BME Research – Topic (AI: Artificial Intelligence) this is mine M.E. (Sorry it was so late.) I write my personal comments in red, anything else has to do with the research and organization. Definitions and anything to memorize go in green. Super edits in purple. THESE ARE THE MOST IMPORTANT ONES PLEASE READ THESE. Introduction of the Assigned Subtopic THIS IS MINE M.E. - The introduction would go after the first title slide and perhaps the table of contents explaining? Introduction: Artificial intelligence. Definitions for artificial intelligence based on articles: Here I put the quote for the definition – the link of where to find the paper – and finally the citation of the paper. Most of which have been provided through research with FIU. I have a separate folder in my laptop saved with all the pdf’s of the research papers. - “An artificial-intelligence approach is proposed to differentiate various biomedical samples via Raman spectroscopy technology to obtain accurate medical diagnosis and decision making. The complete process consists of noise filtering, fluorescence identification, optimization and elimination, spectral normalization, multivariate statistical analysis, and data clustering, as well as the final decision making. Numerous modeling, intelligent control, and systemidentification schemes have been employed.” https://ieeexplore.ieee.org/document/1381368 ZhengMao Ye, "Artificial-intelligence approach for biomedical sample characterization using Raman spectroscopy," in IEEE Transactions on Automation Science and Engineering, vol. 2, no. 1, pp. 67-73, Jan. 2005, doi: 10.1109/TASE.2004.840071. - “…artificial intelligence (AI) has allowed to automate repetitive or tedious tasks for human beings (e.g., the automation of industrial processes or cleaning tasks), as well as to surpass humans’ capacity in performing complex tasks (e.g., processing massive amounts of data to extract new knowledge or overcome human champions playing Chess or Go). Recently, advances related to machine learning (ML), under the terminological umbrella of deep learning (DL), have provided astonishing advances in image recognition, image restoration, image generation, speech recognition, and machine translation, among others.” https://www.proquest.com/ataindex/docview/2423332644/671CB55D918247FAP Q/1?accountid=10901 Mesejo, P., Martos, R., Ibáñez, Ó., Novo, J., & Ortega, M. (2020). A survey on artificial intelligence techniques for biomedical image analysis in skeleton-based forensic human identification. Applied Sciences, 10(14), 4703. doi: http://dx.doi.org/10.3390/app10144703 - “Artificial intelligence (AI) finds applications in most of the areas of human life including health. The AI techniques provide a platform for developing automated processes based on the learning processes. There are many AI applications in the healthcare field such as detecting disease, gathering the patient information, intelligent interaction between patient and doctor, disease information sensing, diagnosis and care plans. Various AI-based applications and devices such as intelligent health information gathering, intelligent communication and service, intelligent diagnosis and carefulness strategies, intelligent medical devices, intelligent precision medicine etc. are currently deployed to address the patient’s health-related issues.” https://www-igi--global-com.eu1.proxy.openathens.net/gateway/book/235693 Sisodia, D. S., Pachori, R., & Garg, L. (Eds.). (2020). Handbook of Research on Advancements of Artificial Intelligence in Healthcare Engineering. IGI Global. http://doi:10.4018/978-1-7998-2120-5 This is the forward – the very first paragraph of the Handbook of AI in healthcare. It is extremely useful when identifying the definition of artificial intelligence in health and BME. - “We have thoroughly investigated the application of quantum dots in imaging, diagnostics, and gene therapy areas. A significant outcome of this review is to propose quantum dots as a new modality in the treatment of cancer and gene therapeutics in the healthcare domain and the potentials of artificial intelligence to improve their performance via the applications of neural networks.” https://www.proquest.com/ataindex/docview/2563364043/671CB55D918247FAP Q/8?accountid=10901 Tiwari, Pawan K., et al. "Pivotal Role of Quantum Dots in the Advancement of Healthcare Research." Computational Intelligence and Neuroscience : CIN 2021 (2021) ProQuest. 14 Nov. 2021 . I believe that any of these four definitions could work when introducing Artificial Intelligence in the first slide because they all have to do with AI in BME. Especially the last topic since one of the examples that Rufus put in the brute PowerPoint was in relation to cancer and the advancement of AI in Healthcare research. All in all, for the first introduction I would put (maybe in less words) : “ Artificial intelligence is the analysis of systems by a program that can filter, identify, optimize, eliminate, neutralize, and make decisions to bring significant outcomes. It makes advances in fields such as quantum dots via application of neural networks and surpasses a human’s capacity in performing complex tasks and processing massive amounts of data to bring forth newer knowledge.” This singular quote brings together the three definitions (not including the handbook of AI in healthcare) of the three articles. IMO, too long, but it amasses everything that needs to be said in slide 1 of BME. Maybe have it in flash cards but not really go into depth about it. Definitions: 1. Raman Spectroscopy: a spectroscopic technique typically used to determine vibrational modes of molecules, although rotational and other low-frequency modes of systems may also be observed. Raman spectroscopy is commonly used in chemistry to provide a structural fingerprint by which molecules can be identified. What is Raman Spectroscopy used for? rapidly characterize the chemical composition and structure of a sample, whether solid, liquid, gas, gel, slurry or powder. Super edit: surface enhanced Raman spectroscopy was one of the research topics for the biophotonics group. It still works for us in the definition of artificial intelligence 2. 3. - Machine Learning AI: Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. AND . . . Deep Learning AI: Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is the overall umbrella term for AI learning. There is a difference between both of them: “Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.” 4. Quantum dots: A quantum dot is a nanometer-sized semiconductor particle traditionally with a core-shell structure. Quantum dots are widely used for their unique optical properties, as they emit light of specific wavelengths if energy is applied to them. What do you do with quantum dots? Currently, quantum dots are used for labeling live biological material in vitro and in vivo in animals (other than humans) for research purposes - they can be injected into cells or attached to proteins in order to track, label or identify specific biomolecules. 5. Cancer and Gene Therapeutics: “Gene-based therapies for cancer in clinical trials include strategies that involve augmentation of immunotherapeutic and chemotherapeutic approaches.” This one comes with its own article and everything. Very interesting, could help. https://academic.oup.com/jnci/article/89/1/21/2526155 check it out maybe? Has nothing to do with AI but could give more insight towards cancer and gene therapies that can be useful for research later down the road like with the person that is doing “latest development”. 6. Neural Networks: Artificial neural networks, usually simply called neural networks, are computing systems inspired by the biological neural networks that constitute animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. I have a feeling he might ask about this one. What are the fields of application for artificial intelligence in Biomedical engineering? Super Edit: Neither of the handbooks have definitions because both of the definitions are in extremely plainclothes words – meaning that there is literally nothing here that needs to be super defined for the professor IMO, but.. I could be wrong who knows. You let me know if anything please. EDIT: I HAVE FOUND THE MOST PERFECT DEFINITION!!!! “ Biomedical engineering is a multidisciplinary field that applies engineering principles and materials to medicine and healthcare. The combination of engineering principles with biological knowledge has contributed to the development of revolutionary and life-saving concepts. Artificial intelligence (AI) is an area of computer science and engineering that provides intelligence to machines. AI in biomedical engineering uses machine-learning algorithms and software to analyze complicated medical data and perform automatic diagnosis” OR “Artificial intelligence (AI) is a replication of human intelligence by computer systems. It is an interdisciplinary field that embraces a number of sciences, professions, and specialized areas of technology. To be precise, AI will not replace people but will augment their capabilities.” https://www.taylorfrancis.com/books/edit/10.1201/9781003045564/handbook-artificialintelligence-biomedical-engineering-saravanan-krishnan-ramesh-kesavan-surendiranmahalakshmi Krishnan, S., Kesavan, R., Surendiran, B., & Mahalakshmi, G.S. (Eds.). (2021). Handbook of Artificial Intelligence in Biomedical Engineering (1st ed.). Apple Academic Press. https://doi.org/10.1201/9781003045564 Bro this is a $200 dollar book and I got to request it for a short time I’m so happy. I’m currently at the library freaking out about this you have no idea. The link I put up is the preview – I don’t really have the book online, but it has the source cited. Featured Technologies: https://test.globalinfocloud.com/technodigisoftnew/wp-content/uploads/2019/07/Applications-of-ArtificialIntelligence-Associated-Technologies.pdf This link automatically downloads the PDF for you so please be careful when using it. The picture is directly from the book. Fields of Application: Health apps, network systems, image processing, surgical robots, molecular pharmaceuticals. The following are the links and citations that are in accordance with the fields of application. I cited them at the end of this paper: - https://dl.acm.org/doi/abs/10.1145/3428361.3428362?casa_token=k0G3Nv1eDDkAAAAA%3AT D6lAa5FIVrFMcdi3jYUaWgPLb5QVW3mvUHKadMSxPxcodvPa6Y5exaZREE4WchXSBN6EU0 FI6k (Health apps) - - https://ieeexplore.ieee.org/document/6690961 (Network Systems) https://www.aaai.org/Papers/AIPS/1994/AIPS94-037.pdf (Image Processing) Link automatically downloads the PDF https://journals.lww.com/annalsofsurgery/Fulltext/2019/08000/Artificial_Intelligence_and_the_F uture_of_Surgical.7.as?casa_token=YLiZOhe6KMEAAAAA:qmi0KCnYAawhCuQBrlcviNscCjH U6B6dvCHZkkq5lS7UMINPFlpmqd6DyAWmfJb_acnfxAMXTE_AYYfESHkZrw (Surgical Robots). https://fiuflvc.primo.exlibrisgroup.com/discovery/fulldisplay?docid=cdi_proquest_miscellaneous_2415303 688&context=PC&vid=01FALSC_FIU:FIU&lang=en&search_scope=CentralIndex&adaptor= Primo%20Central&tab=CentralIndex&query=any,contains,artificial%20intelligence%20%2B% 20protein%20folding&offset=0 (molecular pharmaceuticals). The end for the intro of the Subtopic. Introduction of the Selected Technological Topic Who-The typical big tech companies and China What- Statistics to solve problems/identify things quickly and efficiently Why- Efficiency, saved money, more money generated How- Strong understanding of modeling networks and weighing inputs to determine an output Take home -> AI isn’t going anywhere, its new and potentially dangerous (selfdriving cars, unmanned drones, errors from not learning correctly) THIS IS FROM RUFUS! I USED IT AS KINDA A REFERENCE POINT. I. Protein Folding - YouTube video of a discussion about it: https://youtu.be/dgHhbjXCM2c Ted-ex talks video: https://youtu.be/JAB_GOBNcY0 (read the description of the video.) - https://www.ces.tech/Articles/2021/May/The-AI-Pastry-Scanner-That-Is-Now-FightingCancer.aspx This was the original link that Rufus put in the brute PowerPoint. - What to write on the slide: “Artificial intelligence teaches drugs to target proteins by tackling induced folding problem.” What is the induced folding problem: The protein folding problem is the question of how a protein's amino acid sequence dictates its three-dimensional atomic structure. The notion of a folding “problem” first emerged around 1960, with the appearance of the first atomic-resolution protein structures. - “We explore the possibility of a deep learning (DL) platform that steers drug design to target proteins by inducing binding-competent conformations. We deal with the fact that target proteins are usually not fixed targets but structurally adapt to the ligand in ways that need to be predicted to enable pharmaceutical discovery. In contrast with protein folding predictors, the proposed DL system integrates signals for structural disorder to predict conformations in floppy regions of the target protein that rely on associations with the purposely designed drug to maintain their structural integrity.” https://pubs.acs.org/doi/abs/10.1021/acs.molpharmaceut.0c00470 Citation: Fernández, Ariel. “Artificial Intelligence Teaches Drugs to Target Proteins by Tackling the Induced Folding Problem.” Molecular pharmaceutics 17, no. 8 (2020): 2761–2767. This is a citation from the article title that can be used on the slide. It talks about protein folding and idk if it can be useful in the PowerPoint or just to talk about in general. Definitions: 1. Deep Learning: Already defined. 2. Induced binding-component conformations (ligand binding): In protein-ligand binding, the ligand is usually a molecule which produces a signal by binding to a site on a target protein. The binding typically results in a change of conformational isomerism (conformation) of the target protein. 3. Structural disorder: Structural disorders are usually inevitable in organic materials; therefore they are weak crystalline or amorphous and easy to be bent and transformed. 4. Floppy regions: Basically regions that are unstructured. Regions in proteins that do not adopt wellordered 3D structures under physiological conditions are often dubbed natively unstructured, disordered, intrinsically unstructured or unfolded. Typical are proteins that adopt stable 3D structures only upon binding to substrates to carry out their function Super edit: this Tech topic, I split between topic I and II because they are very similar. Therefore there is not as much information on this sub area than the one beforehand. If you want me to do more research just lmk. :) II. Identifying Cancer from Bread AI https://girlswhocodemcgill.com/2021/05/31/artificial-intelligence-from-croissants-to-cancer/ - What is it? Cyto-AiSCAN “The now specialized Cyto-AiSCAN uses the same technologies that can differentiate a donut from a cream bread to identify cancerous urinary cells with 99% accuracy.” - Who and When? “Seeing BakeryScan on the news in 2017, a doctor at Kyoto’s Louis Pasteur Center for Medical Research realized how, under a microscope, some cancer cells closely resembled some of the pastries and baked goods that the AI system was scanning.” - https://girlswhocodemcgill.com/2021/05/31/artificial-intelligence-from-croissants-to-cancer/ This is a photo from this link. I could barely find any info on CytoAiSCAN anywhere ☹ - “ Now, Brain is dealing with humans, not pastries. This entails that Brain must add major changes to the AI-Scan software; namely, security. In the case of BakeryScan, it wouldn’t have really mattered if information about a bread was leaked (nobody really cares whether a croissant has chocolate frosting or not). On the other hand, serious consequences would ensue if patient information was hacked on CytoAiSCAN (release of patient information such as gender, race, sex could lead to stigmatization and thus should remain private). Lack of measures to ensure confidentiality could hinder the patient from being honest with the physician, impacting patient care. The transition from croissants to cancer means that the program should improve not only in reliability, but also in terms of ethics considerations.” - This could be extremely helpful for the bioethics section. - Citation: https://www.newyorker.com/tech/annals-of-technology/the-pastry-ai-that-learned-tofight-cancer Somers, James. “The Pastry A.I.. That Learned to Fight Cancer.” The New Yorker, The New Yorker, 18 Mar. 2021, https://www.newyorker.com/tech/annals-of-technology/the-pastry-ai-thatlearned-to-fight-cancer. III. Designing Intelligent AI pertaining to race and gender. - Considers the implicit association test. Definition: Implicit association test (IAT system): The Implicit Association Test (IAT) measures the strength of associations between concepts (e.g., black people, gay people) and evaluations (e.g., good, bad) or stereotypes (e.g., athletic, clumsy). - Who: Ai overall chooses the IAT system over regular surveys of how the human race views gender and well, race. I didn’t go in depth here because I am not sure if we are using this at all. If we are, the article is great for facts and ethical concerns. I linked more below it in yellow. https://www.science.org/content/article/even-artificial-intelligence-can-acquirebiases-against-race-and-gender This is the website to the citation Hutson, Matthew. “Even Artificial Intelligence Can Acquire Biases Against Race and Gender.” Science (American Association for the Advancement of Science) (2017). 1. Sutko, Daniel M. “Theorizing Femininity in Artificial Intelligence: a Framework for Undoing Technology’s Gender Troubles.” Cultural studies (London, England) 34, no. 4 (2020): 567–592. https://www.tandfonline.com/doi/full/10.1080/09502386.2019.1671469 2. Abdurrahim, Salem Hamed, Salina Abdul Samad, and Aqilah Baseri Huddin. “Review on the Effects of Age, Gender, and Race Demographics on Automatic Face Recognition.” The Visual computer 34, no. 11 (2017): 1617–1630. https://link.springer.com/article/10.1007/s00371-017-1428-z 3. Toderici, George, Sean M O’Malley, George Passalis, Theoharis, and Ioannis A Kakadiaris. “Ethnicity- and Gender-Based Subject Retrieval Using 3-D FaceRecognition Techniques.” International journal of computer vision 89, no. 2-3 (2010): 382–391. https://go.gale.com/ps/i.do?p=AONE&u=miam11506&id=GALE%7CA365073277&v= 2.1&it=r The end for the subtopics. Scientific and/or Engineering Principles of the Technological Topic I. Characteristics and Developments of CytoAiSCAN - Identifies cancerous urinary cells 99% of the time. - Originally SUPER TEX-SIM for BRAIN Co. in Japan. - Uses algorithms to measure the Nuclei of cells. https://iridescentwomen.com/2021/05/13/pastry-ai-learned-to-fight-cancer/ II. Engineering Principles of Statistics and Graphs - “Statistical methods must be considered as integral part of AI systems, from the formulation of the research questions, the development of the research design, through the analysis up to the interpretation of the results” https://link.springer.com/article/10.1007/s11634-021-00455-6 Friedrich, S., Antes, G., Behr, S. et al. Is there a role for statistics in artificial intelligence?. Adv Data Anal Classif (2021). https://doi.org/10.1007/s11634-021-00455-6 III. Prediction “Building energy prediction can be broadly classified into engineering, Artificial Intelligence (AI) based, and hybrid approaches. While engineering and hybrid approaches use thermodynamic equations to estimate energy use, the AI-based approach uses historical data to predict future energy use under constraints.” https://www.sciencedirect.com/science/article/pii/S1364032116307420?casa_token=d UPoIegnzJAAAAAA:uC4NsKvCSBc97bOMySpUtVjtl3pmsRCsf31sEwzzFP1AelcS lU7PAjT0rV3h6vHbV6VbjSoD Wang, Zeyu, and Ravi S. Srinivasan. “A Review of Artificial Intelligence Based Building Energy Use Prediction: Contrasting the Capabilities of Single and Ensemble Prediction Models.” Renewable and Sustainable Energy Reviews, Pergamon, 10 Nov. 2016, https://www.sciencedirect.com/science/article/pii/S1364032116307420?casa_token=d UPoIegnzJAAAAAA%3AuC4NsKvCSBc97bOMySpUtVjtl3pmsRCsf31sEwzzFP1 AelcSlU7PAjT0rV3h6vHbV6VbjSoD. Super edit: The following is an addition from the Handbook of Artificial Intelligence in Biomedical Engineering. IV. Classification using SVM From the Biomed Handbook previously cited. “Support Vector Machine” (SVM) is a supervised machine learning algorithm that can be used for both classification and regression challenges. However, it is mostly used in classification problems. Citations: This is mine M.E. ZhengMao Ye, "Artificial-intelligence approach for biomedical sample characterization using Raman spectroscopy," in IEEE Transactions on Automation Science and Engineering, vol. 2, no. 1, pp. 67-73, Jan. 2005, doi: 10.1109/TASE.2004.840071. Mesejo, P., Martos, R., Ibáñez, Ó., Novo, J., & Ortega, M. (2020). A survey on artificial intelligence techniques for biomedical image analysis in skeleton-based forensic human identification. Applied Sciences, 10(14), 4703. doi: http://dx.doi.org/10.3390/app10144703 Sisodia, D. S., Pachori, R., & Garg, L. (Eds.). (2020). Handbook of Research on Advancements of Artificial Intelligence in Healthcare Engineering. IGI Global. http://doi:10.4018/978-1-7998-2120-5 Tiwari, Pawan K., et al. "Pivotal Role of Quantum Dots in the Advancement of Healthcare Research." Computational Intelligence and Neuroscience : CIN 2021 (2021) ProQuest. 14 Nov. 2021 . Krishnan, S., Kesavan, R., Surendiran, B., & Mahalakshmi, G.S. (Eds.). (2021). Handbook of Artificial Intelligence in Biomedical Engineering (1st ed.). Apple Academic Press. https://doi.org/10.1201/9781003045564 Matthias Baldauf, Peter Fröehlich, and Rainer Endl. 2020. Trust Me, I’m a Doctor – User Perceptions of AI-Driven Apps for Mobile Health Diagnosis. In 19th International Conference on Mobile and Ubiquitous Multimedia (MUM 2020). Association for Computing Machinery, New York, NY, USA, 167–178. DOI: https://doi.org/10.1145/3428361.3428362 K. Awahara, S. Izumi, T. Abe and T. Suganuma, "Autonomous Control Method Using AI Planning for Energy-Efficient Network Systems," 2013 Eighth International Conference on Broadband and Wireless Computing, Communication and Applications, 2013, pp. 628-633, doi: 10.1109/BWCCA.2013.111. Chien, Steve. "Using AI planning techniques to automatically generate image processing procedures: A preliminary report." Proceedings of the Second International Conference on AI Planning Systems, Chicago, IL. 1994. Panesar, Sandip MD, MSc∗; Cagle, Yvonne MD; Chander, Divya MD, PhD; Morey, Jose MD; Fernandez-Miranda, Juan MD; Kliot, Michel MD, Artificial Intelligence and the Future of Surgical Robotics, Annals of Surgery: August 2019 - Volume 270 - Issue 2 - p 223-226 doi: 10.1097/SLA.0000000000003262 Fernández, Ariel. “Artificial Intelligence Teaches Drugs to Target Proteins by Tackling the Induced Folding Problem.” Molecular pharmaceutics 17, no. 8 (2020): 2761–2767. Somers, James. “The Pastry A.I.. That Learned to Fight Cancer.” The New Yorker, The New Yorker, 18 Mar. 2021, https://www.newyorker.com/tech/annalsof-technology/the-pastry-ai-that-learned-to-fight-cancer. Hutson, Matthew. “Even Artificial Intelligence Can Acquire Biases Against Race and Gender.” Science (American Association for the Advancement of Science) (2017). Sutko, Daniel M. “Theorizing Femininity in Artificial Intelligence: a Framework for Undoing Technology’s Gender Troubles.” Cultural studies (London, England) 34, no. 4 (2020): 567–592. Abdurrahim, Salem Hamed, Salina Abdul Samad, and Aqilah Baseri Huddin. “Review on the Effects of Age, Gender, and Race Demographics on Automatic Face Recognition.” The Visual computer 34, no. 11 (2017): 1617–1630. Toderici, George, Sean M O’Malley, George Passalis, Theoharis Theoharis, and Ioannis A Kakadiaris. “Ethnicity- and Gender-Based Subject Retrieval Using 3D Face-Recognition Techniques.” International journal of computer vision 89, no. 2-3 (2010): 382–391. Friedrich, S., Antes, G., Behr, S. et al. Is there a role for statistics in artificial intelligence?. Adv Data Anal Classif (2021). https://doi.org/10.1007/s11634-02100455-6 Wang, Zeyu, and Ravi S. Srinivasan. “A Review of Artificial Intelligence Based Building Energy Use Prediction: Contrasting the Capabilities of Single and Ensemble Prediction Models.” Renewable and Sustainable Energy Reviews, Pergamon, 10 Nov. 2016, https://www.sciencedirect.com/science/article/pii/S1364032116307420?casa_toke n=dUPoIegnzJAAAAAA%3AuC4NsKvCSBc97bOMySpUtVjtl3pmsRCsf31sEw zzFP1AelcSlU7PAjT0rV3h6vHbV6VbjSoD.