Prenatal diagnosis, as one of the core components in the prevention and control of birth defects, is constrained by both “time sensitivity” and “data availability”. The diagnostic model driven by expert experience and manual interpretation can no longer meet the demands of rapidly evolving detection technologies, which generate massive, high-dimensional data. Additionally, issues such as delayed professional training and regional development imbalances further hinder the overall improvement of prenatal diagnosis efficacy. This article systematically elaborates on typical application scenarios of artificial intelligence-assisted prenatal diagnosis from two core aspects: the intelligent optimization of diagnostic technologies and the standardization of institutional and personnel management. It also explores the potential of emerging intelligent technologies like federated learning and digital twins, aiming to promote the transformation and upgrading of the prenatal diagnosis field from standardization and normalization toward precision and systematic high-quality development.
Cardiovascular disease has caused a huge burden of disease worldwide, and the rapid advancement of smart wearable devices has provided new means for early diagnosis, real-time monitoring, and event prevention of cardiovascular disease. Smart wearable devices can be classified into various categories based on detection signals and physical carrier types. Based on an overview of the composition of such devices, this article further introduces the current cutting-edge research and related market products related to smart blood pressure monitoring, electrocardiogram monitoring, and ultrasound monitoring. It also discusses the future development and challenges of such devices, aiming to provide evidence support for the research and development of smart wearable devices in the diagnosis and treatment of cardiovascular diseases in the future.
Objective To broaden the current understanding of the usage willingness about artificial intelligence (AI) robots and relevant influence factors for elderly patients. Methods The elderly patients in the inpatient ward, outpatient department and physical examination of the Department of Geriatrics, West China Hospital of Sichuan University were selected by convenient sampling for investigation between February and April 2020, to explore the willingness of elderly patients to use AI robots and related influencing factors. Results A total of 446 elderly patients were included. There were 244 males and 202 females. The willingness to use AI robots was (14.40±3.62) points. There were statistically significant differences among the elderly patients with different ages, marital status, living conditions, educational level, current health status, current vision status, current hearing status, self-care ability and family support in their willingness to use AI robots (P<0.05). Multiple linear regression analysis showed that age, education level and family support were the influencing factors of use intention (P<0.05). Among the elderly patients, 60.76% had heard of AI robots, but only 28.03% knew the medical application of AI robots, and only 13.90% had used AI robot services. Most elderly patients (>60%) thought that some adverse factors may reduce their usage willingness, like “the price is too expensive” and “the use is complex, or I don’t know how to use”. Conclusions Elderly patients’ cognition of AI robots is still at a low level, and their willingness to use AI robots is mainly affected by age, education level and family support. It is suggested to consider the personalized needs of the elderly in terms of different ages, education levels and family support, and promote the cheap and user-friendly AI robots, so as to improve the use of AI robots by elderly patients.
Objective To review the research progress on the application of digital orthopedic technology in total hip arthroplasty (THA) for developmental dysplasia of the hip (DDH), thereby providing a reference for clinical decision-making. MethodsA comprehensive literature review was conducted to summarize the effectiveness of various emerging digital orthopedic technologies in the context of THA for DDH. Results Digital orthopedic technologies have significantly enhanced the precision and safety of THA for DDH. Specifically, artificial intelligence-based preoperative planning systems have demonstrated superior accuracy in prosthesis size matching and positioning compared to conventional methods. Additive manufacturing technologies have provided personalized solutions for reconstructing complex bone defects in DDH. Furthermore, robot-assisted and navigation-assisted techniques have effectively improved the accuracy of prosthesis placement and lower limb length restoration in THA. However, each of these digital orthopedic technologies still possesses its own limitations. ConclusionThrough the integration of multiple technologies, digital orthopedics effectively addresses the challenges of precise reconstruction in THA for DDH. Future efforts should focus on further integrating diverse intelligent technologies and equipment to establish a comprehensive digital diagnosis and treatment system, aiming to achieve superior long-term effectiveness.
ObjectiveTo summarize the recent research progress of artificial intelligence (AI) for perioperative management of colorectal cancer (CRC), and to explore its clinical application value and future development direction. MethodThe relevant research on AI in the perioperative management of CRC surgery from China National Knowledge Infrastructure, Wanfang, PubMed, and Google Scholar databases in the past 5 years was retrieved and reviewed. ResultsCurrently, AI had been applied throughout the entire process related to CRC surgery. Preoperatively, AI-assisted analysis of CT or MRI images facilitated precise tumor staging assessment, prediction of neoadjuvant therapy response, and surgical planning optimization. Intraoperatively, real-time endoscopic vision integrated with AI enabled tumor localization, tracking, and tissue identification accuracy, enhancing procedural safety. Postoperatively, AI-supported rehabilitation protocols optimized early mobilization, enabled continuous complication monitoring, and refined follow-up management, providing personalized intervention strategies for early clinical intervention to improve patient outcomes. ConclusionsCurrent research demonstrates promising outcomes of AI applications in CRC perioperative management, yet reveals a significant imbalance in research focus with predominant investigations concentrated on preoperative assistance. Notably, postoperative domains, including fall prevention, medication error detection, complication mitigation, adjuvant therapy decision support, psychosocial support, recurrence surveillance, and survival follow-up, exhibit marked deficiencies in AI exploration and clinical translation, constituting a critical weakness in establishing comprehensive intelligent support throughout the perioperative continuum. Future research must extend beyond addressing intraoperative AI challenges to prioritize AI-augmented prediction of short-/long-term complications, optimization of personalized rehabilitation pathways, precision adjuvant therapy decision support, intelligent follow-up systems, and applications enhancing postoperative quality of life and long-term survival outcomes.
Lung adenocarcinoma has become the most common type of lung cancer. According to the 2015 World Health Organization histological classification of lung cancer, invasive lung adenocarcinoma can be divided into 5 subtypes: lepidic, acinar, papillary, solid, and micropapillary. Relevant studies have shown that the local lobectomy or sublobectomy is sufficient for early lepidic predominant adenocarcinoma, while lobectomy should be recommended for tumors containing micropapillary and solid ingredients (≥5%). Currently, the percentage of micropapillary and solid components diagnosed by frozen pathological examination is 65.7%, and the accuracy of diagnosis is limited. Therefore, to improve the accuracy of diagnosis, it is necessary to seek new methods and techniques. This paper summarized the characteristics and rapid diagnosis tools of early lung adenocarcinoma subtypes.
Reconstructive surgery is fundamentally dedicated to restoring tissues and organs damaged by trauma, disease, or congenital anomalies, with the goal of re-establishing both physiological function and anatomical form. Facial reconstruction, as one of the most representative and technically demanding areas of the discipline, embodies the evolution of its concepts and technological progress. Using facial reconstruction as the point of departure, this article systematically delineates the scientific underpinnings and developmental frontiers of the field. Centered on four core elements—donor construction, vascular reconstruction, precision transplantation, and functional recovery, this article articulates the internal logic and technical considerations of both autologous and allogeneic reconstructive methods. Further, from the perspectives of regenerative donor fabrication, the digital and intelligent transformation of reconstructive surgery, breakthroughs in immune tolerance strategies, and the integration of engineering technologies to enhance functional outcomes, the article envisions potential paradigm shifts that may redefine the discipline. By leveraging facial reconstruction as a highly integrated lens, this work aims to elucidate the key drivers of innovation and chart the future directions of reconstructive surgery.
Electrocardiogram (ECG) is a noninvasive, inexpensive, and convenient test for diagnosing cardiovascular diseases and assessing the risk of cardiovascular events. Although there are clear standardized operations and procedures for ECG examination, the interpretation of ECG by even trained physicians can be biased due to differences in diagnostic experience. In recent years, artificial intelligence has become a powerful tool to automatically analyze medical data by building deep neural network models, and has been widely used in the field of medical image diagnosis such as CT, MRI, ultrasound and ECG. This article mainly introduces the application progress of deep neural network models in ECG diagnosis and prediction of cardiovascular diseases, and discusses its limitations and application prospects.
Objective To investigate an artificial intelligence (AI) automatic segmentation and modeling method for knee joints, aiming to improve the efficiency of knee joint modeling. Methods Knee CT images of 3 volunteers were randomly selected. AI automatic segmentation and manual segmentation of images and modeling were performed in Mimics software. The AI-automated modeling time was recorded. The anatomical landmarks of the distal femur and proximal tibia were selected with reference to previous literature, and the indexes related to the surgical design were calculated. Pearson correlation coefficient (r) was used to judge the correlation of the modeling results of the two methods; the consistency of the modeling results of the two methods were analyzed by DICE coefficient. Results The three-dimensional model of the knee joint was successfully constructed by both automatic modeling and manual modeling. The time required for AI to reconstruct each knee model was 10.45, 9.50, and 10.20 minutes, respectively, which was shorter than the manual modeling [(64.73±17.07) minutes] in the previous literature. Pearson correlation analysis showed that there was a strong correlation between the models generated by manual and automatic segmentation (r=0.999, P<0.001). The DICE coefficients of the 3 knee models were 0.990, 0.996, and 0.944 for the femur and 0.943, 0.978, and 0.981 for the tibia, respectively, verifying a high degree of consistency between automatic modeling and manual modeling. Conclusion The AI segmentation method in Mimics software can be used to quickly reconstruct a valid knee model.
Objective To review the progress of artificial intelligence (AI) and radiomics in the study of abdominal aortic aneurysm (AAA). Method The literatures related to AI, radiomics and AAA research in recent years were collected and summarized in detail. Results AI and radiomics influenced AAA research and clinical decisions in terms of feature extraction, risk prediction, patient management, simulation of stent-graft deployment, and data mining. Conclusion The application of AI and radiomics provides new ideas for AAA research and clinical decisions, and is expected to suggest personalized treatment and follow-up protocols to guide clinical practice, aiming to achieve precision medicine of AAA.