Alessandro Masullo

I’m a lecturer at the University of Bristol. My research focuses on Computer Vision, Human Motion Analysis, Multi-Sensory Fusion and Digital Health. I’m passionate about climbing, technology and music production.

Starting from 2021, I’m going to be teaching two units at the University of Bristol, Sensing Technologies for Diagnostics and Monitoring and Digital Health Project.

MSc/PhD - Sensing Technologies for Diagnostics and Monitoring

[from the unit description]
Low-cost, connected, digital technologies are increasingly seen as vital to the understanding, prevention, diagnosis and management of numerous health conditions over months and years in residential settings and in the community. These technologies, such as smartphone apps, wearables, blood glucose monitors – and ever growing Internet of Things (IoT) devices such as smart home systems (e.g. Echo), smart meters and connected appliances – all offer an unprecedented opportunity to characterise a person’s health condition. With the data processed by AI, they will deliver decision support to health and care professionals, predict a patient’s exacerbations, support independent living, deliver behavioural or even pharmaceutical interventions and allow the efficacy of treatments to be monitored. This unit will discuss nascent technologies and solutions for sensing human vital signs and physical behaviour encompassing entire data capture transmission/processing pipelines: from body worn and biosensors to low power wireless networks and energy constraint data processing.

Syllabus

  • Introduction to sensing and biosensing to detect and monitor diseases
  • Characterisation of operation of sensors and biosensors: sensitivity, specificity, clinical range etc.
  • Principles and transduction approaches for biochemical sensors: electrochemical, MEMs, optical etc.
  • Biomarker detection and bio-receptors e.g. antibodies, enzymes, DNA
  • Sensor system development e.g. data capture, sample preparation
  • Physiological measurement e.g. ECG, EMG, EEG;
  • Basic elements of the wireless channel and radio wave propagation.
  • Low Power IoT wireless networks (IEEE 802.15.4, BLE, 6LoWPAN).
  • Reliability in data transmission
  • Efficient signal representation, compression, and ultimately classification/regression tasks.

Intended learning outcomes

On successful completion of this module students will be able to:

  • Critically evaluate and discuss the role of sensors in home diagnostics and monitoring applications
  • Evaluate a range of elements involved in constructing and operating a biosensor, and select and apply the optimum combination for a given application
  • Analyse a diagnostic or monitoring scenario, and devise and evaluate an effective measurement system from sample/signal collection to user interface
  • Explain the challenges of reliable communications over unreliable channels and basic IoT networking standards.
  • Design and prototype algorithms for data analysis of sensory signals such as step counters, classification and regression

MSc - Digital Health Project

[from the unit description]
Students will be assigned to multidisciplinary groups of 4-6 students. Each group follows the same structured project which leads them through a process of product development, including open-ended research challenges requiring an original contribution to knowledge. The theme of the project will be a long term health condition, such as diabetes or asthma.

The groups are facilitated by trained HPTs and have a quantity of specialist academic, NHS and industry consultant time which they can access. It is up to the students to work out the best use of that time.

Each student will have the opportunity to exercise creativity and problem-solving in their own disciplinary area, as their contribution to the group. The final mark is individual but includes a component based on group performance. The project includes workshops on teamwork, reflection on individual/team performance and includes mentoring/observation of team members by the team members themselves.

The project is structured into 8 stages. The group submits deliverables one week after the end of each stage (late submission penalised according to the Faculty’s normal rules). The collated deliverables will form the group’s dissertation.

Intended learning outcomes

Upon successful completion of this unit students will be able to:

  • Identify methodologically appropriate quantitative and qualitative approaches towards addressing project aims and objectives.
  • Analyse the requirements for a digital technology to address a specific human health problem and apply domain knowledge to synthesize a suitable solution.
  • Formulate and undertake a co-design process with a patient group.
  • Solve complex problems as a productive member of a multidisciplinary team.
  • Critically evaluate and effectively communicate their findings in terms of their motivation, methodology, results and in relation to existing work (both in written and verbal form).
  • Reflect on personal strengths and weaknesses in a team environment.
  • Observe, support and mentor others in their own team roles.
  • Apply data analysis and visualisation techniques to analyse a health-related dataset and present the results of the analysis in an actionable format for decision makers.
  • Design a suitable evaluation approach for a new health technology, in accordance with formal regulatory requirements and best practice guidelines from e.g. NICE.
  • Evidence the need for a new health technology in a particular patient population and explain the business opportunity associated with that need.
  • Deal with an unexpected and time-critical issue that may in practice arise when pioneering the use of new digital technologies in the highly sensitive and often political area of health. Demonstrate sound decision-making, awareness of stakeholders and empathy in that context.