Comparative Analysis of Algorithmic Approaches for Auto-Coding with ICD-10-AM and ACHI Rajvir Kaur Master of Research
Authors Rajvir Kaur Jeewani Anupama Ginige
Introduction • Electronic Health Records (EHRs): Digitised version of paper based medical records • What is Clinical Coding? • Assignment of alphanumeric codes • Manually assigned by clinical coders • Uses: • Funding, insurance claim processing • Research Image Credit: https://medium.com/@Petuum/automated-icd-coding-using-deep-learning-1e9170652175 • Government and policy makers use coded data.
Classification system in different countries • Countries specific classification system: ICD-10-CM (Clinical Modification) ICD-10-CA (Canadian Modification) ICD-10-GM (German Modification) ICD-10-AM (Australian Modification) • Ireland, Singapore, Saudi Arabia Image Credit: https://www.slideshare.net/EduardoPorras2
Challenges in manual coding • Complexity of codes ICD-9 : 3,882 codes ICD-10: Approx. 70,000 codes • 15-42 records per day • Annual cost: 25 billion dollars (U.S.) • Training and recruitment cost • Highly prone to errors “ Boy, this new system is so confusing. your ICD-9 code says that you’re here for a sprained ankle, but your ICD-10 code says it’s complete and irreversible skeletal failure. Image Credit: http://bestptbilling.com/how-to-reduce-icd-10-transition-pain-for-physical-therapy-practice-owners/
Our Contribution • We focus on: • ICD-10-AM and ACHI classification system • Comparing and analysing various approaches based on standard evaluation criteria • Our research concentrates on only two ICD-10-AM and ACHI chapters • Digestive System: Chapter 11: Diseases of the digestive system (ICD-10-AM) Chapter 10: Procedures on digestive system (ACHI) • Respiratory System: Chapter 10: Diseases of the respiratory system (ICD-10-AM) Chapter 7: Procedure on respiratory system (ACHI)
Ethics Approval • Western Sydney University Ethics No.: H12628190 • Dataset: • Total 190 clinical records (Gold Standard) • Collected from hospitals across Australia • Archived by National Centre for Classification in Health (NCCH)
Sample data
Paper based Electronic version • PDF or Image file to Tabular format • Created text narratives • Information extracted from medical records include: Principal Diagnoses (PDx) Family Medical History Additional Diagnoses (ADx) Principal Procedure Smoke related diagnosis Additional Procedure Diabetes condition Type of anaesthesia Supplementary conditions Ventilation details Past Medical History (PMHx) Allied health intervention
Dataset • 190 original records • Additional 45 records similar to digestive and respiratory diseases and interventions 45 Clinical Records = 190 + 45 =235 15 digestive system 30 respiratory system Dataset Digestive system records Respiratory system records Data190 116 74 Data235 131 104
Overview of the Proposed work Clinical Text Processing Using ICD-10-AM/ ACHI TASK 1: TASK 2: ICD-10-AM/ ACHI ICD-10-AM/ ACHI Chapter Classification Code Assignment Rule Machine Pattern Digestive Respiratory Based Learning Matching System System
Approaches and Techniques Clinical Text Processing Approaches and Techniques Pattern Matching Rule-based Machine Learning Pre-processing Regular Pre-processin g 1. Sentence splitting Expression 1. Sentence splitting 2. Abbreviation Expansion 2. Abbreviation Expansion 3. Tokenisation 3. Tokenisation 4. Spell Check 4. Spell Check Evaluation Defining Rules 5. Stop word removal 1. Precision 6. Negation detection 2. Recall 3. F-score Feature Extraction Evaluation 4. Accuracy 1-gram, 2-gram, 3-gram, 4-gram 1. Precision 5. Hamming Loss 2. Recall 6. Jaccard Similarity Classification 3. F-score SVM, Naïve Bayes, Decision Tree 4. Accuracy Random Forest, AdaBoost, kNN, MLP 5. Hamming Loss 6. Jaccard Similarity Evaluation
Pattern Matching • Simplest approach • Search a text-string within the text • Match character for character • Use Regular Expression bronchi, bronchus, bronchial, bronchitis A 51 year old patient has serious cough but no sign of pneumonia keywords
Rule-based approach • Use logical expression and Boolean operations if (logical expression) then (category) ICD-10 Codes Generating rules K05.2 If document contains Acute periodontitis acute periodontitis OR Acute pericoronitis acute pericoronitis OR Parodontal abscess parodontal abscess OR Peridontal abscess peridontal abscess OR Excludes AND document NOT contains acute apical periodontitis (K04.4) acute apical periodontitis AND periapical abscess (K04.7) periapical abscess AND periapical abscess with sinus (K04.6) periapical abscess with sinus assign code K05.2
Machine Learning • ML Image Credit: https://www.newtium.com/Software/Predictive
Data Preprocessing Admission Date: **** Discharge Date:**** 1. Abbreviation Expansion Presenting Problems Respiratory -cough PRINCIPAL DIAGNOSIS Infective exacerbation of bronchiectasis Acute-on-chronic Type 2 respiratory failure Abbreviations Full-form Summary of Progress Dear Doctor, COPD Chronic obstructive pulmonary Thank you for your ongoing care of **** , who presented to **** disease hospital on **** with SOB , cough and chest pain, on a background of bronchiectasis. The patient was admitted under SBO Small bowel obstruction the case of Dr**** (Respiratory) for management of infective exacerbation of bronchiectasis. IHD Ischaemic heart disease Background SOB Shortness of breath Bronchiectasis - Known to Dr****(Respiratory) HTN Hypertension - Bronchiectasis diagnosed 20 years ago, secondary to childhood pertussis Left ventricular failure T2DM Type 2 diabetes mellitus - Known to Dr****(Cardiology) Cough, SOB , Pleuritic chest pain
Data Preprocessing 2. Spell Check Australian English American English oesophagus esophagus tumour tumor Used : NLTK and PyEnchant Python libraries anaemia anemia anaesthetic anesthetic ischaemic ischemic diarrhoea diarrhea
Data Preprocessing 3. Stop word removal ‘again’, ‘about’, ‘there’, ‘once’, ‘during’, ‘out’, ‘they’, ‘own’, ‘an’, ‘some’, ‘its’, ‘yours’ ‘such’, ‘into’, ‘most’, ‘itself’, ‘other’, ‘off’, ‘am’, ‘who’, ‘as’, ‘him’, ‘each’, ‘themselves’, ‘until’, ‘we’, ‘these’, ‘your’, ‘his’, ‘through’, ‘me’, ‘her’, ‘more’ , ‘himself’, ‘this’, ‘down’, ‘should’, ‘our’, ‘their’, ‘while’, ‘above’, ‘both’, ‘up’, ‘ours’, ‘she’, ‘all’, ‘when’, ‘at’, ‘any’, ‘before’, ‘them’, ‘same’, ‘yourselves’, ‘because’, ‘what’, ‘over’, ‘why’, ‘now’, ‘he’, ‘you’, ‘herself’, ‘just’, ‘ourselves’, ‘hers’, ‘yourself’, ‘how’, ‘theirs’ ‘further’, ‘doing’, ‘where’, ‘too’, ‘whom’, ‘those’ no, not, nil, never X
Data Preprocessing 4. Negation Detection negated term The patient is suffering from serious cough but no evidence of pneumonia. keywords Negated findings: (pneumonia, ‘True’) – do not assign code Non-negated findings: (cough, ‘True’) – assign code
Feature Extraction admitted 1 Bag of words representation and 2 bronchiolitis 1 cough 1 diarrhoea 1 for 2 X: The infant was admitted to hospital 1 infant 1 The hospital for bronchiolitis male 1 with worse cough and old 1 wheeze presented 1 to 1 Y: The old male presented for the 3 vomiting and diarrhoea vomiting 1 was 1 wheeze 1 with 1 worse 1
Classification Seven classifiers: Support Vector Machine (SVM) Naïve Bayes (NB) Decision Tree (DT) Random Forest (RF) AdaBoost k-Nearest Neighbor (kNN) Multi Layer Perceptron (MLP)
Evaluation Y i: Ground truth label Zi : Predicted label N: Number of records M: Set of all labels Ground Truth Positive Negative Predicted True Positive False Negative Positive (TP) (FN) False Positive True Negative Negative (FP) (TN)
Recommend
More recommend
