study area using kriging interpolation and kernel density. Additionally, the three scenarios were used in prediction models to simulate future Cd pollution conditions based on current Cd pollution data. The current and future priority planting areas for L. chuanxiong were determined by overlay analysis, and two levels of results were obtained. Results: The results revealed that the current first- and secondary-priority planting areas for L. chuanxiong were 2.06 ×103 km2 and 1.64 ×104 km2, respectively. Of these areas, the seven primary and twelve secondary counties for current L. chuanxiong cultivation should be given higher priority; these areas include Meishan, Qionglai, Pujiang, and other regions. Furthermore, all the priority zones based on the current and future scenarios were mainly concentrated on the Chengdu Plain, southeastern Sichuan and northern Chongqing. Future planning results indicated that Renshou, Pingwu, Meishan, Qionglai, Pengshan, and other regions are very important for L. chuanxiong planting, and a pessimistic scenario will negatively impact this potential planting. The spatial dynamics of priority areas in 2050 and 2070 clearly fluctuated under different prediction scenarios and were mainly distributed in northern Sichuan and western Chongqing. Discussion: Given these results, taking reasonable measures to replan and manage these areas is necessary. This study provides. not only a useful reference for the protection and cultivation of L. chuanxiong, but also a framework for analyzing other cash crops.

Artificial intelligence to detect the femoral intertrochanteric fracture: The arrival of the intelligent-medicine era.

Objective: To explore a new artificial intelligence (AI)-aided method to assist the clinical diagnosis of femoral intertrochanteric fracture (FIF), and further compare the performance with human level to confirm the effect and feasibility of the AI algorithm. Methods: 700 X-rays of FIF were collected and labeled by two senior orthopedic physicians to set up the database, 643 for the training database and 57 for the test database. A Faster-RCNN algorithm was applied to be trained and detect the FIF on X-rays. The performance of the AI algorithm such as accuracy, sensitivity, miss diagnosis rate, specificity, misdiagnosis rate, and time consumption was calculated and compared with that of orthopedic attending physicians. Results: Compared with orthopedic attending physicians, the Faster-RCNN algorithm performed better in accuracy (0.88 vs. 0.84 ± 0.04), specificity (0.87 vs. 0.71 ± 0.08), misdiagnosis rate (0.13 vs. 0.29 ± 0.08), and time consumption (5 min vs. 18.20 ± 1.92 min). As for the sensitivity and missed diagnosis rate, there was no statistical difference between the AI and orthopedic attending physicians (0.89 vs. 0.87 ± 0.03 and 0.11 vs. 0.13 ± 0.03). Conclusion: The AI diagnostic algorithm is an available and effective method for the clinical diagnosis of FIF. It could serve as a satisfying clinical assistant for orthopedic physicians.

Applications of Mixed Reality Technology in Orthopedics Surgery: A Pilot Study.

Objective: The aim of this study is to explore the potential of mixed reality (MR) technology in the visualization of orthopedic surgery. Methods: The visualization system with MR technology is widely used in orthopedic surgery. The system is composed of a 3D imaging workstation, a cloud platform, and an MR space station. An intelligent segmentation algorithm is adopted on the 3D imaging workstation to create a 3D anatomical model with zooming and rotation effects. This model is then exploited for efficient 3D reconstruction of data for computerized tomography (CT) and magnetic resonance imaging (MRI). Additionally, the model can be uploaded to the cloud platform for physical parameter tuning, model positioning, rendering and high-dimensional display. Using Microsoft's HoloLens glasses in combination with the MR system, we project and view 3D holograms in real time under different clinical scenarios. After each procedure, nine surgeons completed a Likert-scale questionnaire on communication and understanding, spatial awareness and effectiveness of MR technology use. In addition to that, the National Aeronautics and Space Administration Task Load Index (NASA-TLX) is also used to evaluate the workload of MR hologram support. Results: 1) MR holograms can clearly show the 3D structures of bone fractures, which improves the understanding of different fracture types and the design of treatment plans; 2) Holograms with three-dimensional lifelike dynamic features provide an intuitive communication tool among doctors and also between doctors and patients; 3) During surgeries, a full lesion hologram can be obtained and blended in real time with a patient's virtual 3D digital model in order to give surgeons superior visual guidance through novel high-dimensional "perspectives" of the surgical area; 4) Hologram-based magnetic navigation improves the accuracy and safety of the screw placement in orthopaedics surgeries; 5) The combination of mixed reality cloud platform and telemedicine system based on 5G provides a new technology platform for telesurgery collaboration. Results of qualitative study encourage the usage of MR technology for orthopaedics surgery. Analysis of the Likert-scale questionnaire shows that MR adds significant value to understanding and communication, spatial awareness, learning and effectiveness. Based on the NASA TLX-scale questionnaire results, mixed reality scored significantly lower under the "mental," "temporal," "performance," and "frustration" categories compared to usual 2D. Conclusion: The integration of MR technology in orthopaedic surgery reduces the dependence on surgeons' experience and provides personalized 3D visualization models for accurate diagnosis and treatment of orthopaedic abnormalities. This integration is clearly one of the prominent future development directions in medical surgery.

Application and Development of Intelligent Medicine in Traditional Chinese Medicine.

As modern science and technology constantly progresses, the fields of artificial intelligence, mixed reality technology, remote technology, etc. have rapidly developed. Meanwhile, these technologies have been gradually applied to the medical field, leading to the development of intelligent medicine. What's more, intelligent medicine has greatly promoted the development of traditional Chinese medicine (TCM), causing huge changes in the diagnosis of TCM ailments, remote treatment, teaching, etc. Therefore, there are both opportunities and challenges for inheriting and developing TCM. Herein, the related research progress of intelligent medicine in the TCM in China and abroad over the years is analyzed, with the purpose of introducing the present application status of intelligent medicine in TCM and providing reference for the inheritance and development of TCM in a new era.

Application of Artificial Intelligence in Medicine: An Overview.

Artificial intelligence (AI) is a new technical discipline that uses computer technology to research and develop the theory, method, technique, and application system for the simulation, extension, and expansion of human intelligence. With the assistance of new AI technology, the traditional medical environment has changed a lot. For example, a patient's diagnosis based on radiological, pathological, endoscopic, ultrasonographic, and biochemical examinations has been effectively promoted with a higher accuracy and a lower human workload. The medical treatments during the perioperative period, including the preoperative preparation, surgical period, and postoperative recovery period, have been significantly enhanced with better surgical effects. In addition, AI technology has also played a crucial role in medical drug production, medical management, and medical education, taking them into a new direction. The purpose of this review is to introduce the application of AI in medicine and to provide an outlook of future trends.

Artificial Intelligence to Diagnose Tibial Plateau Fractures: An Intelligent Assistant for Orthopedic Physicians.

OBJECTIVE: To explore a new artificial intelligence (AI)-aided method to assist the clinical diagnosis of tibial plateau fractures (TPFs) and further measure its validity and feasibility. METHODS: A total of 542 X-rays of TPFs were collected as a reference database. An AI algorithm (RetinaNet) was trained to analyze and detect TPF on the X-rays. The ability of the AI algorithm was determined by indexes such as detection accuracy and time taken for analysis. The algorithm performance was also compared with orthopedic physicians. RESULTS: The AI algorithm showed a detection accuracy of 0.91 for the identification of TPF, which was similar to the performance of orthopedic physicians (0.92±0.03). The average time spent for analysis of the AI was 0.56 s, which was 16 times faster than human performance (8.44±3.26 s). CONCLUSION: The AI algorithm is a valid and efficient method for the clinical diagnosis of TPF. It can be a useful assistant for orthopedic physicians, which largely promotes clinical workflow and further guarantees the health and security of patients.

Applications of Blockchain in the Medical Field: Narrative Review.

BACKGROUND: As a distributed technology, blockchain has attracted increasing attention from stakeholders in the medical industry. Although previous studies have analyzed blockchain applications from the perspectives of technology, business, or patient care, few studies have focused on actual use-case scenarios of blockchain in health care. In particular, the outbreak of COVID-19 has led to some new ideas for the application of blockchain in medical practice. OBJECTIVE: This paper aims to provide a systematic review of the current and projected uses of blockchain technology in health care, as well as directions for future research. In addition to the framework structure of blockchain and application scenarios, its integration with other emerging technologies in health care is discussed. METHODS: We searched databases such as PubMed, EMBASE, Scopus, IEEE, and Springer using a combination of terms related to blockchain and health care. Potentially relevant papers were then compared to determine their relevance and reviewed independently for inclusion. Through a literature review, we summarize the key medical scenarios using blockchain technology. RESULTS: We found a total of 1647 relevant studies, 60 of which were unique studies that were included in this review. These studies report a variety of uses for blockchain and their emphasis differs. According to the different technical characteristics and application scenarios of blockchain, we summarize some medical scenarios closely related to blockchain from the perspective of technical classification. Moreover, potential challenges are mentioned, including the confidentiality of privacy, the efficiency of the system, security issues, and regulatory policy. CONCLUSIONS: Blockchain technology can improve health care services in a decentralized, tamper-proof, transparent, and secure manner. With the development of this technology and its integration with other emerging technologies, blockchain has the potential to offer long-term benefits. Not only can it be a mechanism to secure electronic health records, but blockchain also provides a powerful tool that can empower users to control their own health data, enabling a foolproof health data history and establishing medical responsibility.

Mixed reality assists the fight against COVID-19.

Coronavirus disease 2019 (COVID-19) made a huge effect globally. With the assistance of mixed reality (MR) technology, complicated clinical works became easier to carry out and the condition had been greatly improved with high-tech advantages such as improved convenience, better understanding and communication, higher security, and medical resource saving. This study aimed to introduce one kind of MR application in the fight against COVID-19 and anticipate more feasible smart healthcare applications to enhance our strength for the final victory.