Deep Medicine summary

Artificial intelligence in medicine may seem like part of some distant future. But in fact, it’s already being used to save lives.

In one case, a healthy baby boy went home three days after birth. Five days later, his mother rushed him to the emergency room of Rady Children’s Hospital in San Diego. The newborn was experiencing constant seizures that were only getting worse.

Many people think of doctors as infallible – almost superhuman. But just like everyone else, doctors can have implicit biases that cause errors in both diagnostics and treatment.

Take the representativeness heuristic, a bias that causes people to make decisions based on their past experiences. It might lead a doctor to misdiagnose one illness for another – especially if he isn’t carefully examining all of a patient’s symptoms. Perhaps even more insidious is the overconfidence bias, which causes physicians to believe their diagnoses are correct more often than they actually are.

Have you ever gone to a doctor who barely even looked at you during your visit? Who instead spent most of her time typing notes into a computer? If so, she was probably updating your electronic health record, or EHR. EHRs were developed to make clinicians’ lives easier. Instead, they’ve become a barrier to doctor-patient communication.

Fortunately, things like the EHR are ripe for automation. A type of machine learning called Natural Language Processing could potentially be used to tape and transcribe all the words exchanged during a doctor visit. Doing so would free up doctors’ time so they could focus instead on the person sitting in front of them. 

Algorithms thrive on data – the more and richer, the better. After all, it’s from this data that they identify patterns and determine answers.

Much of what goes on in the clinical environment, however, doesn’t involve patterns. Doctors are constantly making assessments, creating plans, and communicating with patients and their families. So where does AI fit in?

Will humans always require hospitals? The answer might seem obvious. But while it’s true that we’ll always need ICUs and emergency rooms, regular hospital rooms may soon become obsolete.

One “virtual hospital” already exists in the United States: the Virtual Care Center in St. Louis. Nurses and doctors work there and have individualized, extended interactions with patients – but there are no hospital beds to be found. All of the hospital’s patients are monitored remotely, staying either at home or in intensive care units. AI surveillance algorithms in their rooms can detect possible heart failure or sepsis and send warnings to clinicians.

Regardless of age, all humans must take one particular type of medicine in order to survive. That medicine is food.

Ever since the days of the ancient Greek doctor Hippocrates, people have believed that health and food go hand in hand. While government agencies and people in the food industry might argue they hold the key to a healthy diet, is a one-size-fits-all approach even possible? Given how biologically and physiologically different we all are, shouldn’t our diets reflect that?

When the author entered medical school in 1975, health-care facilities and medical practices looked very different than they do today. Clinic appointments were scheduled to last a minimum of one hour for new patients and 30 minutes for returning ones. Notes from a visit were often handwritten in a person’s chart. Monthly productivity reports for doctors didn’t even exist. 

At that time, there were fewer than four million health-care jobs in all of the United States, and annual health-care spending totaled less than $800 per patient per year. By contrast, today, there are over 16 million health-care jobs, and spending tops $11,000 per person, per year.