View clinical trials related to Artificial Intelligence.
Filter by:The goal of this in-silico clinical trial is to learn about the usability and clinical effectiveness of an interpretable deep learning framework (VAE-MLP) using counterfactual explanations and layerwise relevance propagation for prediction of post-hepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC). The main questions it aims to answer are: - To investigate the usability of the VAE-MLP framework for explanation of the deep learning model. - To investigate the clinical effectiveness of VAE-MLP framework for prediction of post-hepatectomy liver failure in patients with hepatocellular carcinoma. In the usability trial the clinicians and radiologists will be shown the counterfactual explanations and layerwise relevance propagation (LRP) plots to evaluate the usability of the framework. In the clinical trial the clinicians and radiologists will make the prediction under two different conditions: with model explanation and without model explanation with a washout period of at least 14 days to evaluate the clinical effectiveness of the explanation framework.
The aim of this study to predict carbapenem resistant Klebsiella spp. earlier in our patients monitored in our Intensive Care Unit in the future, using artificial intelligence. Patients with bloodstream infection and pneumonia caused by Klebsiella spp. will be comparatively examined in two groups, as sensitive and resistant. Resistance will be attempted to be predicted with deep machine learning.
The objective of this study is to apply an artificial intelligence algorithm to diagnose multi-retinal diseases in real-world settings. The effectiveness and accuracy of this algorithm are evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and area under curve.
This study is a multicenter evaluation of diagnostic performance using simulated clinical vignettes. It aims to test the effectiveness of the POSOS app in detecting drug-induced iatrogenesis in urgent medical situations, an issue of public health importance. Participating physicians, who are randomly assigned to either use or not use POSOS, are categorized based on their years of experience. Vignettes, including a mixture of complex, simple, and non-iatrogenesis cases, are assigned to these doctors. During the simulation, physicians respond to their respective vignettes on the YgheniVi platform, with responses recorded at two intervals (5 min and 15 min). The supervising physicians subsequently fill out an e-CRF, providing further data on the time spent, the number of medical research applications used, and the overall user experience of POSOS. A doctor/pharmacist pair then corrects the answers to the vignettes.
Grading endoscopic atrophy according to the Kimura-Takemoto classification can assess the risk of gastric neoplasia development. However, the false negative rate of chronic atrophic gastritis is high due to the varying diagnostic standardization and diagnostic experience and levels of endoscopists. Therefore, this study aims to develop an AI model to identify the Kimura-Takemoto classification.
In this study, we collected the data of immunohistochemistry, gene detection, image, OS, PFS, Orr, and so on. Secondly, the database of immunotherapy for malignant tumor was established, and the predictive model was constructed to verify and establish the rationality and validity of the biomarkers and predictive system of immunotherapy
The goal of this observational study is to evaluate the effectiveness of an AI-based reporting system for upper gastrointestinal endoscopy. The main question it aims to answer is: Whether the AI-based reporting system can improve the completeness of the reports, which are drafted by endoscopists with the AI assistance. Participants will undergo upper gastrointestinal endoscopy examination as routine. The junior endoscopists will draft the report with the assiatance of the AI system. And the senior and expert endoscopists will draft the report using the traditional reporting system without AI assistance.
Trigeminal neuralgia (TN) is the most common cause of facial pain. Medical treatment is the first therapeutic choice whereas surgery, including Gamma Knife radiosurgery (GKRS), is indicated in case of pharmacological therapy failure. However, about 20% of subjects lack adequate pain relief after surgery. Virtual reality (VR) technology has been explored as a novel tool for reducing pain perception and might be the breakthrough in treatment-resistant cases. The investigators will conduct a prospective randomized comparative study to detect the effectiveness of GKRS aided by VR-training vs GKRS alone in TN patients. In addition, using MRI and artificial intelligence (AI), the investigators will identify pre-treatment abnormalities of central nervous system circuits associated with pain to predict response to treatment. The investigators expect that brain-based biomarkers, with clinical features, will provide key information in the personalization of treatment options and bring a huge impact in the management and understanding of pain in TN.
The goal of this observational study is to establish and verify the Chinese version of surgical risk assessment system and explore its clinical application. The main questions it aims to answer are: The process of establishing a Chinese version of surgical risk assessment system; What is the accuracy of the system; How can the system be used in clinic; How does this system compare with other systems (such as NSQIP). Participants will comprehensively collect the general information, examination and pathological information of the patients, using machine learning and artificial intelligence methods for data processing. Finally, the Chinese version of the surgical risk assessment system will be established. After the system is established, investigators will evaluate the accuracy of the system and compare it with other related systems.
To evaluate the usefulness of Deep neural network (DNN) in the evaluation of mediastinal and hilar lymph nodes with Endobronchial ultrasound (EBUS). The study will explore the feasibility of DNN to identify lymph nodes and blood vessel examined with EBUS.