Health data science

Head: Alessandro Puiatti

Health Data Science is the interdisciplinary intersection of (bio)statistics, computer science, and health. It can be defined as the science and art of generating data-driven solutions, through comprehension of complex real-world health problems, employing critical thinking and analytics to derive knowledge from (big) data. In fact, the booming supply of medical information from various sources has the potential to disclose new insights and generate new knowledge in the health domain. Consequently, it could help in reshaping the healthcare delivery system, reducing its costs, improving patient outcomes, and helping in the provision of value-based care. All of these goals could be achieved using techniques of big data analytics, machine learnings, data mining, natural language processing, medical statistics, only to mention a few.

Research topics

  • Applying machine learnings, deep neural networks, and image analysis to understand, describe and anticipate the insurgence of human diseases
  • developing advanced statistics algorithms, based on multivariate analysis, sequential evolutionary analysis, and data mining, for clinical diagnoses and application therapies
  • developing new algorithms and architectures for the Internet of Things in the health domain
  • eHealth, mHealth and Personal Health Systems applications
  • Physiological signal processing and big data analytics
  • Reshaping the healthcare systems and services

Specialty areas:

  • BioSignal Processing
  • Digital Health

BioSignal Processing Specialization unit

Contact person: Francesca D. Faraci

Biosignals are usually collected by biomedical sensors and their analysis is used to provide objective information, upon which clinicians can make important decisions. Researchers are discovering new ways to process these signals using a variety of mathematical techniques and innovative algorithms. Signals can be processed by software to provide physicians with real-time data and greater insights to aid in clinical assessments. By using more sophisticated means to analyze what our bodies are saying, we can potentially determine a person health through more noninvasive measures.
Latest trends in the field show a renovated interest on the application of advanced statistical analysis, artificial intelligence techniques, integrated into scientific software and mobile application.
The unit complement ISIN activity in UI development, web graphic interfaces, cloud computing, data security and so on.

Areas of expertise:

  • Data enhancement
  • Data analysis
  • Data exploitation 

Recent research projects:
Sleep Physician Assistant System (SPAS) (Eurostar 2018 – 2021)
SPAS research project aims to provide a concrete solution to fill existing gaps and better support physicians in the characterization phase of sleep signals. The project intends to develop a flexible platform able to assist the physician in a pragmatic and effective way, freeing him or her from tedious work and making it possible to focus on more complex activities. Through a series of mechanisms based on machine learning techniques, the platform operates like a "silent apprentice" absorbing information and acquiring the skills of the physician, partially replacing him/her in the data processing and evaluation phase.

AutoPlay - Differential Diagnosis, (ABREOC – SUPSI 2019-2022)
AutoPlay-DD project aims at applying the AutoPlay toolkit & system in “Differentiation”. Generally at the age of around two the presence of a neurodevelopmental problems is clear but ASD, speech and language delays and ADHD have overlapping symptoms that make practically impossible to differentiate among these three classes with children so young.

DESyMED (Eurostar 2019-2022)
The System is an innovative system for the treatment of Dry Eye Syndrome. It comprehends an eyewear with ultrasonic nebulizers for creating a constant eyes moisture, sensors to collect wireless eye health status information and a mobile application. Collected information can be shared with the Ophthalmologist. Thanks to a real time continuous monitoring the user will receive a tailored personalized treatment.

Swiss PhD Network of Data Science 2018-2021 
The PhD Network in Data Science is a collaboration between two Swiss universities of applied sciences and Swiss universities. The network aim is to offer students with a master degree (including degrees from a university of applied sciences) the opportunity to obtain a PhD in cooperation between a university of applied sciences and a university.

Digital Health

Contact person: Alessandro Puiatti

The health care domain has been entering in the digital era since many years now, but only recently it started to apply the digitalization of processes and services on a larger scale. An important enabler is the increased availability of all kinds of health-related data. Digital Health is expected to grow in importance in the coming years promising the possibility to enhance the efficiency of healthcare delivery and to make medicine more personalized and precise. In fact, it can empower consumers to make better-informed decisions about their own health and provide new options for facilitating prevention, early diagnosis of life-threatening diseases, and management of chronic conditions outside of traditional care settings.

Areas of expertise:

  • Applied machine learning and deep neural networks;
  • Algorithms and architectures for IoT in the health domain
  • eHealth, mHealth and Personal Health Systems
  • Digital healthcare systems and services

Recent research projects:

  • AutoPlay - (2017-22): An objective and free of context conditioning system for the evaluation of very young children’s ludic development and for early identification and differentiation of Autism from other neurodevelopmental disorders.
  • Frailty (2020): Algorithms for frailty index computation in the management of chronically ill home care patients.
  • SecureMed (2019-2020): Distributed management system for secure patient identification and medications delivery: right patient, right medication, right time.
  • TITAN (2019-20): TrIgger Tools and Algorithms in the management of chronically ill home care patieNts.
  • Sleep, Awake & Move - (2016-2018): Mobile health system for systematic characterization of sleep benefit in Parkinson’s disease
  • IDPlus- (2013-2018): Distributed patient management system for health-care and hospital facilities