Early Detection of In-Patient Deterioration: One Prediction Model Does Not Fit All

Jacob N Blackwell; Jessica Keim-Malpass; Matthew T Clark; Rebecca L Kowalski; Salim N Najjar; Jamieson M Bourque; Douglas E Lake; J Randall Moorman

doi:10.1097/CCE.0000000000000116

Early Detection of In-Patient Deterioration: One Prediction Model Does Not Fit All

Crit Care Explor. 2020 May 11;2(5):e0116. doi: 10.1097/CCE.0000000000000116. eCollection 2020 May.

Authors

Jacob N Blackwell¹, Jessica Keim-Malpass^{2

3}, Matthew T Clark⁴, Rebecca L Kowalski¹, Salim N Najjar¹, Jamieson M Bourque^{1

2}, Douglas E Lake^{1

3}, J Randall Moorman^{1

3

4}

Affiliations

¹ Division of Cardiovascular Medicine, Department of Medicine, University of Virginia, Charlottesville, VA.
² Department of Acute and Specialty Care, University of Virginia School of Nursing Charlottesville, VA.
³ Center for Advanced Medical Analytics, University of Virginia, Charlottesville, VA.
⁴ AMP3D, Charlottesville, VA.

Abstract

Objectives: Early detection of subacute potentially catastrophic illnesses using available data is a clinical imperative, and scores that report risk of imminent events in real time abound. Patients deteriorate for a variety of reasons, and it is unlikely that a single predictor such as an abnormal National Early Warning Score will detect all of them equally well. The objective of this study was to test the idea that the diversity of reasons for clinical deterioration leading to ICU transfer mandates multiple targeted predictive models.

Design: Individual chart review to determine the clinical reason for ICU transfer; determination of relative risks of individual vital signs, laboratory tests and cardiorespiratory monitoring measures for prediction of each clinical reason for ICU transfer; and logistic regression modeling for the outcome of ICU transfer for a specific clinical reason.

Setting: Cardiac medical-surgical ward; tertiary care academic hospital.

Patients: Eight-thousand one-hundred eleven adult patients, 457 of whom were transferred to an ICU for clinical deterioration.

Interventions: None.

Measurements and main results: We calculated the contributing relative risks of individual vital signs, laboratory tests and cardiorespiratory monitoring measures for prediction of each clinical reason for ICU transfer, and used logistic regression modeling to calculate receiver operating characteristic areas and relative risks for the outcome of ICU transfer for a specific clinical reason. The reasons for clinical deterioration leading to ICU transfer were varied, as were their predictors. For example, the three most common reasons-respiratory instability, infection and suspected sepsis, and heart failure requiring escalated therapy-had distinct signatures of illness. Statistical models trained to target-specific reasons for ICU transfer performed better than one model targeting combined events.

Conclusions: A single predictive model for clinical deterioration does not perform as well as having multiple models trained for the individual specific clinical events leading to ICU transfer.

Keywords: clinical computing; continuous predictive analytics monitoring; critical care; deterioration; intensive care unit transfer; predictive analytics.