Artificial Intelligence in Healthcare


By Adrian Sparrow
NeuLine Health

When you hear the words “artificial intelligence”, you might think of a science fiction movie full of robots and lasers. Instead, imagine a doctor’s office, surgery, or laboratory. While still the stuff of science, artificial intelligence has very real applications in healthcare today. 

What is AI?
Artificial intelligence (AI) is a science and set of computational technologies inspired by the ways people use their nervous systems and bodies to sense, learn, reason, and act. According to Britannica, AI is “the ability of a computer or a robot controlled by a computer to do tasks that humans usually do because they require human intelligence and discernment.” (source). AI operates much like how we humans see the world and make actions and decisions in response through trial and error, based on what we learned from our memories and experience.

Artificial intelligence covers several types of algorithms, such as machine learning, natural language processing, and early rule-based expert systems that are being replaced by machine learning today. 

 The earliest substantial work in AI was by English mathematician Alan Turing, who described an abstract computing machine in 1936, which breaks down the elements of information processing into the essential elements of input/output, memory, and a central processing unit. The Turing machine was the basis for digital computers that communicate with binary code (0s and 1s) and eventually the complex, human-like intelligence that we use today.


With rapidly improving technology over the past decade, AI is becoming more and more complex. There are many ways AI helps in the healthcare world, including diagnosis and treatment and administrative work. Clinical documentation and billing processes are common applications that can span different databases and identify and correct issues that can save hospitals, patients, and insurance companies time and money. Because there’s so much information to dictate, collect and compare for each patient, AI drastically shortens the time spent on patient documentation.

Researchers have used AI for decades, notably in genomics. AI is a vital tool in mapping the human genome, the sequence of genes that make up our complete DNA. More than 3 billion base pairs and 30,000 genes across 23 chromosomes is a lot of data to gather and puzzle-piece back together. The Human Genome Project formally began in 1990, and by 2003 92% of the genome had been sequenced. Even with advancing technology and AI, sequencing the last 8% took nearly 20 years and was finally completed in 2022.

For diagnostic applications, AI supports healthcare practices in a variety of ways. Supporting medical imaging analysis, drug discovery, and recognizing the signs of heart attacks and diseases are only a few ways. AI can also contribute to cancer research and radiation treatments and improve patient outcomes. One of AI’s most important features is the ability to act equitably. Algorithms can be taught to decrease or remove bias, such as limitations based on gender and race, by promoting diversity and transparency to reduce health inequities. 

Although advances in artificial intelligence are being made every year, adapting to healthcare is tricky. The rules aren’t clear on where the line between doctor and machine should be drawn, especially when involving patients’ diagnoses and treatments. People may not trust the technology can be truly unbiased or that errors could be made where a human might otherwise prevent or stop them. And while artificial intelligence might be improving, the technology and systems in place may be limited and need to adapt to work with these advances. 

AI is already a part of healthcare, but there’s still a long way to go before robots entirely treat you. 



Patient-Reported Outcomes Part 1 of 2: A Primer

Patient-Reported Outcomes Part 1 of 2: A Primer

Patient-reported outcomes (PROs) are clinical trial measures that capture the patient’s own perspective on how they feel. While they are commonly used in clinical trials, they are also used in the clinic as another measure to gauge a patient’s health over time.

read more