IE-RSME Workshop on Applied Mathematics: AI challenges in Health Care

Raquel Iniesta

Senior Lecturer in Statistical Learning for Precision Medicine, Kings College London, UK

https://www.linkedin.com/in/raqueliniesta/

Raquel is a Senior Lecturer in Statistical Learning for Precision Medicine and leads the Fair Modelling and TDA Lab at the Department of Biostatistics and Health Informatics. With a strong foundation in mathematics, statistics, and machine learning, her research focuses on developing innovative models for precision medicine, particularly in personalizing treatments for depression and hypertension. An experienced lecturer, Raquel teaches both introductory and advanced courses on statistics and machine learning for MSc and PhD students, both in the UK and internationally. Her current work not only involves advancing machine learning models for healthcare but also emphasizes ethical practices in AI, aiming to ensure transparency, fairness, and non-discrimination in medical AI applications. 



Talk title: Why should we care about ethics in medical AI?

 

Abstract: In a society heavily impacted by technology advances, and most particularly by AI emerging on every single sector, we are committed with understanding the current but also the future impacts of using AI for many vital and significant tasks in healthcare, like prescribing a drug or diagnosing a patent with a sever disease. Although AI is still timidly adopted for clinical routine care, it is expected to be gaining grounds quickly. Therefore, this talk is setting up the fundamentals that can assure an AI in medicine that respects the human integrity; that medical doctors will be respected, that patients will be aware on their rights, that developers will be responsible of their tools. On that way we will consider the bigger picture, including the long-term impacts of using AI in healthcare and its possible value to society together with the potential ethical risks for the humanity. We will discuss a framework to society that can contribute to translate ethical principles in human actions intended to preserve a patient centered AI-assisted medical care, that includes an ethical and conscious development of tools, and an ethical integration and deployment of AI systems for healthcare.

Iñigo Urteaga

Ikerbasque Research Fellow, Basque Center for Applied Mathematics

https://www.linkedin.com/in/i%C3%B1igo-urteaga-222b755/

Iñigo is a tenure-track Ikerbasque Research Fellow at the Basque Center for Applied Mathematics (BCAM), specializing in statistical machine learning, computational Bayesian statistics, and sequential decision-making processes. His work focuses on developing algorithms and statistical models for extracting information from data, enhancing computer systems' ability to perform various analytical tasks. Previously, he was an Associate Research Scientist at Columbia University, where he collaborated on machine learning projects for healthcare data. He earned his Ph.D. in Electrical Engineering from Stony Brook University, with a dissertation on Sequential Monte Carlo methods. He holds a degree in telecommunications engineering from the UPV/EHU Faculty of Engineering in Bilbao, Spain. 



Talk title: Probabilistic Machine learning for predictive models in healthcare: a use case on mobile health data

Abstract: Probabilistic machine learning (ML) can enable robust and personalized predictive models in healthcare. In this talk, I will present our research on generative and probabilistic ML to accommodate the idiosyncrasies of mobile health data, such as inconsistent self-tracking adherence. As a case study, I will discuss our statistical modeling approach for a better understanding of the menstrual cycle and its patterns, based on mobile health self-tracked data. I will showcase how probabilistic ML enables disentangling menstruation patterns from self-tracking adherence, to provide accurate, well-calibrated, and informative predictions of interest. 

Carmen Lancho

Assistant Professor at Universidad Rey Juan Carlos

https://www.linkedin.com/in/carmen-lancho-mart%C3%ADn-b2a61a122/

Carmen Lancho Martín is an Assistant Professor in the Department of Computer Science and Statistics at Universidad Rey Juan Carlos, where she completed her PhD thesis “A triple perspective on complexity measures for supervised classification problems” under the guidance of Dr. Isaac Martín de Diego and Dr. Javier Moguerza.  



Title: Success stories from data science in health 

Abstract: In this talk the DSLAB team show how data science is revolutionizing healthcare by enabling innovative solutions for diagnosis, treatment, and prevention. The talk will feature several projects, including: 

• SABERMED: A tool for assessing the reputation of digital content on the web, using data science, big data architectures, and artificial intelligence to detect fraudulent content.


• VR-CARDIO: A holographic and non-invasive visualization system to measure electrical signals produced by the heart, enabling early prevention and diagnosis of heart health issues. 


• SMART BEDS: Automatic bed assistance based on continuous optimization, utilizing intelligent algorithms to dynamically learn from sleep sessions and optimize mattress configurations to enhance sleep quality. 


• RNFC: A predictive model for the ability to walk one month after suffering a hip fracture. 


• ATTRv: Application of artificial intelligence to study predictors of progression in hereditary transthyretin amyloidosis. 

Víctor Aceña

Assistant Professor at Universidad Rey Juan Carlos

https://www.linkedin.com/in/victoracegil/

Victor Aceña Gil is an Assistant Professor in the Department of Computer Science and Statistics at Universidad Rey Juan Carlos. Victor completed his PhD thesis “Sampling Methods for Performance Improvement in Machine Learning Classifiers” under the supervision of Dr. Isaac Martín de Diego and Dr. Javier Moguerza. 



Title: Success stories from data science in health 

Abstract: In this talk the DSLAB team show how data science is revolutionizing healthcare by enabling innovative solutions for diagnosis, treatment, and prevention. The talk will feature several projects, including: 

• SABERMED: A tool for assessing the reputation of digital content on the web, using data science, big data architectures, and artificial intelligence to detect fraudulent content.


• VR-CARDIO: A holographic and non-invasive visualization system to measure electrical signals produced by the heart, enabling early prevention and diagnosis of heart health issues. 


• SMART BEDS: Automatic bed assistance based on continuous optimization, utilizing intelligent algorithms to dynamically learn from sleep sessions and optimize mattress configurations to enhance sleep quality. 


• RNFC: A predictive model for the ability to walk one month after suffering a hip fracture. 


• ATTRv: Application of artificial intelligence to study predictors of progression in hereditary transthyretin amyloidosis. 

Antonio García

Professor at IE University (Business School)

https://www.linkedin.com/in/antonio-garcia-romero-6a299635

Antonio is a Full-time Operations and Business Analytics Professor at IE Business School. He holds a Ph.D. in Economics from the Autonomous University of Madrid, an MSc. in Applied Economics from U. Carlos III, and a BSc. in Theoretical Physics from U. Granada. Antonio has an extensive career in academia, public administration, and consulting. Before joining IE Business School, Antonio spent ten years in the Healthcare sector. He served as Head of Health Innovation Policy in the Madrid Healthcare system. He led various projects, such as developing KPIs to measure hospital innovation, measuring the societal returns of medical research, and improving the health-related start-up ecosystem in the Region of Madrid. Recently, Antonio worked on a project to enhance the efficiency of surgical facilities in a group of private hospitals in Spain. This work was awarded the E-NNOVA 2022 Prize in the Big Data and Artificial Intelligence category. Currently, he is leading the "Disrupting Healthcare" project, which aims to improve the healthcare sector using innovative solutions. The project includes an international collaboration with the Stevens Institute of Technology (USA) to optimize pay-for-performance mechanisms in the Patient Protection and Affordable Care Act (Obamacare). Antonio also serves as a Board Member of Vulpix, a MedTech Start-up.

Dae-Jin Lee

Assistant Professor at IE University (School of Science and Technology)

https://www.linkedin.com/in/idaejin/

Dae-Jin is a full-time assistant professor at IE University's School of Science and Technology in Madrid and Chief Scientist Officer of the Health and Data lab of the Impact Accelerator. Before this, I was a researcher and leader of the Applied Statistics Group at BCAM, the Basque Center for Applied Mathematics, and the scientific coordinator of BCAM's Knowledge Transfer Unit in Data Science. I earned my PhD in Statistics from Universidad Carlos III de Madrid in 2010, followed by a postdoctoral position at CSIRO-Data61 in Melbourne, Australia, until 2014. 

My research focuses on statistical modeling and computational statistics, particularly in biomedical applications and environmental sciences. Biostatistics, longitudinal data, growth curves modelling, health related quality of life data analysis, clinical prediction models, and survival analysis.