Heart transplantation remains the most effective treatment for patients with end-stage heart failure. Over the past decade, significant advancements have been made in the field of heart transplant surgery. However, the enormous demand from heart failure patients and the severe shortage of available donor hearts continue to be major obstacles to the widespread application of heart transplantation. With the development of donor heart recovery, preservation, and evaluation techniques, the use of extended criteria donors and donation after circulatory death has increased. These technological advancements have expanded the safe ischemic time and geographic range for donor heart procurement, significantly enlarging the donor pool and driving a rapid increase in heart transplant cases. Concurrently, many new techniques have emerged in heart transplant surgery and perioperative management, particularly the rapid advancements in mechanical circulatory support and artificial intelligence, which hold the potential to revolutionize the field. This article reviews and discusses the current status and major surgical advancements in adult heart transplantation in the United States, aiming to provide insights and stimulate ongoing exploration and innovation in this field.
ObjectiveTo analyze the predictive value of ensemble classification algorithm of random forest for delirium risk in ICU patients with cardiothoracic surgery. MethodsA total of 360 patients hospitalized in cardiothoracic ICU of our hospital from June 2019 to December 2020 were retrospectively analyzed. There were 193 males and 167 females, aged 18-80 (56.45±9.33) years. The patients were divided into a delirium group and a control group according to whether delirium occurred during hospitalization or not. The clinical data of the two groups were compared, and the related factors affecting the occurrence of delirium in cardiothoracic ICU patients were predicted by the multivariate logistic regression analysis and the ensemble classification algorithm of random forest respectively, and the difference of the prediction efficiency between the two groups was compared.ResultsOf the included patients, 19 patients fell out, 165 patients developed ICU delirium and were enrolled into the delirium group, with an incidence of 48.39% in ICU, and the remaining 176 patients without ICU delirium were enrolled into the control group. There was no statistical significance in gender, educational level, or other general data between the two groups (P>0.05). But compared with the control group, the patients of the delirium group were older, length of hospital stay was longer, and acute physiology and chronic health evaluationⅡ(APACHEⅡ) score, proportion of mechanical assisted ventilation, physical constraints, sedative drug use in the delirium group were higher (P<0.05). Multivariate logistic regression analysis showed that age (OR=1.162), length of hospital stay (OR=1.238), APACHEⅡ score (OR=1.057), mechanical ventilation (OR=1.329), physical constraints (OR=1.345) and sedative drug use (OR=1.630) were independent risk factors for delirium of cardiothoracic ICU patients. The variables in the random forest model for sorting, on top of important predictor variable were: age, length of hospital stay, APACHEⅡ score, mechanical ventilation, physical constraints and sedative drug use. The diagnostic efficiency of ensemble classification algorithm of random forest was obviously higher than that of multivariate logistic regression analysis. The area under receiver operating characteristic curve of ensemble classification algorithm of random forest was 0.87, and the one of multivariate logistic regression analysis model was 0.79.ConclusionThe ensemble classification algorithm of random forest is more effective in predicting the occurrence of delirium in cardiothoracic ICU patients, which can be popularized and applied in clinical practice and contribute to early identification and strengthening nursing of high-risk patients.
Lung cancer has the highest incidence and mortality rates among malignant tumors both in China and worldwide, with approximately 85% of cases being non-small cell lung cancer (NSCLC). In the diagnosis and treatment of lung cancer, conventional imaging and tissue biopsy are often limited by insufficient sensitivity or invasive risks, making it difficult to meet the demands of future precision medicine. In recent years, artificial intelligence (AI)-based radiomics and autoantibody-based liquid biopsy have developed rapidly and have become major research focuses. AI radiomics significantly improves the accuracy of traditional imaging diagnosis by autonomously learning from large-scale imaging databases. Autoantibody liquid biopsy, on the other hand, utilizes tumor-associated autoantigens and antibodies as biomarkers, offering the advantages of being non-invasive, precise, efficient, and capable of reflecting spatiotemporal tumor heterogeneity, thereby demonstrating great potential in NSCLC diagnosis and treatment. This review summarizes recent research advances in autoantibody liquid biopsy and AI radiomics for the management of lung cancer.
ObjectiveTo evaluate the application value of three-dimensional (3D) reconstruction in preoperative surgical diagnosis of new classification criteria for lung adenocarcinoma, which is helpful to develop a deep learning model of artificial intelligence in the auxiliary diagnosis and treatment of lung cancer.MethodsThe clinical data of 173 patients with ground-glass lung nodules with a diameter of ≤2 cm, who were admitted from October 2018 to June 2020 in our hospital were retrospectively analyzed. Among them, 55 were males and 118 were females with a median age of 61 (28-82) years. Pulmonary nodules in different parts of the same patient were treated as independent events, and a total of 181 subjects were included. According to the new classification criteria of pathological types, they were divided into pre-invasive lesions (atypical adenomatous hyperplasia and and adenocarcinoma in situ), minimally invasive adenocarcinoma and invasive adenocarcinoma. The relationship between 3D reconstruction parameters and different pathological subtypes of lung adenocarcinoma, and their diagnostic values were analyzed by multiplanar reconstruction and volume reconstruction techniques.ResultsIn different pathological types of lung adenocarcinoma, the diameter of lung nodules (P<0.001), average CT value (P<0.001), consolidation/tumor ratio (CTR, P<0.001), type of nodules (P<0.001), nodular morphology (P<0.001), pleural indenlation sign (P<0.001), air bronchogram sign (P=0.010), vascular access inside the nodule (P=0.005), TNM staging (P<0.001) were significantly different, while nodule growth sites were not (P=0.054). At the same time, it was also found that with the increased invasiveness of different pathological subtypes of lung adenocarcinoma, the proportion of dominant signs of each group gradually increased. Meanwhile, nodule diameter and the average CT value or CTR were independent risk factors for malignant degree of lung adenocarcinoma.ConclusionImaging signs of lung adenocarcinoma in 3D reconstruction, including nodule diameter, the average CT value, CTR, shape, type, vascular access conditions, air bronchogram sign, pleural indenlation sign, play an important role in the diagnosis of lung adenocarcinoma subtype and can provide guidance for personalized therapy to patients in clinics.
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.
In order to further regulate the application of 3D reconstruction in thoracic surgery, the Chinese Expert Consensus Group on the Application of Integrated 3D Reconstruction with Artificial Intelligence in Thoracic Surgery conducted discussions and developed this consensus. This consensus is based on the clinical experience and existing prospective or retrospective studies of 3D reconstruction technology in various scenarios of thoracic surgery and summarizes recommendations, and also appends a list of 3D reconstruction technology application scenarios that are currently controversial, not fully studied, or still in the exploratory stage, to provide direction and evidence for future clinical research and disease diagnosis and treatment, and to reach a consensus.
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.
Deep brain stimulation (DBS), as a major branch of functional neurosurgery, has been widely used in the treatment of diseases such as Parkinson disease, primary tremor, and muscle tone disorder. It can effectively alleviate patients’ symptoms, reduce drug dependence, and minimize adverse drug reactions. In recent years, with the rapid development of artificial intelligence (AI) in the medical field, it has gradually penetrated into multiple aspects of DBS. This article reviews the current application status of AI technology in DBS therapy and explores its future development prospects, providing new solutions for significant improvement in patients’ quality of life.
Generative artificial intelligence (AI) technology plays a significant role in enhancing data application capabilities, improving disease diagnosis and treatment plans, and advancing health management, drug development, genetic analysis, and precision medicine. However, due to the diagnostic complexity, treatment diversity, and high technical demands of orthopedic diseases, the application of generative AI in orthopedics is still in its early exploration stage. This paper, based on the experience of applying generative AI, summarizes the concept, working principles, progress of application in orthopedics, as well as the existing shortcomings and optimization strategies, aiming to provide valuable insights for the application of generative AI in orthopedics clinical practice.
The rapid development of artificial intelligence put forward higher requirements for the computational speed, resource consumption and the biological interpretation of computational neuroscience. Spiking neuron networks can carry a large amount of information, and realize the imitation of brain information processing. However, its hardware is an important way to realize its powerful computing ability, and it is also a challenging technical problem. The memristor currently is the electronic devices that functions closest to the neuron synapse, and able to respond to spike voltage in a highly similar spike timing dependent plasticity (STDP) mechanism with a biological brain, and has become a research hotspot to construct spiking neuron networks hardware circuit in recent years. Through consulting the relevant literature at home and abroad, this paper has made a thorough understanding and introduction to the research work of the spiking neuron networks based on the memristor in recent years.