Concept-Set Distribution: Single Site, Anomaly Detection, Longitudinal Analysis

PEDSnet

Concept-Set Distribution: Single Site, Anomaly Detection, Longitudinal Analysis

dc.contributor	Patient-Centered Outcomes Research Institute
dc.contributor.author	PEDSnet
dc.contributor.other	Children's Hospital of Philadelphia
dc.date.accessioned	2024-09-09T17:11:49Z
dc.date.created	2024-06-05
dc.description.abstract	This check is intended to aid a user in understanding the distribution of concepts that form or represent a particular variable in a dataset. This check demonstrates how concept sets drive the prevalence or clinical composition of variables in a study. This check is designed for the identification of anomalous data within a single site's data over time. Use of this check will inform a researcher which time periods a given code was used abnormaly frequently or infrequently in the dataset.
dc.description.abstract	#### How to Access This Check 1. You may access the module's R package in [GitHub](https://github.com/ssdqa/https://github.com/ssdqa/conceptsetdistribution).<br> Or, run in R ```{r} install_github('ssdqa/https://github.com/ssdqa/conceptsetdistribution') ``` 2. Using the provided vignettes on GitHub or help in R, follow parameter input instructions for "Single Site", "Anomaly Detection", "Longitudinal Analysis" requirements.
dc.identifier.uri	https://pedsnet.org/metadata/handle/20.500.14642/765
dc.publisher	PEDSnet
dc.relation.uri	https://github.com/ssdqa/conceptsetdistribution
dc.rights	a CC-BY Attribution 4.0 License.
dc.rights.uri	http://creativecommons.org/licenses/by/4.0
dc.subject	Data Quality Check Categorizations::Data Quality Category::Consistency
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Data Source Comparison::Single Site Analysis
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Data Anomaly Method
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Temporal Evaluation::Longitudinal Analysis
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Analysis Level::Event-Level Analysis
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Data Quality Probe::Data Representation Errors
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Data Quality Probe::Information Density
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Data Quality Probe::Anomalous Values from Internal Distributions
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Data Quality Probe::Temporality Consistency Check
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Clinical Probe::Expected Clinical Event Representation
dc.subject	Data Quality Check Categorizations::Error Detection Approach::Clinical Probe::Clinical Data Distributions
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Data Visualization::Control Chart
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Data Anomaly Method::Seasonal-Trend Decomposition Using LOESS
dc.subject	Data Quality Check Categorizations::Dataset Evaluation Strategy::Data Anomaly Method::Time Series Anomalies
dc.title	Concept-Set Distribution: Single Site, Anomaly Detection, Longitudinal Analysis
dspace.entity.type	DQCheck
local.description.raw	The raw data output of this check produces eight columns of data for annual increments if analysis: <br> \|Column \|Data Type \|Definition \| \|-------------------------\|-------------------\|--------------------------------------------------------------------------------------------------------\| \|`site` \|character \|the name of the site being targeted OR "combined" if multiple sites were provided \| \|`time_start` \|date \|the start of the time period being examined \| \|`time_increment` \|character \|the length of each time period \| \|`variable` \|character \|the user-defined variable grouping assigned to the code \| \|`ct_denom` \|numeric \|the number of rows in the domain table associated with the variable \| \|`concept_id` / `concept_code`\|numeric / character\|the code of interest; for OMOP CDMs this will be `concept_id` / for PCORnet CDMS this will be concept_code\| \|`ct_concept` \|numeric \|the number of occurrences of the code \| \|`prop_concept` \|numeric \|the proportion of variable rows with the code of interest (ct_concept / ct_denom) \| <br> For analyses in monthly increments or less, the raw output produces eleven columns: \|Column \|Data Type\|Definition \| \|-----------------\|---------\|----------------------------------------------------------------------------------------------------------------\| \|`observed` \|numeric \|the original proportion of the concept \| \|`season` \|numeric \|the seasonal component of the time series \| \|`trend` \|numeric \|the trend component of the time series \| \|`remainder` \|numeric \|the residual component after "season" and "trend" are removed from "observed" - target of anomaly detection \| \|`seasadj` \|numeric \|the adjusted seasonal component \| \|`anomaly` \|character\|a flag to indicate whether the proportion is an anomaly \| \|`anomaly_direction`\|numeric \|the direction of the anomaly (upper or lower) \| \|`anomaly_score` \|numeric \|the distance between the anomaly and the centerline \| \|`recomposed_l1` \|numeric \|the lower level bound of the processed time series used to identify lower outliers \| \|`recomposed_l2` \|numeric \|the upper level bound of the processed time series used to identify upper outliers \| \|`observed_clean` \|numeric \|the original proportion after the season and trend components have been removed and anomalies have been detected\| {.dqcheck-table}
local.description.viz	This check output varies based on the time increment input by the user. For yearly time increments, a control chart highlights anomalies in the proportion of patients per `concept_id` for the provided variable over time. A P Prime chart is used to account for the high sample size, meaning that the standard deviation has been multiplied by a numerical constant. Blue dots along the line indicate non-anomalous values, while orange dots are anomalies. The chart is accompanied by a concept reference table which provides the total count of the concept in question. When using smaller time increments, such as months or weeks, seasonality can make it difficult to detect true anomalies in a time series. This output computes anomalies while ignoring seasonality and outputs 2 graphs: a time series line graph with anomalies highlighted with a red dot, and a four-faceted time series line graph demonstrating the anomaly decomposition to make clarify how the anomalies were identified.
local.dqcheck.requirement	cohort
local.dqcheck.requirement	domain_tbl
local.dqcheck.requirement	concept_set
local.dqcheck.requirement	omop_or_pcornet
local.dqcheck.requirement	multi_or_single_site
local.dqcheck.requirement	anomaly_or_exploratory
local.dqcheck.requirement	num_concept_combined
local.dqcheck.requirement	num_concept_1
local.dqcheck.requirement	num_concept_2
local.dqcheck.requirement	p_value
local.dqcheck.requirement	age_groups
local.dqcheck.requirement	time
local.dqcheck.requirement	time_span
local.dqcheck.requirement	time_period
local.subject.flat	Single Site Analysis
local.subject.flat	Data Anomaly Method
local.subject.flat	Longitudinal Analysis
local.subject.flat	Event-Level Analysis
local.subject.flat	Consistency
local.subject.flat	Data Representation Errors
local.subject.flat	Information Density
local.subject.flat	Anomalous Values from Internal Distributions
local.subject.flat	Temporality Consistency Check
local.subject.flat	Expected Clinical Event Representation
local.subject.flat	Clinical Data Distributions
local.subject.flat	Control Chart
local.subject.flat	Seasonal-Trend Decomposition Using LOESS
local.subject.flat	Time Series Anomalies