For the past few years, artificial intelligence (AI) technology has developed rapidly and has become frontier and hot topics in medical research. While the deep learning algorithm based on artificial neural networks is one of the most representative tool in this field. The advancement of ophthalmology is inseparable from a variety of imaging methods, and the pronounced convenience and high efficiency endow AI technology with promising applications in screening, diagnosis and follow-up of ophthalmic diseases. At present, related research on ophthalmologic AI technology has been carried out in terms of multiple diseases and multimodality. Many valuable results have been reported aiming at several common diseases of ophthalmology. It should be emphasized that ophthalmic AI products are still faced with some problems towards practical application. The regulatory mechanism and evaluation criteria have not yet integrated as a standardized system. There are still a number of aspects to be optimized before large-scale distribution in clinical utility. Briefly, the innovation of ophthalmologic AI technology is attributed to multidisciplinary cooperation, which is of great significance to China's public health undertakings, and will be bound to benefit patients in future clinical practice.
Artificial intelligence (AI) for science (AI4S) technology, the AI technology for scientific research, has shown tremendous potential and influence in the field of healthcare, redefining the research paradigm of medical science under the guidance of computational medicine. We reviewed the main technological trends of AI4S in reshaping healthcare paradigm: knowledge-driven AI, leveraging extensive literature mining and data integration, emerges an important tool for understanding disease mechanisms and facilitating novel drug development; data-driven AI, delving into clinical and human-related omics data, unveils individual variances and disease mechanisms, and further establishes patient-centric digital twins to guide drug development and personalized medicine. Meanwhile, based on authentic patient digital twin models, adaptable strategies are employed to further propel the development of "e-drugs" that mimic the authentic mechanisms. These digital twins of drugs are evaluated for drug efficacy and safety through large-scale cloud-based virtual clinical trials, and followed by rationally designed real-world clinical trials, thus notably reducing drug development costs and enhancing success rates. Despite encountering challenges such as data scale, quality control, model interpretability, the transition from science insights to engineering solutions, and regulatory hurdles, we anticipate the integration of AI4S technology to revolutionize drug development and clinical practices. This transformation brings revolutionary changes to the medical field, offering novel opportunities and challenges for the development of medical science, and more importantly, providing necessary but personalized healthcare solutions for humankind.
ObjectiveTo explore the application of artificial intelligence in postoperative follow-up of day surgery patients, so as to establish an intelligent medical framework, promote the intelligent process of hospitals, and improve the management level of day surgery.MethodsThe artificial intelligence phonetic system was carried out by the Day Surgery Center, Renji Hospital, Shanghai Jiaotong University School of Medicine on June 1st, 2018. Through the system, the artificial intelligence voice system based on speech and semantic recognition technology was adopted to connect the data of the information center in the hospital to carry out postoperative follow-up of day surgery patients. We selected the 2 245 patients followed up by the artificial intelligence phonetic system from June 1st to November 30th 2018 (the AI follow-up group) and the 2 576 patients followed up by the traditional manual method from January 2nd to May 31st 2018 (the manual follow-up group), to compare the telephone connection rate, information collection rate, and call duration between them.ResultsThere was no statistically significant difference in telephone connection rate (85.70% vs. 86.68%) or information collection rate (98.86% vs. 98.48%) between the AI follow-up group and the manual follow-up group (P>0.05); but there was a statistically significant difference in call duration between the AI follow-up group and the manual follow-up group [(165.48±43.28) vs. (135.37±36.31) seconds, P<0.05], and the AI follow-up group had a longer call duration.ConclusionsThe application of artificial intelligence phonetic system in surgery has a good performance in call connection rate and information collection integrity. It plays an active role in improving efficiency, extending medical services and strengthening medical safety in the management of day surgery.
Pathological myopia is one of the most challenging clinical diseases in the field of ophthalmology. The accurate definition, standard classification, disease evolution mechanism and disease prevention and treatment strategies are still under investigation. The development and application of artificial intelligence provides a powerful tool for the analysis of pathological myopia related data. More and more accurate data information is obtained in the clinical work and clinical research of pathological myopia through the standardized collection and acquisition of the fundus image data, the automatic segmentation and quantitative analysis of the fundus physiological structure, the automatic detection and analysis of the pathological myopia classic lesions and the clinical diagnosis and treatment decision aid, which helps ophthalmologists to understand the pathogenesis and evolution of pathological myopia.
Objective By comparing with the traditional X-ray template measurement method, to explore the accuracy of artificial intelligence preoperative planning system (AI-HIP) to predict the type of prosthesis and guide the placement of prosthesis before total hip arthroplasty (THA) in adult patients with developmental dysplasia of the hip (DDH). Methods Patients with DDH scheduled for initial THA between August 2020 and August 2022 were enrolled as study object, of which 28 cases (28 hips) met the selection criteria were enrolled in the study. Among them, there were 10 males and 18 females, aged from 34 to 77 years, with an average of 59.3 years. There were 12 cases of the left DDH and 16 cases of the right DDH. According to DDH classification, there were 10 cases of Crowe type Ⅰ, 8 cases of type Ⅱ, 5 cases of type Ⅲ, and 5 cases of type Ⅳ. According to Association Research Circulation Osseous (ARCO) staging of osteonecrosis of the femoral head, 13 cases were in stage Ⅲ and 15 cases in stage Ⅳ. The disease duration was 2.5-23.0 years (mean, 8.6 years). The limb length discrepancy (LLD) was 11.0 (8.0, 17.5) mm. Before operation, the prosthesis types of all patients were predicted by AI-HIP system and X-ray template measurement method, respectively. And the preoperative results were compared with the actual prosthesis type during operation in order to estimate the accuracy of the AI-HIP system. Then, the differences in the acetabular abduction angle, acetabular anteversion angle, femoral neck osteotomy position, tip-shoulder distance, and LLD were compared between preoperative planned measurements by AI-HIP system and actual measurement results after operation, in order to investigate the ability of AI-HIP system to evaluate the placement position of prosthesis. Results The types of acetabular and femoral prostheses predicted based on AI-HIP system before operation were consistent with the actual prostheses in 23 cases (82.1%) and 24 cases (85.7%), respectively. The types of acetabular and femoral prostheses predicted based on X-ray template measurement before operation were consistent with the actual prostheses in 16 cases (57.1%) and 17 cases (60.7%), respectively. There were significant differences between AI-HIP system and X-ray template measurement (P<0.05). There was no significant difference in acetabular abduction angle, acetabular anteversion angle, femoral neck osteotomy position, and tip-shoulder distance between AI-HIP system and actual measurement after operation (P>0.05). LLD after operation was significantly lower than that before operation (P<0.05). There was no significant difference between the LLD predicted based on AI-HIP system and the actual measurement after operation (P>0.05). Conclusion Compared with the traditional X-ray template measurement method, the preoperative planning of AI-HIP system has better accuracy and repeatability in predicting the prosthesis type. It has a certain reference for the prosthesis placement of adult DDH.
Atrial fibrillation (AF) is one of the most common arrhythmias. Today, there are a large number of AF patients worldwide, and incidence increases with the increase of age. However, the current diagnosis rate of AF via auxiliary examination is relatively low. In view of the widespread application of artificial intelligence (AI) in the medical field, the diagnosis of AF using AI has also become a research hotspot. This article briefly introduces the relevant aspects of AI and reviews the application of AI in AF prediction.
Objective To explore the application value of artificial intelligence (AI) pulmonary artery assisted diagnosis software for suspected pulmonary embolism patients. Methods The data of 199 patients who were clinically suspected of pulmonary embolism and underwent pulmonary artery CT angiography (CTA) from June 2016 to December 2021 were retrospectively analyzed. Images of pulmonary artery CTA diagnosed by radiologists with different experiences and judged by senior radiologists were compared with the analysis results of AI assisted diagnostic software for pulmonary artery CTA, to evaluate the diagnostic efficacy of this software and low, medium, and senior radiologists for pulmonary embolism. The agreement of pulmonary embolism based on pulmonary artery CTA between the AI software and radiologists with different experiences was evaluated using Kappa test. Results The agreement of the AI software and the evaluation of pulmonary embolism lesions by senior radiologists based on pulmonary artery CTA was high (Kappa=0.913, P<0.001), while the diagnostic results of pulmonary artery CTA AI software was good after judged by senior radiologists based on pulmonary artery CTA (Kappa=0.755, P<0.001). Conclusions The AI software based on pulmonary artery CTA diagnosis of pulmonary embolism has good consistency with diagnostic images of radilogists, and can save a lot of reconstruction and diagnostic time. It has the value of daily diagnosis work and worthy of clinical promotion.
Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia. Early diagnosis and effective management are important to reduce atrial fibrillation‐related adverse events. Photoplethysmography (PPG) is often used to assist wearables for continuous electrocardiograph monitoring, which shows its unique value. The development of PPG has provided an innovative solution to AF management. Serial studies of mobile health technology for improving screening and optimized integrated care in atrial fibrillation have explored the application of PPG in screening, diagnosing, early warning, and integrated management in patients with AF. This review summarizes the latest progress of PPG analysis based on artificial intelligence technology and mobile health in AF field in recent years, as well as the limitations of current research and the focus of future research.
ObjectiveTo conduct a meta-analysis comparing the accuracy of artificial intelligence (AI)-assisted diagnostic systems based on 18F-fluorodeoxyglucose PET/CT (18F-FDG PET/CT) and structural MRI (sMRI) in the diagnosis of Alzheimer's disease (AD). MethodsOriginal studies dedicated to the development or validation of AI-assisted diagnostic systems based on 18F-FDG PET/CT or sMRI for AD diagnosis were retrieved from the Web of Science, PubMed, and Embase databases. Studies meeting the inclusion criteria were collected, and the risk of bias and clinical applicability of the included studies were assessed using the PROBAST checklist. The pooled sensitivity, specificity, and area under the summary receiver operating characteristic (SROC) curve (AUC) were calculated using a bivariate random-effects model. ResultsTwenty-six studies met the inclusion criteria, yielding a total of 38 2×2 contingency tables related to diagnostic performance. Specifically, 24 contingency tables were based on 18F-FDG PET/CT to distinguish AD patients from normal cognitive (NC) controls, and 14 contingency tables were based on sMRI for the same purpose. The meta-analysis results showed that for 18F-FDG PET/CT, the AI-assisted diagnostic systems had a pooled sensitivity, specificity, and SROC-AUC of 89% (95%CI 88% to 91%), 93% (95%CI 91% to 94%), and 0.96 (95%CI 0.93 to 0.97), respectively. For sMRI, the AI-assisted diagnostic systems had a pooled sensitivity, specificity, and SROC-AUC of 88% (95%CI 85% to 90%), 90% (95%CI 87% to 92%), and 0.94 (95%CI 0.92 to 0.96), respectively. ConclusionAI-assisted diagnostic systems based on either 18F-FDG PET/CT or sMRI demonstrated similar performance in the diagnosis of AD, with both showing high accuracy.
Cardiovascular diseases are the leading cause of death and their diagnosis and treatment rely heavily on the variety of clinical data. With the advent of the era of medical big data, artificial intelligence (AI) has been widely applied in many aspects such as imaging, diagnosis and prognosis prediction in cardiovascular medicine, providing a new method for accurate diagnosis and treatment. This paper reviews the application of AI in cardiovascular medicine.