Comment: Artificial intelligence is already improving biomedical research, health care
Of every 10,000 to 15,000 new chemicals identified during drug discovery, only five will make it to human trials. More than 92 percent of these drugs will fail in trials, often because they were not sufficiently safe or effective.
On average, 50 new drugs make it onto the market each year, each taking a decade or more. The development of a single drug that is given to patients can account for a third of a scientist’s career, if they are lucky enough to find such a breakthrough.
Artificial Intelligence promises to make these numbers less daunting by generating hypotheses, analyzing large sets of data and interpreting results faster, more broadly and more deeply than the human brain can. .
AI accelerates everything. In fact, it can identify patterns and relationships that may not be there to the human eye. It integrates data from different sources quickly and efficiently. Case in point: Sanju Sinha, a computational biologist at Sanford Burnham Prebys, developed with colleagues at the National Cancer Institute an AI tool that analyzed data from thousands of cancer samples from people around the world , looking for differences between healthy and cancerous cells, then predicting response and resistance to certain treatments. In early trials of three different cancers, the AI tool, called PERCEPTION, proved remarkably predictive.
It took Sinha and his colleagues two and a half years to develop PERCEPTION and publish their findings. Now they want to expand the work with more courses. At 30, Sinha may not have completed a third of his career yet. He has the resources and the time for great success.
Sinha illustrates another important point: the need for diverse talents. Sinha was trained as a mathematician, not a biologist. His expertise is helping to make it possible to incorporate AI into biomedical research.
It is a paradigm shift. Traditionally, medical schools are organized into traditional medical specialty departments. They have to evolve to accommodate the new skill set that is death-agnostic.
Many of the topics surrounding AI and human health, of course, concern its use by doctors and in the actual treatment of patients.
ChatGPT, an AI chatbot that uses machine learning to understand and produce human-like conversations, has successfully passed the United States Medical Licensing Exam, which doctors must take before being licensed to practice. . Google DeepMind has developed an AI language model trained on medical Q&A datasets that can provide “safe and helpful answers” to questions asked by healthcare professionals and patients.
Some doctors are now using AI to find the most effective treatment protocols, medical devices and drugs. AI can record patient encounters in real-time, improving documentation. Chatbots help patients find available doctors, schedule appointments and answer basic questions.
AI is also used to diagnose other conditions that require matching vision, such as diabetic retinopathy, another form of vision loss, and to scan the brain to detect subtle signs of disease and dementia. These algorithms are able to detect and diagnose diseases in seconds, faster than even experienced doctors.
To be honest, a technological revolution as profound as AI is never simple or easy. Nearly 60 percent of Americans in a 2022 Pew Research Center survey said they would be uncomfortable with the idea of AI being used in their health care; 38 percent believed that using AI to diagnose diseases and recommend treatment will lead to better health outcomes but 33 percent believe it will lead to worse outcomes.
They were very optimistic about AI’s ability to reduce medical errors and reduce racial/ethnic bias that negatively affects access to health care and treatment.
Such skepticism about AI is good. The need to empirically and persuasively prove the therapeutic value of AI is justified. The National Institutes of Health recognize that the safe and responsible use of AI is a work in progress.
AI will not replace the need and value of human doctors who bring, well, humanity that is not put into any database. But AI represents the biggest and boldest advances in biomedical research and medicine, along with CRISPR gene editing, nanomedicine, robotics, cognitive science, precision medicine and mRNA injections.
Indeed, AI makes it possible to accelerate those achievements to greater effect.
Note: This thread was written by a human, not ChatGPT or any similar computer program. I’m happy to report that when ChatGPT was later asked for their thoughts on this topic, our views were in perfect agreement.
Brenner is a physician-scientist and president and chief executive officer of Sanford Burnham Prebys and lives in La Jolla.
Originally published:
#Comment #Artificial #intelligence #improving #biomedical #research #health #care