When the hand of AI falls on medicine

Account subscription benefits alongside Premium Stories, Editorials, Opinions and more. Unlock these with Subscription

Did cataclysmic events happen over the week in healthcare - developments that made us sit up and take note, fume a little, wonder much and record everything? Bringing to you, five major themes that caught our attention this past week, and then, some more.

AI technology is forever invading our columns here, opening up the possibilities of what can happen in the future, and indeed, bringing the future to our door steps today. The last week, there was news about researchers using AI to design, hold your breath - viruses . A particular type of virus actually - a bacteriophage. Infectious Diseases specialist Dr. Abdul Ghafur explains what happens when AI begins to design pathogens. Referring to the Stanford experiment that produced the bacteriophages (bacteria- eating viruses), he explains: “It does not show that AI can casually manufacture dangerous human viruses; it shows that computers are beginning to move from analysing biological information towards proposing biological designs that scientists can physically build. This requires appropriate governance and safeguards.”

“The computer did not create a virus. It did not touch a test tube or handle a living cell. What it did may ultimately be more consequential: it helped decide what the virus’s genome should be,” he writes. Of the 285 AI-generated designs physically synthesised and tested in the laboratory, 16 produced functioning phages. Some were able to overcome bacterial resistance that defeated the original virus. What is new, is not the physical manufacture of a virus. AI has entered the design stage of biology. For medicine, that creates remarkable opportunities. For biosecurity, it raises equally important questions, he says.

Further, in the cardiac diseases sector, AI heart disease prediction tools show promise but are not ready for clinical use , Afshan Yasmeen writes, quoting a review. Published in BMC Medical Informatics and Decision Making , an open-access journal. The review assessed 30 studies published since 2017 on AI-based models developed to predict future cardiovascular disease among adults without established heart disease. Researchers say “Many models demonstrate good discrimination, but very few studies examine whether the predicted risks correspond to what actually happens in different populations.” For more on this, hit the link above.

From AI, to another cutting edge research segment - genetics . Dr. C. Aravinda and Dr. Veera Rajagopal step into that highly niche area and highly technical area: turning off genes. What we can learn from nature switching off human genes , they ask, based on a study from Pakistan.

Imagine the human genome as an enormous instruction book, they describe, containing the information needed to build, run and maintain the body. Its 23 pairs of chromosomes are like chapters, and the text is written in DNA, using an alphabet of just four chemical letters - A, T, G and C. Within this text, genes are individual instructions or recipes, each made from a particular sequence of these DNA letters.