tetano
Editor, Senior Moderator
JMIR Med Inform
. 2021 Apr 3.
doi: 10.2196/25066. Online ahead of print.
Predicting Unexpected Deterioration in COVID-19 Patients using PICTURE Analytic: Validation and Comparison to Existing Methods
Brandon C Cummings[SUP] 1 [/SUP], Sardar Ansari[SUP] 1 [/SUP], Jonathan R Motyka[SUP] 1 [/SUP], Guan Wang[SUP] 1 [/SUP], Richard P Medlin Jr[SUP] 1 [/SUP], Steven L Kronick[SUP] 1 [/SUP], Karandeep Singh[SUP] 2 3 4 1 [/SUP], Pauline K Park[SUP] 5 1 [/SUP], Lena M Napolitano[SUP] 5 1 [/SUP], Robert P Dickson[SUP] 2 6 1 [/SUP], Michael R Mathis[SUP] 7 1 [/SUP], Michael W Sjoding[SUP] 2 1 [/SUP], Andrew J Admon[SUP] 2 4 1 [/SUP], Ross Blank[SUP] 7 1 [/SUP], Jakob I McSparron[SUP] 2 1 [/SUP], Kevin R Ward[SUP] 1 8 4 [/SUP], Christopher E Gillies[SUP] 1 4 [/SUP]
Affiliations
Abstract
Background: The 2019 coronavirus (COVID-19) has led to unprecedented strain on healthcare facilities across the United States. Accurately identifying patients at an increased risk of deterioration may help hospitals manage their resources while improving the quality of patient care. Here we present the results of an analytical model, PICTURE (Predicting Intensive Care Transfers and Other UnfoReseen Events), to identify patients at a high risk for imminent intensive care unit (ICU) transfer, respiratory failure, or death with the intention to improve prediction of deterioration due to COVID-19.
Objective: To validate the PICTURE model's ability to predict unexpected deterioration in general ward and COVID-19 patients, and to compare its performance with the Epic Deterioration Index (EDI), an existing model which has recently been assessed for use in COVID-19 patients.
Methods: The PICTURE model was trained and validated on a cohort of hospitalized non-COVID-19 patients using electronic health record data from 2014-2018. It was then applied to two hold-out test sets: non-COVID-19 patients from 2019 and patients testing positive for COVID-19 in 2020. PICTURE results were aligned to EDI and NEWS scores for head-to-head comparison via Area Under the Receiver Operator Curve (AUROC) and Area Under the Precision Recall Curve (AUPRC). We compared the models' ability to predict an adverse event (defined as ICU transfer, mechanical ventilation use, or death). Shapley values were used to provide explanations for PICTURE predictions.
Results: In non-COVID-19 general ward patients, PICTURE achieved an AUROC (95% CI) of 0.819 (0.805 - 0.834) per observation, compared to the EDI's 0.763 (0.746 - 0.781) (n = 21,740, P < 0.001). In patients testing positive for COVID-19, PICTURE again outperformed the EDI with an AUROC (95% CI) of 0.849 (0.820 - 0.878) compared to the EDI's 0.803 (0.772 - 0.838) (n = 607, P < 0.001). The most important variables influencing PICTURE predictions in the COVID-19 cohort were a rapid respiratory rate, a high level of oxygen support, low oxygen saturation, and impaired mental status (Glasgow coma score).
Conclusions: The PICTURE model is more accurate in predicting adverse patient outcomes for both general ward patients and COVID-19 positive patients in our cohorts compared to the EDI. The ability to consistently anticipate these events may be especially valuable when considering potential incipient waves of COVID-19 infections. The generalizability of the model will require testing in other health care systems for validation.
. 2021 Apr 3.
doi: 10.2196/25066. Online ahead of print.
Predicting Unexpected Deterioration in COVID-19 Patients using PICTURE Analytic: Validation and Comparison to Existing Methods
Brandon C Cummings[SUP] 1 [/SUP], Sardar Ansari[SUP] 1 [/SUP], Jonathan R Motyka[SUP] 1 [/SUP], Guan Wang[SUP] 1 [/SUP], Richard P Medlin Jr[SUP] 1 [/SUP], Steven L Kronick[SUP] 1 [/SUP], Karandeep Singh[SUP] 2 3 4 1 [/SUP], Pauline K Park[SUP] 5 1 [/SUP], Lena M Napolitano[SUP] 5 1 [/SUP], Robert P Dickson[SUP] 2 6 1 [/SUP], Michael R Mathis[SUP] 7 1 [/SUP], Michael W Sjoding[SUP] 2 1 [/SUP], Andrew J Admon[SUP] 2 4 1 [/SUP], Ross Blank[SUP] 7 1 [/SUP], Jakob I McSparron[SUP] 2 1 [/SUP], Kevin R Ward[SUP] 1 8 4 [/SUP], Christopher E Gillies[SUP] 1 4 [/SUP]
Affiliations
- PMID: 33818393
- DOI: 10.2196/25066
Abstract
Background: The 2019 coronavirus (COVID-19) has led to unprecedented strain on healthcare facilities across the United States. Accurately identifying patients at an increased risk of deterioration may help hospitals manage their resources while improving the quality of patient care. Here we present the results of an analytical model, PICTURE (Predicting Intensive Care Transfers and Other UnfoReseen Events), to identify patients at a high risk for imminent intensive care unit (ICU) transfer, respiratory failure, or death with the intention to improve prediction of deterioration due to COVID-19.
Objective: To validate the PICTURE model's ability to predict unexpected deterioration in general ward and COVID-19 patients, and to compare its performance with the Epic Deterioration Index (EDI), an existing model which has recently been assessed for use in COVID-19 patients.
Methods: The PICTURE model was trained and validated on a cohort of hospitalized non-COVID-19 patients using electronic health record data from 2014-2018. It was then applied to two hold-out test sets: non-COVID-19 patients from 2019 and patients testing positive for COVID-19 in 2020. PICTURE results were aligned to EDI and NEWS scores for head-to-head comparison via Area Under the Receiver Operator Curve (AUROC) and Area Under the Precision Recall Curve (AUPRC). We compared the models' ability to predict an adverse event (defined as ICU transfer, mechanical ventilation use, or death). Shapley values were used to provide explanations for PICTURE predictions.
Results: In non-COVID-19 general ward patients, PICTURE achieved an AUROC (95% CI) of 0.819 (0.805 - 0.834) per observation, compared to the EDI's 0.763 (0.746 - 0.781) (n = 21,740, P < 0.001). In patients testing positive for COVID-19, PICTURE again outperformed the EDI with an AUROC (95% CI) of 0.849 (0.820 - 0.878) compared to the EDI's 0.803 (0.772 - 0.838) (n = 607, P < 0.001). The most important variables influencing PICTURE predictions in the COVID-19 cohort were a rapid respiratory rate, a high level of oxygen support, low oxygen saturation, and impaired mental status (Glasgow coma score).
Conclusions: The PICTURE model is more accurate in predicting adverse patient outcomes for both general ward patients and COVID-19 positive patients in our cohorts compared to the EDI. The ability to consistently anticipate these events may be especially valuable when considering potential incipient waves of COVID-19 infections. The generalizability of the model will require testing in other health care systems for validation.