• Home
  • Use of Artificial Intelligence in Medicine – Pros and Cons

Use of Artificial Intelligence in Medicine – Pros and Cons

Advancements in medical technology have brought many benefits in terms of improved medical care, ease of medical record analysis, better medical documentation and so on. Artificial intelligence or AI is another technology that is rapidly spreading across the medical field. Now, systems that can identify symptoms of illness in images ranging from X-rays of the lungs to CT scans of the brain have been developed. These AI systems help physicians evaluate patients more efficiently and less expensively, which is welcome to the healthcare industry that is trying to cut costs without compromising the quality of healthcare. It is also expected that AI systems will soon be implemented by healthcare regulators, insurance companies, and medical billing companies to improve their functioning as regards determining reimbursement payments and insurance policy fees.

use of artificial intelligence in medicine

How efficient are artificial intelligence systems in a medical sense?

  • Studies show that AI outsmarts human physicians in two areas of medicine – in reading images from MRIs, X-rays, and CT scans, and in analyzing pathology slides of tissue samples thereby improving doctors’ ability to provide patients with more accurate information.
    • The FDA has approved an AI device to diagnose diabetic retinopathy after a study established the technology’s efficiency in this regard. The device learned how to distinguish between normal retinal patterns and those with symptoms of diabetic retinopathy by studying thousands of images of people’s retinas. It could parse through gradients of intensity and objects in the scans that no human can distinguish. Another study proved that an AI-trained algorithm, using features that doctors have not yet understood, easily identified the gender of the patients by studying the pictures of people’s retinas. The AI device was correct more than 97% of the time.
    • AI models are improving interpretation of mammograms in detecting early breast cancer. They can also identify the smallest nodules that could be the first signs of lung cancer that are often missed by the radiologist.
    • AI and digital medicine could promote “value-based” care wherein healthcare providers are reimbursed for keeping the population healthy rather than being paid for each procedure they perform. The emphasis is on prevention.
    • AI-powered predictive analytics could be applied to many types of health conditions and this would enable doctors to slow down or even halt the progress of diseases, and in some cases prevent the patients from getting sick.

However, are these systems completely safe to use?

They could bring unintentional consequences, as a group of researchers at Harvard and M.I.T. point out. What the researchers are concerned about is the prospect of adversarial attacks or manipulations that could change the behavior of artificial intelligence systems using tiny pieces of digital data.

  • They give the example of a lung scan – if a few pixels on the scan are changed, you could fool an AI system into seeing an illness that is not actually there, or not seeing an illness that is in fact present.
  • Minor changes made to written descriptions of a patient’s condition could change an AI diagnosis. For instance, “alcohol abuse” could produce a different diagnosis than “alcohol dependence;” and “lumbago” could produce a different diagnosis than “back pain,” the researchers say.

The researchers observe that changing such diagnoses could harm patients. Any changes made by doctors to scans or other patient data could become part of the patient’s permanent medical record and have an impact on the medical decisions taken.

Another major concern is whether the huge amount of patient data gathered to train AI systems is safe with the hospitals, research organizations, Big Pharma, insurance companies and tech companies that hold the data. To cash in on the advantages of digital medicine that is based on data, experts in the field should find a way to safeguard patient data privacy.

Considerable research is being done in the field of artificial intelligence and its applications in the medical sector. It has already been established that AI systems can help doctors do their jobs better. Many patients with chronic conditions agree that this new advanced technology can improve the quality of their lives. Machines have a wonderful capability of consuming and interpreting massive amounts of data and distinguish patterns and facts that human brains cannot. This is very significant with regard to preventive medicine.

AI systems can substitute doctors who can’t see patients face-to-face as often as they want to. In lab analysis, these systems are more accurate than what human doctors or clinicians can do on their own.

AI systems could also power important medical-legal processes such as medical chart review and enhance the quality of medical record review services. To make this possible, information should be collected in a standardized quantifiable way that machines can quickly understand and exploit. AI and machine-learning based technology could be successfully used to study patient medical records and extract valuable insights. When building and testing AI technologies, software developers and regulators must take into account all advantages as well as potential risk areas. To safeguard patient data privacy, appropriate regulation should be put in place.

 

     

    Powered by