Artificial Intelligence in Healthcare
Abstract:
When we start talking about artificial intelligence, questions like “is there a place for AI
in medicine?”, “Will doctors one day be replaced by robots?” comes in mind. Also, these days,
health care is trailing other industries in the acceptance and application of AI. So, this report
would cover the ideas behind the use of complex algorithms and software to emulate human
cognition in the analysis of complicated medical data. In detail, it would tell about the ability of
computer algorithms to approximate conclusions without direct human input.
Introduction:
Artificial Intelligence refers to the simulation of human intelligence in machines that are
programmed to think like humans and mimic their actions. The term may also be applied to any
machine that exhibits traits associated with a human mind such as learning and problem-solving.
Artificial intelligence is based on the principle that human intelligence can be defined in a
way that a machine can easily mimic it and execute tasks, from the simplest to those that are
even more complex. The goals of artificial intelligence include learning, reasoning, and
perception.
History:
If we talk about an AI, then it traces its roots back to a conference at Dartmouth in 1956,
where the term was used for the first time. The successful development of image classifiers since
2012 has contributed to the recent resurgence of AI. Although much progress has been made in
the past decades, AI has suffered from an inconsistent and evolving definition as to what exactly
constitutes ‘real AI’. It is a well-recognized property of AI research that success in reaching a
specific performance goal soon disqualifies that performance as constituting AI, which makes
tracking progress difficult. As an illustration, automated route planners were touted as examples
of advanced AI in the 1970s yet are now so ubiquitous that most people would be surprised to
hear them described as AI. Consequently, the successes of AI from the 1970s through the 1990s
that were once heralded as breakthroughs in medicine, such as the automated interpretation of
electrocardiograms (ECGs), are now regarded as useful but are hardly considered to be examples
of true AI.
What motivated to use AI in Healthcare?
AI can use sophisticated algorithms to ‘learn’ features from a large volume of healthcare
data, and then use the obtained insights to assist clinical practice. It can also be equipped with
learning and self-correcting abilities to improve its accuracy based on feedback.
An AI system can assist physicians by providing up-to-date medical information from
journals, textbooks and clinical practices to inform proper patient care. In addition, an AI system
can help to reduce diagnostic and therapeutic errors that are inevitable in the human clinical
practice. Moreover, an AI system extracts useful information from a large patient population to
assist making real-time inferences for health risk alert and health outcome prediction
Example:
Identifying patients who are medication nonpersistent (fail to refill in a timely manner) is
important for healthcare operations and research. So above mention algorithm was used to
calculate that using electronic pharmacy databases.
AI devices:
AI devices mainly fall into two major categories. The first category includes machine
learning (ML) techniques that analyze structured data such as imaging, genetic and EP data. In
the medical applications, the ML procedures attempt to cluster patients’ traits, or infer the
probability of the disease outcomes. The second category includes natural language processing
(NLP) methods that extract information from unstructured data such as clinical notes/medical
journals to supplement and enrich structured medical data. The NLP procedures target at turning
texts to machine-readable structured data, which can then be analyzed by ML techniques.
Present and Future:
Current healthcare environment does not provide incentives for sharing data on the
system. Nevertheless, a healthcare revolution is under way to stimulate data sharing in the USA.
The reform starts with changing the health service payment scheme. Many payers, mostly
insurance companies, have shifted from rewarding the physicians by shifting the treatment
volume to the treatment outcome. Furthermore, the payers also reimburse for a medication or a
treatment procedure by its efficiency. Under this new environment, all the parties in the
healthcare system, the physicians, the pharmaceutical companies and the patients, have greater
incentives to compile and exchange information.
As the healthcare industry adopts more of the latest technology, the International Data
Corporation (IDC), a global market intelligence in healthcare, made a few predictions on the
future of AI in healthcare would be something like:
➢ Adoption rates of IoT-enabled asset tracking and inventory management systems in
hospitals will have doubled worldwide, improving patient safety, staff satisfaction, and
operational efficiency.
➢ One hospital in four with 200+ beds will have deployed robotics to handle time-
consuming tasks, reduce labor, and prevent errors to enhance the sustainability of its
business operations and improve patient safety.
➢ "By 2020, 20% of healthcare organizations will have moved beyond pilot projects and
will be using blockchain for operations management and patient identity."
➢ "By 2021, 20% of healthcare organizations will have achieved 15–20% productivity
gains through the adoption of cognitive/AI technology."
Opportunities and Obstacles:
There are various opportunities of AI in healthcare but following would be some
opportunities that AI can give to us at this time:
➢ There can be a positive impact on the reduction in mortality rates. AI can help improve
the efficiency of disease diagnosis, management, and treatment.
➢ Based on “study by Frost and Sullivan”, the market for AI has the potential to improve
healthcare outcomes by 30-40 % while simultaneously cutting the treatment cost by
integrating information, reducing unnecessary hospital visits, creating time-saving
administrative duties.
➢ It will not necessarily replace doctors. Instead it will assist doctors by making better data
driven decisions.
➢ It would support to provide efficient medical treatment.
There are not only opportunities but also some obstacles lies in this field. Integration of data
is complex, trust issue, time and energy limitations are some obstacles to implement AI in
healthcare.
Conclusion:
We can conclude that AI in healthcare is most used to perform diagnosis assistance,
management of healthcare enterprises, keeping healthy lifestyle. It still has some challenges like
necessity of specific architecture, necessity of providing privacy and information safety,
necessity of providing reliability and high quality of services. However, the potential of artificial
intelligence is difficult to ignore. It is a decision engine which can exponentially increase the
effectiveness and efficiencies of healthcare organization. Here, current regulations lack of
standards to assess the safety and efficacy of AI systems. To overcome the difficulty, the
US FDA made the first attempt to provide guidance for assessing AI systems. The first guidance
classifies AI systems to be the ‘general wellness products’, which are loosely regulated as long
as the devices intend for only general wellness and present low risk to users. The second
guidance justifies the use of real-world evidence to access the performance of AI systems.
Lastly, the guidance clarifies the rules for the adaptive design in clinical trials, which would be
widely used in assessing the operating characteristics of AI systems. In order to work well, AI
systems need to be trained (continuously) by data from clinical studies. However, once an AI
system gets deployed after initial training with historical data, continuation of the data supply
becomes a crucial issue for further development and improvement of the system. In conclusion,
if AI is well trained and systematically managed with guaranteed safety, it can bring the
evolution in healthcare and save billions of economy and millions of lives.
References:
Hayhurst, Chris. “Getting Smarter: The Promise and Potential of Artificial Intelligence in
Healthcare.” https://search-proquest-
com.trmproxy.mnpals.net/docview/2197278121?OpenUrlRefId=info:xri/sid:primo&accountid=1
2548
Jiang, Fei. “Artificial Intelligence in Healthcare: Past, Present and Future.”
https://svn.bmj.com/content/2/4/230
Parker, Melissa M, et al. “An Algorithm to Identify Medication Nonpersistence Using Electronic
Pharmacy Databases.” Journal of the American Medical Informatics Association : JAMIA,
Oxford University Press, Sept. 2015,
www.ncbi.nlm.nih.gov/pmc/articles/PMC5009927/figure/ocv054-F1/.
Richards, Tim. “Artificial Intelligence in Healthcare: the Ultimate Guide [2019].” CHT
Healthcare, CHT Healthcare, 13 Dec. 2018, www.chthealthcare.com/blog/artificial-intelligence-
in-healthcare.
“Therac-25.” Wikipedia, Wikimedia Foundation, 14 Feb. 2020, en.wikipedia.org/wiki/Therac-
25#/media/File:Therac25_Interface.png.
Yu, Kun-Hsing. “Artificial Intelligence in Healthcare.” https://www-nature-
com.trmproxy.mnpals.net/articles/s41551-018-0305-z.
