Blog

AdobeStock_244479157-ai (2)

Automatic Tagging Validation Study

System developed by CLEW allows large-scale AI Model Development….

A fundamental requirement for developing machine learning (ML) predictive models is to accurately identify (i.e., tag) significant events of interest within the data. These tags are critical for training predictive models to identify features that predict them and validate the models’ performance against those tags, which serve as a gold standard against which the models’ predictions are assessed. However, predictive model development usually requires vast amounts of data, making these events’ manual identification and timestamping inefficient, timely, and expensive.

A new study recently published in the Healthcare Informatics Research journal validates an automatic tagging system developed by Clew Medical. This rule-based tagging system was designed to identify within the electronic medical record (EMR) data-specific deterioration events so that predictive models could be developed and validated for those events. More specifically, the system identified and tagged respiratory and hemodynamic deterioration events within a large ICU database. The study validates the performance of the automatic tagging system by comparing it to tagging by expert human reviewers.

The study results demonstrated how the automated tagging system was able to identify respiratory and hemodynamic deterioration events rapidly and efficiently in a large dataset and tag these events close to the accuracy of the human experts; the overall agreement rate between the automated system and the human experts was 89.4% for respiratory failure events, and 87.1% for hemodynamic instability events.

In summary, the study validates the automatic tagging system for respiratory and hemodynamic deterioration events, providing a rapid and accurate tool for mass tagging of a compound clinical database. The system will allow the replacement of human reviewers and considerable time and resource-saving while creating validated, labeled databases for training artificial intelligence algorithms.

 

Reference:

Jeddah D, Chen O, Lipsky A, Forgacs A, Celniker G, Lilly C, Pessach I. Validation of an Automatic Tagging System for Identifying Respiratory and Hemodynamic Deterioration Events in the Intensive Care Unit. Healthcare Informatics Research, 2021 July; 27(3): 241-248.
https://e-hir.org/journal/view.php?doi=10.4258/hir.2021.27.3.241

SHARE

Share on facebook
Share on twitter
Share on pinterest
Share on linkedin

(*) indicates mandatory field

One moment while we direct
you to the CLEW website

Patient View
Rapid, clear, consistent patient data summary and visualization

  • Patient risk stratification (high, moderate and low risk patients)
  • Intubated patients
  • Vasopressors/inotrope support
  • Empty beds
  • Key patient and unit information
  • Occupancy, ventilator status and vasoactive medication
  • User selectable vital sign display
  • Summary of all relevant lab results
    Dynamic and collaborative caregiver task list
  • Aggregate patient demographicsand PMH (past medical history) andpredicted risk level

Patient View
Rapid, clear, consistent patient data summary and visualization
High Risk Patients

  • Tasks
  • New Admissions (pulled from a left sidebar)
  • User selectable vital sign display
  • Summary of all relevant lab results
  • Dynamic and collaborative caregiver task list
  • Aggregate patient demographics, PMH and risk level

Unit View
Full TeleICU situational awareness, displaying patient data and predicted state from all units and highlighting all notifications

  • Patient risk stratification (high, moderate and low risk patients)
    Intubated patients
  • Patients on vasoactive medication
    Unit occupancy
  • Patients on vasoactive medication
  • High-level estimation of the overall unit acuity

    Key patient and unit information

     

Work List
Integration with the TeleICU workflow by gathering all notifications, tasks, new admissions and high-risk patients

  • Notifications
  • High Risk Patients
  • Tasks
  • New Admissions (pulled from a left sidebar)

Unit View by Layout

Full ICU situational awareness, displaying patient data and predicted risk level, for one unit or multiple units. The display highlights all notifications, low risk patients and other key clinical information, to provide multi-dimensional situational awareness.

  • Patient risk stratification (high, moderate and low risk patients))
  • Intubated patients
  • Vasopressors/inotrope support
  • Empty beds
  • Key patient and unit information
  • Occupancy, ventilator status and vasoactive medication
Thank you for requesting our demo.

You’ll be hearing from our specialist shortly.