{
  "General Information": {
    "summary": "Provide a 2 sentence summary of this dataset.",
    "audit": "Has the dataset been audited before? If yes, by whom and what are the results?"
  },
  "Dataset Versioning": {
    "release_type": "Does the dataset get released as static versions or is it dynamically updated? a. If static, how many versions of the dataset exist? b.If dynamic, how frequently is the dataset updated?",
    "datasheet_version": "Is this datasheet created for the original version of the dataset? If not, which version of the dataset is this datasheet for?",
    "other_datasheets": "Are there any datasheets created for any versions of this dataset?",
    "current_version_details": "Does the current version/sub-version of the dataset come with predefined task(s), labels, and recommended data splits (e.g., for training, development/validation, testing)? If yes, please provide a high-level description of the introduced tasks, data splits, and labeling, and explain the rationale behind them. Please provide the related links and references. If not, is there any resource (website, portal, etc.) to keep track of all defined tasks and/or label definitions?",
    "version_difference": "If the dataset has multiple versions, and this datasheet represents one of them, answer the following questions: a. What are the characteristics that have been changed between different versions of the dataset? b. Explain the motivation/rationale for creating the current version of the dataset. c. Does this version have more subjects/patients represented in the data, or fewer? d. Does this version of the dataset have extended data or new data from the same patients as the older versions? Were any patients, data fields, or data points removed? If so, why? e. Do we expect more versions of the dataset to be released? f. Is this datasheet for a sub-version of the dataset? If yes, does this sub-version of the dataset introduce a new task, labeling, and/or recommended data splits? If the answer to any of these questions is yes, explain the rationale behind it. g. Are you aware of any widespread sub-version(s) of the dataset? If yes, what is the addressed task, or application that is addressed?"
  },
  "Motivation": {
    "purpose": "For what purpose was the dataset created? Was there a specific task in mind? Was there a specific gap that needed to be filled? Please provide a description.",
    "applications": "What are the applications that the dataset is meant to address? (e.g., administrative applications, software applications, research)",
    "discouraged_uses": "Are there any types of usage or applications that are discouraged from using this dataset?",
    "creators": "Who created this dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?",
    "funding": "Who funded the creation of the dataset? If there is an associated grant, please provide the name of the grantor and the grant name and number.",
    "curator_background": "What is the distribution of backgrounds and experience/expertise of the dataset curators/generators?"
  },
  "Data Composition": {
    "instance_representation": "What do the instances that comprise the dataset represent (e.g., documents, images, people, countries)? Are there multiple types of instances? Please provide a description.",
    "total_instances": "How many instances are there in total (of each type, if appropriate)? (breakdown based on schema, provide data stats)?",
    "subjects_represented": "How many patients / subjects does this dataset represent? Answer this for both the preliminary dataset and the current version of the dataset.",
    "sampling_info": "Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set? If the dataset is a sample, then what is the larger set? Is the sample representative of the larger set (e.g., geographic coverage)? If so, please describe how this representativeness was validated/verified. If it is not representative of the larger set, please describe why not (e.g., to cover a more diverse range of instances, because instances were withheld or unavailable). Answer this question for the preliminary version and the current version of the dataset in question.",
    "data_modality": "What data modality does each patient data consist of? If the data is hierarchical, provide the modality details for all levels (e.g: text, image, physiological signal). Break down in all levels and specify the modalities and devices.",
    "raw_or_features": "What data does each instance consist of? “Raw” data (e.g., unprocessed text or images) or features? In either case, please provide a description.",
    "missing_info": "Is any information missing from individual instances? If so, please provide a description, explaining why this information is missing (e.g., because it was unavailable). This does not include intentionally removed information, but might include, e.g., redacted text.",
    "relationships": "Are relationships between individual instances made explicit (e.g., They are all part of the same clinical trial, or a patient has multiple hospital visits and each visit is one instance)? If so, please describe how these relationships are made explicit.",
    "errors_noise": "Are there any errors, sources of noise, or redundancies in the dataset? If so, please provide a description. (e.g., losing data due to battery failure, or in survey data subjects skip the question, radiological sources of noise)",
    "external_links": "Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)? If it links to or relies on external resources: a. Are there guarantees that they will exist, and remain constant, over time b. Are there official archival versions of the complete dataset (i.e., including the external resources as they existed at the time the dataset was created) c. Are there any restrictions (e.g., licenses, fees) associated with any of the external resources that might apply to a future user? Please provide descriptions of all external resources and any restrictions associated with them, as well as links or other access points, as appropriate.",
    "confidential_data": "Does the dataset contain data that might be considered confidential (e.g., data that is protected by legal privilege or by doctor-patient confidentiality, data that includes the content of individuals non-public communications)? If so, please provide a description.",
    "offensive_data": "Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety? If so, please describe why.",
    "de_identification": "If the dataset has been de-identified, were any measures taken to avoid the re-identification of individuals? Examples of such measures: removing patients with rare pathologies or shifting time stamps.",
    "sensitive_data": "Does the dataset contain data that might be considered sensitive in any way (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history)? If so, please provide a description."
  },
  "Devices and Contextual Attributes in Data Collection": {
    "device_details": "For data that requires a device for collection or where the context of the experiment affects the outcome, provide relevant information based on the device or context used.",
    "MRI_machine_used": "If an MRI machine was used, what is the machine and model?",
    "heart_rate_device": "If heart rate was measured, what device was used for measuring heart rate variation?",
    "cortisol_measurement_details": "If cortisol measurement is reported at multiple sites, provide details.",
    "smartphones_used": "If smartphones were used to collect data, provide the names of models.",
    "additional_info": "Provide any other relevant information or details not covered in the above questions."
  },
  "Challenge in Tests and Confounding Factors": {
    "limitation_factors": "Which factors in the data might limit the generalization of potentially derived models?",
    "auxiliary_labels_info": "Is information available as auxiliary labels for challenge tests?",
    "device_diversity": "Describe the number and diversity of devices included in the dataset.",
    "recording_specificities": "Provide details on data recording specificities, e.g., views for chest x-ray images.",
    "recording_sites_info": "Provide information on the number and diversity of recording sites included in the dataset.",
    "distribution_shifts": "Describe any distribution shifts over time in the data.",
    "confounding_factors": "What confounding factors might be present in the data?"
  },
  "Collection and Use of Demographic Information": {
    "demographic_sub_populations": "Does the dataset identify any demographic sub-populations (e.g., by age, gender, ethnicity)?",
    "demographic_categories_assessment": "If yes, describe the reasons these categories were assessed and how this information was acquired.",
    "patient_consent_info": "If patients’ demographic data is included, did they consent to the collection and use of this information?",
    "demographic_outcome_associations": "Are there any known associations between demographics and the outcomes in this dataset?",
    "demographic_update_mechanism": "Is there a mechanism for updating demographic information after its initial collection?",
    "demographic_subgroup_distribution": "Provide a description of the distribution of each subgroup population within the dataset.",
    "regulation_info": "If no demographic data is collected, is there any regulation that prevents such collection?"
  },
  "Pre-processing / De-identification": {
    "de_identification_processing": "Was there any pre-processing done for de-identification of the patients?",
    "data_cleaning_processing": "Was there any pre-processing done for cleaning the data?",
    "raw_data_availability": "Is 'raw' data (post de-identification) saved and available?",
    "exclusion_criteria": "Were any instances excluded from the dataset at the time of preprocessing? If so, why?"
  },
  "Labeling and Subjectivity of Labeling": {
    "explicit_labels": "Is there an explicit label or target associated with each data instance?",
    "label_details": "If yes, describe the labels provided, who performed the labeling, and the labeling strategy used.",
    "label_definition": "If proxy labels are used, provide the label definition.",
    "gold_standard_labels": "What proportion of the data has gold standard labels?",
    "labeller_demographics": "Provide information on the demographics of the labellers and the guidelines they followed.",
    "label_annotation_time": "On average, how much time was required to annotate each instance?",
    "labeller_compensation": "Were the labellers compensated for their time? If so, how?"
  },
  "Collection Process": {
    "REB_IRB_approval": "Were any REB/IRB approvals received for data collection?",
    "data_acquisition_details": "How was the data associated with each instance acquired?",
    "data_collection_mechanisms": "What mechanisms or procedures were used to collect the data?",
    "data_collection_participants": "Who was involved in the data collection process, and how were they compensated?",
    "data_collection_timeframe": "Over what timeframe was the data collected?"
  }
}