Automated annotation of clinical data

Abstract

When annotating a patient's medical or clinical record, an automated annotation system compares aggregated patient data (e.g., historical vital sign data, lab results, patient admission / discharge / transfer information, etc.) and matches events and / or patterns therein to procedure profiles to determine whether a given procedure is required, in progress, or completed. If the probability of procedure necessity or occurrence is above a predetermined threshold, then system inserts an annotation into the clinical record to mitigate a need for a clinician to manually enter the annotation. Alarm parameters are adjusted to reflect a physiological response to the determined procedure, to reduce false alarm triggers. Additionally or alternatively, triggered advisories may be suppressed from the user interface for a time period during which conditions specified in the procedure profile exist, or for a specific period of time following the procedure. In another embodiment, triggered advisories that occur under the specific conditions identified in a procedure profile may be flagged in the patient's medical record with a notification that the suspected procedure is being performed.

Description

technical field [0001] This application is particularly applicable to medical record data systems. However, it should be appreciated that the described techniques may also be applied to other types of data recording systems, other medical systems, and / or other record annotation applications. Background technique [0002] Annotation of medical data involves adding explanatory notes to medical data, such as data automatically collected from patient monitoring systems and stored on a central station. Annotations or explanatory notes identify medical procedures, findings, medications administered, observations, or other relevant information entered by a care provider. Annotations are useful for therapeutic purposes, accounting purposes, administrative and legal purposes, and research purposes. However, annotation is a time-consuming, labor-intensive and expensive manual process. In addition, language choices and abbreviations often vary by annotator, making interpretation and...

AI Technical Summary

Problems solved by technology

Furthermore, without properly annotated data, it is difficult to automatically determine the extent to which clinical practice guidelines have been implemented, which hinders the implementation of computer-executable practice guidelines and protocols

[0005] There is an unmet need in the art for systems and methods that facilitate automated annotation of patient medical data, etc., thereby overcoming the aforementioned deficiencies

Images