AI Will Change the Way We Diagnose and Treat Cancer

How will AI change healthcare? originally appeared on Quora: the place to gain and share knowledge, empowering people to learn from others and better understand the world.

Answer by Abdul Hamid Halabi, Business Lead, Healthcare & Life Sciences at NVIDIA , on Quora:

“I’m sorry, you have cancer.” These are words NO one wants to hear.

When my father-in-law was diagnosed with cancer, I truly wish he’d had access to the amazing healthcare possibilities enabled by AI. Incredibly, a flawed second opinion probably saved his life—and nearly killed him.

Initially, he was told that he simply had stones in his bladder. On second diagnosis, these same results were interpreted to be stage 4 cancer. An aggressive chemotherapy plan almost killed him, but thankfully he’s still alive today. Then things took another turn: Toward the end of his treatment, the cancer was determined to actually be stage 1. This means he could have avoided months of intensive treatment and excruciating pain.

We cannot afford this level of error rate in healthcare. That’s where AI comes in. With a second opinion, AI can reduce misdiagnosis by up to 85%, as was shown by Andrew Beck at Harvard University. And it can give general physicians the level of accuracy of specialist dermatologists, as was shown by Stanford University.

So when you ask “how will AI change healthcare?,” the answer is utterly. Here are just a few examples.

Mayo Clinic researchers have used AI to identify the genomic information of brain tumors without a biopsy. Deep learning was able to discover features present in MRI scans that physicians weren’t even able to see.

At Stanford, researchers are training an artificial intelligence neural network to recognize skin cancer lesions at the accuracy level of an expert dermatologist. Having such technology in every primary care office could bring early skin cancer detection to the masses at a very low cost.

In the field of pathology, the same deep learning technology is being used to train an AI computer on liver lesion detection. This could greatly aid pathologists who work daily with patients. Even in genomics, the 3 billion-long genome sequence in every human is being decoded before our very eyes with this technology.

Everything from developing drugs to detecting health insurance fraud will be impacted by AI, allowing healthcare professionals to focus on what matters most: diagnosis and treatment.

Companies like the one I work at are focused on making AI-assisted healthcare a reality, even helping researchers as they strive towards a cure for cancer. CANDLE is one of our national efforts to bring deep learning to the fight against cancer. The work aims at developing deep learning algorithms and exascale supercomputing to to provide a common platform for all researchers. The U.S. national labs are using deep learning to understand our genomic pathways, to advance drug development, and to improve cancer population health.

The benefits of applying deep learning and AI in healthcare will be felt in many fields affecting patient lives, such as developing drugs, diagnosing medical images, targeting treatment plans, and many more. We will all benefit from early disease detection, from higher quality diagnosis, cheaper cost of care, and, most importantly, greater access to care.

This is just the tip of the iceberg, and personally I can’t wait to see what other challenges we solve with AI.

This question originally appeared on Quora. the place to gain and share knowledge, empowering people to learn from others and better understand the world. You can follow Quora on Twitter, Facebook, and Google+. More questions:

This post was published on the now-closed HuffPost Contributor platform. Contributors control their own work and posted freely to our site. If you need to flag this entry as abusive, send us an email.