TABLE OF CONTENTS
- Introduction
- General options
- Title and abstract screening
- Full-text screening
- Data extraction
- Extract data (recommended)
- Import other PDFs (optional)
- Validate extracted data using Quality assurance stage (optional)
Introduction
This training project aims to provide an overview of the general functionalities of Laser AI, such as References or team managment, the key functions at each stage of the process - Title and abstract screening, Full-text screening and Data extraction.
The following guide contains a list of main actions that can be performed throughout the Training project. Below each task, you will find a link to the Knowledge Base with a detailed explanation of the main function. The ‘Explore more’ section contains additional options, which are not essential, but can help to manage processes more effectively.
Please note that each stage is already started - you can start your exploration from every stage and you don’t need to finish the previous stage to start the next one. The only thing to do is to distribute records to the appropriate stage.
General options
Explore main project list dashboard and single project dashboards
Familiarize with two main dashboard types:
Main projects dashboard overview - here you can preview the list of all project as well as those that belong only to you, search the project and preview their details. You are also able to manage a project - change its settings, archive/delete or move between folders.
Single stage dashboard - a panel dedicated to preview all details of a single project, its progress, team members, references etc.
Invite other reviewers (optional)
Invite additional team members if necessary. Remember that in a single project, you can also change users roles, remove or replace them with new team members.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012659-team-management-at-project-level
Explore more:
Add additional references (optional)
A set of references has already been uploaded for the project, but if you would like to test the functionality for uploading references, you can do so in the 'References' panel. The references will then be ready for distribution at the Title and Abstract Screening stage.
Please note that the model is trained on the basis of previous decisions related to the project topic (polyunsaturated fatty acids). Therefore, records from different RIS files on other topics may not appear as a primary item to be screened during the screening process.
Important: options for the PDF management are described in the section dedicated to the Full-text screening.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012670-import-references-to-the-project
Explore more:
Single reference management options (e.g. Editing structured comments and bliographical data, overwriting decision, history of changes)
Title and abstract screening
Set up Title and abstract screening
a) Explore Title and abstract screening stage dashboard
In the Title and abstract stage dashboard you can manage whole stage, ie. modify Instructions and screening methods, manage screening tasks and team, as well as preview the progress of stage overall and single users.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000003396-title-and-abstract-stage-dashboard-overview
b) Read and edit Title and abstract screening instruction
Screening Instructions is a list of the Inclusion and Exclusion criteria together as well as instructions for researchers and keywords reflecting desired and undesired keywords, useful during the screening.
Here, you can modify the guide, add or remove highlights and add structured comments.
Note that this project is already started, so here, you’re not able to add or remove Exclusion reasons.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000042478
c) Setup distribution for Title and abstract screening
Some of the references are already uploaded and screened to be sent to next stages, but you still have a batch of references to be distributed among your team. You can change who should have records assigned to as well as well as decide how many records should be distributed.
To do it, select ‘Task distribution’ button in the Screening tasks setion and select appropriate method of the records distribution.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012640-task-distribution-for-title-and-abstract-screening
Explore more:
Changing distribution method during Title and abstract screening
Redistribution of tasks during the Title and abstract screening -
d) Set up conflict resolution method (optional)
In the ‘Conflicts’ panel, you can preview all current conflicts, their type (Include vs Exclude/Exclude vs Exclude) and set the method of their resolution.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012641-set-up-conflicts-resolution-during-the-title-and-abstract-screening
Perform Title and abstract screening
a) Familiarize yourself with the List of references and Focus mode in the Title and abstract screening
To learn how to perform Title and abstract screening in Laser, go to Focus mode and explore all its features, such as adding comments and structured comments, creating and sending decisions. You can also customize Focus mode by enabling highlights and abstract formatting, and changing colours.
During the screening, you can filter records in the Reference list panel using multiple criteria such as status, year of publication, structured comments, text word terms or Mesh terms. This will help you find and exclude definitely irrelevant records in batches, as well as find potentially relevant ones ('golds').
Please note that while screening in the Focus mode, records will be automatically sorted based on their probability of inclusion.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012657-how-to-perform-title-and-abstract-screening-
Explore more:
Resolve conflicts during the Title and abstract screening (optional)
If any conflicts arise during the Title and abstract screening, you can test how to perform conflict resolution. Remember that you can choose whether you want to resolve only those conflicts that you’re involved in or those generated by others.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012660-how-to-resolve-a-conflict-during-title-and-abstract-screening-
Full-text screening
Set up Full-text screening
a) Explore Full-text screening stage dashboard
In the Full-text stage dashboard you can manage whole stage, i.e. modify Instructions and screening methods, manage screening tasks and team, as well as preview the progress of stage overall and single users.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012689-full-text-stage-dashboard-overview
b) Read and edit Full-text screening instruction
In the Full-text screening Instruction, you can modify the guide as well as add Structured comments.
Note that this project has already started, so here you’re not able to add or remove new Exclusion reasons.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012691-full-text-screening-instructions-set-up
Explore more:
c) Distribute tasks for Full-text screening
Batch of references can be distributed among your team in the Full-text screening stage. You can change who should have records assigned to, as well as decide how many records should be distributed.
Knowledge base: : https://help.laser.ai/support/solutions/articles/204000012694-task-distribution-for-full-text-screening
Explore more:
d) Manage PDFs (optional)
PDFs retrieval and management are crucial during the Full-text screening. In the Training project you have PDFs already uploaded, but you are able to add additional PDFs like supplements or protocols. You can do it in two ways:
In a Reference Details view
In a Focus mode during Full-text screening
In case of missing PDFs, you can test retrieving PDFs using OpenAlex and Article Galaxy
e) Set up conflict resolution method (optional)
In the ‘Conflicts’ panel, you can preview all current conflicts, their type (Include vs Exclude/Exclude vs Exclude/ Include vs Include) and set the method of their resolution.
Knowledge base:
Perform Full-text screening
a) Familiarize yourself with the List of references and Focus mode in the Full-text screening
If you want to check how to perform Full-text screening in Laser, go to the Focus mode and check all its functionalities like adding comments and structured comments, making and sending decisions.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012708-how-to-perform-full-text-screening
Resolve conflicts during the Title and abstract screening (optional)
If any conflicts during the Title and abstract screening arise in the Training, you can test how to perform conflict resolution. Remember that you can choose whether you want to resolve only those conflicts that you’re involved in or those generated by others.
Knowledge base: https://help.laser.ai/support/solutions/articles/204000012709-how-to-resolve-a-conflict-during-full-text-screening x
Data extraction
Distribute tasks for first extraction
Distribute studies for data extraction. On the Data extraction stage dashboard you will find studies waiting to be distributed. You can choose between three distribution methods. Please note that the open pool method is the most flexible, as it allows, for example, studies to be returned to the pool—enabling other reviewers to extract data from the same study (please note that only last extraction will be saved in this case).
Learn more about distribution
Please note that the models need some time to extract data. You will see a notification indicating that the model is processing. Once at least one PDF has been processed, click the ‘eye’ icon in the left-hand navigation bar. You should also receive an email notifying you that tasks have been assigned to you.
Click here to learn more about my Task board and data extraction tasks.
Extract data (recommended)
We encourage you to test the following features to better understand how the model supports data extraction and to familiarize yourself with the extraction process in Laser AI. Please note that the database format slightly differs from what you may be used to in Excel.
To learn more about the advantages of this database structure, please refer to the following article: ………………….
- Extraction of data into three subfields (main extracted value, author-reported value, and comment)
- Extraction of data using the highlighting mechanism
- Extraction in vocabulary fields
- AI-supported extraction of fields from text
- Extraction within subsections
- AI-supported extraction from tables
Task 1. Extraction of data into three subfields and Extraction of data using the highlighting mechanism
Each data extraction field includes three subfields: main extracted value, author-reported value, and comment. Learn more about: Components of a Single Data Extraction Field
Try to extract all three subfields for at least one data extraction field. For now, select a field that is not AI-supported—there will be no yellow suggestions. Use the highlighting mechanism to extract the data: select the relevant part of the text from the PDF and click the + button in the data extraction form.
To learn more, read about how to extract data using the highlighting mechanism.
Task 2. Extraction in vocabulary fields
In addition to simple text fields, you will find vocabulary fields, where you can select the appropriate code from a provided list that best represents the extracted data (in this data extraction form for example Study type is such field). Please extract at least one vocabulary field and try using the "create new term" option—if the relevant term is not available in the list, you have the option to add a new one.
If you need help please read this article
Task 3. AI-supported extraction of fields from text
When model suggestions are enabled for a field, the extracted value will be highlighted in yellow. Your task is to accept or reject these suggestions.
Select at least one tab to test how this process works—for example, open the Population tab and review the model’s suggestions in the Inclusion/Exclusion Criteria section.
Review the suggestions one by one for the Inclusion Criteria. You can also learn how to use the Batch Accept button (dots button) to speed up the process.
Task 4. Extraction within subsections
Subsections are groups of fields that can be multiplied within the Section. They are used in three cases:
Basic subsection - to extract dependent values and multiply fields, e.g. in the case of multiple countries, In/Out criteria or combinations treatment in one study arm.
For group level data - to extract values per single group/study arm (outcomes, baseline characteristics)
For comparison - to extract comparison values between study arms (outcomes, baseline characteristics)
More detailed information about subsection
Try to extract data within a basic subsection. For example, you will find the subsection Country under the Study Details section in the Study Characteristics tab. The 'Country' field is a perfect example of a subsection field, as a study might be conducted in various locations.
To extract group level data, must first extract all study groups/arms. For example, if you want to extract data for each single study arm separately , extract all arms in the ‘Intervention’ tab.
Please extract the baseline age for each study group and p value (between study groups). In the Population tab, you will find the Baseline Characteristics section, which includes a subsection dedicated to extracting values for each study arm.
For this task, please extract the data manually. In the next task, you will test how to automate this process.
If age is not reported in the publication, you may extract other baseline variables or outcome data instead, as the subsections are structured in a similar way.
Task 5. AI-supported extraction from tables
Repeat Task 4 (extracting age data), but this time use the semi-automated option for tables.
Click on the table, then click the blue Extract button to enter the automatic table extraction module. Next, match the content of the relevant columns to the corresponding fields in your data extraction form.
You can extract all baseline variables from the table at once by selecting all rows.
Please note that extracted values will be highlighted in yellow, indicating that they require your review. You should accept them either one by one or by using the Batch Accept button.
Import other PDFs (optional)
In this project you will find 11 studies that are waiting to be distributed. Please feel free to add more.
Learn more how to upload more PDF.
Validate extracted data using Quality assurance stage (optional)
In Laser AI, you can validate your extracted data through an optional 4-step process.
At the researcher level, once you finish your data extraction and click the 'Finalize' button, the tool will verify the extracted data for any missing elements, such as empty fields, missing connections, or uncoded values.
At the researcher level, you can set up the quality assurance stage, allowing a second researcher to validate the extracted data. This process is similar to the initial data extraction.
The data cleaning module is dedicated to validating vocabulary fields (manager level)
At the manager level, you can review and modify extracted data in the reference list
To test the Quality Assurance (QA) stage, you must first extract data from at least one study. Once that is done, please distribute studies for QA. This process is similar to the distribution used for the first extraction.
How to distrubute studies for QA
The Quality Assurance stage is very similar to the data extraction process. All data extracted by the first reviewer will be highlighted in yellow for your review.
Learn more about how to verify data during the QA stage.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article