br Others br Charlson comorbidity index n br
Charlson comorbidity index, n (%)
Hospital annual volume, n (%)
Insurance status, n (%)
Unknown ACCEPTED MANUSCRIPT 12 (2.6) -
Lymph node dissection, n (%)
Abbreviations: IQR – interquartile range; SD – standard deviation.
Table 2: Complications of cytoreductive prostatectomies stratified according to open vs. robotically-assisted approach, within the National Inpatient Sample between 2008 and 2013.
Overall Open Robotic-assisted p-value
Overall complication, n (%)
Blood transfusion, n (%)
Bowel obstruction, n (%)
Cardiac complication, n (%)
Pulmonary complication, n
Vascular complication, n
Wound complication, n (%)
Table 3: Multiaarable aegaessron modeels paederctng arsk of complrcatonss length of stay ande total hosprtal chaages foa cytoaedeuctie paostatectomy patents taeatede wrth open Reefeaence) is aobotcally-aassrstede appaoachs befoae ande aftea adejustment foa clustearngs wrthrn the aatonal Inpatent Sample between 2008 ande 2013
Multivariable beforre cluteerige Multivariable afer cluteerige
(Prittrg reerettirg mrdel) *
(ligear reerettirg mrdel) °
Abbaeiratons: Oe – Odedes aato All modeels adejustede foa: appaoachs yeaa of deragnosrss ages Chaalson comoabrderty rndeexs rnsuaance statuss aaces teachrng statuss SYBR Green qPCR Master Mix nodee
derssectons hosprtal iolumes aegrons hosprtal bede-asrze ande rncome *Modeel adedertonally adejustede foa all complrcatons
° Modeel adedertonally adejustede foa all complrcatons ande length of stay **eelatie arsk
Contents lists available at ScienceDirect
Journal of Biomedical Informatics
journal homepage: www.elsevier.com/locate/yjbin
Comparison of orthogonal NLP methods for clinical phenotyping and assessment of bone scan utilization among prostate cancer patients
Jean Coqueta, Selen Bozkurta,b, Kathleen M. Kanc, Michelle K. Ferraric, Douglas W. Blayneya,d, James D. Brooksc,d, Tina Hernandez-Boussarda,b,e, a Department of Medicine, Stanford University, Stanford, CA, USA b Department of Biomedical Data Science, Stanford University, Stanford, USA c Department of Urology, Stanford University School of Medicine, Stanford, USA d Stanford Cancer Institute, Stanford University School of Medicine, Stanford, USA e Department of Surgery, Stanford University School of Medicine, Stanford, USA
Electronic health records
Natural language processing
Objective: Clinical care guidelines recommend Episome change newly diagnosed prostate cancer patients at high risk for metastatic spread receive a bone scan prior to treatment and that low risk patients not receive it. The objective was to develop an automated pipeline to interrogate heterogeneous data to evaluate the use of bone scans using a two different Natural Language Processing (NLP) approaches.
Materials and Methods: Our cohort was divided into risk groups based on Electronic Health Records (EHR). Information on bone scan utilization was identified in both structured data and free text from clinical notes. Our pipeline annotated sentences with a combination of a rule-based method using the ConText algorithm (a gen-eralization of NegEx) and a Convolutional Neural Network (CNN) method using word2vec to produce word embeddings.