Artificial Intelligence
in healthcare
Students: Eirini Paraschi and Irene Boulaniki
Class: Α3 - Grade: A3 - School: 1st Arsakeio Senior High School of Psychico
Course: IT Applications
School year 2022-2023
The reason for this project is to inform the readers of this crucial matter that will definitely concern us all in the future. Artificial intelligence is one of the emerging subjects that is able to change our lifestyles and especially healthcare, that is crucially important to us all.
Contents
Introduction
Benefits and Disadvantages
Types of artificial intelligence in healthcare
Machine learning
Natural language processing(NLP)
Rule-based expert systems
Robotic process automation
Sectors of AI in healthcare
Artificial intelligence in cardiology
Artificial intelligence in neurology
Artificial intelligence and basic biology
5.References
Image 1
Artificial intelligence has grown in the last years and especially in the aspect of healthcare in ways nobody can imagine. It has substantial benefits but also diasadvantages.
Benefits
In areas where there is a huge gap in essential skilled personnel, particularly in developing countries, artificial intelligence (AI) could offer assistance in those lacking areas of healthcare.
Standardization of treatments, which are replicated not only in specialized centers, but in any healthcare institution, is another huge benefit of AI, so that the practices implemented in these centers could be produced with the help of artificial intelligence.
The quality/effectiveness of treatment delivered is another area that could benefit significantly from the use of artificial intelligence. Artificial intelligence allows us to perceive correlations invisible to the human eye between the effectiveness of the treatment and the selected treatment regimen. These correlations can be used in the future to select the optimal treatment in patients with similar symptoms.
Disadvantages
There are a variety of ethical implications around the use of AI in healthcare. Healthcare decisions have been made almost exclusively by humans in the past, and the use of smart machines to make or assist with them raises issues of accountability, transparency, permission and privacy.
Another issue to address given today's technologies is transparency. Many AI algorithms – particularly deep learning algorithms used for image analysis – are virtually impossible to interpret or explain.
Mistakes will undoubtedly be made by AI systems in patient diagnosis and treatment and it may be difficult to establish accountability for them.
There are also likely to be incidents in which patients receive medical information from AI systems that they would prefer to receive from an empathetic clinician.
Machine learning systems in healthcare may also be subject to algorithmic bias, perhaps predicting greater likelihood of disease on the basis of gender or race when those are not actually causal factors.
Types of artificial intelligence in healthcare
Artificial intelligence is not one technology, but rather a collection of them.
Image 2
Machine learning
A subset of artificial intelligence (AI) and computer science, machine learning (ML) deals with the study and use of data and algorithms that mimic how humans learn. This helps machines gradually improve their accuracy. ML allows software applications to improve their prediction accuracy without being specifically programmed to do so. It estimates new output values by using historical data as input. Machine learning is one of the most common forms of AI; in a 2018 Deloitte survey of 1,100 US managers whose organizations were already pursuing AI, 63% of companies surveyed were employing machine learning in their businesses.
Image 3
Natural language processing(NLP)
Natural Language Processing (NLP) is a field of Artificial Intelligence (AI) that enables machines to understand and communicate in natural language, like humans do. It involves using algorithms and techniques such as machine learning, deep learning and text analytics to interpret and analyze natural language content from audio recordings, documents, images or other sources.
The adoption of natural language processing in healthcare is rising because of its recognized potential by health systems to search, analyze and interpret mammoth amounts of patient datasets. NLP in healthcare can accurately give voice to the unstructured data of the healthcare universe, giving incredible insight into understanding quality, improving methods, and better results for patients.
Image 4
Image 5
Rule-based expert systems
Expert systems based on variations of ‘if-then’ rules were the prevalent technology for AI in healthcare. Expert systems usually entail human experts and engineers to build an extensive series of rules in a certain knowledge area. They function well up to a point and are easy to follow and process. But as the number of rules grows too large, usually exceeding several thousand, the rules can begin to conflict with each other and fall apart. Also, if the knowledge area changes in a significant way, changing the rules can be burdensome and laborious.
Image 6
Robotic process automation
Feeding off structured data, which is stored in databases and may span patient demographics, names, addresses, and financial information, such bots execute rule-based, repetitive tasks the way human workers would.
In other words, the RPA solutions prevalent in the healthcare industry can be described as software that orchestrates other applications and performs tedious back-office tasks on its own, thus freeing healthcare workers’ time for diagnostic work and meaningful doctor-patient interactions. In particular, intelligent software agents are good at processing transactions, manipulating data, triggering responses, and conversing with internal and external IT systems.
Sectors of AI in healthcare
Artificial intelligence in cardiology
Helping people who have had a stroke. In emergency rooms, when people come in with a stroke called an intracerebral hemorrhage, they get a CT scan. That scan is examined by a computer trained to analyze CT data, cutting the time to diagnosis and limiting brain damage.
Image 7
Preventing heart problems. Applying AI to ECGs has resulted in a low-cost test that can be widely used to detect the presence of a weak heart pump, which can lead to heart failure if left untreated. Mayo Clinic is well situated to advance this use of AI because it has a database of more than 7 million ECGs. First, all identifying patient information is removed to protect privacy. Then this data can be mined to accurately predict heart failure noninvasively, inexpensively and within seconds.
Detecting atrial fibrillation (a-fib) sooner. AI-guided ECGs are also used to detect faulty heart rhythms (atrial fibrillation) before any symptoms are evident.
Image 8
Artificial intelligence in neurology
AI for Neuro-oncology
AI can detect brain tumors and other neurological cancers with high accuracy and consistency. Studies show that optical imaging and deep convolutional neural networks (CNNs) can be used to accurately predict brain tumors in less than 150 seconds.
AI for neuro-vascular diseases
AI has various applications for neurovascular disorders that can affect the blood supply in the brain or spinal cord.
AI can help treat patients who are affected by strokes by providing personalized treatments. See how BrainQ and Google are working on an AI-enabled medical device that can be helped to treat stroke patients:
AI for traumatic brain injuries
Traumatic brain injuries or TBIs are injuries that happen to the brain due to an accident. TBI affects around 60 million people every year globally, with short and long-term health consequences being in terms of their severity.
AI for neurosurgery
AI can help improve pre-operative, intra-operative, and postoperative phases of brain surgery: In preoperative surgery, AI can help improve the accuracy of diagnoses and create a better surgical plan based on historical data.In the intra-operative phase, AI can enable fast and accurate analysis of brain tissue during the procedure. In the postoperative phase, AI can help predict postoperative complications to improve patient recovery and aftercare.
Image 9
Artificial intelligence and basic biology
We already use AI in multiple, wide-ranging fields in biology, from image analysis in microscopy to protein structure prediction and drug discovery.
Artificial Intelligence in Image Analysis
When it comes to image analysis, researchers face many issues, including:
the heterogeneity of the samples;
achieving consistency in analysis, which is challenging due to human error;
requiring complex tasks to be performed; and
large amounts of data making analysis time consuming.
However, AI is helping to make handling these issues easier and quicker.
Artificial intelligence and drug development
Shrinking the drug development cycle is another area where AI can have a huge impact. The creation of more and more specialized treatments is constantly increasing the duration and cost of creating new medications, as well as the failure rate. The ability to collect and analyze data allows, during medical trials, to discover indicators of treatment effectiveness and to direct it to the appropriate receivers-patients, that is, the patients who have a high probability of responding best to it.
Artificial intelligence and structure development
A recent development in AI in biology concerns predicting protein structures based on amino acid sequence, known as AlphaFold. AlphaFold is a revolutionary use of AI that accurately predicts protein structure down to an atomic level, even when no homologous protein structures exist.
It does this by employing a ‘neural network’ to combine knowledge of the physical and biological properties of protein structure while using multi-sequence alignments in the design of the deep learning algorithm.
Sources for the text
https://www.aueb.gr/el/opanews/i-tehniti-noimosyni-stin-ypiresia-tis-ygeias
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6616181/
https://www.imperial.ac.uk/stories/healthcare-ai/
https://www.foreseemed.com/natural-language-processing-in-healthcare
https://www.igi-global.com/chapter/rule-based-systems-for-medical-diagnosis/124441
https://itrexgroup.com/blog/rpa-in-healthcare/
https://www.mayoclinic.org/departments-centers/ai-cardiology/overview/ovc-20486648
https://research.aimultiple.com/neurology-ai/
https://bitesizebio.com/64186/artificial-intelligence-in-biology/
Sources for images
Image 1: https://medium.com/@annoberry/ai-and-psychology-part-3-1751c6978544
UG0V8OBJU1BYZYFE17NH%2Fnatural%252Blanguage%252Bprocessing%252Bin%252Bhealthcare%252B-%252Bforesee%252Bmedical.gif&tbnid=IMsMh8MMWoy0zM&vet=12ahUKEwjRpZDRjcf-AhWKiv0HHeXaCcMQMygAegUIARCtAQ..i&imgrefurl=https%3A%2F%2Fwww.foreseemed.com%2Fnatural-language-processing-in-healthcare&docid=4gttkKcbr02GzM&w=601&h=395&q=natural%20language%20processing%20in%20healthcare&ved=2ahUKEwjRpZDRjcf-AhWKiv0HHeXaCcMQMygAegUIARCtAQ
Image4:https://lh3.googleusercontent.com/xr0Ftd7NoBFMt9um08MEu0V_M0yFVf5QiTdxO5QyDFvPRgYkHS-mJOCa7yejZuG9crIQi5cFxRFhP-VR4muDDhaNMBd_PRS7b4Bv0laz2A
Image 5:https://www.amazon.com/Goldwater-Nichols-Department-Defense-Reorganization-1986/dp/1288294018
Image 6:https://www.callcentrehelper.com/images/stories/2020/02/robotic-process-automation-760.jpg
Image 8: https://www.pharmafile.com/system/files/imagecache/news_full/33482625641_c7347cbaba_h.jpg
Image 9: https://bitesizebio.com/64186/artificial-intelligence-in-biology/