Goto

Collaborating Authors

 margaretta colangelo


New AI Platform Increases Speed and Accuracy Diagnosing Pediatric Cancer

#artificialintelligence

Cancer is the leading cause of death for children. There are over 400,000 new cases of pediatric cancer diagnosed every year. Scientists at The Hospital for Sick Children (SickKids) in Toronto are using AI to increase the speed and accuracy of diagnosing cancer. Dr. Adam Shlien and his colleagues have developed an AI based platform that can can classify every known type of childhood cancer and match a diagnosis for 85% of pediatric cancers. The new AI platform can help doctors and researchers identify specific cancer types faster and more accurately and can help researchers develop new therapeutics.


Exploring Potential Longevity Applications of Rapamycin With ChatGPT

#artificialintelligence

In 2020 I joined the private beta test of Open AI's Generative Pre-trained Transformer 3 (GPT-3), which is an earlier version of ChatGPT. When ChatGPT was released in November 2022, I started experimenting with it. Large language models like ChatGPT are expected to enable a new wave of research, creativity and productivity, because they can help generate solutions for complex problems. For over two years I've been exploring the strengths and limits of this technology and assessing how this tool could be useful to me. I'm also interested how this new technology is being utilized by scientists to make meaningful contributions to academic work.


Insilico Medicine Launches AI-Powered Robotics Lab To Discover New Drugs

#artificialintelligence

This week Insilico Medicine announced the launch of Life Star - their AI powered 6th generation robotics lab for drug discovery. This state of the art lab is equipped with several types of autonomous guided vehicles (AGVs) and advanced imaging devices. The AGV robots are driven by AI and guided by radar. The robots - which are completely controlled by AI - connect all of the automation modules in the lab. Insilico's lab is different from every other lab because Life Star is a 6th generation lab, meaning it does not require any human intervention.


Margaretta Colangelo on LinkedIn: #artificialintelligence #healthcare #innovation #fda

#artificialintelligence

My friends in pharma may like this - the world's first documentary video hackathon covering the discovery of a novel medicine from the development of AI platform to using this AI platform to discover a novel target, generate novel molecule and take it all the way into the human clinical trials. The target was discovered using aging research and it may be the first aging-clock derived therapeutic. We started recording the footage in 2020 and generated over 160 hours worth of footage material, interviews, laboratory experiments, internal presentations, successes, failures, daily life of deeply committed scientists - all on tape. We are now offering 2 years of footage to the documentary video experts to take part in the global competition to tell the story and explain how novel medicines are made. We have a panel of celebrity judges and great prizes for the winners.


Margaretta Colangelo on LinkedIn: NVIDIA Partners With NHS Trusts to Deploy AI Platform in UK Hospitals

#artificialintelligence

Important AI Milestone at Mass General Brigham in Boston -- 1) Mass General Brigham is using an AI model that has reduced the waiting period for breast imaging results from days to 15 minutes. This helps hospitals reduce time and effort needed to annotate new datasets.


Mayo Clinic Platform Accelerator For AI HealthTech Startups

#artificialintelligence

In March 2022 the Mayo Clinic Platform announced their new accelerator program for AI powered health tech startups. The 20 week immersive Mayo Clinic Platform Accelerate Program is designed to help innovative startups establish credibility and get market ready so that they can spark innovation in healthcare. Each company receives a $200,000 benefit package that includes access to Mayo Clinic's rich de-identified data sets, validation frameworks, clinical workflow planning, and mentorship. Startups in the accelerator receive guidance on clinical, regulatory, technology, and business decisions. There are also opportunities for workflow integration and clinical collaboration for research trials, access thought leadership, and peer-reviewed publications.


FDA Publishes Updated List With 521 Authorized AI/ML Enabled Devices

#artificialintelligence

Since 1995, the FDA has authorized more than 500 AI/ML-enabled medical devices via 510(k) clearance, granted De Novo request, or approved PMA. This week the FDA published an updated list with 178 new devices that were authorized through July 2022. According to the FDA, their list is based on publicly available information and is not a comprehensive resource of FDA approved AI/ML-enabled medical devices. In today's DeepTech newsletter I'm sharing a high level analysis of the 521 devices on the list, charts to visualize the data, and a summary of milestones. Note: According to the FDA their list is based on publicly available information and is not a comprehensive resource of approved AI/ML-enabled medical devices.


Highlights From COVID-19 Research Papers Published in September 2020

#artificialintelligence

This is an article by Gabriel Leung, Dean of Medicine at Hong Kong University Medical Center and Malik Peiris Professor at the University Hong Kong 1) COVID vaccines are needed, even if they have minimal impact on transmission 2) COVID vaccines may not help us achieve herd immunity 3) COVID vaccine trials primarily assess prevention of virologically confirmed disease - not infection or transmission 4) an "effective" vaccine confers protection from disease but might not reduce spread 5) if COVID vaccines are effective in reducing morbidity & mortality in high-risk groups, they would have an important role, irrespective of impact on transmission and population immunity 6) if high-risk populations can be shielded by vaccination, COVID control measures could be recalibrated 7) the idea that COVID vaccine-induced population immunity will allow a return to normalcy may be based on false assumptions 8) no country will be truly safe until the entire world is vaccinated. This new study from Akiko Iwasaki, PhD and colleagues at Yale University offers the first clear evidence that COVID can invade brain cells 1) 40-60% of hospitalized COVID patients experience neurological complications including nerve damage and stroke 2) this study suggests that COVID in the brain may be more lethal than the respiratory infection caused by COVID 3) COVID hijacks brain cells to make copies of itself then exploits the brain cells' machinery to multiply 4) then COVID chokes off oxygen to adjacent brain cells causing them to die 5) a few days into the infection there is a dramatic decrease the number of synapses (the connections between neurons in the brain) 6) the researchers didn't find any evidence of an immune response to remedy this problem. It's a silent infection with evasion mechanisms 7) some people may be susceptible because of their genetic background or high viral load. Researchers used Summit Supercomputer to analyze 2.5 billion genetic combinations from COVID; then they made the Bradykinin Hypothesis 1) it took Summit 1 week to run the numbers. These high-powered microscopic images show very high viral loads of SARS-CoV-2 on human respiratory surfaces ready to spread the virus 1) Camille Ehre PhD and colleagues at UNC Chapel Hill School of Medicine generated these microscopic images showing very high viral loads of SARS-CoV-2.


Margaretta Colangelo posted on LinkedIn

#artificialintelligence

Scientists Used AI to Crack COVID19's Genetic Signature and Identify Its Origin. Their machine-learning method achieved 100% accurate classification of the COVID19 sequences and discovered the most relevant relationships among more than 5,000 viral genomes within minutes. Gurjit Randhawa and his colleagues identified the underlying genomic signature for 29 different #COVID19 DNA sequences. Their paper demonstrates how machine learning can use genomic signatures to provide very rapid classification of novel pathogens and supports the scientific hypothesis that COVID19 has its origin in bats. They used an ultra-fast graphics based classification system that delivered accurate classifications of the virus without a priori biological knowledge.


AI Is Central To The Longevity Financial Industry

#artificialintelligence

There are over 1 billion people currently in retirement. New types of financial institutions are evolving to satisfy the needs of the aging population. Investment banks, pension funds, and insurance companies are developing new business models, and are using AI to improve the quality of the analytics used to formulate them. In the near future, the synergy between innovative AI and wealth management will lead to the creation of a new financial institutions optimized for the aging population and age-friendly Longevity banks will make banking easier and safer for seniors. Over 150 financial companies are already developing innovative WealthTech and AgeTech products and services and AI is central to the process.