Cloud Computing In AI Healthcare
March 1, 2023Norway
March 1, 2023Artificial Intelligence’s New Role In Medicine
Artificial Intelligence bests humans at predicting outcomes for brain radiotherapy patients and can identify potential therapeutic targets for cancer...
Role Predicting Outcomes: AI bests humans at predicting outcomes for brain radiotherapy patients.
A new AI technique could be more successful at predicting outcomes for cancer patients with brain metastasis or tumors than the human eye. Researchers at York, a public university in Toronto, Ontario, Canada, used AI neural networks and algorithms trained via deep learning to assess around 124 patients with brain metastasis based on their baseline MRI for treatment planning before radiotherapy. Two to three months after radiotherapy treatment, the patients underwent follow-up MRI, radiation oncologist, and neuroradiologist. The results revealed that specific characteristics of tumor or lesion margin areas in MRI images were essential to predict radiotherapy treatment outcomes, with AI proposing a way to assist humans in predicting treatment failure. While oncologists could predict treatment failure about 65% of the time, the best of several AI models was able to predict treatment failure with 83% accuracy. Given that the median survival rate for brain metastasis patients after radiation therapy ranges from just five months to 4 years, as noted, an early heads-up on potential treatment response can make a big difference. (1)
A new AI technique could be more successful at predicting outcomes for cancer patients with brain metastasis or tumors than the human eye. Researchers at York, a public university in Toronto, Ontario, Canada, used AI neural networks and algorithms trained via deep learning to assess around 124 patients with brain metastasis based on their baseline MRI for treatment planning before radiotherapy. Two to three months after radiotherapy treatment, the patients underwent follow-up MRI, radiation oncologist, and neuroradiologist.
The results revealed that specific characteristics of tumor or lesion margin areas in MRI images were essential to predict radiotherapy treatment outcomes, with AI proposing a way to assist humans in predicting treatment failure. While oncologists could predict treatment failure about 65% of the time, the best of several AI models was able to predict treatment failure with 83% accuracy. Given that the median survival rate for brain metastasis patients after radiation therapy ranges from just five months to 4 years, as noted, an early heads-up on potential treatment response can make a big difference. (1)
Role Developing Medicine: AI Algorithm Can Identify Potential Therapeutic Targets for Cancer
Investigators at Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine described an exceptional artificial intelligence (AI) algorithm with the potential to identify prospective therapeutic targets for glioblastoma multiforme (GBM) and other cancers.
Numerous drugs are being developed as potential therapies. Still, AI technology allows for determining the molecular mechanisms that drive the problem, and applying these to precision medicine approaches remains a challenge.
Investigators at Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine described an exceptional artificial intelligence (AI) algorithm with the potential to identify prospective therapeutic targets for glioblastoma multiforme (GBM) and other cancers. Numerous drugs are being developed as potential therapies. Still, AI technology allows for determining the molecular mechanisms that drive the problem, and applying these to precision medicine approaches remains a challenge.
The research team turned to machine learning (ML) to help identify and experimentally validate two particular kinases related to tumor progression in two subtypes of gliomas and some other lung, breast, and pediatric cancers. (2)
Role Repairing the genome: Novel tool uses AI to predict the efficacy of genome-editing repair options
A group of researchers at the University of Zurich has developed a new tool that utilizes artificial intelligence to predict the effectiveness of various genome-editing repair options. Unintended errors in correcting DNA mutations of genetic diseases can thus be reduced. Department of Quantitative Biomedicine, and his team, developed a strategy that can predict the efficiency of pegRNAs. They created a comprehensive prime editing data set by testing over 100,000 pegRNAs in cells. This allowed them to determine which properties of a pegRNA, such as the length of the DNA sequence, the series of DNA building blocks, or the shape of the DNA molecule, entirely or negatively influence the prime editing process.Subsequently, the team developed an AI-based algorithm to recognize patterns in the pegRNA of relevance for efficiency.
Based on these patterns, the competent tool can predict both the usefulness and accuracy of genome editing with a particular pegRNA. In other words, the algorithm can determine the most efficient pegRNA for correcting one specific mutation. The tool has already been successfully tested in human and mouse cells and is freely available to researchers. (3)
A group of researchers at the University of Zurich has developed a new tool that utilizes artificial intelligence to predict the effectiveness of various genome-editing repair options. Unintended errors in correcting DNA mutations of genetic diseases can thus be reduced. Department of Quantitative Biomedicine, and his team, developed a strategy that can predict the efficiency of pegRNAs.
They created a comprehensive prime editing data set by testing over 100,000 pegRNAs in cells. This allowed them to determine which properties of a pegRNA, such as the length of the DNA sequence, the series of DNA building blocks, or the shape of the DNA molecule, entirely or negatively influence the prime editing process. Subsequently, the team developed an AI-based algorithm to recognize patterns in the pegRNA of relevance for efficiency. Based on these patterns, the competent tool can predict both the usefulness and accuracy of genome editing with a particular pegRNA. In other words, the algorithm can determine the most efficient pegRNA for correcting one specific mutation. The tool has already been successfully tested in human and mouse cells and is freely available to researchers. (3)
Role to prevent sudden arrest: How Cardiac Arrest Can Be Predicted by New Form of Artificial Intelligence
A recent form of artificial intelligence may predict more accurately than a doctor if and when a person will die from cardiac arrest. In a new study, researchers from Johns Hopkins University in Maryland say artificial intelligence called survival study of cardiac arrhythmias risk (SSCAR) might revolutionize how clinical decisions are made in cardiology. Natalia Trayavina Ph.D., a senior author of the study and a professor of biomedical engineering and medicine, mentions in her research how the program works, the programmed algorithm to detect patterns of cardiac scarring that the naked eye can not see. The researchers found that the algorithm’s predictions were more accurate on every measure used compared to doctors. At present, analysis of such images only studies certain aspects of cardiac scarring, such as volume and mass. (4)
A recent form of artificial intelligence may predict more accurately than a doctor if and when a person will die from cardiac arrest. In a new study, researchers from Johns Hopkins University in Maryland say artificial intelligence called survival study of cardiac arrhythmias risk (SSCAR) might revolutionize how clinical decisions are made in cardiology.
Natalia Trayavina Ph.D., a senior author of the study and a professor of biomedical engineering and medicine, mentions in her research how the program works, the programmed algorithm to detect patterns of cardiac scarring that the naked eye can not see. The researchers found that the algorithm’s predictions were more accurate on every measure used compared to doctors. At present, analysis of such images only studies certain aspects of cardiac scarring, such as volume and mass. (4)
Role to improving early detection of severe disease: Can Artificial Intelligence Help Detect Lung Cancer?
A study published today in the journal Radiology looked at the effect AI-based software had in a real-world oncological clinical practice. In it, researchers reported that AI “significantly” improved the detection of lung nodules on chest X-rays. Lung nodules are abnormal growths that form in the lungs. They’re familiar and typically start from previous lung infections. But in rare instances, they can be a sign of lung cancer.One standard screening method for identifying lung nodules is chest X-rays. Dr. Jin Mo Goo, a study co-author and a professor at the Department of Radiology at Seoul National University Hospital in Korea, said that AI can be a powerful tool to help identify lung nodules, especially when radiologists are experiencing a high volume of cases. The first group’s X-rays were analyzed by radiologists aided by AI, while the second group’s X-rays were interpreted without the AI results.Lung nodules were identified in 2% of the participants.
Solid nodules with diameters either more significant than 8 millimeters or subsolid nodules with a substantial portion more critical than 6 millimeters were identified as actionable, meaning that the nodule required follow-up under lung cancer screening criteria. Analysis showed that the detection rate for actionable lung nodules on chest X-rays was higher when aided by AI (0.59%) than without AI assistance (0.25%). (5)
A study published today in the journal Radiology looked at the effect AI-based software had in a real-world oncological clinical practice. In it, researchers reported that AI “significantly” improved the detection of lung nodules on chest X-rays. Lung nodules are abnormal growths that form in the lungs. They’re familiar and typically start from previous lung infections. But in rare instances, they can be a sign of lung cancer.One standard screening method for identifying lung nodules is chest X-rays.
Dr. Jin Mo Goo, a study co-author and a professor at the Department of Radiology at Seoul National University Hospital in Korea, said that AI can be a powerful tool to help identify lung nodules, especially when radiologists are experiencing a high volume of cases. The first group’s X-rays were analyzed by radiologists aided by AI, while the second group’s X-rays were interpreted without the AI results.Lung nodules were identified in 2% of the participants. Solid nodules with diameters either more significant than 8 millimeters or subsolid nodules with a substantial portion more critical than 6 millimeters were identified as actionable, meaning that the nodule required follow-up under lung cancer screening criteria. Analysis showed that the detection rate for actionable lung nodules on chest X-rays was higher when aided by AI (0.59%) than without AI assistance (0.25%). (5)
Role through Radiology science: AI ultrasound application for musculoskeletal imaging
Clarius Mobile Health, which first introduced wireless handheld imaging for medical specialties in 2016, says its third-generation device, HD3, which was approved by the U.S. Food and Drug Administration this week, will also help improve MSK ultrasound training. Upon MSK imaging for specific anatomical sites: the plantar fascia, foot, Achilles tendon, ankle, patellar tendon, or knee. The AI program analyzes and displays a transparent color overlay identifying different tissues such as the tendon, ligaments, and others. Another feature is that clinicians can pause the image and run additional software. The device uses AI to label the tendon and determine the most significant thickness, automatically placing measurement calipers corresponding to the tendon’s top and bottom at its thickest region. (6)
Clarius Mobile Health, which first introduced wireless handheld imaging for medical specialties in 2016, says its third-generation device, HD3, which was approved by the U.S. Food and Drug Administration this week, will also help improve MSK ultrasound training. Upon MSK imaging for specific anatomical sites: the plantar fascia, foot, Achilles tendon, ankle, patellar tendon, or knee. The AI program analyzes and displays a transparent color overlay identifying different tissues such as the tendon, ligaments, and others.
Another feature is that clinicians can pause the image and run additional software. The device uses AI to label the tendon and determine the most significant thickness, automatically placing measurement calipers corresponding to the tendon’s top and bottom at its thickest region. (6)
Role Inside the Hospitals: AI hospital of the future
In China, Medical University Hospital (CMUH) is using AI to create a new era of healthcare. It has developed and deployed hundreds of AI algorithms hosted on Microsoft’s Azure cloud platform that is used daily across the system’s 12 hospitals. The team’s custom-built AI models are helping doctors diagnose diseases like cancer and Parkinson’s. They’re enabling ER staff to treat stroke and heart attack patients quicker. And they’re helping ease the paperwork load on doctors and nurses. The AI models are often incorporated into familiar software doctors use every day. Some are deployed with a literal push of a button. For example, doctors who order an MRI on a knee injury can click a button marked “AI” that predicts the likelihood of a meniscus tear. That instant result can avoid delays in a follow-up appointment and get a patient treated more quickly. (7)
In China, Medical University Hospital (CMUH) is using AI to create a new era of healthcare. It has developed and deployed hundreds of AI algorithms hosted on Microsoft’s Azure cloud platform that is used daily across the system’s 12 hospitals. The team’s custom-built AI models are helping doctors diagnose diseases like cancer and Parkinson’s. They’re enabling ER staff to treat stroke and heart attack patients quicker. And they’re helping ease the paperwork load on doctors and nurses.
The AI models are often incorporated into familiar software doctors use every day. Some are deployed with a literal push of a button. For example, doctors who order an MRI on a knee injury can click a button marked “AI” that predicts the likelihood of a meniscus tear. That instant result can avoid delays in a follow-up appointment and get a patient treated more quickly. (7)