Cecily Morrison

Cecily Morrison

Auto-generated profile, based on publicly available information

Cecily Morrison

Microsoft Research, Cambridge, United Kingdom

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 March 2023 in ACM Transactions on Computer-Human Interaction
Verified
Journal Article
Open access
Anja ThiemeAnja Thieme
Anja Thieme
MHMaryann Hanratty
Maryann Hanratty
MLMaria Lyons
Maria Lyons
JPJorge E. Palacios
Jorge E. Palacios
RMRita Faia Marques
Rita Faia Marques
GDGavin Doherty
Gavin Doherty
Recent advances in AI and machine learning (ML) promise significant transformations in the future delivery of healthcare. Despite a surge in research and development, few works have moved beyond demonstrations of technical feasibility and algorithmic performance. However, to realize many of the ambitious visions for how AI can contribute to clinical impact requires the closer design and study of AI tools or interventions within specific health and care contexts. This article outlines our collaborative, human-centered approach to developing an AI application that predicts treatment outcomes for patients who are receiving human-supported, internet-delivered Cognitive Behavioral Therapy (iCBT) for symptoms of depression and anxiety. Intersecting the fields of HCI, AI, and healthcare, we describe how we addressed the specific challenges of (1) identifying clinically relevant AI applications ; and (2) designing AI applications for sensitive use contexts like mental health. Aiming to better assist the work practices of iCBT supporters, we share how learnings from an interview study with 15 iCBT supporters surfaced their practices and information needs and revealed new opportunities for the use of AI. Combined with insights from the clinical literature and technical feasibility constraints, this led to the development of two clinical outcome prediction models. To clarify their potential utility for use in practice, we conducted 13 design sessions with iCBT supporters that utilized interface mock-ups to concretize the AI output and derive additional design requirements. Our findings demonstrate how design choices can impact interpretations of the AI predictions as well as supporter motivation and sense of agency. We detail how this analysis and the design principles derived from it enabled the integration of the prediction models into a production interface. Reporting on identified risks of over-reliance on AI outputs and needs for balanced information assessment and preservation of a focus on individualized care, we discuss and reflect on what constitutes a responsible, human-centered approach to AI design in this healthcare context.

23 March 2015 in BMC Medicine
Verified
Journal Article
Open access
PDF file
KHKit Huckvale
Kit Huckvale
CMCecily Morrison
Cecily Morrison
JOJing Ouyang
Jing Ouyang
AGAseem Ghaghda
Aseem Ghaghda
Josip CarJosip Car
Josip Car
Interest in mobile apps that support long-term conditions such as asthma is matched by recognition of the importance of the quality and safety of apps intended for patient use. We assessed how changes over a 2-year period affected the clinical suitability of apps providing self-management information and tools for people with asthma by updating a review first performed in 2011. Systematic content assessment of all apps for iOS and Android examining the comprehensiveness of asthma information, consistency with the evidence base for asthma self-management and adherence to best practice principles for trustworthy content, comparing the quality of apps available in 2011 to those released since. Between 2011 and 2013, numbers of asthma apps more than doubled from 93 to 191, despite withdrawal of 25% (n = 23/93) of existing apps. Newer apps were no more likely than those available in 2011 to include comprehensive information, such as the use of action plans, or offer guidance consistent with evidence; 13% (n = 19/147) of all apps, and 39% (n = 9/23) of those intended to manage acute asthma, recommended self-care procedures unsupported by evidence. Despite increases in the numbers of apps targeting specific skills, such as acute asthma management (n = 12 to 23) and inhaler technique (from n = 2 to 12), the proportion consistent with guidelines (17%, n = 4/23) and inhaler instructions (25%, n = 3/12), respectively, was low, and most apps provided only either basic information about asthma (50%, n = 75/147) or simple diary functions (24%, n = 36/147). In addition to persisting questions about clinical quality and safety, dynamic aspects of app turnover and feature evolution affect the suitability of asthma apps for use in routine care. The findings underline the need for coordinated quality assurance processes that can adapt to changing clinical and information governance-related risks, ensure compliance with the evidence base and reflect local variations in clinical practice. It is unclear if substantial clinical benefits can be realized from a landscape dominated by low quality generic information apps and tools that do not adhere to accepted medical practice.

1 October 2013 in Health Policy
Verified
Journal Article
Open access
CMCecily Morrison
Cecily Morrison
ADAndy Dearden
Andy Dearden
A number of recent policies promote public participation in health service design. Yet, a growing literature has articulated a gap between policy aims and actual practice resulting in public participation becoming tokenistic. Drawing on theory from participatory design, we argue that choosing appropriate artefacts to act as representations can structure discussions between public participants and health professionals in ways that both groups find meaningful and valid. Through a case study of a service improvement project in outpatient services for older people, we describe three representational artefacts: emotion maps, stories, and tracing paper, and explain how they helped to mediate interactions between public participants and health professionals. We suggest that using such representational artefacts can provide an alternative approach to participation that stands in contrast to the current focus on the professionalisation of public participants. We conclude that including participatory designers in projects, to chose or design appropriate representational artefacts, can help to address the policy-practice gap of including public participants in health service design.

27 November 2018 in JMIR Mental Health
Verified
Journal Article
Open access
KDKevin Doherty
Kevin Doherty
MBMarguerite Barry
Marguerite Barry
JMJosé Marcano-Belisario
José Marcano-Belisario
BABérenger Arnaud
Bérenger Arnaud
CMCecily Morrison
Cecily Morrison
GDGavin Doherty
Gavin Doherty
Background: Maternal mental health impacts both parental well-being and childhood development. In the United Kingdom, 15% of women are affected by depression during pregnancy or within 1 year of giving birth. Suicide is a leading cause of perinatal maternal mortality, and it is estimated that >50% of perinatal depression cases go undiagnosed. Mobile technologies are potentially valuable tools for the early recognition of depressive symptoms, but complex design challenges must be addressed to enable their use in public health screening.Objective: The aim of this study was to explore the issues and challenges surrounding the use of mobile phones for the self-report of psychological well-being during pregnancy.Methods: This paper presents design research carried out as part of the development of BrightSelf, a mobile app for the self-report of psychological well-being during pregnancy. Design sessions were carried out with 38 participants, including pregnant women, mothers, midwives, and other health professionals. Overall, 19 hours of audio were fully transcribed and used as the basis of thematic analysis.Results: The study highlighted anxieties concerning the pregnancy journey, challenges surrounding current approaches to the appraisal of well-being in perinatal care, and the midwife-patient relationship. Designers should consider the framing of perinatal mental health technologies, the experience of self-report, supporting self-awareness and disclosure, providing value to users through both self-report and supplementary features, and designing for longitudinal engagement.Conclusions: This study highlights the needs, motivations, and anxieties of women with respect to technology use in pregnancy and implications for the design of mobile health technologies.

13 November 2014 in Journal of Medical Internet Research
Verified
Journal Article
Open access
CMCecily Morrison
Cecily Morrison
GDGavin Doherty
Gavin Doherty
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

24 November 2008 in Critical Care
Verified
Journal Article
Open access
PDF file
CMCecily Morrison
Cecily Morrison
MJMatthew Jones
Matthew Jones
ABAlan Blackwell
Alan Blackwell
AVAlain Vuylsteke
Alain Vuylsteke
Introduction: Electronic patient records are becoming more common in critical care. As their design and implementation are optimized for single users rather than for groups, we aimed to understand the differences in interaction between members of a multidisciplinary team during ward rounds using an electronic, as opposed to paper, patient medical record. Methods: A qualitative study of morning ward rounds of an intensive care unit that triangulates data from video-based interaction analysis, observation, and interviews. Results: Our analysis demonstrates several difficulties the ward round team faced when interacting with each other using the electronic record compared with the paper one. The physical setup of the technology may impede the consultant's ability to lead the ward round and may prevent other clinical staff from contributing to discussions. Conclusions: We discuss technical and social solutions for minimizing the impact of introducing an electronic patient record, emphasizing the need to balance both. We note that awareness of the effects of technology can enable ward-round teams to adapt their formations and information sources to facilitate multidisciplinary communication during the ward round.