PAIGE
February 1, 2023Automated Reasoning
February 1, 20232023: The Year of The Artificial Intelligence
AI and deep learning will gain space in the medical field this new year with new approvals by health agencies in different parts of the world...
First State to implement artificial intelligence to detect colorectal cancer
J.W. Ruby Memorial Hospital, one of the leading hospitals of the West Virginia University Health System, is the first place in the state to obtain five GI GeniusTM intelligent endoscopy modules as part of the Medtronic Health Assistance Program for colorectal cancer screening. The Program, launched in December 2022 with support from the American Society for Gastrointestinal Endoscopy and Amazon Services, uses artificial intelligence (AI) to detect from colorectal polyps to severe cancer signs. The module uses advanced AI software to highlight suspicious polyps with a real-time visual feature with a sensitivity rate per lesion of 99.7 percent. Investigations have demonstrated that AI-assisted colonoscopy can improve polyp detection rates, and every 1 percent growth in adenoma detection rate decreases the risk of colorectal cancer by 3 percent.(1)
J.W. Ruby Memorial Hospital, one of the leading hospitals of the West Virginia University Health System, is the first place in the state to obtain five GI GeniusTM intelligent endoscopy modules as part of the Medtronic Health Assistance Program for colorectal cancer screening. The Program, launched in December 2022 with support from the American Society for Gastrointestinal Endoscopy and Amazon Services, uses artificial intelligence (AI) to detect from colorectal polyps to severe cancer signs. The module uses advanced AI software to highlight suspicious polyps with a real-time visual feature with a sensitivity rate per lesion of 99.7 percent.
Investigations have demonstrated that AI-assisted colonoscopy can improve polyp detection rates, and every 1 percent growth in adenoma detection rate decreases the risk of colorectal cancer by 3 percent.(1)
New artificial intelligence systems can empower medical professionals in diagnosing skin diseases
In 2023, deep learning in dermatology will expand beyond dermatoscopic recognition of malignancy. Recently, an AI was trained to recognize non-neoplastic or benign disorders. Korean researchers from the Department of Dermatology, Seoul National University, Seoul, Korea, have invented an algorithm based on deep learning. This algorithm can precisely categorize cutaneous skin disorders, advise primary treatment options, and serve as a supporting tool to magnify clinicians’ diagnostic accuracy. The researchers gathered 220,000 images of the Asian and Caucasian race with 174 skin diseases and trailed neural networks to interpret those images. It was discovered that the algorithm could diagnose 134 skin disorders and improve the performance of the medical staff by suggesting primary treatment options and classifying the disorder. (2)
In 2023, deep learning in dermatology will expand beyond dermatoscopic recognition of malignancy. Recently, an AI was trained to recognize non-neoplastic or benign disorders. Korean researchers from the Department of Dermatology, Seoul National University, Seoul, Korea, have invented an algorithm based on deep learning. This algorithm can precisely categorize cutaneous skin disorders, advise primary treatment options, and serve as a supporting tool to magnify clinicians’ diagnostic accuracy.
The researchers gathered 220,000 images of the Asian and Caucasian race with 174 skin diseases and trailed neural networks to interpret those images. It was discovered that the algorithm could diagnose 134 skin disorders and improve the performance of the medical staff by suggesting primary treatment options and classifying the disorder. (2)
Applying AI To Transform Early Lung Cancer Treatment
On the 6th Friday of 2023, the US Food and Drug Administration (FDA) approved one of the testing for Optellum, a lung-health AI company, and has partnered strategically with the Lung Cancer Initiative at Johnson & Johnson. Through the partnership, Optellum will apply its AI-powered clinical decision support platform to increase lung cancer survival rates through early intervention and prevention, including an AI-powered digital biomarker based on neural networks and imaging analytics. It identifies and risks patients and assigns a Lung Cancer Prediction score to lung nodules, small lesions frequently detected in chest Computed Tomography scans. The Optellum AI will drive accurate early diagnosis and optimal treatment decisions to treat patients at earlier stages, increasing survival rates. The Optellum software achieved FDA clearance in March 2023 and is being implemented in clinical care by leading hospitals initially across the United States, with rollouts in select Asian-Pacific and European markets to follow.(3)
On the 6th Friday of 2023, the US Food and Drug Administration (FDA) approved one of the testing for Optellum, a lung-health AI company, and has partnered strategically with the Lung Cancer Initiative at Johnson & Johnson. Through the partnership, Optellum will apply its AI-powered clinical decision support platform to increase lung cancer survival rates through early intervention and prevention, including an AI-powered digital biomarker based on neural networks and imaging analytics.
It identifies and risks patients and assigns a Lung Cancer Prediction score to lung nodules, small lesions frequently detected in chest Computed Tomography scans. The Optellum AI will drive accurate early diagnosis and optimal treatment decisions to treat patients at earlier stages, increasing survival rates. The Optellum software achieved FDA clearance in March 2023 and is being implemented in clinical care by leading hospitals initially across the United States, with rollouts in select Asian-Pacific and European markets to follow.(3)
Behavioral Health AI predicts the effectiveness of talk therapy
According to new research from the University of Southern California, artificial intelligence can help measure the effectiveness of cognitive-behavioral therapy. Engineering scientists at the University of Southern California, USC’s Signal Analysis and Interpretation Laboratory, set out to explore whether AI could do this job using transcripts of more than 1,100 honest conversations with patients. Early results were satisfactory, with the AI achieving 73% accuracy of what a human evaluator could achieve. Nikolaos Flemotomos, a Ph.D. in engineering at USC, believes this is the most extensive study of automated assessment of this type of therapy and the first using 100 percent real people and conversations. One of the biggest challenges for the AI was capturing multiple interlocutors and discerning the meaning of the text-based conversation.
According to new research from the University of Southern California, artificial intelligence can help measure the effectiveness of cognitive-behavioral therapy. Engineering scientists at the University of Southern California, USC’s Signal Analysis and Interpretation Laboratory, set out to explore whether AI could do this job using transcripts of more than 1,100 honest conversations with patients. Early results were satisfactory, with the AI achieving 73% accuracy of what a human evaluator could achieve.
Nikolaos Flemotomos, a Ph.D. in engineering at USC, believes this is the most extensive study of automated assessment of this type of therapy and the first using 100 percent real people and conversations. One of the biggest challenges for the AI was capturing multiple interlocutors and discerning the meaning of the text-based conversation. However, their creation proved effective in assessing therapists’ interpersonal skills, how they structure sessions, and their capacity to establish rapport, among other factors. USC specialists believe their AI tool could be scaled up to help bolster staff and address the growing demand for these services. Their main goal is not to replace human supervision. However, only to increase the effectiveness of raters and assist in self-assessment. Moving from text-based analysis to loud conversation is an avenue for further exploration. (4)
Why 2023 Could Be The Year For Incurable Pediatric Brain Cancer?
A new machine learning AI can identify a new treatment for incurable pediatric brain cancer. Diffuse intrinsic pontine glioma (DIPG) is a fatal infiltrating type of glioma, and the overall survival time ranges from nine months to a year, according to The Institute of Cancer Research, London, and The Royal Marsden NHS Foundation Trust based in Chelsea. They led the research study. The researchers sought new medications targeting ACVR1 mutations in diffuse intrinsic pontine glioma by using thousands of papers with more than a billion connection edges in the BenevolentAI’s knowledge graph. The BenevolentAI knowledge graph enables scientists to computationally learn novel insights, such as ways to repurpose existing medicines for new treatments and use the AI platform to see if a combination would be effective. The researchers evaluated compounds for potential feedback mechanisms that a combination of inhibitors could thwart. The scientists assessed the novel drug combination in the brains of mice with diffuse intrinsic pontine glioma.(5)
A new machine learning AI can identify a new treatment for incurable pediatric brain cancer. Diffuse intrinsic pontine glioma (DIPG) is a fatal infiltrating type of glioma, and the overall survival time ranges from nine months to a year, according to The Institute of Cancer Research, London, and The Royal Marsden NHS Foundation Trust based in Chelsea. They led the research study. The researchers sought new medications targeting ACVR1 mutations in diffuse intrinsic pontine glioma by using thousands of papers with more than a billion connection edges in the BenevolentAI’s knowledge graph.
The BenevolentAI knowledge graph enables scientists to computationally learn novel insights, such as ways to repurpose existing medicines for new treatments and use the AI platform to see if a combination would be effective. The researchers evaluated compounds for potential feedback mechanisms that a combination of inhibitors could thwart. The scientists assessed the novel drug combination in the brains of mice with diffuse intrinsic pontine glioma.(5)
AI with Virtual Reality: A big integration in Cardiology
The recently FDA-cleared Holoscope-i system, developed by RealView Imaging, an Israeli start-up company, is pioneering the field of interactive live holography. The AI technology projects 3D/4D true holograms of a patient’s heart anatomy in space. This creates high-quality holograms similar to 3D printing and optically indistinguishable from actual objects. RealView Imaging has developed the newest generation of reality technology, producing a super realistic volumetric representation of medical data helping with AI. This new technology is based on a Nobel-prize-winning holographic technology that provides all 3D visual depth features, projecting all the image points simultaneously at multiple depth locations, like a 3D printer of weak points.(6)
The recently FDA-cleared Holoscope-i system, developed by RealView Imaging, an Israeli start-up company, is pioneering the field of interactive live holography. The AI technology projects 3D/4D true holograms of a patient’s heart anatomy in space. This creates high-quality holograms similar to 3D printing and optically indistinguishable from actual objects.
RealView Imaging has developed the newest generation of reality technology, producing a super realistic volumetric representation of medical data helping with AI. This new technology is based on a Nobel-prize-winning holographic technology that provides all 3D visual depth features, projecting all the image points simultaneously at multiple depth locations, like a 3D printer of weak points.(6)
Commercial AI system enables detection of vision-threatening diabetic retinopathy
An AI system that can diagnose diabetic retinopathy without physician assistance, including one of the most severe forms that put patients at risk of total blindness, has outperformed expectations in a clinical trial. Researchers team at the Lundquist Institute for Biomedical Innovation, part of Harbor–UCLA Medical Center located in Los Angeles County, California, in collaboration with other US centers, conducted a clinical trial to evaluate the safety of the EyeArt Automated DR (diabetic retinopathy) Detection System to autonomously detect this kind of the disease, using dilated and undilated eye imaging regimes. The results are awe-inspiring; with the undilated imaging protocol, the AI system can exceed predetermined endpoints for diagnosis, with both sensitivity (greater than 90%) and specificity (greater than 82.5%) of DR detection.(7)
An AI system that can diagnose diabetic retinopathy without physician assistance, including one of the most severe forms that put patients at risk of total blindness, has outperformed expectations in a clinical trial. Researchers team at the Lundquist Institute for Biomedical Innovation, part of Harbor–UCLA Medical Center located in Los Angeles County, California, in collaboration with other US centers, conducted a clinical trial to evaluate the safety of the EyeArt Automated DR (diabetic retinopathy) Detection System to autonomously detect this kind of the disease, using dilated and undilated eye imaging regimes.
The results are awe-inspiring; with the undilated imaging protocol, the AI system can exceed predetermined endpoints for diagnosis, with both sensitivity (greater than 90%) and specificity (greater than 82.5%) of DR detection.(7)