Associate Professor Hanna Suominen, with over 15 years’ experience in longitudinal, multimodal data analytics for saving, structuring, and summarising data, is bridging the gap between Computer Science (CS) and health/social sciences. Her MSc was awarded in applied mathematics, PhD in CS, and Adj/Prof in CS in the University of Turku, Finland in 2005, 2009, and 2013, respectively. She joined The ANU and Data61 as the Team Leader of TAMPA, Theory and Applications of Multimodal Pattern Analysis within the Machine Learning (ML) Group after working in Data61/NICTA as a Team Leader of Natural Language Processing (NLP) and Senior Researcher in ML. Hanna has over 100 publications with 60 co-authors from 10 countries, including Harvard, Karolinska Institutet, and Max Planck. Her work has been published in the most prestigious journals, cited over 1,200 times, and awarded for best papers, ML/NLP-methods, business-plans, and teaching-units. She has scored competitive grants with a total value of over $10-20 million in the past 2 years alone.
Assoc/Prof Hanna J Suominen develops and evaluates machine learning (ML) methods for natural language processing (NLP) and health informatics. She has over 100 publications with over 60 co-authors from 10 countries, including the German Max Planck Institute, Swedish Karolinska Institutet University, and US Harvard University. Her work has been published in the most prestigious journals, cited more than 1,200 times (h-index 19, i10-index 31), and awarded for the best papers, ML/NLP-methods, and business-plans. Please do not hesitate to contact Hanna for research collaboration or summer/long/honours/masters/doctors projects.
Current student projects
Assoc/Prof Hanna Suominen considers the following co-authored papers as her most important publications:
- Suominen H, Kelly L, Goeuriot L. The scholarly influence of the CLEF eHealth initiative by the Conference and Labs of the Evaluation Forum: Review and bibliometric study of the 2012-2017 outcomes. JMIR Res Protoc 2018 7(7): e10961 (Impact Factor: 4.669 for JMIR): In 2013-2017, Hanna co-chaired/led shared 15 tasks to ease and support patients, their next of kin, clinical staff, health scientists, and health care policy makers in accessing, understanding, using, and authoring health information in a multilingual setting as part of the CLEF Conference and Labs of the Evaluation Forum, funded by the European Commission. These CLEF eHealth tasks have generated 184 papers with 1,299 citations for their 741 co-authors from 33 countries and 130 teams across the world. As many as 718 teams registered their interest in the tasks, leading to 130 teams submitting to the 15 tasks. A total of 184 papers using CLEF eHealth data generated 1299 citations, yielding a total scholarly citation influence of almost 963,000 citations for the 741 coauthors, and included authors from 33 countries across the world. Eight tasks produced statistically significant improvements (2, 3, and 3 times with P<.001, P=.009, and P=.04, respectively) in processing quality by at least 1 out of the top 3 methods. These substantial participation numbers, large citation counts, and significant performance improvements encourage continuing to develop these technologies to address patient needs. Consequently, data and tools have been opened for future research and development, and the CLEF eHealth initiative continues to run new challenges.
- Suominen H, Johnson M, Zhou L, Sanchez P, Sirel R, Basilakis J, Hanlen L, Estival D, Dawson L, and Kelly B. Capturing patient information at nursing shift changes: Methodological evaluation of speech recognition and information extraction. J Am Med Inform Assoc 2014 22(e1), e41-66. (Impact Factor: 3.9) and Suominen H, Zhou L, Hanlen L, Ferraro G. Benchmarking clinical speech recognition and information extraction: New data, methods and evaluations. JMIR Med Inform 2015 3(2), e19 (Impact Factor: 4.669 for JMIR): The goal of the former paper was to study speech recognition and information extraction to fill out a handover form for clinical proofing as a way to make documentation more efficient, improve availability of existing documents, and thereby contribute to health and healthcare. Speech recognition resulted in up to 90% correctness with only 4 min of data to adjust a given speaker and at least 90% correctness in information extraction was achieved for 6 out of the 35 headings. This project was funded by NICTA in collaboration Centre for Applied Nursing, CERNER, Clinical Excellence Commission, NSW Ministry of Health, Sydney Local Health Network, South Western Sydney Local Health Network, and Universities of Melbourne, Western Sydney and Wollongong in 2011-2014. In this study, Hanna was the principal ML scientist, who conducted all speech recognition experiments and supervised and in part conducted all information extraction experiments. The latter paper released a synthetic (but realistic) dataset and some processing software to the research and development community for studying clinical documentation and language-processing. The data provided are a simulation of nursing handover, as recorded using a mobile device, built from simulated patient records and handover scripts, spoken by an Australian registered nurse.
See Hanna's Google Scholar profile for he full list of publications.
Hanna has been shortlisted to the top-15% in the L'Oréal-UNESCO for the Australia & New Zealand Women in Science in 2013, selected for the Australia China Young Scientists Exchange Program in 2018, and nominated to run for the ACT Scientist of the Year in 2017 and 2018 by the dean of The ANU College of Engineering and Computer Science.
Hanna's goal is to accelerate the adoption of leading technologies in healthcare, biomedicine, bio-health sciences, and social sciences; guiding the next generation of students is central to this aim. She teaches computer science (CS), mathematics, and engineering interdisciplinary skills, with a focus on multi-professional collaboration and communication. Her teaching practice helps her students better engage with the end-users of their technologies and exposes the next generation of clinicians and scientists to intelligent agents that will be a part of their future careers. The tools Hanna helps them learn to create will transform boring and laborious human labour into machine-assisted workflows, thus freeing up time for more meaningful and joyful tasks and enhancing Australia’s prosperity.
Hanna leads by focusing, committing, and delivering. She has her Finnish sisu – an adamant faith in her team and commitment to communicate and deliver important matters to our academic community, clients, and society. Her work starts from creating concepts, building dream teams, and taking risks to reach delivering products and seizing business opportunities. She energises people by applying different communication strategies to driving, expressive, amiable, and analytical people. She challenges her team and herself for self-improvement, pushes her boundaries, and fights against staying in her comfort zone through adaptive and situational leadership; Hanna takes turns in leading, following, and back-leading. She never gives up but consistently seeks alternative approaches and ways to conciliate in problem situations.
The education Hanna provides is comparable with the best in the world, which is evidenced by the career paths of her bachelor, honour, and master’s project students, which include, for example, Microsoft Research Seattle and Australian Government departments. She is also a member of the Curriculum Development/Education Governance Committee of her school and is committed to improving her skills as an educator; currently, Hanna is taking Masters of Leadership in Curriculumn and Pedagogy in the the Monash University, including the National Excellence in Educational Leadership Initiative (NEELI) Higher Education Advanced Leadership Program.
Hanna typically teaches units with students from diverse disciplinary backgrounds. She appropriately adjusts her teaching approach and finds ways to transfer her knowledge across the various study levels, disciplines, and backgrounds. Unusually for a CS academic, she has developed courses, units, and study materials across the humanities and sciences and acted as a unit convenor for undergraduate, graduate, and post-graduate students in CS/engineering or business/economics; Information Systems in Healthcare (in Finland) and Networked Information Systems (in Australia). She has also convened the three Mathematics and Computer Sciece units (introduction, basic, and advanced) of the International Master’s Programme in Bioinformatics in Finland for students who had done their undergraduate studies in biology, medicine, statistics, CS, engineering, or mathematics.
Prior to joining The ANU in October 2016, she has made award-winning voluntary contribution to teaching in her research role; she was one of the five founders of the Document Analysis unit in The ANU, which achieved The Headline Teaching Score in SELT 2012 with an extremely small dissatisfaction rate. In 2013 in Finland, as part of her Adjunct Professorship assessment, her sample lecture, titled ‘C-value method for summarising key content’, was assessed by the staff members and students as excellent (i.e., the highest grade). She has also created and taught courses at the highest level (Australian Qualifications Framework 10: Doctoral Degree), including mentoring HDR students in ACL, CLEF, and ICML and teaching master classes in the Australian Health Informatics Summer School, Australasian Language Technology Association, HEalth teXt Analysis network in the Nordic and Baltic countries, University of New South Wales, Western Sydney University, and several Australian Government departments.
Hanna has a very interesting academic ancestry: She is a 14th-great-granddaughter of Gottfried Wilhelm Leibniz (e.g., differential and integral calculus, 1646-1716, Germany) and 20th-great-granddaughter of Nicolaus Copernicus (e.g., earth-centric model of the universe, 1473-1534, Poland). However, she is the only woman along this tree of PhD supervisors, traced back to the 1360s, who managed to get a PhD and join the academic profession herself. She recognises that this history gives her an opportunity to take a leadership position that models this possibility for other women in a massively male dominated field. As our discipline goes forward, it will be more important to make sure women are visible as leaders, so Hanna wants to lead the way, by example and show how women can excel in academic leadership positions in science, technology, engineering, and mathematics (STEM).
Hanna actively engages in improving her own organisation and works well in interdisciplinary and multi-professional teams in Australia and overseas. She has been, and will continue to be, an active participant, contributor, and attractor to professional peer groups, career mentoring, and public awareness of science initiatives. In 2004-2005, she was a Lecturer in the Year 7-9 Math Club Origo by the University of Turku, Dept. of Mathematics. Teaching these pupils allowed her to improve their applied mathematics literacy, for example, through washing machines based on fuzzy logic and decoding secrets from cryptic notes in a cipher. For her, seeing this purpose helped drive her desire to master ML on health data - this took until the second year of her university studies, after finally been introduced to mathematical modelling related to medical applications in 2001.
Hanna wants to make these pathways more visible to others so they can be attracted to this exciting research area. To do this, she gives public talks and seminars; for example, in Canberra, she has delivered the following inspirational invited talks: 1) Invited Opening: What is ICT/NLP? International Girls in ICT Day 2014 in The ANU, 2) Text Analytics Technologies and Their Applications to Healthcare. IEEE Women in Engineering/ Distinguished Speakers Seminar 2014 in the University of Canverra, 3) Teaching a Computer to Summarise. EUROSCIENCE 2015 for school kids and their parents at Questacon, and 4) ML for Health Data Analytics. Pint of Science Festival 2018 in Gryphons Caffe Bar, Griffith, ACT.
Hanna's knowledge and skills around how to make big data legible are in great demand by people inside and outside The ANU, so she often acts as a representative of her school, helping others to achieve their goals. She contributes locally and internationationally to science, teaching, supervision, and project work with academic, governmental, and industry partners. She serves the Data61/CSIRO as the TAMPA Team Leader and OHIOH in The ANU as the program leaded in Big Data.
One of her strengths is placing the people using new ML and NLP technologies at the centre of her work and paying careful attention to both their workflow and their information needs. This value sensitive design approach consists of translating real-life tasks as ML and NLP problems, developing their solutions, and evaluating the resulting application outcomes. Her work is of significant interest to The ANU and Data61/CSIRO, as a way to create impact in the wider community regionally, nationally, and internationally. Her unique talent and exceptionally strong skill set both in methods and customer engagement has led to significant projects to several government agencies and private corporations. The quality of her work ensures that she has ongoing relationships with these clients that leads to more opportunities for her organizations.
Hanna's peers recognise her skills and abilities and have given her many opportunities to contribute to her discipline. She has also been invited to serve as a PhD Examiner and/or the 1st Opponent in the Norwegian University of Science and Technology, Aalto University, Finland, and Macquarie University, Sydney, NSW, Australia. She has contributed to the ANU European Reference Group since 2016 by bringing her knowledge about (northern) European funding opportunities and partnerships. In 2008-2010, Hanna worked as the first Project Consortium Coordinator of the Information and Language Technologies to support Health Knowledge and Communication (IKITIK), awarded for the Information and Communications Technologies act of the year 2010 in Southwest Finland. This project was strongly connected with the HEalth teXt Analysis network in the Nordic and Baltic countries (HEXANord), ScanBalt, and other research networks funded by the Academy of Finland; European Commission; Kone Foundation; NordForsk; Tekes, the Finnish Funding Agency for Technology and Innovation; among others.
Hanna is committed to making her organisation an even better place for its students and staff. Hence, she develops and refreshes her skills in first aid, mental health, and workplace health and safety. She is an academic Health and Safety Representative (HSR) in her school, first aid officer both in The ANU and Data61/CSIRO, and member of the Health, Safety, and Environment committees of her school, college, and Data61. She also follows the institutional policies on research ethics carefully and contributes to this body of knowledge by publishing papers on ethics of health record research.