Dataset Information

A new and general approach to signal denoising and eye movement classification based on segmented linear regression.

ABSTRACT: We introduce a conceptually novel method for eye-movement signal analysis. The method is general in that it does not place severe restrictions on sampling frequency, measurement noise or subject behavior. Event identification is based on segmentation that simultaneously denoises the signal and determines event boundaries. The full gaze position time-series is segmented into an approximately optimal piecewise linear function in O(n) time. Gaze feature parameters for classification into fixations, saccades, smooth pursuits and post-saccadic oscillations are derived from human labeling in a data-driven manner. The range of oculomotor events identified and the powerful denoising performance make the method useable for both low-noise controlled laboratory settings and high-noise complex field experiments. This is desirable for harmonizing the gaze behavior (in the wild) and oculomotor event identification (in the laboratory) approaches to eye movement behavior. Denoising and classification performance are assessed using multiple datasets. Full open source implementation is included.

SUBMITTER: Pekkanen J

PROVIDER: S-EPMC5735175 | biostudies-literature | 2017 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A new and general approach to signal denoising and eye movement classification based on segmented linear regression.

Pekkanen Jami J Lappi Otto O

Scientific reports 20171218 1

We introduce a conceptually novel method for eye-movement signal analysis. The method is general in that it does not place severe restrictions on sampling frequency, measurement noise or subject behavior. Event identification is based on segmentation that simultaneously denoises the signal and determines event boundaries. The full gaze position time-series is segmented into an approximately optimal piecewise linear function in O(n) time. Gaze feature parameters for classification into fixations, ...[more]

PMID: 29255207

Similar Datasets

Project description:There is significant evidence that patients with acute eye symptoms are poorly assessed in primary care. There is a tendency to diagnose viral or bacterial conjunctivitis in any acutely red eye. This has led to delays in treatment and in some cases, permanent loss of sight. The aim of this project was to improve acute eye consultations within the Birchwood Medical Practice. The project focused on the "red flag" findings that would identify patients who require referral for same-day ophthalmology assessment. A retrospective baseline audit was carried out on all cases read-coded "conjunctivitis" over the period of one year. Initially, only 2.8% of consultations had documented all four findings. By considering the main factors that lead to poor eye assessments, two main areas for improvement were identified. These were education (reinforced with memory aids) and improving the availability of eye examination equipment within each consultation room. An "eye examination kit" was developed with the needs of the general practitioner in mind. The practice was re-audited six weeks following the intervention. Consultations where all four red flag findings were documented rose from 2.8% to 50%. This was found to be a statistically significant difference (p < 0.01). Pain was checked 63% of the time, compared to 26% prior to intervention. Visual acuity screening had increased to from 35% to 69%. Photophobia was the most significantly increased metric, from being documented only 6% of the time to now 63% of the time. Documentation of whether the symptoms were unilateral or bilateral had also increased from 88% to 94% of consultations. The initial audit indicated that general practitioners often diagnosed conjunctivitis without screening for symptoms of sight-threatening disease. However, it was clear from the results that the doctors had made a significant change to their approach to acute eye consultations. This shows that doctors are willing to make changes to their behaviour when given the right tools and information. It was felt that a first-hand understanding of the problem and an open discussion regarding the changes required was key to the success of this project. This project has shown that significant improvements can be achieved with practical and inexpensive interventions. Therefore, general practices throughout the UK are encouraged to adopt similar strategies to improve the identification of patients needing same-day Ophthalmology assessment.

Dataset Information

A new and general approach to signal denoising and eye movement classification based on segmented linear regression.

Publications

A new and general approach to signal denoising and eye movement classification based on segmented linear regression.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets