scholarly journals Stratifying Risk of Coronary Artery Disease Using Discriminative Knowledge-Guided Medical Concept Pairings from Clinical Notes

2021 ◽  
Author(s):  
Mahdi Abdollahi ◽  
Xiaoying Gao ◽  
Yi Mei ◽  
S Ghosh ◽  
J Li
Keyword(s):  
Language Processing ◽  
Substantial Improvement ◽  
Document Classification ◽  
Clinical Notes ◽  
Unified Medical Language System ◽  
Second Stage ◽  
Third Stage ◽  
Medical Documents ◽  
Artery Disease

Document classification (DC) is one of the broadly investigated natural language processing tasks. Medical document classification can support doctors in making decision and improve medical services. Since the data in document classification often appear in raw form such as medical discharge notes, extracting meaningful information to use as features is a challenging task. There are many specialized words and expressions in medical documents which make them more challenging to analyze. The classification accuracy of available methods in medical field is not good enough. This work aims to improve the quality of the input feature sets to increase the accuracy. A new three-stage approach is proposed. In the first stage, the Unified Medical Language System (UMLS) which is a medical-specific dictionary is used to extract the meaningful phrases by considering disease or symptom concepts. In the second stage, all the possible pairs of the extracted concepts are created as new features. In the third stage, Particle Swarm Optimisation (PSO) is employed to select features from the extracted and constructed features in the previous stages. The experimental results show that the proposed three-stage method achieved substantial improvement over the existing medical DC approaches.

scholarly journals Stratifying Risk of Coronary Artery Disease Using Discriminative Knowledge-Guided Medical Concept Pairings from Clinical Notes

2021 ◽  
Author(s):  
Mahdi Abdollahi ◽  
Xiaoying Gao ◽  
Yi Mei ◽  
S Ghosh ◽  
J Li
Keyword(s):  
Language Processing ◽  
Substantial Improvement ◽  
Document Classification ◽  
Clinical Notes ◽  
Unified Medical Language System ◽  
Second Stage ◽  
Third Stage ◽  
Medical Documents ◽  
Artery Disease

Document classification (DC) is one of the broadly investigated natural language processing tasks. Medical document classification can support doctors in making decision and improve medical services. Since the data in document classification often appear in raw form such as medical discharge notes, extracting meaningful information to use as features is a challenging task. There are many specialized words and expressions in medical documents which make them more challenging to analyze. The classification accuracy of available methods in medical field is not good enough. This work aims to improve the quality of the input feature sets to increase the accuracy. A new three-stage approach is proposed. In the first stage, the Unified Medical Language System (UMLS) which is a medical-specific dictionary is used to extract the meaningful phrases by considering disease or symptom concepts. In the second stage, all the possible pairs of the extracted concepts are created as new features. In the third stage, Particle Swarm Optimisation (PSO) is employed to select features from the extracted and constructed features in the previous stages. The experimental results show that the proposed three-stage method achieved substantial improvement over the existing medical DC approaches.

scholarly journals An Ontology-based Two-Stage Approach to Medical Text Classification with Feature Selection by Particle Swarm Optimisation

2021 ◽  
Author(s):  
Mahdi Abdollahi ◽  
Xiaoying Gao ◽  
Yi Mei ◽  
S Ghosh ◽  
J Li
Keyword(s):  
Classification Problem ◽  
Substantial Improvement ◽  
Two Stage ◽  
Data Set ◽  
Unified Medical Language System ◽  
Domain Specific ◽  
Second Stage ◽  
Medical Text ◽  
Medical Language ◽  
Medical Documents

Document classification (DC) is the task of assigning pre-defined labels to unseen documents by utilizing a model trained on the available labeled documents. DC has attracted much attention in medical fields recently because many issues can be formulated as a classification problem. It can assist doctors in decision making and correct decisions can reduce the medical expenses. Medical documents have special attributes that distinguish them from other texts and make them difficult to analyze. For example, many acronyms and abbreviations, and short expressions make it more challenging to extract information. The classification accuracy of the current medical DC methods is not satisfactory. The goal of this work is to enhance the input feature sets of the DC method to improve the accuracy. To approach this goal, a novel two-stage approach is proposed. In the first stage, a domain-specific dictionary, namely the Unified Medical Language System (UMLS), is employed to extract the key features belonging to the most relevant concepts such as diseases or symptoms. In the second stage, PSO is applied to select more related features from the extracted features in the first stage. The performance of the proposed approach is evaluated on the 2010 Informatics for Integrating Biology and the Bedside (i2b2) data set which is a widely used medical text dataset. The experimental results show substantial improvement by the proposed method on the accuracy of classification.

scholarly journals An Ontology-based Two-Stage Approach to Medical Text Classification with Feature Selection by Particle Swarm Optimisation

2021 ◽  
Author(s):  
Mahdi Abdollahi ◽  
Xiaoying Gao ◽  
Yi Mei ◽  
S Ghosh ◽  
J Li
Keyword(s):  
Classification Problem ◽  
Substantial Improvement ◽  
Two Stage ◽  
Data Set ◽  
Unified Medical Language System ◽  
Domain Specific ◽  
Second Stage ◽  
Medical Text ◽  
Medical Language ◽  
Medical Documents

Document classification (DC) is the task of assigning pre-defined labels to unseen documents by utilizing a model trained on the available labeled documents. DC has attracted much attention in medical fields recently because many issues can be formulated as a classification problem. It can assist doctors in decision making and correct decisions can reduce the medical expenses. Medical documents have special attributes that distinguish them from other texts and make them difficult to analyze. For example, many acronyms and abbreviations, and short expressions make it more challenging to extract information. The classification accuracy of the current medical DC methods is not satisfactory. The goal of this work is to enhance the input feature sets of the DC method to improve the accuracy. To approach this goal, a novel two-stage approach is proposed. In the first stage, a domain-specific dictionary, namely the Unified Medical Language System (UMLS), is employed to extract the key features belonging to the most relevant concepts such as diseases or symptoms. In the second stage, PSO is applied to select more related features from the extracted features in the first stage. The performance of the proposed approach is evaluated on the 2010 Informatics for Integrating Biology and the Bedside (i2b2) data set which is a widely used medical text dataset. The experimental results show substantial improvement by the proposed method on the accuracy of classification.

Systematic review of current natural language processing methods and applications in cardiology

Heart ◽  
2021 ◽  
pp. heartjnl-2021-319769
Author(s):  
Meghan Reading Turchioe ◽  
Alexander Volodarskiy ◽  
Jyotishman Pathak ◽  
Drew N Wright ◽  
James Enlou Tcheng ◽  
...  
Keyword(s):  
Systematic Review ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Clinical Care ◽  
Real World Data ◽  
Clinical Text ◽  
Clinical Notes ◽  
Artery Disease ◽  
Automated Methods

Natural language processing (NLP) is a set of automated methods to organise and evaluate the information contained in unstructured clinical notes, which are a rich source of real-world data from clinical care that may be used to improve outcomes and understanding of disease in cardiology. The purpose of this systematic review is to provide an understanding of NLP, review how it has been used to date within cardiology and illustrate the opportunities that this approach provides for both research and clinical care. We systematically searched six scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, PubMed and Scopus) for studies published in 2015–2020 describing the development or application of NLP methods for clinical text focused on cardiac disease. Studies not published in English, lacking a description of NLP methods, non-cardiac focused and duplicates were excluded. Two independent reviewers extracted general study information, clinical details and NLP details and appraised quality using a checklist of quality indicators for NLP studies. We identified 37 studies developing and applying NLP in heart failure, imaging, coronary artery disease, electrophysiology, general cardiology and valvular heart disease. Most studies used NLP to identify patients with a specific diagnosis and extract disease severity using rule-based NLP methods. Some used NLP algorithms to predict clinical outcomes. A major limitation is the inability to aggregate findings across studies due to vastly different NLP methods, evaluation and reporting. This review reveals numerous opportunities for future NLP work in cardiology with more diverse patient samples, cardiac diseases, datasets, methods and applications.

Identifying Heart Failure Symptoms and Poor Self-Management in Home Healthcare: A Natural Language Processing Study

2021 ◽  
Author(s):  
Sena Chae ◽  
Jiyoun Song ◽  
Marietta Ojo ◽  
Maxim Topaz
Keyword(s):  
Heart Failure ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Symptom Management ◽  
Home Healthcare ◽  
Self Management ◽  
Clinical Notes ◽  
Patients With Heart Failure

The goal of this natural language processing (NLP) study was to identify patients in home healthcare with heart failure symptoms and poor self-management (SM). The preliminary lists of symptoms and poor SM status were identified, NLP algorithms were used to refine the lists, and NLP performance was evaluated using 2.3 million home healthcare clinical notes. The overall precision to identify patients with heart failure symptoms and poor SM status was 0.86. The feasibility of methods was demonstrated to identify patients with heart failure symptoms and poor SM documented in home healthcare notes. This study facilitates utilizing key symptom information and patients’ SM status from unstructured data in electronic health records. The results of this study can be applied to better individualize symptom management to support heart failure patients’ quality-of-life.

scholarly journals Physiological characteristics of endive, lettuce and chicory seeds as a function of spectral quality

2020 ◽  
Vol 11 ◽  
pp. e3227
Author(s):  
Matheus Milani Pretto ◽  
Daniele Cristina Fontana ◽  
Jullie Dos Santos ◽  
Axel Bruno Mariotto ◽  
Braulio Otomar Caron ◽  
...  
Keyword(s):  
Dry Mass ◽  
Germination Percentage ◽  
Spectral Quality ◽  
Second Stage ◽  
Randomized Design ◽  
Seedling Length ◽  
Red Led ◽  
Third Stage ◽  
Significant Length

Seedling production is a critical step in the establishment of vegetables. This work aimed to evaluate the effect of different spectral qualities on the germination and vigor of endive, lettuce, and chicory seeds. The experiment was carried out in three stages. The first stage, two cultivars of lettuce (‘Crespa Repolhuda’ and ‘Vera’) and six spectral qualities (blue LED, red LED, blue + red LED, white LED, fluorescent and dark) were evaluated; the second stage, two cultivars of chicory (‘Lisa Escarola’ and ‘Palla Rosa’) and the same spectral qualities were evaluated. In the third stage, the spectral quality of the endive cultivar ‘Pão de Açúcar’ was evaluated. The experiments were performed in a completely randomized design, with four replications of 50 seeds each. The evaluated parameters were: germination percentage, first count, germination speed index, seedling length, and fresh and dry mass. Endive, lettuce and chicory seeds germinated both in the presence or not of light so that they can be classified as neutral photos. A spectral LED of red quality fostered the development of the most significant volume of fresh mass on the endive, lettuce, and chicory. All the spectral qualities stimulated root growth. The dark, on the other hand, promoted the most significant length of the aerial part, promoting seedlings etiolation.

scholarly journals Development and Evaluation of a Blog about Cleft Lip and Cleft Palate and Hearing

2017 ◽  
Vol 22 (01) ◽  
pp. 060-067 ◽  
Author(s):  
Luciana Maximino ◽  
Ticiana Zambonato ◽  
Mirela Picolini-Pereira ◽  
Camila Castro Corrêa ◽  
Mariza Feniman ◽  
...  
Keyword(s):  
Cleft Palate ◽  
Health Professionals ◽  
Cleft Lip ◽  
Digital Information ◽  
Pedagogical Tool ◽  
Second Stage ◽  
The Third ◽  
Third Stage ◽  
Selection Of

Introduction Cleft lip and cleft palate can result in impairments in communication, specifically in hearing, making the use of technological resources such as blogs a fundamental guideline for health professionals. Objective The aim of this study was to prepare and analyze the access to a blog about cleft lip and cleft palate and hearing as a pedagogical tool for health professionals. Methods The first stage for the development of the blog was the selection of the content that would be addressed and the respective illustrations. The second stage was making the blog available through the WordPress platform, and the third stage included the evaluation of the blog, of the access to the WordPress statistical features, and of the quality of the blog through the Emory questionnaire, which was answered by 75 professionals. Results The blog, titled “Fissure and Hearing”, was developed with the architecture of a digital information environment containing a system of organization, navigation, labeling and search (first stage). The address hosting the blog was: http://fissuraeaudicao.wordpress.com (second stage). The result of the third stage included 56,269 views of the blog from different countries, and Brazil was the country with the highest viewing. Regarding the assessment by the Emory questionnaire, we found that for most of the major issues, the percentages obtained were or equal to 90%, while the analysis of the scales, navigation and structure presented the lowest scores. Conclusion The blog was developed and enabled greater access to information available on the web about cleft lip and cleft palate and hearing.

Socio-Cultural and Religious Influences During Menstruation Among University Students

2020 ◽  
Author(s):  
Keng Sheng Chew ◽  
Shirly Siew Ling Wong ◽  
Ahmad Khairi Hassan ◽  
Kian Ee Po ◽  
Norizzati Zulkhairi ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Factor Analysis ◽  
Religious Beliefs ◽  
Male Gender ◽  
Path Coefficient ◽  
Structural Modelling ◽  
Second Stage ◽  
Confirmatory Factor ◽  
Third Stage

Abstract BackgroundAlthough menstruation is a physiological process it is shrouded with layers of religious and socio-cultural beliefs. The extent to which these socio-cultural and religious beliefs may impact the quality of life of a female university student in our Asian setting has yet to be explored.MethodsThis study was divided into 3 stages. In the first stage 1, a preliminary list of items measuring socio-cultural and religious beliefs during menstruation was generated. In the second stage, exploratory factor analysis was performed using the preliminary list generated. In the third stage, confirmatory factor analysis using reflective measurement model and structural modelling was performed using partial least squares. Practices of these beliefs were included in structural modelling as beliefs without practices may not affect quality of life. Biological symptoms of menstruation were added in as well as another factor that may affect quality of life.ResultsA preliminary list of 22 items was generated based on personal interviews and input from female lecturers. In the second stage, the exploratory factor analysis identified six factors with eigenvalue>1. From the confirmatory factor analysis in third stage, two factors were iteratively removed due to poor factor loadings. The four factors retained were: i) “religious beliefs”; ii) “unpleasant (or dirty) nature of menstruation”; iii) “personal restrictions (dietary and behavior)”; and iv) “restrictions of interactions with male gender”. In structural equation modelling, only 2 factors, i.e., personal restrictions (dietary and behavioral)” (path coefficient 0.74, t-statistics 18.18) and restriction of interactions with males (path coefficient 0.12, t-statistis 3.00) have significant effect on the practices of menstruation beliefs. Biological symptoms (path coefficient -0.34; t-statistics 7.29) and practices of these socio-cultural and religious beliefs (path coefficient -0.17; t-statistics 3.67) in turn, have significant negative effect on quality of life.ConclusionAlthough four factors of socio-cultural and religious beliefs have been identified in this study, only beliefs related to personal dietary and behavioral restrictions and beliefs on restrictions of social interactions with the male gender are significantly practiced, of which, negatively impact quality of life.

scholarly journals PELATIHAN PENULISAN ARTIKEL ILMIAH BERBASIS RISET BAGI GURU DAN TEKNIK SUBMISSION DI JURNAL NASIONAL

2021 ◽  
Vol 5 (1) ◽  
pp. 157
Author(s):  
Mutia Fonna ◽  
Mursalin Mursalin ◽  
Aklimawati Aklimawati ◽  
Muliana Muliana ◽  
Fajriana Fajriana ◽  
...  
Keyword(s):  
Scientific Article ◽  
National Journal ◽  
Second Stage ◽  
Third Stage ◽  
Scientific Papers ◽  
Questions And Answers ◽  
Service Activity ◽  
Training Activities ◽  
Journal Submission

ABSTRAKKegiatan pengabdian ini dilaksanakan di SMP Negeri 1 Dewantara, Aceh utara. Tujuan pengabdian ini untuk memberikan pengetahuan bagi guru-guru dalam menulis artikel ilmiah, mengembangkan pengetahuan dan meningkatkan kualitas penulisan artikel ilmiah, melatih guru untuk mempublikasikan artikel penelitian secara mandiri pada jurnal nasional berbasi OJS (Open Journal System). Kegiatan ini di dasari oleh permasalahan mitra yaitu: (1) Belum adanya pelatihan khusus untuk mendukung penulisan karya ilmiah berbasis riset. (2) Minimnya pengetahuan guru dan keterbatasan ide dalam penulisan karya ilmiah. (3) Guru masih mengalami kesulitan untuk mempublikasikan artikel ilmiah secara mandiri pada jurnal nasional. Metode pelaksanaan kegiatan terdiri dari 3 tahapan yaitu. Tahapan sosialisasi dan diskusi dilakukan melalui penyuluhan (pemaparan materi) tentang (1) Penulisan Artikel Ilmiah Berbasis Riset Bagi Guru dan Teknik Submission di Jurnal Nasional dan (2) Teknik Submission Artikel di Jurnal Nasional Berbasis OJS. Tahap kedua yaitu tahapan diskusi dimana pada tahap ini dilanjutkan dengan diskusi berupa tanya jawab antara pemateri dengan peserta. Tahap ketiga yaitu mempraktekkan bagaimana cara submit artikel ilmiah sesuai dengan target submission jurnal nasional berbasis OJS. Hasil yang diperoleh yaitu semua peserta antusias mengikuti kegiatan pelatihan yang diberikan, hal ini terlihat dari para peserta yang menyimak dengan seksama materi yang disampaikan, dan mengajukan pertanyaan ketika ada kendala yang belum dipahami. Kata kunci: penulisan artikel lmiah; teknik submission ABSTRACTThis service activity was carried out at SMP Negeri 1 Dewantara, North Aceh. The purpose of this service is to provide knowledge for teachers in writing scientific articles, develop knowledge and improve the quality of writing scientific articles, train teachers to publish research articles independently in national journals based on OJS (Open Journal System). This activity is based on partner problems, namely: (1) There is no special training to support the writing of research-based scientific papers. (2) The lack of teacher knowledge and limited ideas in writing scientific papers. (3) Teachers still have difficulty publishing scientific articles independently in national journals. The method of implementing the activity consists of 3 stages, namely. The stages of socialization and discussion are carried out through counseling (exposure to material) on (1) Research-Based Scientific Article Writing for Teachers and Submission Techniques in National Journals and (2) Article Submission Techniques in OJS-Based National Journals. The second stage is the discussion stage where at this stage it is followed by a discussion in the form of questions and answers between the presenter and the participants. The third stage is to practice how to submit scientific articles in accordance with the OJS-based national journal submission target. The results obtained are that all participants are enthusiastic about participating in the training activities provided, this can be seen from the participants who listen carefully to the material presented, and ask questions when there are obstacles that are not yet understood. Keywords: scientific article writing; submission techniques

Sign in / Sign up

Export Citation Format

Share Document