Background

Column

Purpose

The purpose of this interactive dashboard is to summarise the chief complaint text and diagnosis codes as part of the iterative development cycle, or as part of an initial description of the content of these fields in existing syndromes or categories. The data source used in this dashboard is the Chief Complaint Query Validation (CCQV) data source in NSSP-ESSENCE, which includes the chief complaint and discharge diagnosis fields, and does not include facility location, patient location, or other demographic information. This data source was created with the Syndromic Community of Practice (CoP) so that users can test and create new syndrome categories using a large corpus of chief complaint and diagnosis code data that includes more variation than would be present in any one site. Some sites have opted out of contributing their data to the Query Validation data source, including Arizona, Idaho, Illinois, Marion County, Indiana, Massachusetts, North Dakota, and Ohio.

Interactive Visualizations

The visualizations in this dashboard include total weekly volume of encounters, the 200 most frequent n-gram frequencies of chief complaint terms and discharge diagnosis codes, and term co-occurrence network graphs for the ChiefComplaintParsed and CCDD fields. Potential clusters or groupings of terms are visualized by node color and can be selected from the “Select by group” drop down menu. All widgets were produced with the Plotly and visNetwork packages which provide hovering functionality such as displaying data point values, ICD-10 code descriptions, and co-occurrence frequencies.

Query Details

Fields Query
CCDD (,^[;/ ]J70.5^,or,^[;/ ]J705^,or,^[;/ ]X08.8^,or,^[;/ ]X088^,or,^[;/ ]X01.1^,or,^[;/ ]X011^,or,^[;/ ]T59.81^,or,^[;/ ]T5981^,or,^[;/ ]423123007[;/ ]^,or,^[;/ ]508.2^,or,^[;/]5082[;/]^,or,^[;/ ]E898.1^,or,^[;/ ]E8981^,or,^[;/ ]E892^,or,^[;/ ]426936004[;/ ]^,or,^[;/ ]217486005[;/ ]^,or,^wild fire^,or,^wildfire^,or,(,^smoke ^,andnot,(,^ a smoke^,or,^ to smoke^,or,^alarm^,or,^can smoke^,or,^denies smoke^,or,^detector^,or,^did smoke^,or,^does not smoke^,or,^does smoke^,or,^go and smoke^,or,^go smoke^,or,^he smoke^,or,^husband smoke^,or,^n_t smoke^,or,^never smoke^,or,^no smoke^,or,^or smoke^,or,^out and smoke^,or,^outside and smoke^,or,^secondhand^,or,^second hand^,or,^smoke bomb^,or,^smoke shop^,or,^smoke week^,or,^smoke[drs]^,or,^smoke^a lot^,or,^they smoke^,or,^upstairs and smoke^,or,^was smoking^,or,^wife smoke^,or,^without smoke^,or,^blunt^,or,^joint^,),),),andnot,(,^canab^,or,^vape^,or,^cannab^,or,^cig^,or,^crack^,or,^her[io][oi]n^,or,!k2!,or,^marij^,or,!meth!,or,!pot!,or,^spice^,or,^tobac^,or,^weed^,or,^normal saline^,or,^ on fire^,or,^cooking^,or,^kitchen^,or,!stove!,or,!oven!,or,^motor [bc]^,or,^motor[bc]^,or,(,^motor vehicle^,and,(,^collision^,or,^accident^,or,^crash^,),),)

Column

Total Number of Encounters

11805

Date Range

June 28, 2020 to November 08, 2020

Total Weekly Volume of Encounters from Query Validation Data Source -ESSENCE

Chief Complaint

Column

Weekly Mean Number of Characters in Chief Complaint Field

Weekly Median Number of Characters in Chief Complaint Field

Column

Weekly Mean Number of Tokens in Chief Complaint Field

Weekly Median Number of Tokens in Chief Complaint Field

Discharge Diagnosis

Column

Weekly Mean Number of Characters in Discharge Diagnosis Field

Weekly Median Number of Characters in Discharge Diagnosis Field

Column

Weekly Mean Number of Tokens in Discharge Diagnosis Field

Weekly Median Number of Tokens in Discharge Diagnosis Field

Unigram

Column

Chief Complaint

Column

Discharge Diagnosis

Bigram

Column

Chief Complaint

Column

Discharge Diagnosis

Trigram

Column

Chief Complaint

Column

Discharge Diagnosis

Chief Complaint

Chief Complaint Parsed Term Co-occurrence Network Graph

Chief Complaint and Discharge Diagnosis

CCDD Term Co-occurrence Network Graph

Increasing Unigrams

Trends represent the proportion of term occurrences on a weekly time resolution. The numerator is the number of occurrences of the term in a specific week, while the denominator is the sum of all term frequencies in that week. A binomial model is fit to each time series to determine if term occurrence has changed significantly over time. Terms with a positive slope (test statistic) and adjusted p-value < 0.01 are categorized as having significant increase, while terms with a negative slope and adjusted p-value < 0.01 are categorized as having significant decrease.

Column

Column

Decreasing Unigrams

Trends represent the proportion of term occurrences on a weekly time resolution. The numerator is the number of occurrences of the term in a specific week, while the denominator is the sum of all term frequencies in that week. A binomial model is fit to each time series to determine if term occurrence has changed significantly over time. Terms with a positive slope (test statistic) and adjusted p-value < 0.01 are categorized as having significant increase, while terms with a negative slope and adjusted p-value < 0.01 are categorized as having significant decrease.

Column

Column