Artificial Intelligence in Healthcare - A Review (original) (raw)
Artificial Intelligence in Healthcare - A Review
Sakshi Panditrao Golhar 1∗{ }^{1 *}, Shubhada Sudhir Kekapure 2{ }^{2}
1∗2{ }^{1 * 2} Student, Department of Computer Science and Engineering, Jawaharlal Darda Institute of Engineering and Technology, Yavatmal, Maharashtra, India
Abstract
Article Info Volume 9, Issue 4 Page Number : 381-387 Publication Issue July-August 2022
Article History
Accepted : 15 July 2022
Published : 30 July 2022
Abstract
Advances in artificial intelligence (AI), and its subfield machine learning (ML), can be seen in almost every domain of life, including cutting-edge health research. Organizations from health care of different sizes, types and different specialties are now a days more interested in how artificial intelligence has evolved and is helping patient needs and their care, also reducing costs, and increasing efficiency. Artificial intelligence (AI) is a rapidly evolving field in medicine, especially cardiology and brain science, is revolutionizing risk prediction and stratification, diagnostics, precision medicine, workflows, and efficiency .This study explores the implications of AI on healthcare management, and challenges involved with using AI in healthcare along with the review of several research papers that used AI models in different sectors of healthcare like Dermatology, Radiology, drug Interactions, and Discovery etc. Artificial intelligence is not just a technology, it is a collection of technologies. Some among these technologies are widely used in healthcare.
Keywords : Artificial Intelligence (AI), Heathcare, Brain Science, Cardiac surgical procedures, Health Information Systems.
I. INTRODUCTION
The term artificial intelligence (AI) has a range of meanings, from specific forms of AI, such as machine learning, to the more far-fetched idea of AI that meets criteria for consciousness and sentience.
As technology advances and the use of Aritifical Intelligence (AI) technology is adopted in various fields, there are increasing efforts to develop AI technology for healthcare applications. Within the class of AI technology, Machine Learning (ML) systems are being developed that draw from statistics,
mathematics, rule-based systems and biological systems to create solutions that can adapt and learn, thus reducing manual burden. Private companies are building ML into medical decision-making, pursuing tools that support physicians. It is predicted by physician researchers that by familiarity with ML tools that analyze big data will be a fundamental competency for the next generation of physicians, which improves care in areas such as radiology and anatomical pathology.
Millions of dollars are being invested in AI, most implementations are still proofs of concept.
- Copyright: © the author(s), publisher and licensee Technoscience Academy. This is an open-access article distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited ↩︎
The history of artificial intelligence (AI) clearly reveals the connections between brain science and AI .It generally is subsumed by approaches including neural networks, machine learning, deep learning, etc. There can be more than 100 layers in these learning algorithms. The ability of AI to mimic the human brain and even overcome bias is fast contributing to the conceptualization of personalized precision medicine. However, overwhelmingly, the focus has been on diagnosis and risk prediction.
II. APPLIED AI IN HEALTHCARE
A visualization of the framework was created utilizing a nested hierarchy to demonstrate thematic importance of AI in healthcare.
Due to the “black box” nature of AI and the high dependency on accurate patient data for model training, there are unique challenges to successful implementation of AI in healthcare that are not encompassed in common implementation frameworks, such as the Ottawa Model of Research Use. Generating an implementation framework to aid healthcare organizations comprehend the key considerations and drive implementation efforts for AI will speed up adoption and help improve both patient care and patient outcomes.
>> METHODS
An environmental scan was conducted utilizing informal meetings with eight Subject Matter Experts (SMEs) from four hospitals, one national homecare organization, and one academic institution which provided examples of healthcare AI technologies . From these learnings the Affinity Diagram grouping method, was used to help identify key themes that were recurrent in the experiences of implementing AI technologies in the health setting. A literature review was then conducted to further explore the identified themes. This study aims to uncover clinician perceptions, acceptance levels, and professional standards around AI for clinical settings.
>> RESULTS
The key themes that were identified from the experiences of implementing AI technologies in health settings include data, trust, ethics, readiness for change, expertise, buy-in, regulatory strategy, scalability and evaluation.
Figure below illustrates the visualization of implementation framework:
At the core of the framework is the crux of all ML projects: data in healthcare includes large volumes of heterogeneous data from various systems, with different levels of veracity. Availability, quantity and quality of health data are key considerations in the framework that are crucial. The second level includes the ethics around privacy and secondary use of data and the trust of AI “black box” technology by healthcare providers and patient users These themes are fundamental to be able to achieve the next level in the framework, including buy-in, readiness and expertise [10] . Finally, in the outermost level of the implementation framework are the themes: regulatory, scalability and evaluation.
Figure 1-Preliminary Framework for Applied AI in Healthcare
III. AI INSPIRED BY BRAIN SCIENCE
The brain’s convolution property and multilayer structure, which were discovered using electronic detectors, inspired the convolutional neural network and deep learning. The attention mechanism that was discovered using a positron emission tomography (PET) imaging system inspired the attention module . The working memory that was discovered from functional magnetic resonance imaging (fMRI) results inspired the memory module in machine learning models that led to the development of long shortterm memory (LSTM) . The changes in the spine that occur during learning, which were discovered using two-photon imaging systems, inspired the elastic weight consolidation (EWC) model for continual learning, the goal of brain science, which is also termed neuroscience, is to study the structures, functions, and operating mechanisms of biological brains, such as how the brain processes information, makes decisions, and interacts with the environment. It is easy to see that AI can be regarded as the simulation of brain intelligence.
>> BRAIN PROJECTS:
Governments and most scientists seem to have reached a consensus that advancing neural imaging and manipulating techniques can help us explore the working principles of the brain, which will allow us to design a better AI architecture, including both hardware and software. During such studies, mutual collaboration between multiple disciplines including biology, physics, informatics, and chemistry are necessary to enable new discoveries in different aspects. ne typical case in the BRAIN Initiative, which aims to revolutionize machine learning through neuroscience, is machine intelligence from cortical networks (MICrONS). With serial-section electron microscopy, complicated neural structures can be reconstructed in 3D at unprecedented resolutions. In combination with high-throughput data analysis techniques for multiscale data, novel scientific
questions can be developed to explore fundamental neuroscience problems
Instrumental bridges between brain science and AI ur ever-growing understanding of the human brain has benefitted from countless advances in neurotechnology, including the manipulation, processing, and information acquisition of neurons, neural systems, and brains; and cognitive and behavioral learning. Among these advances, the development of new technologies and instruments for high-quality imaging acquisition has been the focus of the past era and is expected to attract the most attention in the future.
Traditional neuroscience research mostly uses electrophysiological methods, such as the use of metal electrodes for nerve excitation and signal acquisition, which have the advantages of high sensitivity and high temporal resolution.
The binary ability of the whole brain to explore both the micro- and macro-dimensions in real time will, beyond any doubt, promote the development of the next generation of AI. Therefore, the developmental goal of a microscopic imaging instrument is to possess broader, higher, faster, and deeper imaging from pixels to voxels and from static to dynamic.
>> BRAIN AND MIRROR NEURONS:
Mirror neurons occur in many brain regions and affect, control, and mirror particular sensi-motor activities across a wide range of interconnections. Several brain areas with mirror neurons include dorsal premotor and primary motor cortex, rostral division of the ventral premotor cortex (area F5), and inferior lateral and ventral intraparietal areas of the parietal lobe, among others.
>> BRAIN DISEASE AND MIRROR NEURONS:
In support of the physiological importance of mirror neurons, is their possible involvement in human brain diseases, for example, in amyotrophic lateral sclerosis (ALS). Mirror neurons appear to be involved in additional brain diseases and a few examples follow.
Alzheimer’s disease is hypothesized to have a link with motor function and this hypothesis is termed the Embodied Cognition Hypothesis. This hypothesis proposes that perception representations are coupled with actions. Mirror neurons may weigh heavily in this regard. Recently, mirror neuron integrity was studied in several categories of aging people: Alzheimer disease, Mild Cognitive impairment with hippocampal atrophy, and normal aging. In Alzheimer’s disease, mirror neurons are explicitly damaged.
>> HALL OF MIRROR NEURONS AND PARADIGM SHIFT:
Based on mirror neuron function in brain, a paradigm shift in relation to consciousness and cognition is proposed that could be termed the ‘hall of mirror neuron’ paradigm. If one postulates that there may be several mirror neuron foci of other mirror neuron foci, and that this could occur at several levels, in a chainlike manner, then such arrays could evolve further away from initial motor-sensory actions that initiated the complementarity of motor vs. mirror neuron groups. The geometric expansion of such ‘hall of mirror neuron’ group may soon exhaust the capacity of classical computers, supporting a further need for quantum computer development.
TOPOLOGICAL MODEL FOR HALL OF MIRROR NEURONS:
Research on brain is a natural setting for application of many different mathematical methods. Thus, concepts in differential topology of manifolds may be of use for neuronal interactions, arrangements, and clusters - viz. mirror neurons. If the ‘hall of mirror neuron’ paradigm is useful, then this type of algebraic and geometric topology will have an additional role in the quantitative analysis of mirror neuron topological interactions.
Moreover, since fiber bundles themselves may function as manifolds, the additional level of mirror neuron foci may be further treated as fiber bundles, and so on. In this way, topological methods assist in modeling such brain activity including terms such as J topology, M manifold, B base space mirror neuron cluster, π\pi mapping, π−1\pi^{-1} inverse mapping, arrow mapping →\rightarrow Consequently
Mi←π0−1→π0Bj(Mi)←π0−1→π0 Bk(Bj(M))←π0 B−1→π0 B⋅(Bk(Bj(M)))\mathrm{Mi} \leftarrow \pi_{0}{ }^{-1} \rightarrow \pi_{0} \mathrm{Bj}(\mathrm{Mi}) \leftarrow \pi_{0}{ }^{-1} \rightarrow \pi_{0} \mathrm{~B} \mathrm{k}(\mathrm{Bj}(\mathrm{M})) \leftarrow \pi_{0} \mathrm{~B}^{-1} \rightarrow \pi_{0} \mathrm{~B} \cdot\left(\mathrm{Bk}(\mathrm{Bj}(\mathrm{M}))\right)
etc…
In addition to interaction in one dimension, it should be noted that interactions among various mirror neurons in the hall of mirror neuron paradigm, could occur multiply, in two or three dimensions, in planar or in cubical arrays, respectively.
ARTIFICIAL INTELLIGENCE-BRAIN HEURISTIC COMPARISION:
The possibility of producing AI-type mirror foci is an additional challenge and the mirror neuron concept is being applied to AI to further the sophistication and subtlety of AI . The hall of mirror neuron paradigm could implement topological groups or swarms of architectures of foci based on these concepts and further widened. Many researchers in AI as well as in neurosciences had assumed basically that AI and brain function could be described using axiomatic algorithms. It had been presumed that there could be no calculation that was inimitable to this standard approach.
IV. ARTIFICIAL INTELLIGENCE IN CARDIOTHORACIC SURGERY:
Machine learning (ML) is a family of statistical and mathematical modeling techniques that uses a variety of approaches to automatically learn and improve the prediction of a target state, without explicit programming (e.g. Boolean rules). Different methods, such as Bayesian networks, random forests, deep learning, and artificial neural networks, each use
different assumptions and mathematical frameworks for data input, and learning occurs within the algorithm.
A deep learning model was used to predict which individuals with treatment-resistant epilepsy would most likely benefit from surgery. AI platforms can provide roadmaps to aid the surgical team in the operating room, reducing risk and making surgery safer. In cardiothoracic surgery, previous studies have developed machine learning algorithms that can outperform standard operative risk scores in predicting intrahospital mortality after cardiac procedures.
>> SURGICAL DATA SCIENCE :
With the emergence of novel technologies and their incorporation into the operating room (OR), alongside the enormous amount of data generated through patient surgical care, a new scientific discipline called surgical data science (SDS) was created. The main goal of SDS is to improve the quality of interventional healthcare and its value by capturing, organizing, processing and modeling data. 10 Within SDS, complex data can emerge from different sources, such as patients; operators involved in delivering care; sensors for measuring patient and procedure-related data; and domain knowledge. Built upon SDS, promising applications of AI and ML have been developed with the ultimate goal of supporting surgical decisionmaking and improving patient safety.
The use of AI, especially computer vision, offers a promising opportunity to automate, standardize and scale performance assessment in surgery, including cardiothoracic surgery. Prior investigations have documented the reliability of video-based surgical motion analyses for assessing laparoscopic performance in the operating room as compared to the traditional time-intensive, human rater approach.
>> AUGMENTED COGNITION IN THE OR:
As a high-tech work environment, the contemporary OR has incorporated novel computational systems to
the clinical workflow, aiming to optimize processes and support the surgical team. Cardiothoracic surgery is a perfect example of how AI can be used to support surgical care through cognitive augmentation. The cardiothoracic OR is a high-risk high-stakes environment, where multiple specialized professionals interact with each other, coordinate tasks as a team, and use a variety of equipment, technological devices and interfaces to effectively care for complex patients in need of surgical treatment. By functioning as a complex socio-technical system, the cardiothoracic team performs tasks in a coordinated way, requiring cognitive abilities that are beyond each individual team member’s performance. To monitor cognitive states at both individual and team levels, physiological metrics such as heart rate variability (HRV), electroencephalography (EEG) and nearinfrared spectroscopy (NIRS) are the most used, since they allow real-time objective measures of cognitive load
>> COMPUTER VISION IN SURGERY:
To encompass all the advances and future potentials of the use of AI to enhance cognition in the OR, a new interdisciplinary field called “cognitive surgery” or “cognition-guided surgery” has recently been created. Computer vision is a branch of AI that extracts and processes data from images and videos and provides the machine understanding of this data. In surgery, the main applications of computer vision are related to surgical workflow segmentation, instrument recognition and detection, and imageguided surgical interventions. However, a new area for applying computer vision in the OR, especially in team-based complex procedures, such as cardiothoracic surgery, is in the understanding of individual and team behaviors. In surgery, most of the applications of this technology involve tracking surgeon’s gestures and hands motion to extract objective metrics of technical psychomotor skills. However, recent studies have explored the use of position and motion data generated by computer
vision applications to measure team dynamics and coordination in the OR.
> AUTONOMOUS ROBOTIC SURGERY :
Robotic technology is going to change the face of surgery in the near future. Robots are expected to become the standard modality for many common procedures, including coronary bypass and abdominal surgery. The complexity of these tasks is also shifting from the low-level automation early medical robots to high-level autonomous features, such as complex endoscopic surgical manoeuvres and shared-control approaches in stabilized image-guided beating-heart surgery. Future progress will require a continuous interdisciplinary work, with breakthroughs such as nanorobots entering the field. Autonomous robotic surgery is a fascinating field of research involving progress in artificial intelligence technology.
> HUMAN-MACHINE TEAMING IN THE OR:
The way computer-based systems are designed and operated in the cardiothoracic OR plays a critical role in workflow efficiency, clinicians’ cognitive load and, ultimately, surgical performance. When AI systems are integrated within a complex OR environment, the opportunity for human-machine teaming emerges, creating novel cognitive engineering opportunities that have the potential to enhance patient safety and improve clinical outcomes in complex team based surgery.
> PUTTING AI THE CENTER OF HEART FAILURE CARE:
At least 1-2% of the global healthcare budget is spent on Heart Failure(HF).Being able to pool datasets smartly and extrapolating relevance at an individual level, our AI approach offers huge potential for reducing clinician burden, improving clinical efficacy, and enhancing patient experience and outcomes. Through the development of reinforcement learning algorithms, machine learning recognizes patterns in
new data to create its own logic to continuously improve cardiovascular
disease prediction and diagnosis. However, through strategic selection of underlying data and use of sensitivity checks, algorithm developers can mitigate AI bias. . Transparency regarding the quality of data, population representativeness, and performance assessment will be imperative.AI is the new tool in the toolbox that is already transforming cardiology. The PASSION-HF consortium see AI as an enabler to personalize medicine and to optimize. Effective HF self-care in consideration of disease complexity.
V. CONCLUSION
Artificial intelligence technologies are now undergoing a lot of development. In a health system that has historically been sluggish to accept new technologies technologies, it is crucial to take into account the adoption of a new technology in its early stages, particularly one with additional trust and transparency difficulties.Computer professionals and brain researchers need to address the limitations of computers and need to comprehend the exceeding complexity of the brain and consciousness. Paradigms require developments that conceptualize beyond current computer models. Quantum computers need to be developed that are capable of handling the complexities of such tasks. Some studies have attempted to optimize surgical coordination and team communication by using a data-driven approach that integrates human and non-human agents to enhance safety and mitigate errors in the cardiothoracic OR.
VI.REFERENCES
[1]. A Framework for Applied AI in Healthcare Tran Truonga,b, Paige Gilbankb, Kaleigh Johnson-Coverb, Adriana Ieraci MEDINFO 2019: Health and Wellbeing e-Networks for All L. Ohno-Machado and B. Séroussi (Eds.) DOI: 10.3233/SHTI190751
[2]. Artificial Intelligence and brain Paul Shapshak ISSN 0973-2063 (online) 0973-8894 Bioinformation 14(1): 038-041 (2018) DOI: 10.6026/97320630014038
[3]. From Brain Science to Artificial Intelligence Jingtao Fan a , Lu Fang b , Jiamin Wu a , Yuchen Guo a , Qionghai Da https://doi.org/10.1016/j.eng.2019.11.012
[4]. Artificial intelligence in cardiothoracic surgery Article in Minerva Cardioangiologica . September 2020 DOI: 10.23736/S0026-4725.20.05235-4
[5]. Putting AI at the centre of heart failure care ESC Heart Failure published by John Wiley & Sons Ltd ESC Heart Failure 2020; 7: 3257-3258 Published online 17 June 2020 in Wiley Online Library (wileyonlinelibrary.com) DOI: 10.1002/ehf2.12813
Cite this article as :
Sakshi Panditrao Golhar, Shubhada Sudhir Kekapure, “Artificial Intelligence in Healthcare A Review”, International Journal of Scientific Research in Science and Technology (IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011, Volume 9 Issue 4, pp. 381-387, July-August 2022. Available at doi :
https://doi.org/10.32628/IJSRST229454
Journal URL : https://ijsrst.com/IJSRST229454