Multicenter evaluation of a method to identify delayed diagnosis of diabetic ketoacidosis and sepsis in
Kenneth A Michelson1, Richard G Bachur1, Andrea T Cruz2
1Division of Emergency Medicine, Boston Children's Hospital, Boston, MA, USA.
Insights
Automated identification of delayed pediatric sepsis diagnosis is possible using emergency department revisit data. While effective for diabetic ketoacidosis, sepsis identification requires further refinement due to lower specificity.
Area of Science:
- Pediatric Emergency Medicine
- Health Informatics
- Clinical Decision Support
Background:
- Delayed diagnosis of serious pediatric conditions like diabetic ketoacidosis (DKA) and sepsis in emergency departments (EDs) leads to poor outcomes.
- Automated methods are needed to identify these delays for timely intervention.
Purpose of the Study:
- To develop a method for automatically identifying delayed diagnoses of new-onset DKA and sepsis in pediatric EDs.
- To evaluate the effectiveness of using administrative data for this automated identification.
Main Methods:
- Retrospective analysis of pediatric patients (<21 years) from five EDs with two encounters within 7 days.
- Diagnosis of DKA or sepsis on the second encounter.
- Validated rubric used for delayed diagnosis assessment.
- Logistic regression derived a decision rule using administrative data.
Main Results:
- Delayed diagnosis was found in 89% of DKA cases with revisits within 7 days.
- For sepsis, 17% of patients had delayed diagnosis; fewer days between encounters was a key factor.
- The sepsis model achieved 83.5% sensitivity and 61.3% specificity for delayed diagnosis.
Conclusions:
- A 7-day revisit effectively identifies delayed diagnosis of pediatric DKA.
- Automated identification of delayed sepsis diagnosis using revisits shows promise but requires manual review due to low specificity.
Objectives:
To derive a method of automated identification of delayed diagnosis of two serious pediatric conditions seen in the emergency department (ED): new-onset diabetic ketoacidosis (DKA) and sepsis.
Methods:
Patients under 21 years old from five pediatric EDs were included if they had two encounters within 7 days, the second resulting in a diagnosis of DKA or sepsis. The main outcome was delayed diagnosis based on detailed health record review using a validated rubric. Using logistic regression, we derived a decision rule evaluating the likelihood of delayed diagnosis using only characteristics available in administrative data. Test characteristics at a maximal accuracy threshold were determined.
Results:
Delayed diagnosis was present in 41/46 (89 %) of DKA patients seen twice within 7 days. Because of the high rate of delayed diagnosis, no characteristic we tested added predictive power beyond the presence of a revisit. For sepsis, 109/646 (17 %) of patients were deemed to have a delay in diagnosis. Fewer days between ED encounters was the most important characteristic associated with delayed diagnosis. In sepsis, our final model had a sensitivity for delayed diagnosis of 83.5 % (95 % confidence interval 75.2-89.9) and specificity of 61.3 % (95 % confidence interval 56.0-65.4).
Conclusions:
Children with delayed diagnosis of DKA can be identified by having a revisit within 7 days. Many children with delayed diagnosis of sepsis may be identified using this approach with low specificity, indicating the need for manual case review.
