Early Self Diagnosis of Lung Cancer via Web Search and HCI
A key to lung cancer survival is early presentation to health services and evidence shows this can be influenced by information from various sources. The internet is a potentially cost-effective means of disseminating information, 60% UK adults access it almost every day although there are socio-demographic differences in use. Internet use is growing in that part of the population at highest risk of lung cancer and penetration via internet based interventions is becoming increasingly possible. For lung cancer patients the internet is the most commonly used non-physician source of information.
Conversely, there are many knowledge resources (taxonomies, ontologies, and the like) are produced as part of healthcare research, to drive tools for healthcare professionals, and by healthcare companies.
We ask the questions:
1. Can this knowledge be used to augment public patient engagement by enhancing current web search;
2. what additional infrastructure is required to support these changes;
3. will precision and recall be enhanced by such an infrastructure; and
4. what level of behavioural change can be induced by enhancing information seeking and retrieval?
This study will investigate the role of different information sources in triggering intention to seek help, and the potential of web search to reach the population at high lung cancer risk and how this can be improved.
The study will use:
1. Systematic review and critical evaluation techniques to evaluate web-based sources of information about lung cancer to establish the quality and user friendliness of information available online.
2. Secondary analysis of qualitative interview techniques to identify information resources that lung cancer patients use prior to diagnosis and establish whether this information contributes to any decision to present to health services and/or has other impacts on behaviour or lifestyle.
3. Methods developed in computer-human interaction research to develop an effective strategy for signposting target online lung cancer information.
This will enable us to develop methods to steer the ’worried well’ to relevant websites and to seek appropriate help. Further work will assess the generalisability of the infrastructure and the practicality of applying it to different knowledge resources, for different health conditions as a health intervention to enable an early user driven route to diagnosis and treatment.
Web Search has become the ’go-to’ resource for many. Being able to leverage search results to direct users towards appropriately tailored resources has the potential to increase earlier visits to GP; critical for early diagnosis and treatment. Web Search results are a list of signposts-to-resources generated from search terms. The key is to ensure signposts are placed at the top of the first page of results. Until recently, we could not elicit or analyse search terms, or relate them to lung cancer. New infrastructure coupled with existing knowledge resources may enable this.
The student will use existing interview data to identify common search terms and develop infrastructure to apply existing knowledge resources to these search terms. We would expect to see better results in recall and prediction when with current algorithms. The infrastructure may need to instrument the browser such that a history of health search, relevant to that particular user, would be kept and used to enhance single point of time searches..
Candidates who have been offered a place for PhD study in the School of Computer Science may be considered for funding by the School.
Funding opportunities exist for students wishing to join our 3-year PhD programme and the 4-year PhD in our Centre for Doctoral Training in Computer Science. Each year around 20 new PhD students are awarded funding via the School. Further details on School funding can be found at: http://www.cs.manchester.ac.uk/study/postgraduate-research/programmes/phd/funding/school-studentships/.
In addition, exceptional students may be considered for the President's Doctoral Scholar Award and the Dean's Award. Further details on these opportunities can be found at: http://www.eps.manchester.ac.uk/our-research/funding/.
How good is research at University of Manchester in Computer Science and Informatics?
FTE Category A staff submitted: 44.86
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities