Warfarin, a classic oral anticoagulant, is characterized by a narrow therapeutic window and considerable interindividual variability in dosing requirements. This makes precise dose adjustment challenging in clinical practice and increases the risk of bleeding or thrombosis. To improve dose prediction, this study developed a streamlined multilayer perceptron (MLP) model using real-world data from the International Warfarin Pharmacogenomics Consortium (IWPC) database. The LASSO-proj algorithm was applied for high-precision feature selection prior to model construction. The resulting model demonstrated strong predictive performance on the test set, achieving a coefficient of determination (R2) of 0.456, a mean absolute error (MAE) of 8.92 mg/week, and 48.522% of its predictions falling within ±20% of the actual stable therapeutic dose. Through SHAP-based interpretation using DeepExplainer, key features influencing warfarin dosing were identified, including the VKORC1 genotype, body weight, age, and ethnicity. The interpretable MLP framework incorporating LASSO-proj not only maintains high predictive accuracy, but also significantly enhances model transparency, providing a valuable tool for guiding warfarin therapy.
Human society has entered the age of artificial intelligence(AI). Medical practice and education are undergoing profound changes. The government strongly advocates the application of AI in the field of education and it has been incorporated into the national strategy. The integration of medical education and AI technology is changing the paradigm of modern medical education. This paper introduces the current application status of AI in medical education, and analyzes the existing problems and proposes corresponding resolutions, so as to lay a foundation for promoting the integration of medical education and AI.
Rare diseases are characterized by low incidence rates, high heterogeneity, and significant genetic relevance, posing global challenges in clinical diagnosis and treatment, including delayed diagnosis and a scarcity of therapeutic options. Artificial intelligence (AI) technology offers novel solutions to address these challenges in the field of rare diseases. This paper explores the advancements in AI applications for rare diseases from two perspectives: auxiliary diagnosis and treatment decision-making. In terms of auxiliary diagnosis, AI can integrate superficial features, electronic health records, genomic data, and multi-modal data to achieve early and precise diagnosis. Regarding treatment decision-making, AI facilitates drug target discovery, drug repurposing, and the design of gene therapy vectors, thereby promoting the development and application of new treatments. Furthermore, this paper analyzes the challenges of AI in rare disease diagnosis and treatment concerning data, technical algorithms, and clinical application, and proposes future directions, including the construction of a collaborative data ecosystem, enhancement of algorithm interpretability, and improvement of regulatory frameworks.
Ophthalmic imaging examination is the main basis for early screening, evaluation and diagnosis of eye diseases. In recent years, with the improvement of computer data analysis ability, the deepening of new algorithm research and the popularization of big data platform, artificial intelligence (AI) technology has developed rapidly and become a hot topic in the field of medical assistant diagnosis. The advantage of AI is accurate and efficient, which has great application value in processing image-related data. The application of AI not only helps to promote the development of AI research in ophthalmology, but also helps to establish a new medical service model for ophthalmic diagnosis and promote the process of prevention and treatment of blindness. Future research of ophthalmic AI should use multi-modal imaging data comprehensively to diagnose complex eye diseases, integrate standardized and high-quality data resources, and improve the performance of algorithms.
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.
Objective To develop an automatic diagnostic tool based on deep learning for lumbar spine stability and validate diagnostic accuracy. Methods Preoperative lumbar hyper-flexion and hyper-extension X-ray films were collected from 153 patients with lumbar disease. The following 5 key points were marked by 3 orthopedic surgeons: L4 posteroinferior, anterior inferior angles as well as L5 posterosuperior, anterior superior, and posterior inferior angles. The labeling results of each surgeon were preserved independently, and a total of three sets of labeling results were obtained. A total of 306 lumbar X-ray films were randomly divided into training (n=156), validation (n=50), and test (n=100) sets in a ratio of 3∶1∶2. A new neural network architecture, Swin-PGNet was proposed, which was trained using annotated radiograph images to automatically locate the lumbar vertebral key points and calculate L4, 5 intervertebral Cobb angle and L4 lumbar sliding distance through the predicted key points. The mean error and intra-class correlation coefficient (ICC) were used as an evaluation index, to compare the differences between surgeons’ annotations and Swin-PGNet on the three tasks (key point positioning, Cobb angle measurement, and lumbar sliding distance measurement). Meanwhile, the change of Cobb angle more than 11° was taken as the criterion of lumbar instability, and the lumbar sliding distance more than 3 mm was taken as the criterion of lumbar spondylolisthesis. The accuracy of surgeon annotation and Swin-PGNet in judging lumbar instability was compared. Results ① Key point: The mean error of key point location by Swin-PGNet was (1.407±0.939) mm, and by different surgeons was (3.034±2.612) mm. ② Cobb angle: The mean error of Swin-PGNet was (2.062±1.352)° and the mean error of surgeons was (3.580±2.338)°. There was no significant difference between Swin-PGNet and surgeons (P>0.05), but there was a significant difference between different surgeons (P<0.05). ③ Lumbar sliding distance: The mean error of Swin-PGNet was (1.656±0.878) mm and the mean error of surgeons was (1.884±1.612) mm. There was no significant difference between Swin-PGNet and surgeons and between different surgeons (P>0.05). The accuracy of lumbar instability diagnosed by surgeons and Swin-PGNet was 75.3% and 84.0%, respectively. The accuracy of lumbar spondylolisthesis diagnosed by surgeons and Swin-PGNet was 70.7% and 71.3%, respectively. There was no significant difference between Swin-PGNet and surgeons, as well as between different surgeons (P>0.05). ④ Consistency of lumbar stability diagnosis: The ICC of Cobb angle among different surgeons was 0.913 [95%CI (0.898, 0.934)] (P<0.05), and the ICC of lumbar sliding distance was 0.741 [95%CI (0.729, 0.796)] (P<0.05). The result showed that the annotating of the three surgeons were consistent. The ICC of Cobb angle between Swin-PGNet and surgeons was 0.922 [95%CI (0.891, 0.938)] (P<0.05), and the ICC of lumbar sliding distance was 0.748 [95%CI(0.726, 0.783)] (P<0.05). The result showed that the annotating of Swin-PGNet were consistent with those of surgeons. ConclusionThe automatic diagnostic tool for lumbar instability constructed based on deep learning can realize the automatic identification of lumbar instability and spondylolisthesis accurately and conveniently, which can effectively assist clinical diagnosis.
Objective To evaluate medical students’ perceptions and attitudes toward artificial intelligence (AI)-assisted diagnosis of renal cell carcinoma (RCC), and to analyze their educational needs regarding AI in pathological diagnosis. Methods A questionnaire survey (including closed and open-ended questions) was conducted to assess medical students’ perceptions, attitudes, and educational needs concerning AI-assisted RCC diagnosis. Participants included medical students from different specialties and standardized training residents. The questionnaire covered demographic information, perceptions and attitudes toward AI, and AI-related educational needs. Results A total of 249 respondents completed the survey. The majority were standardized training residents, mostly aged 23-26 years, and 40.96% had practical experience in pathological diagnosis of RCC. The median scores for most closed-ended questions were 4. Respondents generally considered “efficiency” and “improved accuracy” as the most prominent advantages of AI, with timeliness, automated diagnosis, reduction of human error, and precise diagnosis being the most emphasized aspects. Analysis of AI-related educational needs revealed high-frequency keywords such as “expanding sample size” “balanced responsibility allocation” and “enhancing collaboration skills.” Conclusion Medical students hold a positive attitude toward AI and its application in RCC diagnosis, but there remains a lack of formal AI-related education.
Systematic reviews and meta-analyses are essential methods in evidence-based medicine for integrating research evidence and guiding clinical decision-making. However, with the rapid expansion of medical research data, traditional approaches face significant challenges in terms of efficiency, accuracy, and reliability. In recent years, the rapid advancement of artificial intelligence (AI) technologies, particularly in natural language processing (NLP), machine learning (ML), and large language models (LLMs), has provided robust support for automating and intelligentizing systematic reviews and meta-analyses. This paper systematically reviews the progress of AI applications in these fields, tracing the evolution from traditional tools to intelligent platforms, and analyzes the functional characteristics, application scenarios, and limitations of existing AI-driven tools. Furthermore, it explores the challenges posed by AI in terms of adaptation to the medical field, multimodal data processing, and ethical transparency, while offering potential solutions and optimization strategies. Looking ahead, with the continuous optimization of technology, enhanced data sharing, and the establishment of industry standards, AI is expected to significantly improve the efficiency and quality of systematic reviews and meta-analyses, driving the transition from "tool-driven" to "intelligent collaboration." The deep integration of AI not only injects innovative momentum into evidence-based medicine but also reshapes its methodological foundation, laying a solid basis for a more intelligent, equitable, and efficient future.
ObjectiveTo study the efficiency and difference of the artificial intelligence (AI) system based on fundus-reading in community and hospital scenarios in screening/diagnosing diabetic retinopathy (DR) among aged population, and further evaluate its application value. MethodsA combination of retrospective and prospective study. The clinical data of 1 608 elderly patients with diabetes were continuously treated in Henan Eye Hospital & Henan Eye Institute from July 2018 to March 2021, were collected. Among them, there were 659 males and 949 females; median age was 64 years old. From December 2018 to April 2019, 496 elderly diabetes patients were prospectively recruited in the community. Among them, there were 202 males and 294 female; median age was 62 years old. An ophthalmologist or a trained endocrinologist performed a non-mydriatic fundus color photographic examination in both eyes, and a 45° frontal radiograph was taken with the central fovea as the central posterior pole. The AI system was developed based on the deep learning YOLO source code, AI system based on the deep learning algorithm was applied in final diagnosis reporting by the "AI+manual-check" method. The diagnosis of DR were classified into 0-4 stage. The 2-4 stage patients were classified into referral DR group. ResultsA total of 1 989 cases (94.5%, 1 989/2 104) were read by AI, of which 437 (88.1%, 437/496) and 1 552 (96.5%, 1 552/1 608) from the community and hospital, respectively. The reading rate of AI films from community sources was lower than that from hospital sources, and the difference was statistically significant (χ2=51.612, P<0.001). The main reasons for poor image quality in the community were small pupil (47.1%, 24/51), cataract (19.6%, 10/51), and cataract combined with small pupil (21.6%, 11/51). The total negative rate of DR was 62.4% (1 241/1 989); among them, the community and hospital sources were 84.2% and 56.3%, respectively, and the AI diagnosis negative rate of community source was higher than that of hospital, and the difference was statistically significant (χ2=113.108, P<0.001). AI diagnosis required referral to DR 20.2% (401/1 989). Among them, community and hospital sources were 6.4% and 24.0%, respectively. The rate of referral for DR for AI diagnosis from community sources was lower than that of hospitals, and the difference was statistically significant (χ2=65.655, P<0.001). There was a statistically significant difference in the composition ratio of patients with different stages of DR diagnosed by AI from different sources (χ2=13.435, P=0.001). Among them, community-derived patients were mainly DR without referral (52.2%, 36/69); hospital-derived patients were mainly DR requiring referral (54.9%, 373/679), and the detection rate of treated DR was higher (14.3%). The first rank of the order of the fundus lesions number automatically identified by AI was drusen (68.4%) and intraretinal hemorrhage (48.5%) in the communities and hospitals respectively. Conclusions It is more suitable for early and negative DR screening for its high non-referral DR detection rate in the community. Whilst referral DR were mainly found in hospital scenario.
Objective To construct and evaluate a screening and diagnostic system based on color fundus images and artificial intelligence (AI)-assisted screening for optic neuritis (ON) and non-arteritic anterior ischemic optic neuropathy (NAION). MethodsA diagnostic test study. From 2016 to 2020, 178 cases 267 eyes of NAION patients (NAION group) and 204 cases 346 eyes of ON patients (ON group) were examined and diagnosed in Zhongshan Ophthalmic Center of Sun Yat-sen University; 513 healthy individuals of 1 160 eyes (the normal control group) with normal fundus by visual acuity, intraocular pressure and optical coherence tomography examination were collected from 2018 to 2020. All 2 909 color fundus images were as the data set of the screening and diagnosis system, including 730, 805, and 1 374 images for the NAION group, ON group, and normal control group, respectively. The correctly labeled color fundus images were used as input data, and the EfficientNet-B0 algorithm was selected for model training and validation. Finally, three systems for screening abnormal optic discs, ON, and NAION were constructed. The subject operating characteristic (ROC) curve, area under the ROC (AUC), accuracy, sensitivity, specificity, and heat map were used as indicators of diagnostic efficacy. ResultsIn the test data set, the AUC for diagnosing the presence of an abnormal optic disc, the presence of ON, and the presence of NAION were 0.967 [95% confidence interval (CI) 0.947-0.980], 0.964 (95%CI 0.938-0.979), and 0.979 (95%CI 0.958-0.989), respectively. The activation area of the systems were mainly located in the optic disc area in the decision-making process. ConclusionAbnormal optic disc, ON and NAION, and screening diagnostic systems based on color fundus images have shown accurate and efficient diagnostic performance.