Related Experiment Video
Updated: Jan 5, 2026
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
Published on: May 10, 2022
Sensitivity and specificity of an algorithm based on medico-administrative data to identify hospitalized patients
Emmanuel Oger1, Marie-Anne Botrel2, Catherine Juchault3
1Univ Rennes, EA 7449 REPERES [Pharmacoepidemiology and Health Services Research], Rennes, France. emmanuel.oger@univ-rennes1.fr.
Insights
An ICD-10-based algorithm for identifying major bleeding events showed low sensitivity (65%) and varied accuracy across bleeding types. Medical validation and specific data collection are recommended over relying solely on this algorithm.
Area of Science:
- Medical Informatics
- Clinical Epidemiology
- Health Services Research
Background:
- Validation studies for International Classification of Diseases, 10th Revision (ICD-10) algorithms to detect major bleeding are limited.
- Existing research often focuses on positive predictive values, neglecting other crucial accuracy metrics.
Purpose of the Study:
- To assess the sensitivity and specificity of an ICD-10-based algorithm for identifying major bleeding events in adult patients admitted to a hospital.
- To evaluate the algorithm's performance across different types of major bleeding.
Main Methods:
- A cross-sectional, retrospective analysis was conducted on adult hospital stays at Rennes University Hospital, France, in 2014.
- An index test using ICD-10 diagnoses identified potential major bleeding events.
- A two-step reference standard involved electronic health record review and expert chart analysis to classify stays as major bleeding or no major bleeding.
Main Results:
- The algorithm identified 637 bleeding events out of 16,012 hospital stays, with the reference standard confirming 736 major bleeding events.
- Overall sensitivity was 65% (95% CI, 62-69%) and specificity was 99.0%.
- Accuracy varied by bleeding type, with higher sensitivity for intracranial hemorrhage (96% PPV) compared to other bleeding events (59% PPV).
Conclusions:
- The ICD-10-based algorithm demonstrates low overall sensitivity for detecting major bleeding events.
- Significant variations in accuracy across different bleeding types necessitate caution when using this algorithm alone.
- The findings underscore the need for dedicated data collection and expert medical validation for accurate assessment of major bleeding incidence.
Background:
Validation studies on an ICD-10-based algorithm to identify major bleeding events are scarce, and mostly focused on positive predictive values.
Objective:
To evaluate the sensitivity and specificity of an ICD-10-based algorithm in adult patients referred to hospital.
Methods:
This was a cross-sectional, retrospective analysis. Among all hospital stays of adult patients referred to Rennes University Hospital, France, through the emergency ward in 2014, we identified major bleeding events according to an index test based on a list of ICD-10 diagnoses. As a reference, a two-step process was applied: firstly, a computerized request for electronic health records from the emergency ward, using several hemorrhage-related diagnostic codes and specific emergency therapies so as to discard stays with a very low probability of bleeding; secondly, a chart review of selected records was conducted by a medical expert blinded to the index test results and each hospital stay was classified into one of two exclusive categories: major bleeding or no major bleeding, according to pre-specified criteria.
Results:
Out of 16,012 hospital stays, the reference identified 736 major bleeding events and left 15,276 stays considered as without the target condition. The index test identified 637 bleeding events: 293 intracranial hemorrhages, 197 gastrointestinal hemorrhages and 147 other bleeding events. Overall, sensitivity was 65% (95%CI, 62 to 69), and specificity was 99.0%. We observed differential sensitivity and specificity across bleeding types, with the highest values for intracranial hemorrhage. Positive predictive values ranged from 59% for "other" bleeding events, to 71% (95%CI, 65 to 78) for gastrointestinal hemorrhage, and 96% for intracranial hemorrhage.
Conclusions:
Low sensitivity and differential measures of accuracy across bleeding types support the need for specific data collection and medical validation rather than using an ICD-10-based algorithm for assessing the incidence of major bleeding.
