MIT experts develop AI models that can detect pancreatic cancer early

Researchers at MIT’s CSAIL division, which focuses on computer engineering and AI development, built two machine learning algorithms that can detect pancreatic cancer at a higher threshold than current diagnostic standards. The two models together formed to create the “PRISM” neural network. It is designed to specifically detect pancreatic ductal adenocarcinoma (PDAC), the most prevalent form of pancreatic cancer.

The current standard PDAC screening criteria catches about 10 percent of cases in patients examined by professionals. In comparison, MIT’s PRISM was able to identify PDAC cases 35 percent of the time.

While using AI in the field of diagnostics is not an entirely new feat, MIT’s PRISM stands out because of how it was developed. The neural network was programmed based on access to diverse sets of real electronic health records from health institutions across the US. It was fed the data of over 5 million patient’s electronic health records, which researchers from the team said “surpassed the scale” of information fed to an AI model in this particular area of research. “The model uses routine clinical and lab data to make its predictions, and the diversity of the US population is a significant advancement over other PDAC models, which are usually confined to specific geographic regions like a few healthcare centers in the US,” Kai Jia, MIT CSAIL PhD senior author of the paper said.

MIT’s PRISM project started over six years ago. The motivation behind developing an algorithm that can detect PDAC early has a lot to do with the fact that most patients get diagnosed in the later stages of the cancer’s development — specifically about eighty percent are diagnosed far too late.

The AI works by analyzing patient demographics, previous diagnoses, current and previous medications in care plans and lab results. Collectively, the model works to predict the probability of cancer by analyzing electronic health record data in tandem with things like a patient’s age and certain risk factors evident in their lifestyle. Still, PRISM is still only able to help diagnose as many patients at the rate the AI can reach the masses. At the moment, the technology is bound to MIT labs and select patients in the US. The logistical challenge of scaling the AI will involve feeding the algorithm more diverse data sets and perhaps even global health profiles to increase accessibility.

Nonetheless, this isn't MIT’s first stab at developing an AI model that can predict cancer risk. It notably developed a way to train models how to predict the risk of breast cancer among women using mammogram records. In that line of research, MIT experts confirmed, the more diverse the data sets, the better the AI gets at diagnosing cancers across diverse races and populations. The continued development of AI models that can predict cancer probability will not only improve outcomes for patients if malignancy is identified earlier, it will also lessen the workload of overworked medical professionals. The market for AI in diagnostics is so ripe for change that it is piquing the interest of big tech commercial companies like IBM, which attempted to create an AI program that can detect breast cancer a year in advance.

This article originally appeared on Engadget at https://www.engadget.com/mit-experts-develop-ai-models-that-can-detect-pancreatic-cancer-early-222505781.html?src=rss

An experimental rice-sized implant monitors how drugs affect tumors

Researchers at Brigham and Women’s Hospital in Boston have developed an implant, notably as small as a grain of rice, that can test the effects of drugs on a patient’s brain tumor in real-time during surgery. Currently, monitoring the effects of drugs on a brain cancer patient during surgery is limited to intraoperative brain imaging and tissue sampling after a drug has been administered. The technique known as microdialysis currently stands as one of the more minimally invasive sampling options for testing the impact of drugs on brain tumors, but even that requires an entire catheter to be inserted into the patient’s skull cavity.

During development, researchers from Brigham and Women’s Hospital designed the device specifically to help test treatments in patients with brain cancers or gliomas, a type of tumor that originates in the brain or spinal cord. The device is designed to only remain implanted in a patient for about two to three hours while it delivers microdoses of the respective drug that is under observation. It can observe the impact of up to 20 drugs on the market for cancerous tumors, according to the researchers. Once the device is removed (sometime before the surgery ends), the surrounding tissue is returned to the lab for analysis.

In a statement published Wednesday, Pierpaolo Peruzzi, co-principal investigator and assistant professor in the Department of Neurosurgery at Brigham and Women’s Hospital said that knowing the impact of cancer drugs on these tumors is critical. “We need to be able to understand, early on, which drug works best for any given patient,” he said.

 Brigham and Women’s Hospital building pictured
Brigham and Women’s Hospital

During the development process, researchers at the Brigham and Women’s Hospital ran a clinical trial to observe the actual impact of the implant on real patients. The study found that none of the patients in the trial experienced any adverse effects. The researchers were able to collect biological data from the devices, such as what molecular changes happened when each drug was administered. While the study demonstrated that the implant could be easily incorporated into surgical practice, the researchers are still determining how the data it can gather should be used to optimize tumor therapy.

The researchers are now conducting another study that focuses on implanting the device through a minimally invasive procedure 72 hours before their main surgery. Advancements in the cancer treatment space continue to expand, with new iterations of drug cocktails and viruses that can fight cancer cells emerging in the biotech space. Implants like the one developed by the Brigham and Women’s Hospital bring scientists one step closer to better being able to use tools and data to provide more personalized care treatment plans for cancer patients.

This article originally appeared on Engadget at https://www.engadget.com/an-experimental-rice-sized-implant-monitors-how-drugs-affect-tumors-210038580.html?src=rss

An experimental rice-sized implant monitors how drugs affect tumors

Researchers at Brigham and Women’s Hospital in Boston have developed an implant, notably as small as a grain of rice, that can test the effects of drugs on a patient’s brain tumor in real-time during surgery. Currently, monitoring the effects of drugs on a brain cancer patient during surgery is limited to intraoperative brain imaging and tissue sampling after a drug has been administered. The technique known as microdialysis currently stands as one of the more minimally invasive sampling options for testing the impact of drugs on brain tumors, but even that requires an entire catheter to be inserted into the patient’s skull cavity.

During development, researchers from Brigham and Women’s Hospital designed the device specifically to help test treatments in patients with brain cancers or gliomas, a type of tumor that originates in the brain or spinal cord. The device is designed to only remain implanted in a patient for about two to three hours while it delivers microdoses of the respective drug that is under observation. It can observe the impact of up to 20 drugs on the market for cancerous tumors, according to the researchers. Once the device is removed (sometime before the surgery ends), the surrounding tissue is returned to the lab for analysis.

In a statement published Wednesday, Pierpaolo Peruzzi, co-principal investigator and assistant professor in the Department of Neurosurgery at Brigham and Women’s Hospital said that knowing the impact of cancer drugs on these tumors is critical. “We need to be able to understand, early on, which drug works best for any given patient,” he said.

 Brigham and Women’s Hospital building pictured
Brigham and Women’s Hospital

During the development process, researchers at the Brigham and Women’s Hospital ran a clinical trial to observe the actual impact of the implant on real patients. The study found that none of the patients in the trial experienced any adverse effects. The researchers were able to collect biological data from the devices, such as what molecular changes happened when each drug was administered. While the study demonstrated that the implant could be easily incorporated into surgical practice, the researchers are still determining how the data it can gather should be used to optimize tumor therapy.

The researchers are now conducting another study that focuses on implanting the device through a minimally invasive procedure 72 hours before their main surgery. Advancements in the cancer treatment space continue to expand, with new iterations of drug cocktails and viruses that can fight cancer cells emerging in the biotech space. Implants like the one developed by the Brigham and Women’s Hospital bring scientists one step closer to better being able to use tools and data to provide more personalized care treatment plans for cancer patients.

This article originally appeared on Engadget at https://www.engadget.com/an-experimental-rice-sized-implant-monitors-how-drugs-affect-tumors-210038580.html?src=rss

YouTube will tackle cancer misinformation as part of its updated health policy

The internet is a source of many things, such as yummy recipes, tech deals and horrible misinformation. The latter often spreads through social media sites, something they have to combat (or usually choose to ignore). Right now, YouTube is choosing to fight, announcing a new long-term policy plan to grapple with medical misinformation, especially about cancer.

YouTube's new guidelines for health content will fall under three categories: prevent, treatment and denial misinformation. Prevent will allegedly review and remove videos that oppose guidelines set out by trusted authorities or contradict vaccine safety and efficacy (the platform banned content with vaccine misinformation in 2021). Treatment should center on taking down any misinformation about — unsurprisingly — treating medical conditions, including unproven remedies. The platform claims that denial will focus on removing any content that makes a false claim, such as that people didn't die due to COVID-19.

"To determine if a condition, treatment or substance is in scope of our medical misinformation policies, we'll evaluate whether it's associated with a high public health risk, publicly available guidance from health authorities around the world, and whether it's generally prone to misinformation," YouTube's Director and Global Head of Healthcare and Public Health Partnerships Dr. Garth Graham and its VP and Global Head of Trust and Safety Matt Halprin said in the joint release outlining the new policies.

Starting now, YouTube says it will be removing videos specifically about cancer which violate any of these policies — an effort it claims will ramp up more in the coming weeks. For example, if a video states that garlic cures cancer, it's coming down. YouTube is also sharing a playlist of science-backed cancer-related videos and teaming up with Mayo Clinic to create even more informational videos about cancer.

These policies come less than two months after YouTube announced it would "stop removing content that advances false claims that widespread fraud, errors, or glitches occurred in the 2020 and other past US Presidential elections" because it curtailed political speech. So misinformation is allowed when it threatens democracy, just not across every category on the site — cool. Though, YouTube does say that it will allow some health videos with falsehoods to remain if the context is right, such as public interest. The platform says in some cases, content will be allowed to stay up but will be given an age restriction.

This article originally appeared on Engadget at https://www.engadget.com/youtube-will-tackle-cancer-misinformation-as-part-of-its-updated-health-policy-120516307.html?src=rss

Scientists genetically engineer bacteria to detect cancer cells

An international team of scientists has developed a new technology that can help detect (or even treat) cancer in hard-to-reach places, such as the colon. The team has published a paper in Science for the technique dubbed CATCH, or cellular assay for targeted, CRISPR-discriminated horizontal gene transfer. For their lab experiments, the scientists used a species of bacterium called Acinetobacter baylyi. This bacterium has the ability to naturally take up free-floating DNA from its surroundings and then integrate it into its own genome, allowing it to produce new protein for growth.  

What the scientists did was engineer A. baylyi bacteria so that they'd contain long sequences of DNA mirroring the DNA found in human cancer cells. These sequences serve as some sort of one-half of a zipper that locks on to captured cancer DNA. For their tests, the scientists focus on the mutated KRAS gene that's commonly found in colorectal tumors. If an A. baylyi bacterium finds a mutated DNA and integrates it into its genome, a linked antibiotic resistance gene also gets activated. That's what the team used to confirm the presence of cancer cells: After all, only bacteria with active antibiotic resistance could grow on culture plates filled with antibiotics. 

While the scientists were successfully able to detect tumor DNA in mice injected with colorectal cancer cells in the lab, the technology is still not ready to be used for actual diagnosis. The team said it's still working on the next steps, including improving the technique's efficiency and evaluating how it performs compared to other diagnostic tests. "The most exciting aspect of cellular healthcare, however, is not in the mere detection of disease. A laboratory can do that," Dan Worthley, one of the study's authors, wrote in The Conversation. In the future, the technology could also be used for targeted biological therapy that can deploy treatment to specific parts of the body based on the presence of certain DNA sequences. 

This article originally appeared on Engadget at https://www.engadget.com/scientists-genetically-engineer-bacteria-to-detect-cancer-cells-114511365.html?src=rss

AI-assisted cancer screening could cut radiologist workloads in half

A newly published study in the the Lancet Oncology journal has found that the use of AI in mammogram cancer screening can safely cut radiologist workloads nearly in half without risk of increasing false-positive results. In effect, the study found that the AI’s recommendations were on par with those of two radiologists working together.

“AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe,” the study found.

The study was performed by a research team out of Lund University in Sweden and, accordingly, followed 80,033 Swedish women (average age of 54) for just over a year in 2021-2022 . Of the 39,996 patients that were randomly assigned AI-empowered breast cancer screenings, 28 percent or 244 tests returned screen-detected cancers. Of the other 40,024 patients that received conventional cancer screenings, just 25 percent, or 203 tests, returned screen-detected cancers.

Of those extra 41 cancers detected by the AI side, 19 turned out to be invasive. Both the AI-empowered and conventional screenings ran a 1.5 percent false positive rate. Most impressively, radiologists on the the AI side had to look at 36,886 fewer screen readings than their counterparts, a 44 percent reduction in their workload.

“These promising interim safety results should be used to inform new trials and program-based evaluations to address the pronounced radiologist shortage in many countries, but they are not enough on their own to confirm that AI is ready to be implemented in mammography screening," lead author, Dr Kristina Lång, warned in a release. “We still need to understand the implications on patients’ outcomes, especially whether combining radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology.”

Cancer detection has been an aspirational goal for computer vision researchers and AI companies for years now. I mean, who doesn’t want to be the company to build the tricorder that infallibly spots cancerous growths in their earliest stages? Machine vision systems designed for these screenings have improved steadily in recent years and in specific cases have shown to be as reliable as human clinicians, with the likes of IBM, Google, MIT and NVIDIA investing in similar cancer screening research in recent years.

This article originally appeared on Engadget at https://www.engadget.com/ai-assisted-cancer-screening-could-cut-radiologist-workloads-in-half-193427969.html?src=rss

Scientists have successfully engineered bacteria to fight cancer in mice

Researchers at Stanford Medicine have made a promising discovery that could lead to new cancer treatments in the future. Scientists conducted tests in which they altered the genomes of skin-based microbes and bacteria to fight cancer. These altered microbes were swabbed onto cancer-stricken mice and, lo and behold, tumors began to dissipate.

The bacteria in question, Staphylococcus epidermidis, was grabbed from the fur of mice and altered to produce a protein that stimulates the immune system with regard to specific tumors. The experiment seemed to be a resounding success, with the modified bacteria killing aggressive types of metastatic skin cancer after being gently applied to the fur. The results were also achieved without any noticeable inflammation.

“It seemed almost like magic,” said Michael Fischbach, PhD, an associate professor of bioengineering at Stanford. “These mice had very aggressive tumors growing on their flank, and we gave them a gentle treatment where we simply took a swab of bacteria and rubbed it on the fur of their heads.”

This is yet another foray into the misunderstood world of microbiomes and all of the bacteria that reside there. Gut biomes get all of the press these days, but the skin also plays host to millions upon millions of bacteria, fungi and viruses, and the purpose of these entities is often unknown.

In this instance, scientists found that staph epidermidis cells trigger the production of immune cells called CD8 T cells. The researchers basically hijacked the S. epidermidis into producing CD8 T cells that target specific antigens. In this case, the antigens were related to skin cancer tumors. When the cells encountered a matching tumor, they began to rapidly reproduce and shrink the mass, or extinguish it entirely.

“Watching those tumors disappear — especially at a site distant from where we applied the bacteria — was shocking,” Fischbach said. “It took us a while to believe it was happening.”

As with all burgeoning cancer treatments, there are some heavy caveats. First of all, these experiments are being conducted on mice. Humans and mice are biologically similar in many respects, but a great many treatments that work on mice are a dud with people. Stanford researchers have no idea if S. epidermidis triggers an immune response in humans, though our skin is littered with the stuff, so they may need to find a different microbe to alter. Also, this treatment is designed to treat skin cancer tumors and is applied topically. It remains to be seen if the benefits carry over to internal cancers.

With that said, the Stanford team says they expect human trials to start within the next few years, though more testing is needed on both mice and other animals before going ahead with people. Scientists hope that this treatment could eventually be pointed at all kinds of infectious diseases, in addition to cancer cells.

This article originally appeared on Engadget at https://www.engadget.com/scientists-have-successfully-engineered-bacteria-to-fight-cancer-in-mice-165141857.html?src=rss

Scientists have successfully engineered bacteria to fight cancer in mice

Researchers at Stanford Medicine have made a promising discovery that could lead to new cancer treatments in the future. Scientists conducted tests in which they altered the genomes of skin-based microbes and bacteria to fight cancer. These altered microbes were swabbed onto cancer-stricken mice and, lo and behold, tumors began to dissipate.

The bacteria in question, Staphylococcus epidermidis, was grabbed from the fur of mice and altered to produce a protein that stimulates the immune system with regard to specific tumors. The experiment seemed to be a resounding success, with the modified bacteria killing aggressive types of metastatic skin cancer after being gently applied to the fur. The results were also achieved without any noticeable inflammation.

“It seemed almost like magic,” said Michael Fischbach, PhD, an associate professor of bioengineering at Stanford. “These mice had very aggressive tumors growing on their flank, and we gave them a gentle treatment where we simply took a swab of bacteria and rubbed it on the fur of their heads.”

This is yet another foray into the misunderstood world of microbiomes and all of the bacteria that reside there. Gut biomes get all of the press these days, but the skin also plays host to millions upon millions of bacteria, fungi and viruses, and the purpose of these entities is often unknown.

In this instance, scientists found that staph epidermidis cells trigger the production of immune cells called CD8 T cells. The researchers basically hijacked the S. epidermidis into producing CD8 T cells that target specific antigens. In this case, the antigens were related to skin cancer tumors. When the cells encountered a matching tumor, they began to rapidly reproduce and shrink the mass, or extinguish it entirely.

“Watching those tumors disappear — especially at a site distant from where we applied the bacteria — was shocking,” Fischbach said. “It took us a while to believe it was happening.”

As with all burgeoning cancer treatments, there are some heavy caveats. First of all, these experiments are being conducted on mice. Humans and mice are biologically similar in many respects, but a great many treatments that work on mice are a dud with people. Stanford researchers have no idea if S. epidermidis triggers an immune response in humans, though our skin is littered with the stuff, so they may need to find a different microbe to alter. Also, this treatment is designed to treat skin cancer tumors and is applied topically. It remains to be seen if the benefits carry over to internal cancers.

With that said, the Stanford team says they expect human trials to start within the next few years, though more testing is needed on both mice and other animals before going ahead with people. Scientists hope that this treatment could eventually be pointed at all kinds of infectious diseases, in addition to cancer cells.

This article originally appeared on Engadget at https://www.engadget.com/scientists-have-successfully-engineered-bacteria-to-fight-cancer-in-mice-165141857.html?src=rss

NVIDIA and Medtronic are building an AI-enhanced endoscopy tool

NVIDIA is deepening its efforts to fight cancer using AI. The GPU maker is teaming with Medtronic to build AI into the GI Genius endoscopy tool (shown below). The two will use NVIDIA's IGX hardware and Holoscan medical platform to help detect the polyps that can lead to colorectal cancer. Doctors will get "AI-enhanced" diagnostic images, the companies say.

The first GI Genius systems built with NVIDIA tech are expected to arrive later this year. The device can use a range of AI tools, and Medtronic is betting that using NVIDIA's Clara platform could help develop algorithms for real-time medical procedures.

Medtronic GI Genius endoscopy tool
Medtronic

The news comes the same time as NVIDIA is expanding its BioNeMo Cloud service that helps bring generative AI to drug discovery. The new offering helps train AI models (and handle inference) used to develop new therapeutic proteins and otherwise advance fields like biology and chemistry. Researchers can speed up one of the most time-consuming processes in their pipeline, NVIDIA claims.

The news comes soon after Google unveiled AI technology for cancer therapy and ultrasound diagnosis. Other tech giants have devoted more of their AI work to healthcare in recent years. Intel partnered with Penn Medicine on AI to detect brain tumors, while Microsoft aimed to speed up cervical cancer detection and take some of the load from overworked doctors.

For NVIDIA, this is as much about translating its AI expertise to health tech as it is winning another customer. Still, the alliance could lead to some very practical benefits. As with some other AI-based cancer detection systems, this could help physicians begin treatment early and increase the chances of recovery.

This article originally appeared on Engadget at https://www.engadget.com/nvidia-and-medtronic-are-building-an-ai-enhanced-endoscopy-tool-161532723.html?src=rss

NVIDIA and Medtronic are building an AI-enhanced endoscopy tool

NVIDIA is deepening its efforts to fight cancer using AI. The GPU maker is teaming with Medtronic to build AI into the GI Genius endoscopy tool (shown below). The two will use NVIDIA's IGX hardware and Holoscan medical platform to help detect the polyps that can lead to colorectal cancer. Doctors will get "AI-enhanced" diagnostic images, the companies say.

The first GI Genius systems built with NVIDIA tech are expected to arrive later this year. The device can use a range of AI tools, and Medtronic is betting that using NVIDIA's Clara platform could help develop algorithms for real-time medical procedures.

Medtronic GI Genius endoscopy tool
Medtronic

The news comes the same time as NVIDIA is expanding its BioNeMo Cloud service that helps bring generative AI to drug discovery. The new offering helps train AI models (and handle inference) used to develop new therapeutic proteins and otherwise advance fields like biology and chemistry. Researchers can speed up one of the most time-consuming processes in their pipeline, NVIDIA claims.

The news comes soon after Google unveiled AI technology for cancer therapy and ultrasound diagnosis. Other tech giants have devoted more of their AI work to healthcare in recent years. Intel partnered with Penn Medicine on AI to detect brain tumors, while Microsoft aimed to speed up cervical cancer detection and take some of the load from overworked doctors.

For NVIDIA, this is as much about translating its AI expertise to health tech as it is winning another customer. Still, the alliance could lead to some very practical benefits. As with some other AI-based cancer detection systems, this could help physicians begin treatment early and increase the chances of recovery.

This article originally appeared on Engadget at https://www.engadget.com/nvidia-and-medtronic-are-building-an-ai-enhanced-endoscopy-tool-161532723.html?src=rss