Inclusion of Unstructured Clinical Text Improves Early Prediction of Death or Prolonged ICU Stay*

Weissman, Gary E.; Hubbard, Rebecca A.; Ungar, Lyle H.; Harhay, Michael O.; Greene, Casey S.; Himes, Blanca E.; Halpern, Scott D.

doi:10.1097/ccm.0000000000003148

Cited by 69 publications

(70 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Weissman et al 36 studied the feasibility of incorporating clinical free text into a model to predict the combined outcome of mortality or prolonged length of stay, but their analysis was limited to a single institution, so they were not able to assess generalizability. Moreover, Weissman et al 36 found only very small marginal gains in predictive performance when using more complex machine learning methods, namely gradient boosting, over regularized logistic regression, as we used here.…”

Section: Discussionmentioning

confidence: 99%

Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data

et al. 2018

View full text Add to dashboard Cite

Key Points Question Can a prediction model for mortality in the intensive care unit be improved by using more laboratory values, vital signs, and clinical text in electronic health records? Findings In this cohort study of 101 196 patients in the intensive care unit, a machine learning–based model using all available measurements of vital signs and laboratory values, plus clinical text, exhibited good calibration and discrimination in predicting in-hospital mortality, yielding an area under the receiver operating characteristic curve of 0.922. Meaning Applying methods from machine learning and natural language processing to information already routinely collected in electronic health records, including laboratory test results, vital signs, and clinical free-text notes, significantly improves a prediction model for mortality in the intensive care unit compared with approaches that use only the most abnormal vital sign and laboratory values.

show abstract

Section: Discussionmentioning

confidence: 99%

Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Frost et al [23], using used text fields from over 43,000 patients to, predict risk of frequent emergency department visits and high system costs with a Cstatistic of 0.71 and 0.76, respectively. Weissman et al [24] showed that inclusion of unstructured text along with structured data improved prediction of death in the ICU by using four different predictive modeling approaches. Text-mining of clinical notes has been used to identify postoperative complications in veterans [25] but, to the best of our knowledge, has not been utilized for predicting postoperative surgery outcomes in children.…”

Section: Methodsmentioning

confidence: 99%

“…Frost et al [23], using used text fields from over 43,000 patients to, predict risk of frequent emergency department visits and high system costs with a C-statistic of 0.71 and 0.76, respectively. Weissman et al [24] showed that inclusion of unstructured text along with structured data improved prediction of death in the ICU by using four different predictive modeling approaches.…”

Section: Introductionmentioning

confidence: 99%

Unstructured Text in EMR Improves Prediction of Death after Surgery in Children

et al. 2019

View full text Add to dashboard Cite

Text fields in electronic medical records (EMR) contain information on important factors that influence health outcomes, however, they are underutilized in clinical decision making due to their unstructured nature. We analyzed 6497 inpatient surgical cases with 719,308 free text notes from Le Bonheur Children’s Hospital EMR. We used a text mining approach on preoperative notes to obtain a text-based risk score to predict death within 30 days of surgery. In addition, we evaluated the performance of a hybrid model that included the text-based risk score along with structured data pertaining to clinical risk factors. The C-statistic of a logistic regression model with five-fold cross-validation significantly improved from 0.76 to 0.92 when text-based risk scores were included in addition to structured data. We conclude that preoperative free text notes in EMR include significant information that can predict adverse surgery outcomes.

show abstract

“…Using neural networks, classification algorithms can be constructed for identification of the most important terms in physician notes, which then can be used to construct ML models to predict outcomes such as mortality in the surgical ICU. 39 One such model, called Early Mortality Prediction for Intensive Care Unit patients, has been shown to outperform traditional scoring systems such as acute physiology and chronic health evaluation (APACHE) and sequential organ failure assessment (SOFA) despite missing values within the training datasets. The area under the curve (AUC) is 0.82 ± 0.04 compared with the traditional scoring systems which range from 0.54 to 0.65.…”

Section: Predictive Analyticsmentioning

confidence: 99%

Artificial Intelligence in Neuroanesthesiology and Neurocritical Care

Rajagopalan

Kulkarni²

2020

Journal of Neuroanaesthesiology and Critical Care

View full text Add to dashboard Cite

Artificial intelligence (AI) already influences almost every sector of our daily life, including the rapidly evolving technologies and datasets of healthcare delivery. The applications in medicine have significantly evolved over the past few decades and have shown promising results. Despite constant efforts to incorporate AI into the field of anesthesiology since its inception, it is still not commonplace. Neuroanesthesiology and neurocritical care is a discipline of medicine that deals with patients having disorders of the nervous system comprising a complex combination of both medical and surgical disease conditions. AI can be used for better monitoring, treatment, and outcome prediction, thereby reducing healthcare costs, minimizing delays in patient management, and avoiding medical errors. In this review, we have discussed the applications of AI and its potential in aiding the clinician’s judgment in several aspects of neuroanesthesiology and neurocritical care, some of the barriers to its implementation, and the future trends in improving education in this field, all of which will require further work to understand its exact scope.

show abstract

Inclusion of Unstructured Clinical Text Improves Early Prediction of Death or Prolonged ICU Stay*

Cited by 69 publications

References 44 publications

Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data

Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data

Unstructured Text in EMR Improves Prediction of Death after Surgery in Children

Artificial Intelligence in Neuroanesthesiology and Neurocritical Care

Contact Info

Product

Resources

About