Approximately 100,000 patients die every year as a result of a medical error and one million patients are injured as a result of human errors made by clinical staff (Kohn et al., 2000). In UK medical imaging departments prior to the 1990’s, it was the mainstay of the radiologist to report on images and make a clinical diagnosis. Radiographer reporting alongside radiologists was subsequently introduced in the mid 1990’s to accommodate the changes in service demand and the lack of radiologist workforce.
Making a medical diagnosis is a difficult and error prone task due to the vast amount of information that staff must assimilate. Cognitive errors can be found in the majority of cases (Kachalia et al., 2007). Reducing the number of diagnostic errors requires interventions to improve the cognitive processes that underlie clinical reasoning when image reporting.
Current research has used eye tacking software to investigate image interpretation methods, patterns of search and diagnostic accuracy. More recently Artifical Intelligence (AI) has been implemented into imaging software to aid diagnosis in medical imaging. Despite this, there is a paucity of information on AI interfaces/layout and how different AI design influences the clinicians opinion.
Aim: To investigate the use of AI when reporting radiographic images and identify which AI generated information influences the student and expert clinicians decision making process.
Objectives: To identify
*patterns of interpretation
*reliance on AI suggestions/signposting
*correlations between interpretation methods, patterns, confidence and diagnostic accuracy,
*duration of each interpretation for different types of pathology
*diagnostic accuracy amongst students and experts
*inter and intra-rater reliability amongst participants
*common interpretation errors and pitfalls
Methods: Ethical approval will be sought from OREC to enable inclusion of staff and students from the NHS to participate in the study. A selection of radiology departments in Northern Ireland and associated Trusts in Scotland will be in included. Clinicians will be enrolled onto the study. They will interpret a series of digital medical images with “fake” AI information alongside whilst thinking aloud. This will allow the investigators to gain insight into the subject’s cognitive processes whilst image viewing. Whilst thinking-aloud, the Tobii Eye Tracking device will be used to non-invasively and unobtrusively track participant eye movement patterns. After each interpretation the subject will be asked to give a verbal diagnosis, identifying if any pathology is present and their level of confidence in their chosen diagnosis.
Data collection
Throughout each session the following data will be collected: A questionnaire of a participants’ background, gender, age and medical expertise. Eye tracking data via a Tobii Eye Tracker. The Tobii eye tracking and eye control technology makes it possible for computers to know exactly where participants are looking on screen using infrared technology.
Data analysis
Inferential and descriptive statistics will be used.
References will be requested for shortlisted candidates
Please note, the successful candidate will be required to obtain AccessNI clearance prior to registration due to the nature of the project.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The following scholarship options are available to applicants worldwide:
These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.
Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.
Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 5 February 2021
12:00AM
Interview Date
W/C 1st March 2021
Preferred student start date
Mid September 2021
Telephone
Contact by phone
Email
Contact by email