- Using Machine Learning on mHealth-based Data Sources
- End-user Development of Mobile AI-based Clinical Apps using Punya (PUNYA2022)
- Machine learning for complex medical temporal sequences
- Data Science for Starters: How to Train and be Trained
- 13th International Workshop on Knowledge Representation for Health Care (KR4HC 2022) (cancelled)
- 1st Workshop on Artificial Intelligence in Nursing: Advances, Methods and Path Forward (AINurse22)
In this tutorial, at first, participants will be provided with relevant aspects and issues of the mobile application engineering side (e.g., offline vs online features), the created data sources (e.g., data collection procedure), and relevant related technical (e.g., proper APIs) as well as medical aspects (e.g., regulatory aspects) of mHealth apps. In the second part of the tutorial, the participants will get practical insights into conducted machine learning analyses of long-running developed mHealth apps. This includes a detailed discussion with tangible results on the opportunities as well as the shortcomings when using machine learning on mHealth data.
Main topics: In-situ data collection, mobile health (mHealth), mHealth mobile application engineering aspects, regulatory and interdisciplinary aspects, machine learning
Intended audience: People with an interest on machine learning analyses on mHealth data
Pre-requisites:Of note, an introduction in relevant parts of mobile health will be provided, while an introduction in relevant machine learning concepts (e.g., outcome metrics) or basic data science aspects (e.g., CRISP-DM, statistical tests) will not be provided. Therefore, a basic foundation in machine learning and statistics would be beneficial, but are not exclusion criteria.
Outcomes: Insights into fundamental pros and cons when using machine learning on medical data that was gathered with mobile technology in-situ
This tutorial provides a gentle introduction for both non-technical and technical attendees to develop AI-enabled mobile apps for healthcare and life sciences, using an intuitive and visual online platform called Punya (based on MIT App Inventor). We foresee Punya being utilized for the exploratory development and prototyping of mobile health apps, without requiring specialized development skills and thus reducing the effort and cost involved. Punya features components for Knowledge Representation and Reasoning (KRR) as well as Machine Learning (ML). During the tutorial, the attendees will develop a smart health app outfitted with KRR and ML features.
Main topics: Mobile Health (mHealth), Artificial Intelligence, Self-Management of Chronic Illness, Ecological Momentary Interventions.
Intended audience: People with an interest in mobile health apps, e.g., for self-management of chronic illness, delivery of psychological interventions, or patient education for behavior change.
Pre-requisites: Some knowledge on Semantic Web is a plus but not required. We will provide some light reading material that can be perused by participants before attending. No special setup is required as Punya is an online Web platform.
Outcomes: Attendees will have gained experience with developing mobile health apps outfitted with AI components, including Semantic Web and Machine Learning, using the Punya platform.
This tutorial introduces the concept of learning on medical temporal sequences and elaborates on challenges and learning methods for clinical data and for mHealth data.
Main topics: patient pathways, Ecological Momentary Assessments (EMA), chronic diseases, temporal prediction, time series classification, counterfactuals, missingness, temporal gaps.
Intended audience: AIME participants who work on chronic conditions, are familiar with basic concepts of learning on static medical data, and are interested in exploiting temporal aspects.
Pre-requisites: Familiarity with basics of machine learning methods. Familiarity with types of medical data collections would be good but is not required, we will introduce basic concepts at the beginning.
Outcomes: Attendees will acquire familiarity with ways of preparing temporal medical data, identifiying methods for analysing them and evaluating the solutions from the medical perspective and the machine learning perspective.
Overview: Given the right tool, it may take only a few hours to familiarize anyone with data science. Data science, machine learning, and artificial intelligence are drivers of change in all fields of science, including biomedicine. But only a few professionals understand the essential concepts behind data science, and even fewer engage in building models using their data. The tutorial will explain how anybody can learn about the crucial mechanics behind data science and machine learning in the workshops that take only a few hours. After the tutorial, it should be evident that after a short training of this kind, the professionals can gain enough intuition about data science to recognize opportunities that this field can offer and actively engage in data science projects. Besides good mentors and an encouraging working environment, the right tool is critical for such training.
Main topics: data science, explorative data analysis, machine learning, data visualization, AI teaching
Intended audience: We have designed this tutorial for both the teachers and trainees. We will present both the training steps a hands-on workshop could include and, as a demonstration, go through the actual training.
Prerequisites: None. The tutorial will be hands-on. We encourage the attendees to bring their laptops, and before attending the tutorial, install Orange (https://orangedatamining.com) and perhaps check out a few intro videos at http://youtube.com/orangedatamining.
Outcomes: You will learn about the workflow-based construction of analytical pipelines, where we will combine interactive visualizations and machine learning. We will show that this combination can be the key to the tool's simplicity, effective communication of results, and flexibility to adopt analytics to any data type and problem domain. We will illustrate the use of a tool, Orange, that supports such an interactive interface with practical cases and explain clustering, model development, data visualization, and analysis of various types of data, including those from gene expressions.
This workshop has been cancelled.
Artificial intelligence (AI) is poised to revolutionize healthcare via data driven solutions to improve patient outcomes. Nurses, the largest sector of healthcare providers internationally, are rapidly adopting AI technologies in their everyday work. Existing nursing AI technologies help nurses to identify patients at risk, assist in prioritizing nursing care, and improve nursing workflows. On the other hand, AI has the potential to introduce unintended consequences, including racial or other biases or erroneous care recommendations. AI technologies are being increasingly applied on data generated by nurses and nurses are becoming one of the largest sectors to use AI in healthcare. This generates an increasing interest in safe, ethical and clinically appropriate use of cutting edge AI technologies in nursing.
This workshop, organized by the Nursing and Artificial Intelligence Leadership (NAIL) Collaborative, will focus on AI in nursing and provide a platform for discussions about the recent advances, cutting edge AI methods, and chart a path forward for nursing AI. These goals will be achieved through a combination of presentation types, including paper presentations, invited talks, panels, demos, and general discussion. Intended workshop participants are individuals involved in developing and applying AI for nursing, including those with clinical (e.g., nursing, medicine), technical (e.g., machine learning, computer/data science) and human factors (e.g., visualization and UI/UX) backgrounds. AIME participants who are focusing on using AI technologies based on nursing data or intended to be used by nurses will benefit from this workshop by learning about current AI applications and cutting-edge methods. The workshop will also chart AI research areas that require further development to advance patient outcomes.
Submission deadline: April 8th, 2022 (via Easychair)
Notification of acceptance: April 18th, 2022
Workshop: June 17th, 2022