In the community of Life Sciences, there is a lot of discussion about how artificial intelligence, the acceleration of drug research, which allows large pharmaceutical companies and biotechnics inside to discover more new molecules to advance clinical tests. But drug discovery faster by itself will not result in more drugs or even a faster medication development, said Liz Beatty, director of Startup Startup of Inate Clinical Test Technology.
No matter how fast a drug is discovered, ultimately, it must be tested in humans. Beatty, whose experience includes the execution of clinical trials in Bristol Myers Squibb for 16 years, said that more than 80% of clinical trials lose their deadlines due to registration problems. The clinical trial portion of drug development remains very dependent on humans. Pictures and laboratory reports, often hundreds of pages, has been a historical manual work, said Beatty. Inate’s technology platform uses AI to authorize the process. A human still makes the final decision on whether a patient meets the criteria for a clinical trial, but the reductions of technology to the mines which used to take hours.
“We are real, we can accelerate the rhythm of the investigation by allowing the use of AI in this part of the ecosystem, where historical is a point of pain, it cannot be addressed before the new advances in AI,” said Beatty.
Beatty’s comments reached this week’s panel discussion, the Medcity News investment conference in Chicago. He joined Chelsea Vane, Vice President of Product Management, Digital Products of Ge Healthcare, and Bobby Reddy, co -founder and CEO of Pretty. The panel, “how is the AI of the health industry reforming,” was moderated by Michelle Hoffmann, executive director of the Chicago Biomedical Consortium?
AI is not just a tool for the discovery of drugs and clinical trials. Technologies that incorporate AI are already touching patients. Pretty has commercialized technology that guides doctors in the diagnosis of sepsis, a reaction of the dangerous immune system to an infection. Sepsis causes inflammatory damage and organs that can be threatening in life. The diagnosis has a historical leg a human effort, made through the review of a doctor of clinical findings and laboratory tests.
Pretty technology, sepsis immunoscore, incorporates different types of data, such as vital signs, standard laboratory tests, demographic information and biomarkers. The AI analyzes the thesis data to provide the deepest doctors of patient biology. This approach is necessary due to the nature of sepsis. Instead of being a single disease, it is a syndrome, a collection of different diseases, said Reddy.
The FDA granted the authorization of Immunoscore the authorization of Novo last year as the first diagnostic tool for sepsis. While the traditional way of diagnosing sepsis relaxis in human trial and experience, which varies from one doctor to another, pre -pool technology makes sepsis diagnosis more consistent.
“It is more standardized, it is based on thousands or adapts to patients,” said Reddy. “So it is more precise, it is more unified, it is more realistic.”
For Ge Healthcare, AI has the effect of increasing patient access to care. Vane pointed out Air Recon DL, a deep learning image reconstruction technology for magnetic resonance. This technology eliminates the noise and distortion of the images, producing more clear images. Vane said Air Recon DL accelerates scan times of up to 50%. Consistently, more scanning can be made and doctors can support more patients. While Air Recon DL is specifically for MRI, Ge Healthcare also has AI applications for computerized tomographs.
Ge Healthcare is also using AI to improve cancer attention. The company’s face of the company’s oncology is an application that brings together different types of data from a patient from different sources (such as medical images and electronic medical records), and provides doctors with a unique vision. With this technology, doctors no longer need to jump between multiple systems to obtain the complete image of a patient’s history, reducing to minutes what used to take a clinician hours, Vane said. Beyond the complex medical history to summarize, the application can also help evaluate a patient’s choice for a clinical trial.
“By adding all these multimodal data in a single unified view and then summarizing that using the
Photo: Nick Fanion, Breaking Media