Update questions.json

questions.json

@@ -33,6 +33,54 @@
     "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?"
   }
 }