Detection of Surgical Site Infection Utilizing Automated Feature Generation in Clinical Notes

Postsurgical complications (PSCs) are known as a deviation from the normal postsurgical course and categorized by severity and treatment requirements. Surgical site infection (SSI) is one of major PSCs and the most common healthcare-associated infection, resulting in increased length of hospital stay and cost. In this work, we proposed an automated way to generate keyword features using sublanguage analysis with heuristics to detect SSI from cohort in clinical notes and evaluated these keywords with medical experts. To further validate our approach, we also applied different machine learning algorithms on cohort using automatically generated keywords. The results showed that our approach was able to identify SSI keywords from clinical narratives and can be used as a foundation to develop an information extraction system or support search-based natural language processing (NLP) approaches by augmenting search queries.

[1]  Hongfang Liu,et al.  Leveraging Collaborative Filtering to Accelerate Rare Disease Diagnosis , 2017, AMIA.

[2]  C. Wild.  Building a safer health system , 2001 .

[3]  Richard M Reichley,et al.  Clinical validation of the AHRQ postoperative venous thromboembolism patient safety indicator. , 2009, Joint Commission journal on quality and patient safety.

[4]  Karl Pearson F.R.S..  X. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling , 2009 .

[5]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[6]  Sunghwan Sohn,et al.  Facilitating post-surgical complication detection through sublanguage analysis , 2014, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  M. McHugh,et al.  The Chi-square test of independence , 2013, Biochemia medica.

[9]  Yugyung Lee,et al.  Using semantic web technologies for quality measure phenotyping algorithm representation and automatic execution on EHR data , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[10]  Andrew Taylor,et al.  Extracting Knowledge from Biological Descriptions , 1995 .

[11]  C. Elger,et al.  Prediction of post-surgical seizure outcome in left mesial temporal lobe epilepsy , 2013, NeuroImage: Clinical.

[12]  Cui Tao,et al.  An integrative computational approach to identify disease-specific networks from PubMed literature information , 2013, 2013 IEEE International Conference on Bioinformatics and Biomedicine.

[13]  Robert Pringle,et al.  Post-Operative Complications in the Elderly Surgical Patient , 1983 .

[14]  David R Flum,et al.  Blueprint for a new American College of Surgeons: National Surgical Quality Improvement Program. , 2008, Journal of the American College of Surgeons.

[15]  C. Christiansen,et al.  Validity of selected AHRQ patient safety indicators based on VA National Surgical Quality Improvement Program data. , 2009, Health services research.

[16]  Hongfang Liu,et al.  Accelerating Rare Disease Diagnosis with Collaborative Filtering , 2017, AMIA.

[17]  Hoberdan Oliveira Pereira,et al.  Tempo de internação pré‐operatório: um fator de risco para reduzir a infecção cirúrgica em fraturas de fêmur , 2015 .

[18]  S. Johnson.  A semantic lexicon for medical language processing. , 1999, Journal of the American Medical Informatics Association : JAMIA.

[19]  Michael Pine,et al.  Adverse outcomes in surgery: redefinition of postoperative complications. , 2009, American journal of surgery.

[20]  T. Horan,et al.  Guideline for Prevention of Surgical Site Infection, 1999. Centers for Disease Control and Prevention (CDC) Hospital Infection Control Practices Advisory Committee. , 1999, American journal of infection control.

[21]  Hongfang Liu,et al.  Using Human Phenotype Ontology for Phenotypic Analysis of Clinical Notes , 2017, MedInfo.

[22]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[23]  K. Pearson.  On the Criterion that a Given System of Deviations from the Probable in the Case of a Correlated System of Variables is Such that it Can be Reasonably Supposed to have Arisen from Random Sampling , 1900 .

[24]  Steven H. Brown,et al.  Automated identification of postoperative complications within an electronic medical record using natural language processing. , 2011, JAMA.

[25]  R V Patel,et al.  Effects of epidural anesthesia and analgesia on coagulation and outcome after major vascular surgery. , 1991, Anesthesia and analgesia.

[26]  Tej D. Azad,et al.  Size and distribution of the global volume of surgery in 2012 , 2016, Bulletin of the World Health Organization.

[27]  Hans Gombotz,et al.  Preoperative identification of patients with increased risk for perioperative bleeding , 2013, Current opinion in anaesthesiology.

[28]  Neeraj Bhargava,et al.  Decision Tree Analysis on J48 Algorithm for Data Mining , 2013 .

[29]  Yugyung Lee,et al.  BmQGen: Biomedical query generator for knowledge discovery , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[30]  Steven H. Brown,et al.  Exploring the Frontier of Electronic Health Record Surveillance: The Case of Postoperative Complications , 2013, Medical care.

[31]  Ming-Hua Li,et al.  Complications of stent placement for benign stricture of gastrointestinal tract. , 2004, World journal of gastroenterology.

[32]  Vitaly Herasevich,et al.  Derivation and validation of automated electronic search strategies to extract Charlson comorbidities from electronic medical records. , 2012, Mayo Clinic proceedings.

[33]  A. Adler,et al.  Endoscopic Access to the Papilla of Vater for Endoscopic Retrograde Cholangiopancreatography in Patients with Billroth II or Roux-en-Y Gastrojejunostomy , 1997, Endoscopy.

[34]  Huan-Chao Keh,et al.  Intelligent Postoperative Morbidity Prediction of Heart Disease Using Artificial Intelligence Techniques , 2012, Journal of Medical Systems.

[35]  Zachary Terner,et al.  Automated prediction of adverse post-surgical outcomes , 2014, 2014 Systems and Information Engineering Design Symposium (SIEDS).

[36]  Yugyung Lee,et al.  Predicate Oriented Pattern Analysis for Biomedical Knowledge Discovery , 2016, Intelligent information management.

[37]  Yugyung Lee,et al.  SMARTSPACE: Multiagent Based Distributed Platform for Semantic Service Discovery , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[38]  Ameet Talwalkar,et al.  Foundations of Machine Learning , 2012, Adaptive computation and machine learning.

[39]  Christopher G Chute,et al.  An Information Extraction Framework for Cohort Identification Using Electronic Health Records , 2013, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[40]  Hongfang Liu,et al.  Phenotypic Analysis of Clinical Narratives Using Human Phenotype Ontology , 2020, MedInfo.

[41]  Jon C. Gould,et al.  Perioperative bleeding and blood transfusion are major risk factors for venous thromboembolism following bariatric surgery , 2018, Surgical Endoscopy.

[42]  Feichen Shen.  A graph analytics framework for knowledge discovery , 2016 .

[43]  Yugyung Lee,et al.  MedTQ: Dynamic Topic Discovery and Query Generation for Medical Ontologies , 2018, ArXiv.

[44]  Zhiyi Zuo,et al.  Haptoglobin 2‐2 Phenotype Is Associated With Increased Acute Kidney Injury After Elective Cardiac Surgery in Patients With Diabetes Mellitus , 2017, Journal of the American Heart Association.

[45]  Hongfang Liu,et al.  Using machine learning for concept extraction on clinical documents from multiple data sources , 2011, J. Am. Medical Informatics Assoc..

[46]  P. Gay,et al.  Postoperative complications in patients with obstructive sleep apnea syndrome undergoing hip or knee replacement: a case-control study. , 2001, Mayo Clinic proceedings.

[47]  R. Nakamura,et al.  Quantitation of "acute-phase proteins" postoperatively. Value in detection and monitoring of complications. , 1976, American journal of clinical pathology.

[48]  Olivier Bodenreider,et al.  The Unified Medical Language System (UMLS): integrating biomedical terminology , 2004, Nucleic Acids Res..

[49]  José Luis Rojo-Álvarez,et al.  Predicting colorectal surgical complications using heterogeneous clinical data and kernel methods , 2016, J. Biomed. Informatics.

[50]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[51]  Yugyung Lee,et al.  BioBroker: Knowledge Discovery Framework for Heterogeneous Biomedical Ontologies and Data , 2018 .

[52]  Carol Friedman,et al.  A broad-coverage natural language processing system , 2000, AMIA.

[53]  Yugyung Lee,et al.  Knowledge Discovery from Biomedical Ontologies in Cross Domains , 2016, PloS one.

[54]  Feichen Shen.  A pervasive framework for real-time activity patterns of mobile users , 2015, 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[55]  T. Crowe,et al.  Nutritional status, nutrition practices and post-operative complications in patients with gastrointestinal cancer. , 2010, Journal of human nutrition and dietetics : the official journal of the British Dietetic Association.

[56]  Cui Tao,et al.  Phenotyping on EHR Data Using OWL and Semantic Web Technologies , 2013, ICSH.

[57]  Richard Kittredge,et al.  Sublanguage : studies of language in restricted semantic domains , 1982 .

[58]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[59]  N. Demartines,et al.  Classification of Surgical Complications: A New Proposal With Evaluation in a Cohort of 6336 Patients and Results of a Survey , 2004, Annals of Surgery.

[60]  Bráulio Roberto Gonçalves Marinho Couto,et al.  Length of preoperative hospital stay: a risk factor for reducing surgical infection in femoral fracture cases , 2015, Revista brasileira de ortopedia.

[61]  Robert B. Winter,et al.  The Surgical and Medical Perioperative Complications of Anterior Spinal Fusion Surgery in the Thoracic and Lumbar Spine in Adults: A Review of 1223 Procedures , 1995, Spine.

[62]  Hongfang Liu,et al.  Journal of Biomedical Informatics , 2022 .

[63]  Zhen Wang,et al.  Towards a multi-level framework for supporting systematic review — A pilot study , 2014, 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[64]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .