dwongh/openscore

Software for viewing and reporting EEGs according to the SCORE standard.

openscore's Issues

Switch view back to Patient Info tab whenever a new EEG is loaded

This would give a clearer indication to the user that the context has shifted to the new recording.

Auto populate from text files

Use directories with EEG and corresponding text reports to autopopulate the fields in the score report. The text from the report is currently loaded into the patient history box, but we need to remove prevbious diagnosis (for teetacsi), and potentially filll other fields if we can identify them

Can't load EEG

File -> Load EEG allows me to select a folder, but then I get the error message below.

'MainWindow' object has no attribute 'load_eeg'

Alertness should be multiple choice

EEG recordings may have patient any of sleeping, drowsy, awake throughout the recording and so should be able to select more than one

Diagnosis appears set to 'Normal' when no choice is made

If a recording is 'Normal' the interpreter may go to the 'diagnostic significance' tab and see than 'Normal' is already selected (by default) then move on. This causes the diagnosis to be recorded as 'null' rather than 'Normal'. Is it possible to make these radio buttons behave like tristate checkboxes?

Review medical terminology and options

Several options given in drop down menus are likely missing correct or standard medical terminology. Need to review and identify these placeholders and update them if necessary.

EDFBrowser source not found

The link in the readme yields '404 not found'. Is it a private repo?

Has this version of EDFBrowser referred to above been modified in some way that means that the official version doesn't work with OpenSCORE? If so, the README should make that clear.

Units in findings

Units for all 'frequency' and 'amplitude' fields in Findings should be indicated (e.g. in the static text) as Hz or microvolts.

In the first 'amplitude' drop-down box, units are currently written as millivolts ('mV'). These should be microvolts, ideally written as V. If it's not easy to get the Greek mu to appear, 'uV' is fine.

Should close EDFBrowser when OpenSCORE is closed

EDFBrowser stays open in separate process when OpenSCORE is closed. Need to add a close method to OpenSCORE to do clean up.

Risky default of checkboxes to

Score files currently store 'false' or 0 for any checkboxes that were not ticked. This could cause confusion between whether something has been confirmed as false or simply not considered. Would it be possible to use tristate checkboxes instead?

Risky auto-population of date & times

Under Recording Conditions, date & time of recording and latest meal are auto-populated with the current time. This creates a risk of capturing false data if the user fails to overwrite these values. Ideally, they should be left blank. If that's too much hassle for now, they could be auto-populated with a date in the future (e.g. by one year) and then a simple check against this date can be used to prevent future dates from being saved.

ModuleNotFoundError: No module named 'main_window'

I couldn't find which package might need to be installed for this to work. Is it a custom module that hasn't been pushed to the remote?

I tried skipping this import and swapping 'QMainWindow' in for 'MainWindow' in the code. That ran, but just opened a blank window.

EEQ Sequence relies on TUEG dataset directory structure

Creating the mirror directories currently relies on the structure of the TUEG dataset. Specifying paths to edf recordings which are not in the same structure as the the TUEG dataset will fail

Separation of general purpose OpenSCORE from TEETACSI variant.

Hopefully OpenSCORE will become useful to a fairly broad community of researchers or even clinicians. At the moment, some features such as eye-tracking are not needed by general users. The complexity of OpenSCORE should be minimised to ensure its relevance. How it would it be to separate 'general purpose OpenSCORE' from 'TEETACSI OpenSCORE', e.g. by having a separate repo for TEETACSI, using this OpenSCORE repo as a submodule?

Features to consider separating, in descending order of priority:

• eye tracking
• sequence mode
• auto-population from text reports. Actually, this could be a great feature for OpenSCORE, but it would take a bit of work to free it up from the assumptions around use of the Temple dataset (e.g. file naming and report format).

Perhaps it's best not to act on this just yet, to postpone introducing the dev complexity of managing and documenting two repos. Let me know how much of a headache you think it would be though.