More on Operations

AI can help make physicians' lives easier

For AI to have impact, it must take a human-centered approach, easily integrate into physician workflows and be friendly to use.

Susan Morse, Managing Editor

Artificial intelligence has the ability to make physicians' lives easier, according to experts and former clinicians.

For example, AI has the ability to make medicine keyboard-free, a futuristic goal which would be welcomed by physicians who spend most of their time with a patient in front of a computer. The technology would require a visual interface or dictation. 

But AI is starting to move into a keyboard-free environment, said Dr. Ruben Amarasingham, a former practicing physician who is founder and CEO of Pieces Technologies, a healthcare artificial intelligence and technology company. 

"Physicians are crying out for help," Amarasingham said. "I think the industry is in the first inning of nine innings." 

A frequent complaint from physician colleagues is that they wish medicine would operate the way their other technologies, such as IPhones, GPS or online banking systems do, said Garrett Vyangtas, managing director OSF Ventures, a venture optimization company.

The bottom line is that for AI to become a part of standard practice it must take a human-centered approach, be easily integrated into physician workflows and be friendly to use.

"If we see too steep of a learning curve, we get concerned that the full potential of the technology won't be realized," Vyangtas said.

Working against this need for ease are entrenched workflows of information and proprietary EHR systems.


Burnout and stress in healthcare cause an ongoing issue that's been exacerbated this past year by the COVID-10 pandemic.

AI systems such as a keyboard-free work environment would bring the joy of practice back into medicine, Amarasingham said.

AI and machine learning are improving clinical processes now, through technology such as natural language processing that aids chart-documentation over a patient's lifetime.

AI can accelerate the integration of peer-reviewed science, which currently takes an estimated 15 years. As medical knowledge triples every year, AI can help make recommendations of what's going to happen by taking the most recent evidence and marrying it with the patient. It can reveal which patient is most likely to respond to a given intervention and tailor that intervention based on a patient's risk profile.

When a person becomes ill, they generally do so in a predictable way for a given disease. AI is an incredible tool for pattern recognition.

Because medicine is not just about clinical care, AI can think about patients holistically, integrating their social determinants of health into the record. This will ultimately reduce stress for physicians, who are increasingly feeling responsible for the total outcome of a patient.

AI can go to work in the operating room. It can monitor blood loss during surgery or can see changes in biomarkers that would take time for the clinician to find.


As it has for other aspects of healthcare, COVID-19 has driven faster transformation in the AI space, such as in the use of chatbots for patient screening and care optimization. AI has also been an important accelerant for vaccine and therapeutics developers. 


"If AI is not reducing the stress or complexity of the workflow, it is either not working, not optimized or not useful," Amarasingham said during a recent roundtable discussion. "Everything in healthcare delivery touches some sort of workflow, including patient activities. Therefore, it is through workflows that AI can help improve some of the most critical outcomes, reduce costs and enhance clinical accuracy."

Twitter: @SusanJMorse
Email the writer:

The Diverse Roles of AI & ML

Machine learning applications are proliferating and improving, and this month we'll explore the many ways they're being put to work.