Data Mining - Concepts and Techniques.

The pervasive use of electronic health databases has increased the accessibility of free-text clinical reports for supplementary use Several text classification approaches, such as supervised machine learning (SML) or rule-based approaches, have been utilized to obtain beneficial information from free-text clinical reports In recent years, many researchers have worked in the clinical text classification field and published their results in academic journals However, to the best of our knowledge, no comprehensive systematic literature review (SLR) has recapitulated the existing primary studies on clinical text classification in the last five years Thus, the current study aims to present SLR of academic articles on clinical text classification published from January 2013 to January 2018 Accordingly, we intend to maximize the procedural decision analysis in six aspects, namely, types of clinical reports, data sets and their characteristics, pre-processing and sampling techniques, feature engineering, machine learning algorithms, and performance metrics To achieve our objective, 72 primary studies from 8 bibliographic databases were systematically selected and rigorously reviewed from the perspective of the six aspects This review identified nine types of clinical reports, four types of data sets (ie, homogeneous–homogenous, homogenous–heterogeneous, heterogeneous–homogenous, and heterogeneous–heterogeneous), two sampling techniques (ie, over-sampling and under-sampling), and nine pre-processing techniques Moreover, this review determined bag of words, bag of phrases, and bag of concepts features when represented by either term frequency or term frequency with inverse document frequency, thereby showing improved classification results SML-based or rule-based approaches were generally employed to classify the clinical reports To measure the performance of these classification approaches, we used precision, recall, F-measure, accuracy, AUC, and specificity in binary class problems In multi-class problems, we primarily used micro or macro-averaging precision, recall, or F-measure Lastly, open research issues and challenges are presented for future scholars who are interested in clinical text classification This SLR will definitely be a beneficial resource for researchers engaged in clinical text classification

Clinical text classification research trends: Systematic literature review and open issues

Legendre polynomials based feature extraction for online signature verification. Consistency analysis of feature combinations

Relation pattern extraction and information extraction from the web. This article presents an information extraction method which collects additional information on the web so as to enrich already existing information and then fill in a knowledge base. Our method is based on lexical and syntactical patterns, both used as search queries and extraction patterns to allow the analysis of unstructured documents. To do so, we first defined relevant criteria coming from the analysis phase so as to ease the discovery of new values. MOTS-CLES : Construction de patrons, extraction d’information, extraction d’entités nommées, syntaxe en dépendances, apprentissage de patrons d’extraction, web comme corpus.

https://hal.archives-ouvertes.fr/hal-01843585/document

Actes de la conférence Traitement Automatique de la Langue Naturelle, TALN 2018

Electronic health records are used to extract patient's information instantly and remotely, which can help to keep track of patients' due dates for checkups, immunizations, and to monitor health performance. The Health Insurance Portability and Accountability Act (HIPAA) in the USA protects the patient data confidentiality, but it can be used if data is re-identified using `HIPAA Safe Harbor' technique. Usually, this re-identification is performed manually, which is very laborious and time captivating exertion. Various techniques have been proposed for automatic extraction of useful information, and accurate diagnosis of diseases. Most of these methods are based on Machine Learning and Deep Learning Methods, while the auxiliary diagnosis is performed using Rule-based methods. This review focuses on recently published papers, which are categorized into Rule-Based Methods, Machine Learning (ML) Methods, and Deep Learning (DL) Methods. Particularly, ML methods are further categorized into Support Vector Machine Methods (SVM), Bayes Methods, and Decision Tree Methods (DT). DL methods are decomposed into Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Deep Belief Network (DBN) and Autoencoders (AE) methods. The objective of this survey paper is to highlight both the strong and weak points of various proposed techniques in the disease diagnosis. Moreover, we present advantage, disadvantage, focused disease, dataset employed, and publication year of each category.

/pdf/implementation-and-use-of-disease-diagnosis-systems-for-1z6i8ppwk1.pdf

Implementation and Use of Disease Diagnosis Systems for Electronic Medical Records Based on Machine Learning: A Complete Review

Automatic online and offline signature recognition and verification is becoming ubiquitous in person identification and authentication problems, in various domains requiring different levels of security. There has recently been an increasing interest in developing such systems, with several views on which are the best discriminator features. This paper presents a new offline signature verification system, which considers a new combination of previously used features and introduces two new distance-based ones. A new feature grouping is presented. We have experimented with two classification methods and two feature selection techniques. The best performance so far was obtained with the Naive Bayes classifier on the reduced feature set (through feature selection).

An offline system for handwritten signature recognition

Purpose




Improving healthcare services by developing assistive technologies includes both the health aid devices and the analysis of the data collected by them. The acquired data modeled as a knowledge base give more insight into each patient’s health status and needs. Therefore, the ultimate goal of a health-care system is obtaining recommendations provided by an assistive decision support system using such knowledge base, benefiting the patients, the physicians and the healthcare industry. This paper aims to define the knowledge flow for a medical assistive decision support system by structuring raw medical data and leveraging the knowledge contained in the data proposing solutions for efficient data search, medical investigation or diagnosis and medication prediction and relationship identification.




Design/methodology/approach




The solution this paper proposes for implementing a medical assistive decision support system can analyze any type of unstructured medical documents which are processed by applying Natural Language Processing (NLP) tasks followed by semantic analysis, leading to the medical concept identification, thus imposing a structure on the input documents. The structured information is filtered and classified such that custom decisions regarding patients’ health status can be made. The current research focuses on identifying the relationships between medical concepts as defined by the REMed (Relation Extraction from Medical documents) solution that aims at finding the patterns that lead to the classification of concept pairs into concept-to-concept relations.




Findings




This paper proposed the REMed solution expressed as a multi-class classification problem tackled using the support vector machine classifier. Experimentally, this paper determined the most appropriate setup for the multi-class classification problem which is a combination of lexical, context, syntactic and grammatical features, as each feature category is good at representing particular relations, but not all. The best results we obtained are expressed as F1-measure of 74.9 per cent which is 1.4 per cent better than the results reported by similar systems.




Research limitations/implications




The difficulty to discriminate between TrIP and TrAP relations revolves around the hierarchical relationship between the two classes as TrIP is a particular type (an instance) of TrAP. The intuition behind this behavior was that the classifier cannot discern the correct relations because of the bias toward the majority classes. The analysis was conducted by using only sentences from electronic health record that contain at least two medical concepts. This limitation was introduced by the availability of the annotated data with reported results, as relations were defined at sentence level.




Originality/value




The originality of the proposed solution lies in the methodology to extract valuable information from the medical records via semantic searches; concept-to-concept relation identification; and recommendations for diagnosis, treatment and further investigations. The REMed solution introduces a learning-based approach for the automatic discovery of relations between medical concepts. We propose an original list of features: lexical – 3, context – 6, grammatical – 4 and syntactic – 4. The similarity feature introduced in this paper has a significant influence on the classification, and, to the best of the authors’ knowledge, it has not been used as feature in similar solutions.

Feature Engineered Relation Extraction – Medical Documents Setting

The large amount of unstructured medical documents written in natural language bears a massive quantity of knowledge, whose extraction becomes useful. An automatic relation identification strategy leads to the discovery of relations, (possible unknown) interactions, and associations between medical conditions, investigations and treatments. The current paper introduces a learning based approach for the automatic discovery of relations between medical concepts, entitled REMed. We propose an original list of features, grouped into four categories with the following distribution: lexical - 3, context - 6, grammatical -- 4 and syntactic - 4. We analyzed the influence of each category on the classification performance and determined that the performance of the REMed solution is comparable with similar solutions. We report the overall F-measure as 74.9% that outperforms the best solution reported in the similar systems with 1.2%. This performance was achieved mostly by the features from the lexical and context categories.

REMed: automatic relation extraction from medical documents

Topic extraction from Electronic Health Records is a sensitive step of the knowledge extraction process. As the meaning of a discourse can be completely distorted by negations, the correct identification of terms vs negated terms is mandatory. Our work is an attempt of automated negation identification in unstructured health records. We analyzed a corpus of medical documents containing 5103 sentences and we found that while adverbs have a distribution of 3%, the negation covers almost 2% of the words used in the corpus, justifying an in depth analysis of negation. The main contribution of the paper addresses the existing drawback of negation identification approaches in the literature that do not consider negation represented with negation prefixes. In this paper we address the tasks of syntactic and morphologic negation identification. In order to identify morphologic negation we propose the PreNex algorithm that consists in breaking down the terms into prefix and root word and the analysis of the root's validity using additional available resources (WordNet). The syntactic negation identification relies on a pattern matching approach where the negated concepts are identified based on a predefined Ust of negation identifiers. The results we obtained are promising and ensure a reliable negation identification approach for medical documents. We report a precision of 92.62% and recall of 93.60% in case of the morphologic negation identification and an overall performance in the morphologic and syntactic negation identification of 95.96% precision and 94.23% recall.

Exploiting word meaning for negation identification in electronic health records

This paper presents an enhanced method of partitioning a dataset into clusters when dealing with the handwritten signature recognition problem. The goal of the present system is improving the performance of two previously developed systems. In the first version of our system we dealt with data extraction from signature images and obtained a recognition rate of 91.04% using the Naive Bayes classifier and the feature selection method. In the second version of our system we performed a hierarchical partitioning of the dataset into clusters in order to obtain a faster and better classification and then we applied the Naive Bayes classifier in order to determine the recognition rate. The best results were reported when partitioning the data into 7 and 8 clusters and the mean accuracy obtained was 91%. In the current version of our system, we identified the most appropriate model for each cluster by selecting the best performance obtained after applying 7 different classifiers on the clusters. In order to improve the recognition rate and reduce the time required to build a model, we applied the feature selection method on each of the clusters with the previously determined classifiers. We obtained an increased accuracy with 1.62%on a dataset with 14 instances/class and an increment of 3.24% on a dataset with 20 instances/class.

Ioana Barbantan

Papers

An offline system for handwritten signature recognition

Feature Engineered Relation Extraction – Medical Documents Setting

REMed: automatic relation extraction from medical documents

Exploiting word meaning for negation identification in electronic health records

Enhancements on a signature recognition problem