Artificial Intelligence in Healthcare - A Review

International Journal of Scientific Research in Science and Technology Print ISSN: 2395-6011 | Online ISSN: 2395-602X (www.ijsrst.com) doi : https://doi.org/10.32628/IJSRST229454 Artificial Intelligence in Healthcare - A Review Sakshi Panditrao Golhar1*, Shubhada Sudhir Kekapure2 1*,2 Student, Department of Computer Science and Engineering, Jawaharlal Darda Institute of Engineering and Technology, Yavatmal, Maharashtra, India ABSTRACT Article Info Advances in artificial intelligence (AI), and its subfield machine learning (ML), Volume 9, Issue 4 can be seen in almost every domain of life, including cutting-edge health Page Number : 381-387 research. Organizations from health care of different sizes, types and different specialties are now a days more interested in how artificial intelligence has Publication Issue evolved and is helping patient needs and their care, also reducing costs, and July-August 2022 increasing efficiency. Artificial intelligence (AI) is a rapidly evolving field in medicine, especially cardiology and brain science, is revolutionizing risk Article History prediction and stratification, diagnostics, precision medicine, workflows, and Accepted : 15 July 2022 efficiency .This study explores the implications of AI on healthcare Published : 30 July 2022 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 mathematics, rule-based systems and biological systems to create solutions that can adapt and learn, The term artificial intelligence (AI) has a range of thus reducing manual burden. Private companies are meanings, from specific forms of AI, such as machine building ML into medical decision-making, pursuing learning, to the more far-fetched idea of AI that meets tools that support physicians. It is predicted by criteria for consciousness and sentience. physician researchers that by familarity with ML tools that analyze big data will be a fundamental As technology advances and the use of Aritifical competency for the next generation of physicians, Intelligence (AI) technology is adopted in various which improves care in areas such as radiology and fields, there are increasing efforts to develop AI anatomical pathology. technology for healthcare applications. Within the class of AI technology, Machine Learning (ML) Millions of dollars are being invested in AI, most systems are being developed that draw from statistics, 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 381 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 The history of artificial intelligence (AI) clearly ➢ RESULTS reveals the connections between brain science and The key themes that were identified from the AI .It generally is subsumed by approaches including experiences of implementing AI technologies in neural networks, machine learning, deep learning, etc. health settings include data, trust, ethics, readiness for There can be more than 100 layers in these learning change, algorithms. The ability of AI to mimic the human scalability and evaluation. expertise, buy-in, regulatory strategy, brain and even overcome bias is fast contributing to the conceptualization of personalized precision medicine. However, overwhelmingly, the focus has Figure below illustrates the visualization of implementation framework: been on diagnosis and risk prediction. At the core of the framework is the crux of all ML II. projects: data in healthcare includes large volumes of APPLIED AI IN HEALTHCARE heterogeneous data from various systems, with A visualization of the framework was created utilizing different levels of veracity. Availability, quantity and a quality of health data are key considerations in the nested hierarchy to demonstrate thematic importance of AI in healthcare. framework that are crucial. The second level includes Due to the “black box” nature of AI and the high the ethics around privacy and secondary use of data dependency on accurate patient data for model and the trust of AI “black box” technology by training, there are unique challenges to successful healthcare providers and patient users These themes implementation of AI in healthcare that are not are fundamental to be able to achieve the next level in encompassed in common implementation frameworks, the framework, including buy-in, readiness and such as the Ottawa Model of Research Use. Generating an implementation framework to aid expertise [10] . Finally, in the outermost level of the implementation framework are the themes: healthcare regulatory, scalability and evaluation. 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 utlizing 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. International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 382 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 III. AI INSPIRED BY BRAIN SCIENCE questions can be developed to explore fundamental neuroscience problems The brain’s convolution property and multilayer Instrumental bridges between brain science and AI structure, which were discovered using electronic ur ever-growing understanding of the human brain detectors, inspired the convolutional neural network has and deep learning . The attention mechanism that was neurotechnology, discovered using a positron emission tomography processing, and information acquisition of neurons, (PET) imaging system inspired the attention module . neural systems, and brains; and cognitive and The working memory that was discovered from behavioral learning. Among these advances, the functional magnetic resonance imaging (fMRI) results development of new technologies and instruments for inspired the memory module in machine learning high-quality imaging acquisition has been the focus of models that led to the development of long short- the past era and is expected to attract the most term memory (LSTM) . The changes in the spine that attention in the future. occur during learning, which were discovered using Traditional two-photon imaging systems, inspired the elastic electrophysiological methods, such as the use of metal weight consolidation (EWC) model for continual electrodes for nerve excitation and signal acquisition, learning. the goal of brain science, which is also which have the advantages of high sensitivity and termed neuroscience, is to study the structures, high temporal resolution. functions, and operating mechanisms of biological The binary ability of the whole brain to explore both brains, such as how the brain processes information, the micro- and macro-dimensions in real time will, makes decisions, and interacts with the environment. beyond any doubt, promote the development of the It is easy to see that AI can be regarded as the simulation of brain intelligence. next generation of AI. Therefore, the developmental goal of a microscopic imaging instrument is to possess benefitted from countless including neuroscience the research advances in manipulation, mostly uses broader, higher, faster, and deeper imaging from ➢ BRAIN PROJECTS: pixels to voxels and from static to dynamic. 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 Mirror neurons occur in many brain regions and affect, control, and mirror particular sensi-motor to design a better AI architecture, including both activities across a wide range of interconnections. hardware and software. During such studies, mutual Several brain areas with mirror neurons include collaboration between multiple disciplines including dorsal premotor and primary motor cortex, rostral biology, physics, informatics, and chemistry are division of the ventral premotor cortex (area F5), and necessary to enable new discoveries in different inferior lateral and ventral intraparietal areas of the aspects. ne typical case in the BRAIN Initiative, which parietal lobe, among others. BRAIN AND MIRROR NEURONS: aims to revolutionize machine learning through neuroscience, is machine intelligence from cortical ➢ networks (MICrONS). With serial-section electron In support of the physiological importance of mirror microscopy, complicated neural structures can be reconstructed in 3D at unprecedented resolutions . In neurons, is their possible involvement in human brain diseases, for example, in amyotrophic lateral sclerosis combination with high-throughput data analysis (ALS). Mirror neurons appear to be involved in techniques for multiscale data , novel scientific additional brain diseases and a few examples follow. BRAIN DISEASE AND MIRROR NEURONS: International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 383 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 Alzheimer’s disease is hypothesized to have a link Moreover, since fiber bundles themselves may with motor function and this hypothesis is termed the function as manifolds, the additional level of mirror Embodied Cognition Hypothesis. This hypothesis neuron foci may be further treated as fiber bundles, proposes that perception representations are coupled and so on. In this way, topological methods assist in with actions. Mirror neurons may weigh heavily in modeling such brain activity including terms such as J this regard. Recently, mirror neuron integrity was topology, M manifold, B base space mirror neuron studied in several categories of aging people: cluster, π mapping, π-1 inverse mapping, arrow Alzheimer disease, Mild Cognitive impairment with mapping → Consequently hippocampal atrophy, and normal aging. In Alzheimer’s disease, mirror neurons are explicitly Mi ←πij-1→πij Bj(Mi) ←πjk-1→πjk Bk(Bj(Mi)) ←πkl- damaged. 1 ➢ HALL OF MIRROR NEURONS AND In addition to interaction in one dimension, it should PARADIGM SHIFT: be noted that interactions among various mirror →πkl B1(Bk(Bj(Mi))) etc… Based on mirror neuron function in brain, a paradigm neurons in the hall of mirror neuron paradigm, could shift in relation to consciousness and cognition is occur multiply, in two or three dimensions, in planar proposed that could be termed the ‘hall of mirror or in cubical arrays, respectively. 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 ➢ ARTIFICIAL INTELLIGENCE-BRAIN HEURISTIC COMPARISION: chainlike manner, then such arrays could evolve The possibility of producing AI-type mirror foci is an further away from initial motor-sensory actions that initiated the complementarity of motor vs. mirror additional challenge and the mirror neuron concept is being applied to AI to further the sophistication and neuron groups. The geometric expansion of such ‘hall subtlety of AI . The hall of mirror neuron paradigm of mirror neuron’ group may soon exhaust the could implement topological groups or swarms of capacity of classical computers, supporting a further architectures of foci based on these concepts and need for quantum computer development. further widened. Many researchers in AI as well as in ➢ TOPOLOGICAL MODEL FOR HALL OF neurosciences had assumed basically that AI and brain function could be described using axiomatic MIRROR NEURONS: algorithms. It had been presumed that there could be no calculation that was inimitable to this standard Research on brain is a natural setting for application approach. of many different mathematical methods. Thus, of use for neuronal interactions, arrangements, and IV. ARTIFICIAL INTELLIGENCE IN CARDIOTHORACIC SURGERY: clusters – viz. mirror neurons. If the ‘hall of mirror Machine learning (ML) is a family of statistical and neuron’ paradigm is useful, then this type of algebraic mathematical modeling techniques that uses a variety and geometric topology will have an additional role in of approaches to automatically learn and improve the the quantitative analysis of mirror neuron topological interactions. prediction of a target state, without explicit programming (e.g. Boolean rules). Different methods, concepts in differential topology of manifolds may be such as Bayesian networks, random forests, deep learning, and artificial neural networks, each use International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 384 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 different assumptions and mathematical frameworks the clinical workflow, aiming to optimize processes for data input, and learning occurs within the and support the surgical team. Cardiothoracic surgery algorithm. is a perfect example of how AI can be used to support A deep learning model was used to predict which surgical care through cognitive augmentation. The individuals with treatment-resistant epilepsy would cardiothoracic most likely benefit from surgery. AI platforms can environment, provide roadmaps to aid the surgical team in the professionals interact with each other, coordinate operating room, reducing risk and making surgery tasks as a team, and use a variety of equipment, safer. In cardiothoracic surgery, previous studies have technological devices and interfaces to effectively care developed machine learning algorithms that can for complex patients in need of surgical treatment. By outperform in functioning as a complex socio-technical system, the cardiac cardiothoracic team performs tasks in a coordinated predicting standard operative intrahospital risk mortality scores after procedures. OR is where a high-risk multiple high-stakes specialized way, requiring cognitive abilities that are beyond each individual team member’s performance. To monitor ➢ SURGICAL DATA SCIENCE : cognitive states at both individual and team levels, With the emergence of novel technologies and their physiological metrics such as heart rate variability incorporation into the operating room (OR), alongside (HRV), electroencephalography (EEG) and near- the enormous amount of data generated through infrared spectroscopy (NIRS) are the most used, since patient surgical care, a new scientific discipline called they allow real-time objective measures of cognitive surgical data science (SDS) was created. The main goal load of SDS is to improve the quality of interventional ➢ COMPUTER VISION IN SURGERY: healthcare and its value by capturing, organizing, processing and modeling data.10 Within SDS, To encompass all the advances and future potentials of the use of AI to enhance cognition in the OR, a complex data can emerge from different sources, such new interdisciplinary field called “cognitive surgery” as patients; operators involved in delivering care; or “cognition-guided surgery” has recently been sensors for measuring patient and procedure-related created. Computer vision is a branch of AI that data; and domain knowledge. Built upon SDS, extracts and processes data from images and videos promising applications of AI and ML have been developed with the ultimate goal of supporting and provides the machine understanding of this data. In surgery, the main applications of computer vision surgical decisionmaking and improving patient safety. are related to surgical workflow segmentation, The use of AI, especially computer vision, offers a instrument recognition and detection, and image- promising opportunity to automate, standardize and guided surgical interventions.However, a new area for scale performance assessment in surgery, including applying computer vision in the OR, especially in cardiothoracic surgery. Prior investigations have team-based documented the reliability of video-based surgical cardiothoracic surgery, is in the understanding of motion laparoscopic individual and team behaviors. In surgery, most of the performance in the operating room as compared to applications of this technology involve tracking the traditional time-intensive, human rater approach. surgeon’s gestures and hands motion to extract analyses for assessing ➢ AUGMENTED COGNITION IN THE OR: As a high-tech work environment, the contemporary complex procedures, such as objective metrics of technical psychomotor skills.However, recent studies have explored the use of position and motion data generated by computer OR has incorporated novel computational systems to International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 385 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 vision applications to measure team dynamics and new data to create its own logic to continuously coordination in the OR. improve cardiovascular disease prediction and diagnosis. However, through ➢ AUTONOMOUS ROBOTIC SURGERY : strategic selection of underlying data and use of Robotic technology is going to change the face of sensitivity checks, algorithm developers can mitigate surgery in the near future. Robots are expected to AI bias. . Transparency regarding the quality of data, become the standard modality for many common population procedures, including coronary bypass and abdominal assessment will be imperative.AI is the new tool in surgery. The complexity of these tasks is also shifting the toolbox that is already transforming cardiology. from the low-level automation early medical robots to The PASSION-HF consortium see AI as an enabler to high-level autonomous features, such as complex personalize medicine and to optimize. Effective HF endoscopic surgical manoeuvres and shared-control self-care in consideration of disease complexity. representativeness, and performance approaches in stabilized image-guided beating-heart surgery. Future progress will require a continuous V. CONCLUSION interdisciplinary work, with breakthroughs such as nanorobots entering the field. Autonomous robotic Artificial surgery is a fascinating field of research involving undergoing a lot of development. In a health system progress in artificial intelligence technology. that has historically been sluggish to accept new intelligence technologies are now technologies technologies, it is crucial to take into ➢ HUMAN-MACHINE TEAMING IN THE OR: account the adoption of a new technology in its early The way computer-based systems are designed and stages, particularly one with additional trust and operated in the cardiothoracic OR plays a critical role in workflow efficiency, clinicians’ cognitive load and, transparency difficulties.Computer professionals and brain researchers need to address the limitations of ultimately, surgical performance. When AI systems computers and need to comprehend the exceeding are integrated within a complex OR environment, the complexity of the brain and consciousness. Paradigms opportunity for human-machine teaming emerges, require developments that conceptualize beyond creating novel cognitive engineering opportunities current computer models. Quantum computers need that have the potential to enhance patient safety and improve clinical outcomes in complex team based to be developed that are capable of handling the complexities of such tasks. Some studies have surgery. attempted to optimize surgical coordination and team communication by using a data-driven approach that ➢ PUTTING AI THE CENTER OF HEART FAILURE CARE: integrates human and non-human agents to enhance safety and mitigate errors in the cardiothoracic OR. VI. REFERENCES 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 [1]. A Framework for Applied AI in Healthcare level, our AI approach offers huge potential for Tran Truonga,b, Paige Gilbankb, Kaleigh reducing clinician burden, improving clinical efficacy, and enhancing patient experience and outcomes. Johnson-Coverb, Adriana Ieraci Through the development of reinforcement learning L. Ohno-Machado and B. Séroussi (Eds.) DOI: algorithms, machine learning recognizes patterns in 10.3233/SHTI190751 MEDINFO 2019: Health and Wellbeing e-Networks for All International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 386 Sakshi Panditrao Golhar et al Int J Sci Res Sci & Technol. July-August 2022, 9 (4) : 381-387 [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 September Minerva Cardioangiologica · 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 International Journal of Scientific Research in Science and Technology (www.ijsrst.com) | Volume 9 | Issue 4 387