TY - JOUR
T1 - Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care
T2 - A retrospective cohort analysis using machine learning and unstructured big data
AU - De Silva, Kushan
AU - Mathews, Noel
AU - Teede, Helena
AU - Forbes, Andrew
AU - Jönsson, Daniel
AU - Demmer, Ryan T.
AU - Enticott, Joanne
PY - 2021/5
Y1 - 2021/5
N2 - Background: Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies. Objective: To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause mortality among people with diabetes following critical care. Materials and methods: Mortality of diabetes patients were predicted using three cohorts of clinical text in a critical care database, written by physicians (n = 45253), nurses (159027), and both (n = 204280). Natural language processing was used to pre-process text documents and LASSO-regularized logistic regression models were trained and tested. Confusion matrix metrics of each model were calculated and AUROC estimates between models were compared. All predictive words and corresponding coefficients were extracted. Outcome probability associated with each text document was estimated. Results: Models built on clinical text of physicians, nurses, and the combined cohort predicted mortality with AUROC of 0.996, 0.893, and 0.922, respectively. Predictive performance of the models significantly differed from one another whereas inter-rater reliability ranged from substantial to almost perfect across them. Number of predictive words with non-zero coefficients were 3994, 8159, and 10579, respectively, in the models of physicians, nurses, and the combined cohort. Physicians’ and nursing notes, both individually and when combined, strongly predicted 1-year all-cause mortality among people with diabetes following critical care. Conclusion: Clinical notes of physicians and nurses are strong and novel prognostic markers of diabetes-associated mortality in critical care, offering potentially generalizable and scalable applications. Clinical text-derived personalized risk estimates of prognostic outcomes such as mortality could be used to optimize patient care.
AB - Background: Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies. Objective: To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause mortality among people with diabetes following critical care. Materials and methods: Mortality of diabetes patients were predicted using three cohorts of clinical text in a critical care database, written by physicians (n = 45253), nurses (159027), and both (n = 204280). Natural language processing was used to pre-process text documents and LASSO-regularized logistic regression models were trained and tested. Confusion matrix metrics of each model were calculated and AUROC estimates between models were compared. All predictive words and corresponding coefficients were extracted. Outcome probability associated with each text document was estimated. Results: Models built on clinical text of physicians, nurses, and the combined cohort predicted mortality with AUROC of 0.996, 0.893, and 0.922, respectively. Predictive performance of the models significantly differed from one another whereas inter-rater reliability ranged from substantial to almost perfect across them. Number of predictive words with non-zero coefficients were 3994, 8159, and 10579, respectively, in the models of physicians, nurses, and the combined cohort. Physicians’ and nursing notes, both individually and when combined, strongly predicted 1-year all-cause mortality among people with diabetes following critical care. Conclusion: Clinical notes of physicians and nurses are strong and novel prognostic markers of diabetes-associated mortality in critical care, offering potentially generalizable and scalable applications. Clinical text-derived personalized risk estimates of prognostic outcomes such as mortality could be used to optimize patient care.
KW - Critical care
KW - Diabetes
KW - Electronic health records
KW - LASSO
KW - Machine learning
KW - Mortality
KW - Natural language processing
KW - Prognosis
KW - Text mining
UR - http://www.scopus.com/inward/record.url?scp=85102144887&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2021.104305
DO - 10.1016/j.compbiomed.2021.104305
M3 - Article
C2 - 33705995
AN - SCOPUS:85102144887
SN - 0010-4825
VL - 132
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 104305
ER -