Nov. 29, 2022 – AI could help improve clinical trials by overcoming some traditional human biases in these fields and diversity, equity and inclusion in drug development, but we’re not there yet, experts say. The technology can also help doctors conduct data insights to make diagnosis and treatment more precise.
Start with quality. Artificial intelligence (AI) relies on vast amounts of data to create algorithms, or computer instructions, to develop best practices and predictions. But those instructions are only as good as the data used to create them. And people are the ones who create the data.
“It is people who underpin the development of artificial intelligence technology, and those people have their own biases,” Medical said Naheed Kurji, chair of the board of directors of the Alliance for AI in Healthcare. “So the algorithm will have its own biases.”
Technological illnesses diagnosed using voice are an example .
“There are many cases, examples of companies failing to recognize language differences between cultures” Kurji said. When technology is based on the speech patterns of a limited population, “then when the model is applied in the real world to a different population with different accents, the model fails.”
“The results are not representative.”
Another example is genetic and genomic data.
“Give or take, over 90% of genetic and genomic data comes from European descent. It Not someone from the African continent, Southeast Asia, Asia or South America,” said Kurji, who is also president and CEO of Cyclica Inc., a Toronto-based data-driven drug discovery company.
Therefore, “a lot of research done on this level of data is inherently biased, “He said.
Create data with diversity , being fair, inclusive and inclusive of peoples and cultures around the world is not a hopeless challenge. But it will take time, experts say. Once realized, AI should come closer to being free from human and systemic bias.
Raising awareness is critical.
“The solution to the problem comes from people’s innate understanding that there are biases,” Kurji said, and then only Include fair and balanced data that passes the diversity test.
Another AI Promising avenues simplify the drug development process, narrow the pool of potential drug candidates, and make clinical trials more cost-effective.
“If source data has challenges and limitations, AI will continue to propagate those limitations,” Sastry Chilukuri, co-CEO of data-driven clinical trials company Medidata and founder and president of Acorn AI, agrees. “Source data must become more representative, and must become fairer, so that AI reflects what is happening.”
When it comes to human or systemic bias in drug development, “it’s an oversimplification to say that artificial intelligence or machine learning can fix it,” says Angeli Moeller, Ph.D., director of data and integration Head of Generated Insights at Roche in Berlin. “But responsible use of artificial intelligence and machine learning can help us identify bias and find ways to mitigate any negative effects it may have.”
Meanwhile, AI aims to simplify Drug development, the technology could also help all doctors do their jobs better, experts say. AI can, for example, help by disseminating knowledge and expertise widely, sharing best practices of doctors experienced in treating more complex patients. This will help guide those who treat only a small number of such patients each year.
Chilukuri said the volume of operations in New York City or Delhi could be as high as hundreds of patients a year. “But if you go to the interior of the US like Nebraska, surgeons don’t see as much volume.
AI can help doctors “by providing the same first-class care that enables them to deliver the same first-class care to all populations at a faster rate,” he said.
AI can help in targeted therapy by using data to identify patients at highest risk. Kurji The technology could also improve bottleneck areas in medicine, such as the time it takes to interpret radiology images, said the technology.
An AI company whose “whole business model is not to replace your radiologist, but to make radiologists better,” notes that one of the company’s goals is to “prevent Omission or accumulation without timely action fast enough for that patient resulted in death or serious illness. ”
Radiologists are so busy they may have 30 seconds or less to explain each scan, Chilukuri Said. AI can flag lesions of potential interest, but it can also compare images to past scans of the same patient. This view provided by AI is not only applicable to radiology, but also to the field of data-driven medicine.
Advancing Personalized Medicine
AI can also guide individual surgical approaches, “because it’s not Like humans come in small, medium and large,” Chilukuri said. The technology could help surgeons determine exactly where to operate on an individual patient.
Moeller agrees that AI has the potential to advance personalized medicine.
“AI can help with diagnosis and risk prediction, which could mean earlier intervention,” said Moeller, who is also on the AI in Healthcare Alliance committee. “For example, if you look at a diabetic patient, he or she suffers from How likely are you to have eye problems with macular edema? “
This technique also helps to see the big picture.
“Machine Learning Can Find Your Medical Textbook Among Crowds patterns that may not be there,” Moeller said.
Chilukuri predicts that, in addition to diagnosis and treatment, AI can Aid recovery by customizing recovery for each patient.
“Not everyone will experience the exact same way of recovery. So, you have highly personalized AI plans that really keep you on track and predict where you’re going. “