AI can't replace doctor's gut instincts, MIT study says

Many technology companies are developing artificial intelligence systems that can analyze medical data to help diagnose or treat health problems. Such systems raise the question of whether cutting-edge tools can perform or as well as or in certain cases much better than a human doctor -- though researchers say AI probably won't be replacing physicians anytime soon.

A new study from MIT computer scientists suggests that human doctors provide a dimension that, as yet, artificial intelligence does not. By analyzing doctors' written notes on intensive care unit patients, the researchers found that the doctors' "gut feelings" about a particular patient's condition played a significant role in determining how many tests they ordered for the patient.

This intuition plays an even stronger role during the first day or two of a patient's hospital stay, when the amount of data doctors have on patients is less than on subsequent days.

Researchers used sentiment analysis to determine what role this gut feeling plays. Sentiment analysis, which is often used for gauging consumer attitudes, is based on computer algorithms that examine written language and tally positive or negative sentiments associated with words used in the text. The researchers performed their analysis on the MIMIC database, a collection of medical records from 60,000 ICU patients admitted to Beth Israel Deaconess Medical Center in Boston over a 10-year period.

They wanted to determine what, if anything, the doctors' notes added on top of the information available in the medical records. They computed sentiment scores from the notes to see if there was any correlation with how many diagnostic imaging tests the doctors ordered for patients.

If medical data alone was driving doctors' decisions, then sentiment would not have any correlation with the number of tests ordered. However, the researchers found that when they accounted for all other factors, the doctors' sentiments did indeed help predict how many tests they would order. This effect was strongest at the beginning of a patient's hospital stay, when doctors had less medical information to go on, and then declined as time went by.

They also found that when doctors felt more pessimistic about a patient's condition, they ordered more testing, but only up to a certain point. If they felt very positively about the patient's condition, they ordered fewer tests.

Next, the researchers hope to learn more about just what factors contribute to doctors' gut feelings. That could potentially lead to the development of artificial intelligence systems that could learn to incorporate the same information that doctors are using to evaluate patients.

Lisa Hedges, a consult analyst at Software Advice, told Healthcare Finance News last week that utilizing aspects of artificial intelligence can be beneficial in addressing the physician shortage, and can be especially useful for small hospitals struggling to stay afloat in rural markets. Smaller practices may not be able to fully utilize some of the bigger technological innovations that are on the horizon, but due to the practice size, they don't require as much from technology, either. They can still benefit from innovations like AI-assisted decision support, or chatbots, which are evolving into the Amazon Echos of healthcare.

Twitter: @JELagasse
Email the writer: jeff.lagasse@himssmedia.com