Artificial Intelligence in increasingly raising concerns worldwide that it will lead to massive unemployment. Tesla’s Elon Musk famously warned that AI could lead to robots replacing human workforce and Govts forced to pay citizens. For a long time though, healthcare sector was not seen to be a threat, given its specialized nature and often ambiguous symptoms leading to variation in judgments amongst doctors themselves. That is until now. Recent developments have shown that AI may be catching up.
Artificial Intelligence making waves in medical diagnosis
IBM’s supercomputer made waves when it was able to diagnose a rare form of leukemia in a patient and may have even saved her life. Initially, doctors had diagnosed her with acute myeloid leukemia. But her recovery from chemotherapy was poor which raised suspicions of misdiagnosis. This led the doctors to use IBM’s Watson to look for answers.
The cloud-based, artificial intelligence-powered supercomputer then cross-referenced and analyzed data from tens of millions of oncology papers from research institutes all over the world and detected over a thousand diagnostically important genetic mutations in her DNA and not just hereditary characteristics that were unrelated to her disease.
All this was accomplished in a mere 10 minutes.
This is not the only notable case though. Stanford researchers have developed an algorithm that analyses chest X-ray images and offers diagnoses. It can diagnose up to 14 types of medical conditions and is able to diagnose pneumonia better than expert radiologists. Named CheXNet it was developed by Stanford Machine Learning Group and it is based on the publically available ChestX-ray14dataset initially released by the National Institutes of Health Clinical Center on Sept. 26 containing 112,120 frontal-view chest X-ray images labeled with up to 14 possible pathologies.
How Artificial Intelligence can help healthcare
As these two examples show, Artifical Intelligence and machine learning can perform complex medical tasks faster and more accurately. It is being increasingly used to complement doctors to aid in diagnosis through smart devices and diagnostic tools. As more and more medical records are becoming online, a rich pool of data exists which can be used to ‘train’ algorithms to recognize patterns and flag potential threats.
Recently, Google launched the Google Deepmind Health project, which will mine the data of medical records in order to provide better and faster health services in collaboration with the Moorfields Eye Hospital NHS Foundation Trust to improve eye treatment.
It is entirely conceivable that in the future, machines will act as assistants in clinical decision making helping doctors to narrow down the search field and thus provide faster diagnosis and treatment options. It is very likely that this will lead to individually tailored treatment that will be precise and particular to the patient concerned.