At present, artificial intelligence (AI) has been widely used in the diagnosis and treatment of various ophthalmological diseases, but there are still many problems. Due to the lack of standardized test sets, gold standards, and recognized evaluation systems for the accuracy of AI products, it is difficult to compare the results of multiple studies. When it comes to the field of image generation, we hardly have an efficient approach to evaluating research results. In clinical practice, ophthalmological AI research is often out of touch with actual clinical needs. The requirements for the quality and quantity of clinical data put more burden on AI research, limiting the transformation of AI studies. The prediction of systemic diseases based on fundus images is making progressive advancement. However, the lack of interpretability of the research lower the acceptance. Ophthalmology AI research also suffer from ethical controversy due to unconstructed regulations and regulatory mechanisms, concerns on patients’ privacy and data security, and the risk of aggravating the unfairness of medical resources.
With the development of society and the progress of technology, artificial intelligence (AI) and big data technology have penetrated into all walks of life in social production and promoted social production and lifestyle greatly. In the medical field, the applications of AI, such as AI-assisted diagnosis and treatment, robots, medical imaging and so on, have greatly promoted the development and transformation of the entire medical industry. At present, with the support of national policy, market, and technology, we should seize the opportunity of AI development, so as to build the first-mover advantage of AI development. Of course, the development and challenges are coexisted. In the future development process, we should objectively analyze the gap between our country and developed countries, think about the unfavorable factors such as AI chips and data problems, and extend the application and service of AI and big data to all links of medical industry, integrate with clinic fully, so as to better promote the further development of AI medicine treatment in China.
Objective To systematically evaluate the accuracy of endoscopy-based artificial intelligence (AI)-assisted diagnostic systems in the diagnosis of early-stage esophageal cancer and provide a scientific basis for its diagnostic value. MethodsPubMed, EMbase, The Cochrane Library, Web of Science, Wanfang database, VIP database and CNKI database were searched by computer to search for the relevant literature about endoscopy-based AI-assisted diagnostic systems for the diagnosis of early esophageal cancer from inception to March 2022. The QUADAS-2 was used for quality evaluation of included studies. Meta-analysis of the literature was carried out using Stata 16, Meta-Disc 1.4 and RevMan 5.4 softwares. A bivariate mixed effects regression model was utilized to calculate the combined diagnostic efficacy of the AI-assisted system and meta-regression analysis was conducted to explore the sources of heterogeneity. ResultsA total of 17 articles were included, which consisted of 13 retrospective cohort studies and 4 prospective cohort studies. The results of the quality evaluation using QUADAS-2 showed that all included literature was of high quality. The obtained meta-analysis results revealed that the AI-assisted system in the diagnosis of esophageal cancer presented a combined sensitivity of 0.94 (95%CI 0.91 to 0.96), a specificity of 0.85 (95%CI 0.74 to 0.92), a positive likelihood ratio of 6.28 (95%CI 3.48 to 11.33), a negative likelihood ratio of 0.07 (95%CI 0.05 to 0.11), a diagnostic odds ratio of 89 (95%CI 38 to 208) and an area under the curve of 0.96 (95%CI 0.94 to 0.98). ConclusionThe AI-assisted diagnostic system has a high diagnostic value for early stage esophageal cancer. However, most of the included studies were retrospective. Therefore, further high-quality prospective studies are needed for validation.
ObjectiveTo build a small-sample ultra-widefield fundus images (UWFI) multi-disease classification artificial intelligence model, and initially explore the ability of artificial intelligence to classify UWFI multi-disease tasks. MethodsA retrospective study. From 2016 to 2021, 1 608 images from 1 123 patients who attended the Eye Center of the Renmin Hospital of Wuhan University and underwent UWFI examination were used for UWFI multi-disease classification artificial intelligence model construction. Among them, 320, 330, 319, 268, and 371 images were used for diabetic retinopathy (DR), retinal vein occlusion (RVO), pathological myopia (PM), retinal detachment (RD), and normal fundus images, respectively. 135 images from 106 patients at the Tianjin Medical University Eye Hospital were used as the external test set. EfficientNet-B7 was selected as the backbone network for classification analysis of the included UWFI images. The performance of the UWFI multi-task classification model was assessed using the receiver operating characteristic curve, area under the curve (AUC), sensitivity, specificity, and accuracy. All data were expressed using numerical values and 95% confidence intervals (CI). The datasets were trained on the network models ResNet50 and ResNet101 and tested on an external test set to compare and observe the performance of EfficientNet with the 2 models mentioned above. ResultsThe overall classification accuracy of the UWFI multi-disease classification artificial intelligence model on the internal and external test sets was 92.57% (95%CI 91.13%-92.92%) and 88.89% (95%CI 88.11%-90.02%), respectively. These were 96.62% and 92.59% for normal fundus, 95.95% and 95.56% for DR, 96.62% and 98.52% for RVO, 98.65% and 97.04% for PM, and 97.30% and 94.07% for RD, respectively. The mean AUC on the internal and external test sets was 0.993 and 0.983, respectively, with 0.994 and 0.939 for normal fundus, 0.999 and 0.995 for DR, 0.985 and 1.000 for RVO, 0.991 and 0.993 for PM and 0.995 and 0.990 for RD, respectively. EfficientNet performed better than the ResNet50 and ResNet101 models on both the internal and external test sets. ConclusionThe preliminary UWFI multi-disease classification artificial intelligence model using small samples constructed in this study is able to achieve a high accuracy rate, and the model may have some value in assisting clinical screening and diagnosis.
ObjectiveTo establish an artificial intelligence robot-assisted diagnosis system for fundus diseases based on deep learning optical coherence tomography (OCT) and evaluate its application value. MethodsDiagnostic test studies. From 2016 to 2019, 25 000 OCT images of 25 000 patients treated at the Eye Center of the Second Affiliated Hospital of Zhejiang University School of Medicine were used as training sets and validation sets for the fundus intelligent assisted diagnosis system. Among them, macular epiretinal membrane (MERM), macular edema, macular hole, choroidal neovascularization (CNV), and age-related macular degeneration (AMD) were 5 000 sheets each. The training set and the verification set are 18 124 and 6 876 sheets, respectively. Through the transfer learning Attention ResNet structure algorithm, the OCT image was characterized by lesion identification, the disease feature was extracted by a specific procedure, and the given image was distinguished from other types of disease according to the statistical characteristics of the target lesion. The model algorithms of MERM, macular edema, macular hole, CNV and AMD were initially formed, and the fundus intelligent auxiliary diagnosis system of five models was established. The performance of each model-assisted diagnosis in the fundus intelligent auxiliary diagnostic system was evaluated by applying the subject working characteristic curve, area under the curve (AUC), sensitivity, and specificity. ResultsWith the intelligent auxiliary diagnosis system, the diagnostic sensitivity of the MERM was 93.5%, the specificity was 99.23%, and AUC was 0.983 7; the diagnostic sensitivity of macular edema was 99.02%, the specificity was 98.17%, and AUC was 0.994 6; the diagnostic sensitivity of macular hole was 98.91%, the specificity was 99.91%, AUC was 0.996 2; the diagnostic sensitivity of CNV was 97.54%, the specificity was 94.71%, AUC was 0.987 5; the diagnostic sensitivity of AMD was 95.12%, the specificity was 97.09%, AUC was 0.985 3. ConclusionsThe artificial intelligence robot-assisted diagnosis system for fundus diseases based on deep learning for OCT images has accurate and efficient diagnostic performance for assisting the diagnosis of MERM, macular edema, macular hole, CNV, and AMD.
Objective To develop a neural network architecture based on deep learning to assist knee CT images automatic segmentation, and validate its accuracy. Methods A knee CT scans database was established, and the bony structure was manually annotated. A deep learning neural network architecture was developed independently, and the labeled database was used to train and test the neural network. Metrics of Dice coefficient, average surface distance (ASD), and Hausdorff distance (HD) were calculated to evaluate the accuracy of the neural network. The time of automatic segmentation and manual segmentation was compared. Five orthopedic experts were invited to score the automatic and manual segmentation results using Likert scale and the scores of the two methods were compared. Results The automatic segmentation achieved a high accuracy. The Dice coefficient, ASD, and HD of the femur were 0.953±0.037, (0.076±0.048) mm, and (3.101±0.726) mm, respectively; and those of the tibia were 0.950±0.092, (0.083±0.101) mm, and (2.984±0.740) mm, respectively. The time of automatic segmentation was significantly shorter than that of manual segmentation [(2.46±0.45) minutes vs. (64.73±17.07) minutes; t=36.474, P<0.001). The clinical scores of the femur were 4.3±0.3 in the automatic segmentation group and 4.4±0.2 in the manual segmentation group, and the scores of the tibia were 4.5±0.2 and 4.5±0.3, respectively. There was no significant difference between the two groups (t=1.753, P=0.085; t=0.318, P=0.752). Conclusion The automatic segmentation of knee CT images based on deep learning has high accuracy and can achieve rapid segmentation and three-dimensional reconstruction. This method will promote the development of new technology-assisted techniques in total knee arthroplasty.
ObjectiveTo investigate the early effectiveness of artificial intelligence (AI) assisted total hip arthroplasty (THA) system (AIHIP) in the treatment of patients with Crowe type Ⅳ developmental dysplasia of the hip (DDH).MethodsThe clinical data of 23 patients with Crowe type Ⅳ DDH who met the selection criteria between May 2019 and December 2020 were retrospectively analyzed. There were 3 males and 20 females, the age ranged from 44 to 74 years, with an average of 52.65 years. The absolute value of the lower limbs discrepancy before operation was (15.17±22.17) mm. The preoperative Harris score was 62.4±7.2. The AIHIP system was used for preoperative planning, and the operations were all performed via conventional posterolateral approach. Thirteen patients with difficulty in reduction during operation underwent subtrochanteric shortening osteotomy (SSOT). The operation time, hospital stay, and adverse events were recorded; Harris score was used to evaluate the function of the affected limb at 1 day before operation and 1 week and 6 months after operation; pelvic anteroposterior X-ray film was taken at 1 day after operation to evaluate the position of the prosthesis. The matching degree of prosthesis was evaluated according to the consistency of intraoperative prosthesis model and preoperative planning.ResultsThe matching degree of acetabular cup model after operation was 16 cases of perfect matching, 4 cases of general matching (1 case of +1, 3 cases of –1), and 3 cases of mismatch (all of them were +2), the coincidence rate was 86.96%. The matching degree of femoral stem model was perfect matching in 22 cases and general matching in 1 case of –1, and the coincidence rate was 100%. One patient had a periprosthesis fracture during operation, and was fixed with a wire cable during operation, and walked with the assistance of walking aid at 6 weeks after operation; the rest of the patients walked with the assistance of walking aid at 1 day after operation. The operation time was 185-315 minutes, with an average of 239.43 minutes; the hospital stay was 8-20 days, with an average of 9.96 days; and the time of disengagement from the walking aid was 2-56 days, with an average of 5.09 days. All patients were followed up 6 months. All incisions healed by first intension, and there was no complication such as infection, dislocation, refracture, and lower extremity deep venous thrombosis; X-ray films at 1 day and 6 months after operation showed that the acetabular and femoral prostheses were firmly fixed and within the safe zone; the absolute value of lower limbs discrepancy at 1 day after operation was (11.96±13.48) mm, which was not significantly decreased compared with that before operation (t=0.582, P=0.564). All osteotomies healed at 6 months after operation. The Harris scores at 1 week and 6 months after operation were 69.5±4.9 and 79.2±5.7 respectively, showing significant differences between pre- and post-operation (P<0.05). At 6 months after operation, the hip function was evaluated according to Harris score, and 13 cases were good, 9 cases were fair, and 1 case was poor.ConclusionAIHIP system-assisted THA (difficult to reposition patients combined with SSOT) for adult Crowe type Ⅳ DDH has high preoperative planning accuracy, easy intraoperative reduction, early postoperative landing, and satisfactory short-term effectiveness.
Retinopathy of prematurity (ROP) is a major cause of vision loss and blindness among premature infants. Timely screening, diagnosis, and intervention can effectively prevent the deterioration of ROP. However, there are several challenges in ROP diagnosis globally, including high subjectivity, low screening efficiency, regional disparities in screening coverage, and severe shortage of pediatric ophthalmologists. The application of artificial intelligence (AI) as an assistive tool for diagnosis or an automated method for ROP diagnosis can improve the efficiency and objectivity of ROP diagnosis, expand screening coverage, and enable automated screening and quantified diagnostic results. In the global environment that emphasizes the development and application of medical imaging AI, developing more accurate diagnostic networks, exploring more effective AI-assisted diagnosis methods, and enhancing the interpretability of AI-assisted diagnosis, can accelerate the improvement of AI policies of ROP and the implementation of AI products, promoting the development of ROP diagnosis and treatment.
With the rapid development of artificial intelligence (AI) technology, its application in hospital management is gradually becoming an important means to improve operational efficiency and the quality of patient health care. This article systematically explores the multidimensional applications of AI in hospital management, including medical services, administration, patient engagement and experience. Through in-depth analysis, the paper evaluates the potential of AI in these areas, especially the significant effect in improving operational efficiency and optimising patient healthcare services. However, the application of AI also faces many challenges, such as data privacy issues, algorithmic bias, operational management, and economic factors. This article not only identifies these challenges, but also provides specific inspiration and recommendations for hospital management in China, emphasises the importance of adaptability and continuous learning, and calls on hospital administrators to actively embrace change in order to achieve both improved patient health outcomes and operational efficiency.
With the advancement and development of computer technology, the medical decision-making system based on artificial intelligence (AI) has been widely applied in clinical practice. In the perioperative period of cardiovascular surgery, AI can be applied to preoperative diagnosis, intraoperative, and postoperative risk management. This article introduces the application and development of AI during the perioperative period of cardiovascular surgery, including preoperative auxiliary diagnosis, intraoperative risk management, postoperative management, and full process auxiliary decision-making management. At the same time, it explores the challenges and limitations of the application of AI and looks forward to the future development direction.