Leveraging Âé¶¹Ó³»´«Ã½\u2019s Expertise in Computer Vision<\/strong><\/p>\nChen used his computer vision and machine learning expertise to develop the AI model to understand medical images.<\/p>\n
\u201cMy role was to figure out how we can extract useful information from visual data, especially for medical imaging and how can we integrate this information with other types of data modalities like text,\u201d Chen says. \u201cImaging modalities are a big part of this because in healthcare, we have a lot of imaging data such as X-rays, CT scans and MRI.\u201d<\/p>\n
BiomedGPT can perform multiple tasks, including image classification, report generation and visual question answering, and is designed to be computationally efficient and open-sourced to foster collaboration, the researchers state in their study. A clinician can upload an image and enter queries into BiomedGPT such as \u201cWhat disease does this image depict?\u201d or \u201cPlease determine the patient\u2019s eligibility by comparing the given patient note and clinical trial details\u201d and receive feedback based on an existing set of provided data integrated into the AI model\u2019s framework.<\/p>\n
According to the study, BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering and a satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts.<\/p>\n
Chen emphasizes though that clinicians and experts ultimately are responsible for reviewing the accuracy AI predications and supplementing the data.<\/p>\n
\u201cWe are not trying to replace the clinician, but rather to enhance or make their workflow more efficient,\u201d Chen says. \u201cA physician can look at an AI report and perhaps for some of the less complex cases they can quickly check to see if it is correct. The human will still be involved and with their expertise, they can make the correct prediction or the diagnosis.\u201d<\/p>\n
He says the model is designed to be computation friendly and also fully open sourced.<\/p>\n
\u201cThis is trying to foster the collaborations with research institute hospitals to use this and also improve the model over the time,\u201d he says.<\/p>\n
Next Steps<\/strong><\/p>\nThe study and analysis of BiomedGPT are promising, but there is still much to refine, Chen says.<\/p>\n
New datasets and imaging could be integrated while there also remains more evaluations for the platform\u2019s consideration of safety, equity and bias.<\/p>\n
\u201cOne thing is that we are looking to incorporate is more or [varied] data and modalities,\u201d he says. \u201cFor example, we can include more video data and physiological signals like EKGs and heart rate monitoring. Another direction is we want to address are some of the most important issues in healthcare AI in general, like the privacy.”<\/p>\n
The University of Georgia, Harvard University, Massachusetts General Hospital, University of Pennsylvania, Children\u2019s Hospital of Philadelphia, University of California, Santa Cruz, The Mayo Clinic, Samsung Research America, Stanford University and UTHealth (University of Texas) also contributed to this research.<\/p>\n
The BiomedGPT open source model is available strictly for academic research purposes here<\/a>.<\/p>\nResearcher\u2019s Credentials:<\/strong><\/p>\nChen is an associate professor at Âé¶¹Ó³»´«Ã½\u2019s CRCV and previously served as a postdoctoral scholar for the center from 2016 to 2018. His main research interests are computer vision, image and video processing, and machine learning. In 2016 Chen earned his doctoral degree in electrical engineering from the University of Texas at Dallas. He is a senior member of the Institute of Electrical and Electronics Engineers and a member of the Association for Computing Machinery.<\/p>\n","protected":false},"excerpt":{"rendered":"
The open-source AI model analyzes medical images, generates detailed reports, answers clinical questions and integrates multimodal data to streamline diagnostics and improve accuracy.<\/p>\n","protected":false},"author":8698,"featured_media":144846,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"lazy_load_responsive_images_disabled":false,"footnotes":"","_links_to":"","_links_to_target":"","_wp_rev_ctl_limit":""},"categories":[5,12,23,24],"tags":[8113,982,18082,14914,14916],"tu_author":[],"class_list":["post-144844","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-colleges","category-health","category-research","category-science-technology","tag-center-for-research-in-computer-vision","tag-college-of-sciences","tag-health","tag-medicine","tag-research"],"yoast_head":"\n
Âé¶¹Ó³»´«Ã½ Helps Develop AI Tool That May Assist Understaffed Hospitals | Âé¶¹Ó³»´«Ã½ News<\/title>\n \n \n \n \n \n \n \n \n \n \n \n \n \n\t \n\t \n\t \n \n \n \n \n \n\t \n\t \n\t \n