This blog will explain how Artificial Intelligence can be used in the medical field to improve the standards of health care. Artificial Intelligence and automation are on their way to revolutionize the workplace. Fifty percent of the activities that are carried out by people nowadays can be automated and it’s a legit concern to think how our field may be affected by this change.
Artificial intelligence in medicine and healthcare has been a particularly hot topic in recent years. While there is a sense of great potential in the application of AI in medicine, there are also concerns about the loss of the ‘human touch’ in such an essential and people-focused profession. Before touching on potential concerns, let’s walk through some medical history and see if AI fits in there.
Old School: Physicians, Take Notes
Physicians using handwritten notes for patient care are totally old school. Although this method is still used widely across the world (especially in developing and underdeveloped countries) and is convenient for the physicians, it also carries some serious disadvantages.
Practice patterns that are developed this way, evolve based on what the individual physician had learned over time which cannot be guaranteed to be the best practice. Also, these notes are prone to misinterpretation by other doctors or health care providers. Finally, there’s a possibility that a certain allergy isn’t mentioned in the notes, which can cost a patient his/her life in worst cases.
Machines in action - Electronic Medical record
Electronic Medical record is something more like structured data entry. It asks physicians to enter the data into predefined boxes instead of handwritten notes. Ideally, this system makes use of a Clinical Decision Support system and would make recommendations based on the best practices (An ideal case but is not in wide practice yet).
Now, this raises some concern as doctors feel like slaves to the EMR. They try to figure out how to get the system working instead of using their time and energy to focus on the patients. Many doctors spend hours after work just trying to catch up entering the information into the EMR so they can see as many patients as they did before the advent of this technology.
Physicians’ engagement with the EMR makes the patient feel like a third wheel during their own clinic visit rather than an active participant in the doctor-patient relationship.
The Future - Artificial Intelligence
Unfortunately, the symptoms do not always produce the right diagnosis from the treating physicians but we can make use of our skills to put information into the hands of physicians in time. This gives rise to another school of thought, i.e., data-driven decisions around risk and care management. For many years, physicians have had to adjust to the rigidity of EMR software. This has contributed to professional burnout as well as erosion in the doctor-patient relationship. From a patient’s perspective, more information is not necessarily a good thing. Dr. Google may know everything, but that doesn’t know you. When it comes to your health, one size simply does not fit all.
Now, most people fear competition from automation. Well, yes! There’s been a talk of Robo-Doctors as it is cheaper, faster, and a more accurate solution to the medical problems.
But this is more of a fantasy than a reality. People might be inspired by Big Hero 6 to come up with such a fantasy. Here’s the thing, though. Kasparov (world chess champion) had beaten Big Blue (the supercomputer) before; but in 1997, “Big Blue,” competed again against Kasparov and won. Somewhat frustrated, Kasparov used the experience to create a new chess tournament—one that had 3 types of competitors: humans, computers, and human with computers. Time and again, the winners of that tournament were the human-computer teams: The computers performed complicated calculations but could not replace human intuition and creativity.
The reason to state the story above is that AI in healthcare is not a replacement but a supplement that provides a way to change our relationship to data. Doctors can also stop being documentarians and go back to being humanitarians, with better answers at their fingertips. Patients are offered a chance to learn about their problems without being burdened by the worry of the unlikely. It is the combination of human and machine that offers a path forward.
Here’s a proposed solution.
- Gathering of data through patient interviews and tests
- Processing and analyzing results
- Using multiple sources of data to come to an accurate diagnosis
- Determining an appropriate treatment method (often presenting options)
- Preparing and administering the chosen treatment method
- Patient monitoring
- Aftercare, follow-up appointments etc.
The debate for AI being used in medicine is that quite a lot of the above-mentioned tasks can be automated - which means tasks are completed more quickly. Well, this frees up a medical professional’s time, ones that cannot be automated, and so are seen as a more valuable use of human resources.
Also, the computers can learn at an incredibly fast pace and they may be able to assist physicians in an augmentative manner. The integration can be done into the EMR to make the software contextual. Now, the system knows enough about the patient to offer a personalized advice to the physician, accessing a medical library and incorporating clinical outcomes into the patient’s care plan. It will also measure the likely risks, suggest tests, and save time by offering to complete the documentation with the physician’s oversight.
Concluding Note
AI is the answer to our personalized patient care. It has a patient-facing side in the form of mobile applications or web that offers a similar “contextual” experience. Patients can upload all their medical records and ask questions about their health issues and get personalized recommendations as opposed to Dr. Google. Furthermore, it can help physicians to better diagnose and suggest personalized treatment which will undoubtedly help save more lives.
Rushi MehtaPosted Nov 28, 2018, 6:22 AM
Good Article written