Abstract Details

Title Predicting Neurological Recovery from Coma Post-cardiac Arrest Using Natural Language Processing

Topic Neuro Trauma and Critical Care

Presentation(s) P7 - Poster Session 7 (5:00 PM-6:00 PM)

Poster/Presentation
Number 7-006

Objective Predict neurologic outcomes for comatose patients following cardiac arrest using natural language processing from electronic health records (EHR).

Background Clinical notes from the EHR are an abundant and heterogeneous source that captures a patient's clinical course. Machine learning algorithms have the potential to identify patterns from clinical notes that may support prognostication following cardiac arrest.

Design/Methods The cohort included comatose adult cardiac arrest patients from two hospitals in San Francisco and the MIMIC-III database. Patient neurologic outcomes were classified as Good (CPC 1-3) or Poor (CPC 4-5) at hospital discharge based on manual review of clinical notes. Clinical notes were reduced to 200 characters following specific headers, concatenated, tokenized, and lemmatized to extract n-gram features. A logistic regression model with L-BFGS optimization was trained on 70% of patients to predict neurological outcomes at discharge. Model performance was evaluated on the remaining 30% of patients using AUROC and AUPRC scores. Performance on the model was then compared between predictions on all notes vs a subset of notes limited to 24 hours after cardiac arrest.

Results We gathered 4,988 notes from 357 patients, with 242 of these patients having poor outcomes at discharge. The most common note types included consult notes (33.6%) and nursing notes (55.9%). The model’s AUROC and AUPRC micro-averages were 0.9 and 0.89, respectively. The model predicted 80% of individuals in the poor outcome group (CPC 4-5) and 76% in the good outcome group (CPC 1-3) when using all notes. The model performance decreased 7% when comparing predictions from all notes to 24 hours of notes.

Conclusions Our model had excellent performance for discriminating good and poor outcomes but had moderate accuracy. The model changed prediction class over time in 7% of patients, highlighting the dynamic process in the prognostic assessment of neurological recovery by clinicians in cardiac arrest.

Authors/Disclosures
Parker Houston, BS PRESENTER	Mr. Houston has nothing to disclose.
Sophie Furlow, MEng	Ms. Furlow has received personal compensation for serving as an employee of Abbott.
Kevin Bao	Mr. Bao has nothing to disclose.
Bo Zhou (University of California, San Francisco)	No disclosure on file
Gerardo H. Velasquez	Mr. Velasquez has nothing to disclose.
Amanjot Bains	Ms. Bains has nothing to disclose.
Kinshuk Basu	Mr. Basu has nothing to disclose.
Ori Lieberman, MD, PhD (UCSF)	Dr. Lieberman has received research support from UCSF.
Claude Hemphill III, MD, FAAN (Zuckerberg San Francisco General Hospital)	Dr. Hemphill has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Zoll. Dr. Hemphill has received personal compensation in the range of $0-$499 for serving on a Scientific Advisory or Data Safety Monitoring board for Aurenar. Dr. Hemphill has received personal compensation in the range of $10,000-$49,999 for serving as an Expert Witness for various legal firms. The institution of Dr. Hemphill has received research support from NIH/NINDS.
M. B. Westover, MD, PhD (MGH)	Dr. Westover has received personal compensation in the range of $50,000-$99,999 for serving as a Consultant for Beacon Biosignals. Dr. Westover has stock in Beacon Biosignals. The institution of Dr. Westover has received research support from NIH. Dr. Westover has received publishing royalties from a publication relating to health care. Dr. Westover has a non-compensated relationship as a cofounder with Beacon Biosignals that is relevant to AAN interests or activities.
Marta Fernandes (Massachusetts General Hospital)	Marta Fernandes has nothing to disclose.
Edilberto Amorim, MD	The institution of Dr. Amorim has received research support from American Heart Association. The institution of Dr. Amorim has received research support from Society of Critical Care Medicine. The institution of Dr. Amorim has received research support from Zoll Foundation. The institution of Dr. Amorim has received research support from Hellman Foundation. The institution of Dr. Amorim has received research support from Regents of the University of California. The institution of Dr. Amorim has received research support from Citizens United Against Epilepsy. The institution of Dr. Amorim has received research support from Regents of the University of California. The institution of Dr. Amorim has received research support from American Heart Association. The institution of Dr. Amorim has received research support from NIH. The institution of Dr. Amorim has received research support from Department of Defense. The institution of Dr. Amorim has received research support from Department of Defense. The institution of Dr. Amorim has received research support from American Heart Association.

��ɫ��

��ɫ��