Our technology has been vetted through twenty-two peer-reviewed publications.

Discharge earlier, increase throughput

AutoTriage provides sound discharge recommendations, maintaining an accuracy of 93% and
a specificity of 94.5%. AutoTriage achieves this high performance by analyzing relationships
between various risk factors though its incorporation of patient vital signs, trends in vital
signs, and correlations between vital signs.1

Discharge earlier, increase throughput
1. Calvert JS, Price DA, Barton CW, Chettipally UK, Das R. Discharge recommendation based
on a novel technique of homeostatic analysis. JAMIA. 2017; 24: 24-29. Read the paper here.

Reduce bounce back to the ICU

In order to help clinicians best allocate limited ICU resources and improve patient outcomes,
we have applied AutoTriage to the difficult prediction task of unplanned readmission to the
ICU. Using only six vital signs and patient age, our machine learning tool more accurately
predicted down-transfer success than a purpose built transfer stability scoring system.

2. Desautels T, Das R, Calvert J, Trivedi M, Summers C, Wales DJ, Ercole A. Prediction of early unplanned intensive care unit readmission
in a UK tertiary-care hospital: A cross-sectional machine learning approach. BMJ Open. 2017; Sept 15: 7(9):e017199.
 Read the paper here.

Get better visibility into high risk patients

We have also applied our AutoTriage algorithm to the task of inpatient mortality prediction,
both inside and outside the intensive care unit. AutoTriage more accurately predicts mortality
than commonly used risk prediction tools and is able to maintain both sensitivity and specificity
above 80% for 12-hour mortality predictions. AutoTriage can be utilized even in data-scarce
settings by using our transfer learning algorithms.3

Discharge earlier, increase throughput
3. Desautels T, Calvert J, Hoffman J, Mao Q, Jay M, Fletcher G, Barton C, Chettipally U, Kerem Y, Das R. Using transfer learning for improved
mortality prediction in a data-scarce hospital setting. Biomed. Inform. Insights. 2017; 9: 1178222617712994. Read the paper here.

Interested in learning more?

Contact Us