Last edited on October 14, 2024
Terminology Glossary
A
AI (Artificial Intelligence). AI involves the replication of human-like intelligence processes using computer systems. This encompasses tasks such as learning, reasoning, problem-solving, and making decisions in a way that mimics human cognitive abilities. In healthcare, AI is used for diagnosis, treatment planning, and medical research. [1]
Algorithm. An algorithm is a structured set of instructions used by artificial intelligence systems to perform specific tasks or solve complex problems. In medicine, algorithms can be used for tasks like analyzing medical images or predicting patient outcomes. [2]
AI Ethics. AI ethics pertain to the ethical considerations and responsibilities that AI stakeholders, such as developers, engineers, and policymakers and medical professionals, must address to ensure the responsible development and use of AI technology in healthcare. This involves establishing systems and principles to promote safety, fairness, and patient privacy in AI applications. [3]
Artificial General Intelligence (AGI): A concept suggesting a more advanced version of AI than we know today, one that can perform tasks much better than humans while also teaching and advancing its own capabilities. While not yet realized, AGI could potentially revolutionize medical research and treatment. [4]
Autonomous Agents: AI models that have the capabilities, programming, and other tools to accomplish specific tasks independently. In healthcare, this could include AI-driven diagnostic systems or robotic surgical assistants. [5]
AI-Assisted Surgery: The use of AI technologies to enhance surgical procedures, including preoperative planning, intraoperative guidance, and postoperative care. [6]
AI in Drug Discovery: The application of AI techniques to accelerate the process of identifying, designing, and testing new pharmaceutical compounds. [7]
AI-Powered Health Monitoring: The use of AI algorithms to analyze data from wearable devices and other sensors to monitor patient health and detect potential issues early. [8]
B
Bias (in AI). A systemic prejudice built into algorithms or data that can lead to unfair or discriminatory outcomes. In medicine, this could result in disparities in diagnosis or treatment recommendations for different patient populations. [9]
Big data. Extremely large and complex datasets that are difficult to process with traditional methods. In healthcare, this might include electronic health records, genomic data, and medical imaging data. [10]
Biomedical Informatics. The application of information technology and computational methods to solve problems in medicine and healthcare. [11]
BioNLP (Biomedical Natural Language Processing). A subfield of natural language processing specializing in processing biomedical text data, such as medical literature, clinical notes, and patient records. [12]
Bioinformatics: The application of computational techniques to analyze and interpret biological data, particularly in the fields of molecular biology and genetics. [13]
C
ChatGPT. ChatGPT is a chatbot developed by OpenAI that gained considerable attention for its ability to generate human-like text responses. While not specifically designed for medical use, it has implications for medical education and patient communication. [14]
Cognitive computing. Another term for artificial intelligence, emphasizing systems that can learn, reason, and solve problems in ways similar to human cognition. In medicine, cognitive computing systems can assist in complex diagnostic processes. [15]
Computer-Aided Diagnosis (CAD): The use of AI and computer vision techniques to assist medical professionals in interpreting medical images and making diagnoses. [16]
Clinical Decision Support Systems (CDSS): AI-powered tools that provide clinicians with patient-specific information and evidence-based recommendations to enhance decision-making in patient care. [17]
Convolutional Neural Networks (CNNs): A type of deep learning algorithm particularly effective in image analysis, widely used in medical imaging for tasks like tumor detection or organ segmentation. [18]
D
Data Augmentation: Remixing existing data or adding a more diverse set of data to train an AI. In medical AI, this can be used to expand limited datasets or create more representative training data. [19]
Data Mining: The process of systematically extracting valuable information and identifying patterns from large and complex datasets. In medicine, this can be used to uncover insights from patient records or research data. [20]
Deep Learning: A subset of machine learning that emulates human knowledge acquisition using neural networks with multiple layers. In medicine, it's particularly useful for tasks like image analysis in radiology or pathology. [21]
Digital Pathology: The use of AI in analyzing digitized pathology slides, enhancing the accuracy and efficiency of disease diagnosis. [22]
Digital Twins: Virtual representations of physical entities (like organs or entire physiological systems) that can be used to simulate and predict outcomes in personalized medicine. [23]
E
Explainable AI (XAI): Techniques that aim to make AI models more transparent and interpretable for humans. This is crucial in medicine to understand how AI arrives at diagnoses or treatment recommendations. [24]
Electronic Health Records (EHR) Analytics: The application of AI and machine learning techniques to analyze and derive insights from electronic health records. [25]
Ensemble Learning: A machine learning technique that combines multiple models to improve prediction accuracy, often used in medical diagnosis and prognosis. [26]
F
Federated Learning: A machine learning technique that trains an algorithm across multiple decentralized devices or servers holding local data samples, without exchanging them. This is particularly useful in healthcare for maintaining patient privacy while leveraging data from multiple institutions. [27]
Feature Engineering: The process of selecting and transforming variables when creating a predictive model. In medical AI, this involves identifying the most relevant clinical features for a given task. [28]
G
Generative AI: AI technology that creates content by learning patterns from large datasets. In medicine, this could be used to generate synthetic medical data for research or training purposes. [29]
Genomics AI: The application of AI techniques to analyze and interpret genomic data, aiding in personalized medicine and genetic research. [30]
GPU Acceleration: The use of graphics processing units to speed up AI computations, crucial for processing large medical datasets and complex AI models. [31]
H
Human-in-the-loop (HITL): A system where humans and machines work together to make decisions. This is particularly relevant in clinical decision support systems, where AI assists but doesn't replace human medical judgment. [32]
Healthcare Chatbots: AI-powered conversational agents designed to interact with patients, provide health information, and assist with basic medical queries. [33]
I
Internet of Medical Things (IoMT): The network of medical devices and applications that collect and share health data, often analyzed by AI systems to improve patient care and health outcomes. [34]
Image Segmentation: An AI technique used to partition medical images into multiple segments or objects, crucial for tasks like tumor boundary detection or organ volume measurement. [35]
Intelligent Character Recognition (ICR): An advanced form of Optical Character Recognition (OCR) that uses AI to recognize and digitize handwritten text in medical records. [36]
K
K-Nearest Neighbors (KNN): A machine learning algorithm used for classification and regression, applied in medical diagnosis to find similar patient cases. [37]
L
Large Language Model (LLM): Sophisticated machine learning algorithms capable of understanding, summarizing, generating, and predicting textual content. In medicine, LLMs can be used to analyze medical literature or assist in clinical documentation. [38]
Long Short-Term Memory (LSTM) Networks: A type of recurrent neural network capable of learning long-term dependencies, useful in analyzing time-series medical data like ECG signals. [39]
M
Machine Learning: A subset of AI that enables software applications to improve their predictive accuracy by autonomously learning from data. In healthcare, it's used for tasks like predicting disease progression or patient outcomes. [40]
Medical Imaging AI: The use of AI techniques to analyze and interpret medical images such as X-rays, CT scans, and MRIs, aiding in diagnosis and treatment planning. [41]
Multi-modal Learning: AI systems that can process and integrate multiple types of data (e.g., images, text, and numerical data) to make more comprehensive medical assessments. [42]
N
Natural Language Processing (NLP): A subfield of AI that focuses on understanding and generating human language. In healthcare, NLP is used to extract information from clinical notes and medical literature. [43]
Neural Networks: A type of machine learning model inspired by the structure and function of the human brain, used in various medical AI applications. [44]
Neural Style Transfer: An AI technique that can apply the style of one image to the content of another, potentially useful in medical imaging for standardizing image appearance across different machines or protocols. [45]
O
Optical Character Recognition (OCR): A technology that uses AI to convert different types of documents, such as scanned paper documents, PDF files, or images, into editable and searchable data. In healthcare, OCR can be used to digitize paper medical records. [46]
P
Precision Medicine: A medical approach that tailors treatment to individual patients based on their genetic, molecular, and environmental factors. AI plays a crucial role in analyzing the complex data involved in precision medicine. [47]
Predictive Analytics: The use of data to predict future outcomes. In healthcare, this can be used to forecast patient risks, disease outbreaks, or resource needs. [48]
Population Health Management: The use of AI to analyze large sets of patient data to identify trends and make predictions about health outcomes for specific populations. [49]
R
Reinforcement Learning: A type of machine learning where an AI agent learns to make decisions by taking actions in an environment to maximize a reward. In healthcare, this could be used to optimize treatment plans or drug dosing. [50]
Responsible AI: The ethical and trustworthy development, implementation, and use of AI systems in healthcare, focusing on positive societal impact while avoiding harmful consequences and fostering trust among patients and healthcare providers. [51]
Robotics in Healthcare: The use of AI-powered robots in medical settings, from surgical assistance to patient care and rehabilitation. [52]
Radiomics: The extraction of large amounts of features from radiographic medical images using data-characterization algorithms. [53]
S
Supervised Learning: A type of machine learning where the algorithm is trained on labeled data. In medicine, this could involve training an AI to recognize specific diseases in medical images. [54]
Support Vector Machines (SVM): A machine learning algorithm used for classification and regression analysis, applied in medical diagnosis and prognosis. [55]
Synthetic Data Generation: The creation of artificial data that mimics the statistical properties of real data, used to augment medical datasets while preserving patient privacy. [56]
T
Telemedicine AI: The use of AI to enhance remote healthcare services, including symptom checking, triage, and follow-up care. [57]
Transfer Learning: A machine learning method where a model developed for one task is reused as the starting point for a model on a second task. In medical AI, this can be useful for adapting models to new but related medical tasks with limited data. [58]
Text Mining: The process of deriving high-quality information from text, often used to extract insights from medical literature and clinical notes. [59]
U
Unsupervised Learning: A type of machine learning where the algorithm is trained on unlabeled data. In healthcare, this could be used to discover unknown patterns in patient data. [60]
U-Net: A convolutional neural network architecture commonly used for biomedical image segmentation tasks. [61]
V
Virtual Health Assistants: AI-powered digital assistants that can provide health information, reminders, and basic medical advice to patients. [62]
Voice Recognition in Healthcare: The use of AI to convert spoken words into text, useful for dictation in electronic health records or voice-controlled medical devices. [63]
W
Wearable AI: AI algorithms embedded in wearable devices to analyze health data in real-time and provide personalized health insights and recommendations. [64]
References
[1] Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke and Vascular Neurology 2017;2:e000101.
[2] Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2019;380(14):1347-1358.
[3] Char DS, Shah NH, Magnus D. Implementing Machine Learning in Health Care - Addressing Ethical Challenges. N Engl J Med. 2018;378(11):981-983.
[4] Goertzel B, Pennachin C. Artificial General Intelligence. Springer, Berlin, Heidelberg, 2007.
[5] Yang GZ, Cambias J, Cleary K, et al. Medical robotics-Regulatory, ethical, and legal considerations for increasing levels of autonomy. Sci Robot. 2017;2(4):8638.
[6] Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial Intelligence in Surgery: Promises and Perils. Ann Surg. 2018;268(1):70-76.
[7] Vamathevan J, Clark D, Czodrowski P, et al. Applications of machine learning in drug discovery and development. Nat Rev Drug Discov. 2019;18(6):463-477.
[8] Majumder S, Mondal T, Deen MJ. Wearable Sensors for Remote Health Monitoring. Sensors (Basel). 2017;17(1):130.
[9] Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data. JAMA Intern Med. 2018;178(11):1544-1547.
[10] Krumholz HM. Big Data And New Knowledge In Medicine: The Thinking, Training, And Tools Needed For A Learning Health System. Health Aff (Millwood). 2014;33(7):1163-1170.
[11] Kulikowski CA, Shortliffe EH, Currie LM, et al. AMIA Board white paper: definition of biomedical informatics and specification of core competencies for graduate education in the discipline. J Am Med Inform Assoc. 2012;19(6):931-938.
[12] Demner-Fushman D, Chapman WW, McDonald CJ. What can natural language processing do for clinical decision support? J Biomed Inform. 2009;42(5):760-772.
[13] Luscombe NM, Greenbaum D, Gerstein M. What is bioinformatics? A proposed definition and overview of the field. Methods Inf Med. 2001;40(4):346-358.
[14] Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models. PLOS Digital Health. 2023;2(2):e0000198.
[15] Chen Y, Argentinis JE, Weber G. IBM Watson: How Cognitive Computing Can Be Applied to Big Data Challenges in Life Sciences Research. Clin Ther. 2016;38(4):688-701.
[16] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
[17] Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. NPJ Digit Med. 2020;3:17.
[18] Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9(4):611-629.
[19] Shorten C, Khoshgoftaar TM. A survey on Image Data Augmentation for Deep Learning. J Big Data. 2019;6:60.
[20] Cios KJ, Moore GW. Uniqueness of medical data mining. Artif Intell Med. 2002;26(1-2):1-24.
[21] Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29.
[22] Niazi MKK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. Lancet Oncol. 2019;20(5):e253-e261.
[23] Bruynseels K, Santoni de Sio F, van den Hoven J. Digital Twins in Health Care: Ethical Implications of an Emerging Engineering Paradigm. Front Genet. 2018;9:31.
[24] Holzinger A, Biemann C, Pattichis CS, Kell DB. What do we need to build explainable AI systems for the medical domain? arXiv:1712.09923. 2017.
[25] Goldstein BA, Navar AM, Pencina MJ, Ioannidis JP. Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review. J Am Med Inform Assoc. 2017;24(1):198-208.
[26] Polikar R. Ensemble learning. In: Zhang C, Ma Y, eds. Ensemble Machine Learning. Springer; 2012:1-34.
[27] Rieke N, Hancox J, Li W, et al. The future of digital health with federated learning. NPJ Digit Med. 2020;3:119.
[28] Kuhn M, Johnson K. Applied Predictive Modeling. New York: Springer; 2013.
[29] Dash S, Gunluk O, Wei D. Boolean Decision Rules via Column Generation. Advances in Neural Information Processing Systems. 2018;31:4655-4665.
[30] Zou J, Huss M, Abid A, Mohammadi P, Torkamani A, Telenti A. A primer on deep learning in genomics. Nat Genet. 2019;51(1):12-18.
[31] Eklund A, Dufort P, Forsberg D, LaConte SM. Medical image processing on the GPU - Past, present and future. Med Image Anal. 2013;17(8):1073-1094.
[32] Holzinger A. Interactive machine learning for health informatics: when do we need the human-in-the-loop? Brain Inform. 2016;3(2):119-131.