Health Tech Lunch 2021

Coming soon...

Health Tech Lunch - 23.11.2021, 12h00-13h30 - Techno-Pôle, Sierre (Room Maïa)

Presentation by David-Zacharie Issom (Researcher & Lecturer, Division of Medical Information Sciences - University Hospitals of Geneva (HUG))

Can patient-led digital innovation reduce health inequalities?

Seeing the miniaturization of biometric sensors, the rise of mobile health technologies and the artificial intelligence revival, David-Z. Issom, patient expert, researcher-lecturer in health informatics and doctor in global health at the University Hospitals of Geneva, sought to answer this question a few years ago. To elucidate it, David conducted several studies in collaboration with prominent actors of Digital health transformation in Nordic countries; the Karolinska Institute in Stockholm, the University of Tromsø, and the Norwegian Centre for E-health Research. To favor the development of solutions able to address the challenges of the 21st century while leaving no one behind, his research targeted populations affected by chronic complex disorders and facing various inequalities (e.g., racial, gender, socioeconomic, geographic, climatic). Who better than people directly affected can encourage the creation of solutions taking into account complex problems, without creating other problems that are likely to affect them?

Title : Empowering people with sickle cell disease through crowdsensing: a patient-led approach

Abstract

Health inequalities have a significant impact on many aspects of society, such as lost productivity, decreased life expectancy, or poor Quality of Life (QoL). Particularly neglected, are the over 25 million people with Sickle cell disease (SCD), a genetic and chronic disease that affects populations who are particularly exposed to various disparities (e.g., access to healthy environment, wealth, racism). This disease kills most affected people before their 5th birthday, and survivors are left-alone to self-manage various precipitating of potentially lethal symptoms and complications. Mobile health apps have shown some potential to support self-management for people with chronic diseases. However, only a minority of patients use such apps for more than a week. As a result, the people who would benefit most from these apps often underuse them. The objective of this thesis was to investigate whether radical patient-centered approaches, namely Patient-Led Research (PLR), could encourage the design, the development and the adoption of apps that would support patient-important self-management needs and patient empowerment. Several studies were conducted with patients using a mixed methods approach, and following this PLR approach. As a demonstrator, a digital companion in the form of a chatbot has been developed and evaluated by different groups of patients, who agreed on the usefulness and usability of the companion. This patient-led approach to innovation allowed to point out various patient-important aspects such as robustness, easy integration in day-to-day life in order to not add any additional burden to already hectic daily self-care practices, health data interoperability and data security. This approach also allowed to emphasize the importance of patients’ voices and experiential knowledge in designing system which take into action various disparities, so they do not increase health inequalities.

Program

  • 12:00 to 12:45 - Talk and Q&A
  • 12:45 to 13:30 - Lunch at the cafeteria (Mikado)

Registration : https://doodle.com/poll/vcr5p5gfz6bth6ii

Health Tech Lunch - 12.10.2021, 12h00-13h30 - Techno-Pôle, Sierre (Room Electra)

Presentation by Gloria Luzzani (Research associate, CCRS at University of Zurich and Adjunct Professor, UCSC (IT))

Bio

Gloria Luzzani is a research associate at the Center of Corporate Social Responsibility (CCRS) at the University of Zurich and Adjunct Professor at Università Cattolica del Sacro Cuore (UCSC, Piacenza – IT). Her work has been focusing on the design of future-oriented wine and food system, by means of careful assessment of sustainable impact, bottom-up approach, and the development and implementation of best practices for a regenerative food and nutrition systems. Her research efforts are tackling the change for a business meaningful contribution to SDGs. She is the Learning & Development manager for the University’s Master program on Food & Beverage: food services management and sustainability (UCSC). She has a wide spectrum of interests ranging from sustainable food production and consumption, sustainability in food services, sustainable development and its implementation.

Title : Sustainable nutrition: challenges for shaping the future diets 

Abstract

Concern about the environmental impact of food has increased among policy makers and consumers. Some consumers are increasingly inclined to switch their consumption patterns for environmental reasons. These choices can be based on beliefs and (mis)perception that are not necessarily grounded in a sound scientific information. Nevertheless, a significant change in dietary patterns could have relevant impact on consumers’ health and a disruptive effect on some food chains. Therefore, a more in-depth analysis of diets impact is needed to provide consumers with detailed and reliable information on the sustainability and the healthiness of different dietary patterns. This analysis should take into account the urgent challenge that the food system is facing: to provide sufficient, safe, nutritious food to a growing population, while reducing its pressure on the ecosystem and human health. Agriculture and food research is striving to build a resilient food system to ensure food safety and accessibility while staying within the ecological carrying capacity of the planet and ensuring decent work and economic development. Growing concern about the environmental burdens of food production has opened up a new area of research interest: sustainable nutrition. Sustainable diets have been defined by FAO as “those diets with low environmental impacts which contribute to food and nutrition security and healthy life for present and future generations… protective and respectful of biodiversity and ecosystems, culturally acceptable, accessible, economically fair and affordable; nutritionally adequate, safe and healthy, while” able to optimize “natural and human resources”. Therefore, sustainable nutrition would have to take into account all environmental dimensions of food production and consumption and relate them to local and cultural diet patterns. In such contest, an interdisciplinary approach is needed in order to assess, improve and communicate sustainability of diet. During the speech we are going to take a deep dive into the carbon footprint of different dietary pattern, the relevance of multi-indicators in describing diets environmental impact, their relation to health impact and the way forward to a more precise sustainable diets, that also take into account health status of consumers and patients. 

Content

  • Sustainable nutrition and its link with the sustainability of food system 
  • Healthy nutrition and healthy diets
  • Assessment of diets sustainability: indicators and challenges
  • Nutritional quality and environmental impact
  • The way forward: optimizing sustainable diets to consumers and patient needs.

Program

  • 12:00 to 12:45 - Talk and Q&A
  • 12:45 to 13:30 - Lunch at the cafeteria

Registration : https://doodle.com/poll/hezvmesye4aped9v

Health Tech Lunch - 28.09.2021, 12h00-13h30 - Techno-Pôle, Sierre (Room Maïa)

Presentation by Suraj Srinivas (Recently completed his Ph.D. at Idiap Research Institute and EPFL where he worked with Prof. Francois Fleuret)

Title : Pitfalls of Saliency Map Interpretation in Deep Neural Networks 

Abstract

A popular method of interpreting neural networks is to use saliency map representations, which assign importance scores to each input feature of the model. In this talk, I will discuss two of our recent works which expose pitfalls in these methods. First, we will discuss how existing saliency maps cannot satisfy two desirable properties simultaneously, and we propose the “full-gradient representation” which avoids these problems. Based on this representation, we propose an approximate saliency method called FullGrad which we find explains model behaviour better than competing methods in literature. Second, we find that a popular saliency map method, the input-gradients, can be arbitrarily structured due to the shift-invariance of softmax. We investigate why standard neural network models have input-gradients with interpretable structure even when this is unnecessary, and we find that standard models have an implicit generative modeling component, which is responsible for this behaviour. Overall, our works show that interpreting black-box models using off-the-shelf interpretability methods can be risky and they must be used with caution.

Program

  • 12:00 to 12:45 - Talk and Q&A
  • 12:45 to 13:30 - Lunch at the cafeteria

Registration : https://doodle.com/poll/ydts7z3sembm834q?utm_source=poll&utm_medium=link

Health Tech Lunch - 17.06.2021, 12h00-13h00 - Haute école de travail social, Corinna Bille (salle 501), Sierre & Online

Presentation by David Pichonnaz (Professeur HES assistant, Institut Travail Social, HES-SO Valais-Wallis)

Bio

David Pichonnaz est sociologue des groupes professionnels et du travail. Ses recherches portent sur les métiers relationnels du service public, en particulier le travail social, policier et soignant, ainsi que sur les parcours de socialisation, qu’il étudie en s’appuyant sur l’analyse dispositionnelle.

Title : Vivre avec la mucoviscidose et s’insérer professionnellement : l’impact des ressources familiales et du rapport à la maladie 

Abstract

Cette présentation rend compte des premiers résultats d’une étude en cours, basée sur des entretiens semi-directifs approfondis, conduits avec 25 personnes vivant avec la mucoviscidose, en Suisse. La recherche part du constat, établi par la littérature, que les modalités des parcours de formation et d’insertion professionnelles de ces individus ne sont pas significativement corrélés avec la gravité de la maladie, ni avec l’étendue ou la difficulté des traitements. Pourtant, les travaux existants ont négligé la prise en compte des inégalités sociales, de même que du vécu subjectif de la maladie. Tout incite à penser, pourtant, que l’insertion professionnelle doit être étudiée, pour cette population particulière, en tenant compte de facteurs sociaux : d’une part, les ressources familiales disponibles et leur transmission (ou non), et, d’autre part, le rapport à la maladie (davantage que les symptômes objectivement mesurés).

Program

  • 12h00-12h45 : Talk
  • 12h45-13h00 : Q&A

Health Tech Lunch - 01.06.2021, 10h30-12h00 - Campus Energypolis/HEI (room 21N105) & Online

Presentation by Bruno Correia (Tenure Track Assistant Professor, EPFL, Laboratory of Protein Design & Immunoengineering)

Bio

Throughout my PhD and postdoctoral studies I was trained in world-renowned laboratories and institutions in the United States of America (University of Washington and The Scripps Research Institute). Very early in my scientific career I found out my fascination about protein structure and function. My PhD studies evolved in the direction of immunogen design and vaccine engineering which sparked my interest in the many needs and opportunities in vaccinology and translational research. My efforts resulted in an enlightening piece of work where for the first time, computationally designed immunogens elicited potent neutralizing antibodies. During my postdoctoral studies I joined a chemical biology laboratory at the Scripps Research Institute. In this stage I developed novel chemoproteomics methods for the identification of protein-small molecule interaction sites in complex proteomes. In March 2015, I joined the École Polytechnique Fédérale de Lausanne (EPFL) – Switzerland as a tenure track assistant professor. The focus of my research group is to develop computational tools for protein design with particular emphasis in applying these strategies to immunoengineering (e.g. vaccine and cancer immunotherapy). The activities in my laboratory focus on computational design methods development and experimental characterization of the designed proteins. Our laboratory has been awarded with 2 prestigious research grants from the European Research Council. Lastly, I have been awarded the prize for best teacher of Life sciences in 2019.

Title : Expanding the landscape of functional proteins by computational design 

Abstract

Finely orchestrated protein activities are at the heart of the most fundamental cellular processes. The rational and structure-based design of novel functional proteins holds the promise to revolutionize many important aspects in biology, medicine and biotechnology. Computational protein design has led the way in rational protein engineering, however many of the designed proteins have been solely focused on structural accuracy and are completely impaired of function.

I will present my group’s efforts on the development of novel computational approaches to predict and design protein function. Specifically, I will describe a new methodological framework to learn surface patterns displayed in protein structures that can be used to decipher their interactions with other molecules. I will also present a computational strategy to explore de novo protein topologies, aiming to solve prevalent problems in protein design that relate to the lack of optimal structural templates for the design of function. By expanding beyond the known protein structural space, our approaches present new paradigms for the rational design of functional proteins. I will showcase important applications for our computationally designed proteins in the domains of vaccine design, T cell-based therapies, biosensors and synthetic biology.

Program

  • 10h30-12h00 : Talk & Q&A
  • 12h00-13h00 : Lunch at Restaurant la Ruche

Health Tech Lunch - 20.04.2021, 9h45 - Online

Presentation by Stéphane Baeriswyl (Université de Berne)

Title : Design and X-ray structure determination of antimicrobial peptides

Bio

I am a motivated chemist with multidisciplinary experience. I have good knowledge in peptide synthesis and protein production & purification. My areas of expertise include microbiology (BSL2), analytics (LC/MS, NMR), microscopy and computational modeling as well. I have a PhD degree in chemistry.

Program

  • 09:45-11:00 : Talk & Q&A

Health Tech Lunch - 25.01.2021, 16h00 - Online

Presentation by Iam Palatnik (Pontifical Catholic University of Rio de Janeiro, Brazil)

Title : LIME in Medical Image Classification

Abstract

An application of Local Interpretable Model Agnostic Explanations (LIME) is described for two case studies: Metastases and Malaria classification. Some of the key challenges of using LIME for this purpose - most notably the instability of explanations - are discussed, as well as some potential solutions. Namely, a genetic algorithm based solution called EvEx, where explanations are evolved as the average of a Pareto Front, and Squaregrid, a parameterless rough approximation. The results seem to show that EvEx finds more consistent explanations for regions of high explanatory weight, and that Squaregrid could be a viable way to diminish the need for segmentation parameter fine tuning.

Program

  • 16:00-16:45 : talk
  • 16:45-17:00 : Q&A