Limits...
ClinicalTime: Identification of Patients with Acute Kidney Injury using Temporal Abstractions and Temporal Pattern Matching.

Capurro D, Barbe M, Daza C, María JS, Trincado J, Gomez I - AMIA Jt Summits Transl Sci Proc (2015)

Bottom Line: Classification accuracy was measured.Its performance was superior to simply using ICD-9 codes, which correctly classified 66% of all patients.ClinicalTime, a temporal query system, is a valid method to add to the currently available ones to identify patient phenotypes in patient databases and, thus, improving our ability to re-use routinely collected electronic clinical data for secondary purposes.

View Article: PubMed Central - PubMed

Affiliation: Pontificia Universidad Católica de Chile, Santiago, Chile ; University of Washington, Seattle, WA.

ABSTRACT

Introduction: The rising cost of providing healthcare services creates an extreme pressure to know what works best in medicine. Traditional methods of generating clinical evidence are expensive and time consuming. The availability of electronic clinical data generated during routine patient encounters provides an opportunity to use that information to generate new clinical evidence. However, electronic clinical data is frequently marred by inadequate quality that impedes such secondary uses. This study provides a proof-of-concept and tests the classification accuracy of ClinicalTime-a temporal query system-to identify patient cohorts in clinical databases.

Methods: we randomly selected a sample of medical records from the MIMIC-II database, an anonymized database of intensive care patients. Records were manually classified as having an acute kidney injury or not according to the AKIN criteria. Those records were then blindly classified using ClinicalTime to represent the AKIN criteria. Classification accuracy was measured.

Results: ClinicalTime correctly classified 88% of all patients, with a sensitivity of 0.93 and specificity of 0.84. Its performance was superior to simply using ICD-9 codes, which correctly classified 66% of all patients.

Conclusions: ClinicalTime, a temporal query system, is a valid method to add to the currently available ones to identify patient phenotypes in patient databases and, thus, improving our ability to re-use routinely collected electronic clinical data for secondary purposes.

No MeSH data available.


Related in: MedlinePlus

patterns of clinical time intervals used to search for patients meeting the AKIN acute kidney injury criteria. Pattern a) involves two temporal intervals of serum creatinine related by a temporal relation (Before), a change in creatinine with a magnitude (0.3 mg/dL or 50% from baseline), a maximum distance (<48 hours) and a direction (elevation). Pattern b) involves only one temporal interval of urinary output of type ‘moving window’ in which ClinicalTime checks whether the condition was met in any 6-hour time-window.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4525253&req=5

f1-2090794: patterns of clinical time intervals used to search for patients meeting the AKIN acute kidney injury criteria. Pattern a) involves two temporal intervals of serum creatinine related by a temporal relation (Before), a change in creatinine with a magnitude (0.3 mg/dL or 50% from baseline), a maximum distance (<48 hours) and a direction (elevation). Pattern b) involves only one temporal interval of urinary output of type ‘moving window’ in which ClinicalTime checks whether the condition was met in any 6-hour time-window.

Mentions: After manually annotating this sample, we built a query using ClinicalTime that represented the following patterns of time intervals as shown in Figure 1.


ClinicalTime: Identification of Patients with Acute Kidney Injury using Temporal Abstractions and Temporal Pattern Matching.

Capurro D, Barbe M, Daza C, María JS, Trincado J, Gomez I - AMIA Jt Summits Transl Sci Proc (2015)

patterns of clinical time intervals used to search for patients meeting the AKIN acute kidney injury criteria. Pattern a) involves two temporal intervals of serum creatinine related by a temporal relation (Before), a change in creatinine with a magnitude (0.3 mg/dL or 50% from baseline), a maximum distance (<48 hours) and a direction (elevation). Pattern b) involves only one temporal interval of urinary output of type ‘moving window’ in which ClinicalTime checks whether the condition was met in any 6-hour time-window.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4525253&req=5

f1-2090794: patterns of clinical time intervals used to search for patients meeting the AKIN acute kidney injury criteria. Pattern a) involves two temporal intervals of serum creatinine related by a temporal relation (Before), a change in creatinine with a magnitude (0.3 mg/dL or 50% from baseline), a maximum distance (<48 hours) and a direction (elevation). Pattern b) involves only one temporal interval of urinary output of type ‘moving window’ in which ClinicalTime checks whether the condition was met in any 6-hour time-window.
Mentions: After manually annotating this sample, we built a query using ClinicalTime that represented the following patterns of time intervals as shown in Figure 1.

Bottom Line: Classification accuracy was measured.Its performance was superior to simply using ICD-9 codes, which correctly classified 66% of all patients.ClinicalTime, a temporal query system, is a valid method to add to the currently available ones to identify patient phenotypes in patient databases and, thus, improving our ability to re-use routinely collected electronic clinical data for secondary purposes.

View Article: PubMed Central - PubMed

Affiliation: Pontificia Universidad Católica de Chile, Santiago, Chile ; University of Washington, Seattle, WA.

ABSTRACT

Introduction: The rising cost of providing healthcare services creates an extreme pressure to know what works best in medicine. Traditional methods of generating clinical evidence are expensive and time consuming. The availability of electronic clinical data generated during routine patient encounters provides an opportunity to use that information to generate new clinical evidence. However, electronic clinical data is frequently marred by inadequate quality that impedes such secondary uses. This study provides a proof-of-concept and tests the classification accuracy of ClinicalTime-a temporal query system-to identify patient cohorts in clinical databases.

Methods: we randomly selected a sample of medical records from the MIMIC-II database, an anonymized database of intensive care patients. Records were manually classified as having an acute kidney injury or not according to the AKIN criteria. Those records were then blindly classified using ClinicalTime to represent the AKIN criteria. Classification accuracy was measured.

Results: ClinicalTime correctly classified 88% of all patients, with a sensitivity of 0.93 and specificity of 0.84. Its performance was superior to simply using ICD-9 codes, which correctly classified 66% of all patients.

Conclusions: ClinicalTime, a temporal query system, is a valid method to add to the currently available ones to identify patient phenotypes in patient databases and, thus, improving our ability to re-use routinely collected electronic clinical data for secondary purposes.

No MeSH data available.


Related in: MedlinePlus