Charlene Jennifer Ong

Charlene Jennifer Ong

Auto-generated profile, based on publicly available information

Charlene Jennifer Ong

Boston Medical Center, Boston, USA

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2017 in Stroke
Verified
Journal Article
Closed access
PDF file
COCharlene Jennifer Ong
Charlene Jennifer Ong
JGJeffrey Gluckstein
Jeffrey Gluckstein
OLOsvaldo Laurido-Soto
Osvaldo Laurido-Soto
YYYan Yan
Yan Yan
RDRajat Dhar
Rajat Dhar
JLJin-Moo Lee
Jin-Moo Lee
Background and Purpose—: Rapid recognition of those at high risk for malignant edema after stroke would facilitate triage for monitoring and potential surgery. Admission data may be insufficient for accurate triage decisions. We developed a risk prediction score using clinical and radiographic variables within 24 hours of ictus to better predict potentially lethal malignant edema. Methods—: Patients admitted with diagnosis codes of cerebral edema and ischemic stroke, NIHSS score (National Institute of Health Stroke Score) of ≥8 and head computed tomographies within 24 hours of stroke onset were included. Primary outcome of potentially lethal malignant edema was defined as death with midline shift ≥5 mm or decompressive hemicraniectomy. We performed multivariate analyses on data available within 24 hours of ictus. Bootstrapping was used to internally validate the model, and a risk score was constructed from the results. Results—: Thirty-three percent of 222 patients developed potentially lethal malignant edema. The final model C statistic was 0.76 (confidence interval, 0.68–0.82) in the derivation cohort and 0.75 (confidence interval, 0.72–0.77) in the bootstrapping validation sample. The EDEMA score (Enhanced Detection of Edema in Malignant Anterior Circulation Stroke) was developed using the following independent predictors: basal cistern effacement (=3); glucose ≥150 (=2); no tPA (tissue-type plasminogen activator) or thrombectomy (=1), midline shift >0 to 3 (=1), 3 to 6 (=2), and 6 to 9 (=4); >9 (=7); and no previous stroke (=1). A score over 7 was associated with 93% positive predictive value. Conclusions—: The EDEMA score identifies patients at high risk for potentially lethal malignant edema. Although it requires external validation, this scale could help expedite triage decisions in this patient population.

19 June 2020 in PLOS ONE
Verified
Journal Article
Open access
PDF file
COCharlene Jennifer Ong
Charlene Jennifer Ong
AOAgni Orfanoudaki
Agni Orfanoudaki
RZRebecca Zhang
Rebecca Zhang
FCFrancois Pierre M. Caprasse
Francois Pierre M. Caprasse
MHMeghan Hutch
Meghan Hutch
DBDimitris Bertsimas
Dimitris Bertsimas
Accurate, automated extraction of clinical stroke information from unstructured text has several important applications. ICD-9/10 codes can misclassify ischemic stroke events and do not distinguish acuity or location. Expeditious, accurate data extraction could provide considerable improvement in identifying stroke in large datasets, triaging critical clinical reports, and quality improvement efforts. In this study, we developed and report a comprehensive framework studying the performance of simple and complex stroke-specific Natural Language Processing (NLP) and Machine Learning (ML) methods to determine presence, location, and acuity of ischemic stroke from radiographic text. We collected 60,564 Computed Tomography and Magnetic Resonance Imaging Radiology reports from 17,864 patients from two large academic medical centers. We used standard techniques to featurize unstructured text and developed neurovascular specific word GloVe embeddings. We trained various binary classification algorithms to identify stroke presence, location, and acuity using 75% of 1,359 expert-labeled reports. We validated our methods internally on the remaining 25% of reports and externally on 500 radiology reports from an entirely separate academic institution. In our internal population, GloVe word embeddings paired with deep learning (Recurrent Neural Networks) had the best discrimination of all methods for our three tasks (AUCs of 0.96, 0.98, 0.93 respectively). Simpler NLP approaches (Bag of Words) performed best with interpretable algorithms (Logistic Regression) for identifying ischemic stroke (AUC of 0.95), MCA location (AUC 0.96), and acuity (AUC of 0.90). Similarly, GloVe and Recurrent Neural Networks (AUC 0.92, 0.89, 0.93) generalized better in our external test set than BOW and Logistic Regression for stroke presence, location and acuity, respectively (AUC 0.89, 0.86, 0.80). Our study demonstrates a comprehensive assessment of NLP techniques for unstructured radiographic text. Our findings are suggestive that NLP/ML methods can be used to discriminate stroke features from large data cohorts for both clinical and research-related investigations.

14 September 2018 in Neurocritical Care
Verified
Journal Article
Closed access
PDF file
COC. Ong
C. Ong
MHM. Hutch
M. Hutch
SSS. Smirnakis
S. Smirnakis

1 November 2015 in Stroke
Verified
Journal Article
Open access
PDF file
CYChester K. Yarbrough
Chester K. Yarbrough
COCharlene J. Ong
Charlene J. Ong
ABAlexander B. Beyer
Alexander B. Beyer
KLKim Lipsey
Kim Lipsey
CDColin P. Derdeyn
Colin P. Derdeyn
Background and Purpose—Stroke affects ≈700 000 patients annually. Recent randomized controlled trials comparing endovascular thrombectomy (ET) with medical therapy, including intravenous thrombolysis (IVT) with tissue-type plasminogen activator, have shown effectiveness of ET for some stroke patients. The study objective is to evaluate the effect of ET on good outcome in stroke patients. Methods—We searched PubMed, Embase, Web of Science, SCOPUS, ClinicalTrials.gov, and Cochrane databases to identify original research publications between 1996 and 2015 that (1) reported clinical outcomes in patients for stroke at 90 days with the modified Rankin Scale; (2) included at least 10 patients per group; (3) compared outcome with a control arm, and (4) included anterior circulation strokes in each arm. Two authors reviewed articles for inclusion independently. Results—Nine of 23 809 studies met inclusion criteria. In primary analysis, ET was associated with increased odds for good outcome (odds ratio [OR], 1.75; 95% confidence interval [CI], 1.20–2.54). In secondary analysis, younger patients (OR, 1.85; 95% CI, 1.50–2.28), older patients (OR, 1.93; 95% CI, 1.10–3.37), patients receiving intravenous thrombolysis (OR, 1.83; 95% CI, 1.46–2.31), patients with worse strokes (OR, 2.23; 95% CI, 1.56–3.18), and patients with more moderate strokes (OR, 1.72; 95% CI, 1.36–2.18) had increased odds for good outcome. Symptomatic intracranial hemorrhage and mortality were similar between ET and control patients. No evidence of publication bias was seen. Conclusions—ET improves good outcomes after anterior circulation stroke. ET should be strongly considered for all patients presenting within 6 hours of onset with a stroke affecting a proximal, anterior circulation vessel without a contraindication to ET.

8 October 2018 in Neurocritical Care
Verified
Journal Article
Closed access
PDF file
COC. Ong
C. Ong
MHM. Hutch
M. Hutch
MBM. Barra
M. Barra
AKA. Kim
A. Kim
SZS. Zafar
S. Zafar
SSS. Smirnakis
S. Smirnakis

1 December 2020 in Journal of Stroke and Cerebrovascular Diseases
Verified
Journal Article
Closed access
FNFelix Nwajei
Felix Nwajei
PAPria Anand
Pria Anand
MAMohamad Abdalkader
Mohamad Abdalkader
VAVanesa C. Andreu Arasa
Vanesa C. Andreu Arasa
HAHugo Aparicio
Hugo Aparicio
ACAnna M. Cervantes-Arslanian
Anna M. Cervantes-Arslanian