This document presents a study that analyzed concept definitions in SNOMED CT to identify redundant elements. The researchers adapted rules defined by Spackman to detect four types of redundancies: concepts, ungrouped exists restrictions, exists restrictions within role groups, and entire role groups. Applying these rules identified redundancies in 12% of SNOMED CT concepts. Role groups accounted for 41% of all redundant elements detected. The results were evaluated for completeness by comparing to another method for identifying underspecified concepts, and soundness by verifying logical closure was preserved after removing redundancies. Identifying and removing redundant elements could help improve the usability, flexibility and maintenance of SNOMED CT.
A comparison of ICD & SNOMED CT by example using an ICD-10 code and its SNOMED CT pre-coordinated expression equivalent to demonstrate what all are possible with either
A simple web-based interface for advanced SNOMED CT queriesSnow Owl
SNOMED CT – as the most comprehensive biomedical ontology – has the potential to utilize semantic query methods that operate on the defining attributes of the concepts. This type of semantic querying is widely used, and some of the query languages already extended the attribute constraints with the option for limited lexical and metadata search criteria.
Since the introduction of RF2 the expressibility of SNOMED CT can increase, and various national extensions make use of this extensibility by adding specific description logic features that are relevant for their content.
An example for this is the Singapore Drug Dictionary that is based on the SNOMED CT concept model, but applies additional attribute types. The standard query languages are not powerful enough for such content.
This demonstration introduces a search interface that allows querying both standard SNOMED CT content as well as pharmaceutical extensions that utilize optional description logic extensions. These advanced queries are created by terminologists with an understanding of SNOMED CT. End-users can then use these queries to browse relevant subsets of the terminology appropriate for their use case. For example, clinicians can browse only drugs that are clinically relevant, while regulators can constrain their searches to controlled substances.
The tool also allows early validation of intensional reference set content, without having to implement and publish the reference sets. Practical examples using an online browser (Snow Owl Web) will highlight challenges and lessons learnt when working with real-world clinicians and regulators lacking SNOMED CT training.
Please see our website http://b2i.sg for further information.
A brief introduction to SNOMED CT - the ontology based medical terminology. This covers the basic definitions, the difference between SNOMED CT and ICD9, Post co-ordination use-cases and some general information.
This is not an extensive guide for SNOMED CT adoption in a system
This document summarizes a seminar on optical coherence tomography (OCT). OCT uses low-coherence interferometry to produce high-resolution, cross-sectional tomographic images of internal tissue microstructures by measuring backscattered light. The document outlines the basic principles and components of OCT, its advantages over other imaging modalities, its applications in fields like dermatology and cardiology, limitations around penetration depth and acquisition speed, and the future potential for whole-market revenue of $2.5 billion annually as resolution and speed improve.
This document discusses optical coherence tomography (OCT). It begins with an introduction to OCT, explaining that it uses low-coherence interferometry to produce 2D or 3D images of internal tissue microstructures. It then covers the basic components of an OCT system including a Michelson interferometer. The document outlines several advantages of OCT such as its high resolution, rapid data acquisition, and ability to be used in small catheter designs. Applications discussed include imaging of the esophagus, epithelium, early cancers, and vulnerable plaques. Limitations and future areas of research focus on increasing penetration depth and resolution.
A comparison of ICD & SNOMED CT by example using an ICD-10 code and its SNOMED CT pre-coordinated expression equivalent to demonstrate what all are possible with either
A simple web-based interface for advanced SNOMED CT queriesSnow Owl
SNOMED CT – as the most comprehensive biomedical ontology – has the potential to utilize semantic query methods that operate on the defining attributes of the concepts. This type of semantic querying is widely used, and some of the query languages already extended the attribute constraints with the option for limited lexical and metadata search criteria.
Since the introduction of RF2 the expressibility of SNOMED CT can increase, and various national extensions make use of this extensibility by adding specific description logic features that are relevant for their content.
An example for this is the Singapore Drug Dictionary that is based on the SNOMED CT concept model, but applies additional attribute types. The standard query languages are not powerful enough for such content.
This demonstration introduces a search interface that allows querying both standard SNOMED CT content as well as pharmaceutical extensions that utilize optional description logic extensions. These advanced queries are created by terminologists with an understanding of SNOMED CT. End-users can then use these queries to browse relevant subsets of the terminology appropriate for their use case. For example, clinicians can browse only drugs that are clinically relevant, while regulators can constrain their searches to controlled substances.
The tool also allows early validation of intensional reference set content, without having to implement and publish the reference sets. Practical examples using an online browser (Snow Owl Web) will highlight challenges and lessons learnt when working with real-world clinicians and regulators lacking SNOMED CT training.
Please see our website http://b2i.sg for further information.
A brief introduction to SNOMED CT - the ontology based medical terminology. This covers the basic definitions, the difference between SNOMED CT and ICD9, Post co-ordination use-cases and some general information.
This is not an extensive guide for SNOMED CT adoption in a system
This document summarizes a seminar on optical coherence tomography (OCT). OCT uses low-coherence interferometry to produce high-resolution, cross-sectional tomographic images of internal tissue microstructures by measuring backscattered light. The document outlines the basic principles and components of OCT, its advantages over other imaging modalities, its applications in fields like dermatology and cardiology, limitations around penetration depth and acquisition speed, and the future potential for whole-market revenue of $2.5 billion annually as resolution and speed improve.
This document discusses optical coherence tomography (OCT). It begins with an introduction to OCT, explaining that it uses low-coherence interferometry to produce 2D or 3D images of internal tissue microstructures. It then covers the basic components of an OCT system including a Michelson interferometer. The document outlines several advantages of OCT such as its high resolution, rapid data acquisition, and ability to be used in small catheter designs. Applications discussed include imaging of the esophagus, epithelium, early cancers, and vulnerable plaques. Limitations and future areas of research focus on increasing penetration depth and resolution.
This document summarizes a seminar on optical coherence tomography (OCT). OCT uses low-coherence interferometry to produce high-resolution, cross-sectional tomographic images of internal tissue microstructures. It has advantages over other imaging modalities like high resolution, rapid acquisition, and small catheter designs. The document outlines OCT applications in fields like cardiology, dermatology, and gastroenterology. It also discusses current limitations and future work to improve penetration depth, resolution, and acquisition rates to further clinical applications.
Feasibility of Using Backscattered Light to Recover Refractive Index Gradient...Payman Rajai
The goal is to determine if the data available in commercial optical coherence tomography (OCT) systems is sufficient to reconstruct the crystalline lens GRIN
Learning target Pattern-of-Life for wide-area Anomaly Detectionzepolitat
The document presents a methodology for learning pattern-of-life (POL) models from GPS tracking data to detect anomalies. It proposes a hierarchical model with temporal and spatial layers. The temporal layer models preferred schedules using kernel density estimation (KDE) and conformal anomaly detection. The spatial layer models preferred routes using online clustering. The methodology is tested on two datasets and detects spatial and spatiotemporal anomalies. Results show CAD detects narrower anomalies than KDE. Future work includes improving the models and testing other techniques.
Reduced Radiation Exposure in Dual-Energy Computed Tomography of the Chest: ...MehranMouzam
ABSTRACT:
Objective: This study purports to answer the question: Does a dual-energy CT scan of the chest using reduced radiation result in images of equal or better quality compared to those produced by the gold standard of care?
Methods: With the agreement of the Ethical Review Committee and written informed consent from 32 patients, who received dual-energy CT (DECT) scan of the chest in a dual-source scanner, a second set of images was taken at a reduced radiation dose. On virtual monochromatic images at 40 and 60 keV, three thoracic radiologists evaluated image quality, normal thoracic structures, and pulmonary and mediastinal aberrations. Students analyzed the data using analysis of variance, Kappa statistics, and Wilcoxon signed-rank tests.
Results: No irregularities in the scans were missed in the virtual monochrome photographs of all patients at a lower radiation dose, and the images were found to be of sufficient quality. At 40 and 60 keV, standard-of-care pictures produced equal contrast enhancement and lesion detection. Observers were entirely consistent with one another. Among other characteristics, reduced-dose DECT had a CTDIvol of 3.0 ±0.6 mGy, and a size specified dose estimate (SSDE) of 4.0 ±0.6 mGy, a dose-length product (DLP) of 107 ±30 mgy.cm, and an effective dose (ED) of 1.15 ±0.4 mSv.
Conclusion: Dual-energy computed tomography of the chest allows for the administration of lower radiation doses (CTDIvol <3 mGy).
Energy-based Model for Out-of-Distribution Detection in Deep Medical Image Se...Seunghyun Hwang
Presented work is accepted in Korean domestic conference, Korean Society of Artificial Intelligence in Medicine (KOSAIM) 2020, as a poster session.
- by Seunghyun Hwang (Yonsei University, Severance Hospital, Center for Clinical Data Science)
DISTANT-CTO: A Zero Cost, Distantly Supervised Approach to Improve Low-Resour...Anjani Dhrangadhariya
PICO recognition is an information extraction task for identifying participant, intervention, comparator, and outcome information from clinical literature.
Manually identifying PICO information is the most time-consuming step for conducting systematic reviews (SR) which is already a labor-intensive process.
A lack of diversified and large, annotated corpora restricts innovation and adoption of automated PICO recognition systems.
The largest-available PICO entity/span corpus is manually annotated which is too expensive for a majority of the scientific community.
To break through the bottleneck, we propose DISTANT-CTO, a novel distantly supervised PICO entity extraction approach using the clinical trials literature, to generate a massive weakly-labeled dataset with more than a million ``Intervention'' and ``Comparator'' entity annotations.
We train distant NER (named-entity recognition) models using this weakly-labeled dataset and demonstrate that it outperforms even the sophisticated models trained on the manually annotated dataset with a 2\% F1 improvement over the Intervention entity of the PICO benchmark and more than 5\% improvement when combined with the manually annotated dataset.
We investigate the generalizability of our approach and gain an impressive F1 score on another domain-specific PICO benchmark.
The approach is not only zero-cost but is also scalable for a constant stream of PICO entity annotations.
This document provides an overview of nanotechnology. It defines nanotechnology as the manipulation of matter at the nanoscale, or 1 to 100 nanometers. Nanotechnology involves both nanoscience, which studies materials at this scale, and applying these materials to develop new products. Some key points covered include that materials have unique properties at the nanoscale, nanoparticles like gold are being researched for medical applications, carbon nanotubes are being studied for uses like drug delivery, and nanotechnology offers advantages like protecting drugs but also faces challenges like potential health effects.
SNOMED CT concept model for molecular pathology_final.pptxHariHaran685388
This document discusses the need for standardized terminology to represent observational data in molecular genetics and precision medicine. It outlines challenges in representing genetic and molecular pathology findings in existing clinical terminologies like SNOMED CT and LOINC. The document proposes a harmonized concept model between SNOMED CT and LOINC for observable entities to address these challenges. It describes work at UNMC to apply this model to structured encoding of cancer pathology reports, incorporating genetic and molecular data. The goal is to develop terminology that enables clinical decision support and research by integrating genetic and molecular research findings with clinical concept models.
The Open Source Drug Discovery (OSDD) strategy uses an open innovation model with a porous-walled funnel to facilitate the free flow of ideas and projects. It brings in more contributors to look at projects and enables redundancies and parallelization. OSDD acts as a facilitator to marry academic and delivery-focused approaches and provides expertise, discovery platforms, and coordination of activities from both individual and centrally coordinated projects. OSDD has established multiple platforms for drug discovery including compound management, screening, target validation, and mechanistic studies. It has an extensive portfolio involving over 180 principal investigators from over 100 institutions working on projects ranging from whole cell screening to structure-based drug design.
End-to-end Fine-grained Neural Entity Recognition of Patients, Interventions,...Anjani Dhrangadhariya
Is multitask learning worthy in PICO recognition? We explored this question in out paper with the same name (Read our paper here https://arodes.hes-so.ch/record/8949?ln=FR). These slides correspond to the paper and were presented in CLEF2021 Romania, Bucharest.
Analogy, Causality, and Discovery in Science: The engines of human thoughtCITE
13 January 2015, Tuesday
12:45 pm – 2:00 pm
has been changed to RMS 101, Runme Shaw Bldg., HKU
By Professor Kevin Niall DUNBAR,
College of Education, University of Maryland, College Park, US
http://sol.edu.hku.hk/analogy-causality-discovery-science-engines-human-thought/
Dendral was an early artificial intelligence system developed in the 1960s at Stanford University to help chemists identify unknown organic molecules. It used mass spectrometry data and knowledge of chemistry to generate possible molecular structures and test them against the data. Dendral consisted of two subprograms: Heuristic Dendral, which produced potential structures, and Meta Dendral, which learned to explain the correlation between structures and spectra. The system pioneered the use of heuristics, knowledge engineering, and the plan-generate-test problem-solving paradigm in expert systems.
This document discusses the history and concepts of molecular modelling in drug design. It describes how early drug design involved trial and error methods to find biologically active molecules through random screening. The development of X-ray crystallography in the 1970s allowed visualization of 3D molecular structures, advancing drug design. Molecular modelling uses computer techniques based on chemistry and experimental data to analyze molecules and predict properties. The first generation of rational drug design used quantitative structure-activity relationships based on 2D structures. The second generation involves molecular modelling to simulate molecular interactions and design molecules meeting biological requirements through direct and indirect approaches as well as database searches and 3D computer-aided drug design.
Anne Casey RN MSc FRCN
Editor, Paediatric Nursing
Royal College of Nursing Adviser on Information Standards
Clinical Domain Lead, NHS Information Standards Board for Health and Social Care
(15/10/08, SNOMED Workshop)
Single Stage Operation for Multiple Cerebral Aneurysms of the Anterior Circul...Cristina Caterina Aldea
Presented at:
Congressis 2012, Iasi - First Prize at Surgical Section
Also presented at: Medicalis Cluj-Napoca, Romania 2012; Leiden International Medical Students Conference 2013
A new super vised approach for breast cancer diagnosis based on ar tificial s...Menad1992
The document presents a new supervised approach for breast cancer diagnosis based on artificial social bees. It uses two algorithms: the social bees algorithm and the nearest neighbor (1-NN) algorithm. For each cell nucleus, 10 features are computed from medical data. The dataset contains 569 samples of benign and malignant cases. Artificial worker bees are used to classify the data based on different distance metrics, and the nearest neighbor algorithm is used for diagnosis.
Dendral was an early expert system developed in the 1960s at Stanford University to help organic chemists identify unknown organic molecules. It used mass spectrometry data and knowledge of chemistry to generate possible chemical structures. Dendral included both Heuristic Dendral, which produced candidate structures, and Meta Dendral, a machine learning system that proposed mass spectrometry rules relating structure to spectra. The project pioneered the use of heuristics programming and helped establish artificial intelligence approaches like the plan-generate-test problem solving paradigm. Many subsequent expert systems were influenced by Dendral.
The main objective of this work is to facilitate the identification, sharing, and reasoning about cerebral tumors observations via the formalization of their semantic meanings in order to facilitate their exploitation in both the clinical practice and research. We focused our analysis on the VASARI terminology as a proof of concept, but we are convinced that our work can be useful in other biomedical imaging contexts.
This document describes a study that used structural matching of concept pairs from six reference terminologies and SNOMED CT in the UMLS to identify potential relationships for semantic harmonization. 241 concept pairs were reviewed. 59.3% represented alternative classifications, 23.6% potential parent-child relationships, and 14.5% new synonyms. Some errors were also identified. The study demonstrates that structural matching may complement expert review in identifying concepts for import/export between terminologies.
Formalization and automated computation of diabetes quality indicators with C...Kathrin Dentler
Clinical quality indicators are often used to measure the quality of healthcare services and can be classified into structure-related, process-related and outcome-related indicators. The objective of this study is to investigate whether the electronic medical record (EMR) data in Chinese hospitals can be used for the automated computation of di- abetes quality indicators, especially the process-related indicators. The clinical quality indicators formalization (CLIF) tool and SNOMED CT terminology were adopted to formalize some selected diabetes indicators into executable queries and patient data were collected from the EMR of a Chinese diabetes specialty hospital. The formalized indicators were run on the patient data to test the feasibility of the automated computation of formalized indicators. In this study, all of the 38 indicators can be for- malized and 32 of them can be computed based on the EMR data. The results indicated that Chinese EMRs can be used for the computation of most diabetes indicators, including some process-related indicators, and it also can be improved to better support the computation of more indicators.
Computing Healthcare Quality Indicators Automatically: Secondary Use of Pati...Kathrin Dentler
I) Formalizing quality indicators using the CLIF method allowed 159 indicators to be computed automatically from patient data.
II) Secondary use of patient data for quality indicator computation is challenging due to barriers like data quality issues. Indicator results differed depending on whether primary or secondary data was used.
III) Semantic interoperability is essential for automatic quality indicator computation, and was tested through reasoning engines and analyzing redundant elements in medical coding systems.
More Related Content
Similar to Redundant Elements in SNOMED CT Concept Definitions
This document summarizes a seminar on optical coherence tomography (OCT). OCT uses low-coherence interferometry to produce high-resolution, cross-sectional tomographic images of internal tissue microstructures. It has advantages over other imaging modalities like high resolution, rapid acquisition, and small catheter designs. The document outlines OCT applications in fields like cardiology, dermatology, and gastroenterology. It also discusses current limitations and future work to improve penetration depth, resolution, and acquisition rates to further clinical applications.
Feasibility of Using Backscattered Light to Recover Refractive Index Gradient...Payman Rajai
The goal is to determine if the data available in commercial optical coherence tomography (OCT) systems is sufficient to reconstruct the crystalline lens GRIN
Learning target Pattern-of-Life for wide-area Anomaly Detectionzepolitat
The document presents a methodology for learning pattern-of-life (POL) models from GPS tracking data to detect anomalies. It proposes a hierarchical model with temporal and spatial layers. The temporal layer models preferred schedules using kernel density estimation (KDE) and conformal anomaly detection. The spatial layer models preferred routes using online clustering. The methodology is tested on two datasets and detects spatial and spatiotemporal anomalies. Results show CAD detects narrower anomalies than KDE. Future work includes improving the models and testing other techniques.
Reduced Radiation Exposure in Dual-Energy Computed Tomography of the Chest: ...MehranMouzam
ABSTRACT:
Objective: This study purports to answer the question: Does a dual-energy CT scan of the chest using reduced radiation result in images of equal or better quality compared to those produced by the gold standard of care?
Methods: With the agreement of the Ethical Review Committee and written informed consent from 32 patients, who received dual-energy CT (DECT) scan of the chest in a dual-source scanner, a second set of images was taken at a reduced radiation dose. On virtual monochromatic images at 40 and 60 keV, three thoracic radiologists evaluated image quality, normal thoracic structures, and pulmonary and mediastinal aberrations. Students analyzed the data using analysis of variance, Kappa statistics, and Wilcoxon signed-rank tests.
Results: No irregularities in the scans were missed in the virtual monochrome photographs of all patients at a lower radiation dose, and the images were found to be of sufficient quality. At 40 and 60 keV, standard-of-care pictures produced equal contrast enhancement and lesion detection. Observers were entirely consistent with one another. Among other characteristics, reduced-dose DECT had a CTDIvol of 3.0 ±0.6 mGy, and a size specified dose estimate (SSDE) of 4.0 ±0.6 mGy, a dose-length product (DLP) of 107 ±30 mgy.cm, and an effective dose (ED) of 1.15 ±0.4 mSv.
Conclusion: Dual-energy computed tomography of the chest allows for the administration of lower radiation doses (CTDIvol <3 mGy).
Energy-based Model for Out-of-Distribution Detection in Deep Medical Image Se...Seunghyun Hwang
Presented work is accepted in Korean domestic conference, Korean Society of Artificial Intelligence in Medicine (KOSAIM) 2020, as a poster session.
- by Seunghyun Hwang (Yonsei University, Severance Hospital, Center for Clinical Data Science)
DISTANT-CTO: A Zero Cost, Distantly Supervised Approach to Improve Low-Resour...Anjani Dhrangadhariya
PICO recognition is an information extraction task for identifying participant, intervention, comparator, and outcome information from clinical literature.
Manually identifying PICO information is the most time-consuming step for conducting systematic reviews (SR) which is already a labor-intensive process.
A lack of diversified and large, annotated corpora restricts innovation and adoption of automated PICO recognition systems.
The largest-available PICO entity/span corpus is manually annotated which is too expensive for a majority of the scientific community.
To break through the bottleneck, we propose DISTANT-CTO, a novel distantly supervised PICO entity extraction approach using the clinical trials literature, to generate a massive weakly-labeled dataset with more than a million ``Intervention'' and ``Comparator'' entity annotations.
We train distant NER (named-entity recognition) models using this weakly-labeled dataset and demonstrate that it outperforms even the sophisticated models trained on the manually annotated dataset with a 2\% F1 improvement over the Intervention entity of the PICO benchmark and more than 5\% improvement when combined with the manually annotated dataset.
We investigate the generalizability of our approach and gain an impressive F1 score on another domain-specific PICO benchmark.
The approach is not only zero-cost but is also scalable for a constant stream of PICO entity annotations.
This document provides an overview of nanotechnology. It defines nanotechnology as the manipulation of matter at the nanoscale, or 1 to 100 nanometers. Nanotechnology involves both nanoscience, which studies materials at this scale, and applying these materials to develop new products. Some key points covered include that materials have unique properties at the nanoscale, nanoparticles like gold are being researched for medical applications, carbon nanotubes are being studied for uses like drug delivery, and nanotechnology offers advantages like protecting drugs but also faces challenges like potential health effects.
SNOMED CT concept model for molecular pathology_final.pptxHariHaran685388
This document discusses the need for standardized terminology to represent observational data in molecular genetics and precision medicine. It outlines challenges in representing genetic and molecular pathology findings in existing clinical terminologies like SNOMED CT and LOINC. The document proposes a harmonized concept model between SNOMED CT and LOINC for observable entities to address these challenges. It describes work at UNMC to apply this model to structured encoding of cancer pathology reports, incorporating genetic and molecular data. The goal is to develop terminology that enables clinical decision support and research by integrating genetic and molecular research findings with clinical concept models.
The Open Source Drug Discovery (OSDD) strategy uses an open innovation model with a porous-walled funnel to facilitate the free flow of ideas and projects. It brings in more contributors to look at projects and enables redundancies and parallelization. OSDD acts as a facilitator to marry academic and delivery-focused approaches and provides expertise, discovery platforms, and coordination of activities from both individual and centrally coordinated projects. OSDD has established multiple platforms for drug discovery including compound management, screening, target validation, and mechanistic studies. It has an extensive portfolio involving over 180 principal investigators from over 100 institutions working on projects ranging from whole cell screening to structure-based drug design.
End-to-end Fine-grained Neural Entity Recognition of Patients, Interventions,...Anjani Dhrangadhariya
Is multitask learning worthy in PICO recognition? We explored this question in out paper with the same name (Read our paper here https://arodes.hes-so.ch/record/8949?ln=FR). These slides correspond to the paper and were presented in CLEF2021 Romania, Bucharest.
Analogy, Causality, and Discovery in Science: The engines of human thoughtCITE
13 January 2015, Tuesday
12:45 pm – 2:00 pm
has been changed to RMS 101, Runme Shaw Bldg., HKU
By Professor Kevin Niall DUNBAR,
College of Education, University of Maryland, College Park, US
http://sol.edu.hku.hk/analogy-causality-discovery-science-engines-human-thought/
Dendral was an early artificial intelligence system developed in the 1960s at Stanford University to help chemists identify unknown organic molecules. It used mass spectrometry data and knowledge of chemistry to generate possible molecular structures and test them against the data. Dendral consisted of two subprograms: Heuristic Dendral, which produced potential structures, and Meta Dendral, which learned to explain the correlation between structures and spectra. The system pioneered the use of heuristics, knowledge engineering, and the plan-generate-test problem-solving paradigm in expert systems.
This document discusses the history and concepts of molecular modelling in drug design. It describes how early drug design involved trial and error methods to find biologically active molecules through random screening. The development of X-ray crystallography in the 1970s allowed visualization of 3D molecular structures, advancing drug design. Molecular modelling uses computer techniques based on chemistry and experimental data to analyze molecules and predict properties. The first generation of rational drug design used quantitative structure-activity relationships based on 2D structures. The second generation involves molecular modelling to simulate molecular interactions and design molecules meeting biological requirements through direct and indirect approaches as well as database searches and 3D computer-aided drug design.
Anne Casey RN MSc FRCN
Editor, Paediatric Nursing
Royal College of Nursing Adviser on Information Standards
Clinical Domain Lead, NHS Information Standards Board for Health and Social Care
(15/10/08, SNOMED Workshop)
Single Stage Operation for Multiple Cerebral Aneurysms of the Anterior Circul...Cristina Caterina Aldea
Presented at:
Congressis 2012, Iasi - First Prize at Surgical Section
Also presented at: Medicalis Cluj-Napoca, Romania 2012; Leiden International Medical Students Conference 2013
A new super vised approach for breast cancer diagnosis based on ar tificial s...Menad1992
The document presents a new supervised approach for breast cancer diagnosis based on artificial social bees. It uses two algorithms: the social bees algorithm and the nearest neighbor (1-NN) algorithm. For each cell nucleus, 10 features are computed from medical data. The dataset contains 569 samples of benign and malignant cases. Artificial worker bees are used to classify the data based on different distance metrics, and the nearest neighbor algorithm is used for diagnosis.
Dendral was an early expert system developed in the 1960s at Stanford University to help organic chemists identify unknown organic molecules. It used mass spectrometry data and knowledge of chemistry to generate possible chemical structures. Dendral included both Heuristic Dendral, which produced candidate structures, and Meta Dendral, a machine learning system that proposed mass spectrometry rules relating structure to spectra. The project pioneered the use of heuristics programming and helped establish artificial intelligence approaches like the plan-generate-test problem solving paradigm. Many subsequent expert systems were influenced by Dendral.
The main objective of this work is to facilitate the identification, sharing, and reasoning about cerebral tumors observations via the formalization of their semantic meanings in order to facilitate their exploitation in both the clinical practice and research. We focused our analysis on the VASARI terminology as a proof of concept, but we are convinced that our work can be useful in other biomedical imaging contexts.
This document describes a study that used structural matching of concept pairs from six reference terminologies and SNOMED CT in the UMLS to identify potential relationships for semantic harmonization. 241 concept pairs were reviewed. 59.3% represented alternative classifications, 23.6% potential parent-child relationships, and 14.5% new synonyms. Some errors were also identified. The study demonstrates that structural matching may complement expert review in identifying concepts for import/export between terminologies.
Similar to Redundant Elements in SNOMED CT Concept Definitions (20)
Formalization and automated computation of diabetes quality indicators with C...Kathrin Dentler
Clinical quality indicators are often used to measure the quality of healthcare services and can be classified into structure-related, process-related and outcome-related indicators. The objective of this study is to investigate whether the electronic medical record (EMR) data in Chinese hospitals can be used for the automated computation of di- abetes quality indicators, especially the process-related indicators. The clinical quality indicators formalization (CLIF) tool and SNOMED CT terminology were adopted to formalize some selected diabetes indicators into executable queries and patient data were collected from the EMR of a Chinese diabetes specialty hospital. The formalized indicators were run on the patient data to test the feasibility of the automated computation of formalized indicators. In this study, all of the 38 indicators can be for- malized and 32 of them can be computed based on the EMR data. The results indicated that Chinese EMRs can be used for the computation of most diabetes indicators, including some process-related indicators, and it also can be improved to better support the computation of more indicators.
Computing Healthcare Quality Indicators Automatically: Secondary Use of Pati...Kathrin Dentler
I) Formalizing quality indicators using the CLIF method allowed 159 indicators to be computed automatically from patient data.
II) Secondary use of patient data for quality indicator computation is challenging due to barriers like data quality issues. Indicator results differed depending on whether primary or secondary data was used.
III) Semantic interoperability is essential for automatic quality indicator computation, and was tested through reasoning engines and analyzing redundant elements in medical coding systems.
Semantic Integration of Patient Data and Quality Indicators based on openEHR ...Kathrin Dentler
The document discusses using openEHR archetypes to semantically integrate patient data and quality indicators. It describes mapping clinical data from a Dutch hospital database onto openEHR archetypes and SNOMED CT codes. Quality indicators were then formalized using the archetypes and constraints to query the structured patient data and calculate indicator results. The approach demonstrated the potential for open archetypes to enable sharable, computable quality indicator definitions and integration of heterogeneous clinical data sources.
The Reproducibility of CLIF, a Method for Clinical Quality Indicator Formali...Kathrin Dentler
In order to be able to automatically calculate clinical quality indicators, we have proposed CLIF, a stepwise method for clinical quality indicator formalisation. Quality indicators are used for external accountability and hospital comparison. As clinical quality indicators are computed in a decentralised manner by the hospitals themselves, reproducibility of the formalisation method is essential to ensure the comparability of calculated values. Thus, we performed a case study to investigate the reproducibility of CLIF. Eight participants formalised the same sample quality indicator with the help of a web-based indicator-authoring tool that facilitates the application of CLIF. We analysed the results per step and concluded that the method itself leads to reproducible results. To further improve reproducibility, ambiguities in the indicator text must be clarified and trained experts are needed to encode clinical concepts and to specify the relations between concepts.
Comparison of Reasoners for large Ontologies in the OWL 2 EL ProfileKathrin Dentler
This document compares several reasoners for classifying large ontologies in the OWL 2 EL profile. It introduces the author's PhD project on semantic interoperability for clinical data using SNOMED CT. It outlines dimensions for comparing reasoners, including reasoning characteristics, usability, and performance. Results show how reasoners differ in methodology, features, and performance when classifying SNOMED CT, with some reasoners proving more sound and complete.
Towards the Automated Calculation of Clinical Quality IndicatorsKathrin Dentler
The document presents a method for automatically calculating clinical quality indicators by formalizing them as SPARQL queries. It describes a 7-step method to translate indicators into queries, tests the method on 4 indicators, and finds it can formalize most constructs with acceptable runtimes. However, one indicator cannot be fully expressed in SPARQL. The authors conclude the method works for a proof of concept but needs more indicators and real data to fully evaluate it.
Approximation and Self-Organisation on the Web of DataKathrin Dentler
This document discusses using computational intelligence techniques like evolutionary computing and collective intelligence to handle challenges posed by the growing Web of Data. It describes how these techniques can provide adaptive, scalable, and robust approaches to tasks like ontology mapping, query answering, and reasoning. Evolutionary computing is proposed for optimization problems, while collective intelligence approaches may enable emergent behaviors from decentralized data flows and reasoning. While computational intelligence loses precision, it gains properties like adaptation, simplicity, scalability, and interactive behavior that are well-suited to the dynamic, distributed nature of the Web of Data.
5-hydroxytryptamine or 5-HT or Serotonin is a neurotransmitter that serves a range of roles in the human body. It is sometimes referred to as the happy chemical since it promotes overall well-being and happiness.
It is mostly found in the brain, intestines, and blood platelets.
5-HT is utilised to transport messages between nerve cells, is known to be involved in smooth muscle contraction, and adds to overall well-being and pleasure, among other benefits. 5-HT regulates the body's sleep-wake cycles and internal clock by acting as a precursor to melatonin.
It is hypothesised to regulate hunger, emotions, motor, cognitive, and autonomic processes.
Osteoporosis - Definition , Evaluation and Management .pdfJim Jacob Roy
Osteoporosis is an increasing cause of morbidity among the elderly.
In this document , a brief outline of osteoporosis is given , including the risk factors of osteoporosis fractures , the indications for testing bone mineral density and the management of osteoporosis
Promoting Wellbeing - Applied Social Psychology - Psychology SuperNotesPsychoTech Services
A proprietary approach developed by bringing together the best of learning theories from Psychology, design principles from the world of visualization, and pedagogical methods from over a decade of training experience, that enables you to: Learn better, faster!
Mercurius is named after the roman god mercurius, the god of trade and science. The planet mercurius is named after the same god. Mercurius is sometimes called hydrargyrum, means ‘watery silver’. Its shine and colour are very similar to silver, but mercury is a fluid at room temperatures. The name quick silver is a translation of hydrargyrum, where the word quick describes its tendency to scatter away in all directions.
The droplets have a tendency to conglomerate to one big mass, but on being shaken they fall apart into countless little droplets again. It is used to ignite explosives, like mercury fulminate, the explosive character is one of its general themes.
8 Surprising Reasons To Meditate 40 Minutes A Day That Can Change Your Life.pptxHolistified Wellness
We’re talking about Vedic Meditation, a form of meditation that has been around for at least 5,000 years. Back then, the people who lived in the Indus Valley, now known as India and Pakistan, practised meditation as a fundamental part of daily life. This knowledge that has given us yoga and Ayurveda, was known as Veda, hence the name Vedic. And though there are some written records, the practice has been passed down verbally from generation to generation.
Travel vaccination in Manchester offers comprehensive immunization services for individuals planning international trips. Expert healthcare providers administer vaccines tailored to your destination, ensuring you stay protected against various diseases. Conveniently located clinics and flexible appointment options make it easy to get the necessary shots before your journey. Stay healthy and travel with confidence by getting vaccinated in Manchester. Visit us: www.nxhealthcare.co.uk
DECLARATION OF HELSINKI - History and principlesanaghabharat01
This SlideShare presentation provides a comprehensive overview of the Declaration of Helsinki, a foundational document outlining ethical guidelines for conducting medical research involving human subjects.
Histololgy of Female Reproductive System.pptxAyeshaZaid1
Dive into an in-depth exploration of the histological structure of female reproductive system with this comprehensive lecture. Presented by Dr. Ayesha Irfan, Assistant Professor of Anatomy, this presentation covers the Gross anatomy and functional histology of the female reproductive organs. Ideal for students, educators, and anyone interested in medical science, this lecture provides clear explanations, detailed diagrams, and valuable insights into female reproductive system. Enhance your knowledge and understanding of this essential aspect of human biology.
The skin is the largest organ and its health plays a vital role among the other sense organs. The skin concerns like acne breakout, psoriasis, or anything similar along the lines, finding a qualified and experienced dermatologist becomes paramount.
Redundant Elements in SNOMED CT Concept Definitions
1. Introduction Materials & methods Results Conclusion
Redundant Elements in SNOMED CT
Concept Definitions
Kathrin Dentler and Ronald Cornet
31. May @ AIME 2013. Paper: http://www.few.vu.nl/~kdr250/
publications/AIME2013-Redundant-Elements-SNOMED.pdf
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 1/23
2. Introduction Materials & methods Results Conclusion
Outline
1 Introduction
2 Materials & methods
3 Results
4 Conclusion
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 2/23
3. Introduction Materials & methods Results Conclusion
SNOMED CT
Systematized Nomenclature Of Medicine Clinical Terms
Meaning-based recording & retrieval, reuse,
interoperability!
Most comprehensive clinical terminology: around 300,000
concepts
Concepts are organized in hierarchies with multiple levels
of granularity
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 3/23
4. Introduction Materials & methods Results Conclusion
SNOMED CT
Systematized Nomenclature Of Medicine Clinical Terms
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 4/23
5. Introduction Materials & methods Results Conclusion
SNOMED CT Concept Definitions in EL+
RoleGroups
Finding X includes an inflamed arm and a broken leg:
∃Finding site.Arm
∃Associated morphology.Inflammation
∃Finding site.Leg
∃Associated morphology.Fracture
→unclear what belongs together. Therefore, role-value pairs
can be grouped in RoleGroups (RG):
∃RG(Finding site.Arm
Associated morphology.Inflammation)
∃RG(Finding site.Leg Associated morphology.Fracture)
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 5/23
6. Introduction Materials & methods Results Conclusion
SNOMED CT Concept Definitions in EL+
Conjunctions ( ) of other concepts (superconcepts) and
role-value pairs (∃), ungrouped or grouped in RoleGroups.
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 6/23
7. Introduction Materials & methods Results Conclusion
(Intra-Axiom) Redundancies
Redundant element
Stated explicitly even though it is implied by the
definition of the same concept or a stated superconcept.
Can be removed without affecting the logical closure.
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 7/23
8. Introduction Materials & methods Results Conclusion
(Intra-Axiom) Redundancies
Confuse knowledge modellers (Spackman; Chief
Terminologist at IHTSDO)
Make a terminology less flexible and harder to maintain
(Grimm and Wissmann)
Should be recognized & rendered transparent (Cimino)
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 8/23
9. Introduction Materials & methods Results Conclusion
(Intra-Axiom) Redundancies
Example
Example: Two concepts July 2012
Non-imaging thyroid uptake test
Radionuclide study of endocrine function
∃RG(∃Method.Radionuclide imaging
∃Procedure site.Thyroid structure
∃Using substance.Radioactive isotope)
Thyroid uptake with thyroid stimulation
Stimulation test Non-imaging thyroid uptake test
Radionuclide uptake study
∃RG(∃Method.Radionuclide imaging
∃Procedure site.Thyroid structure
∃Using substance.Radioactive isotope)
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 9/23
10. Introduction Materials & methods Results Conclusion
(Intra-Axiom) Redundancies
Might lead to content-related problems when concepts drift
Example: Two concepts January 2013
Non-imaging thyroid uptake test
Radionuclide study of endocrine function
∃RG(∃Method.Radionuclide imaging
∃Procedure site.Thyroid structure
∃Using substance.Radioactive isotope)
Thyroid uptake with thyroid stimulation
Stimulation test Non-imaging thyroid uptake test
Radionuclide uptake study
∃RG(::::::::::::::::::::::::::::::::
∃Method.Radionuclide imaging
∃Procedure site.Thyroid structure
∃Using substance.Radioactive isotope)
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 10/23
11. Introduction Materials & methods Results Conclusion
Approach
Spackman: defined rules to determine and eliminate
redundant expressions in concept definitions (2002)
We adapted and extended these rules; one rule per
element:
1 concepts
2 ungrouped exists restrictions
3 exists restrictions within rolegroups
4 rolegroups
Aim: apply the rules to the entire SNOMED CT; support
knowledge modellers
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 11/23
12. Introduction Materials & methods Results Conclusion
Four rules of redundancy detection
Concept
A concept is redundant when it is more general than or
equivalent to another concept in the definition of the same
concept or a superconcept.
Example: Structure of lobe of brain
Structure of lobe of brain
Brain part Brain tissue structure
Brain tissue structure Brain part
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 12/23
13. Introduction Materials & methods Results Conclusion
Four rules of redundancy detection
Ungrouped exists restriction
An ungrouped exists restriction is redundant when it is more
general than or equivalent to another ungrouped exists
restriction within the definition of the same concept or a
superconcept.
Example: Parenteral form thymoxamine
Thymoxamine (product)
Alpha blocking vasodilator Alpha 1 blocking agent
∃Has active ingredient.Thymoxamine (substance)
Parenteral form thymoxamine (product) ≡
Thymoxamine (product)
∃Has active ingredient.Thymoxamine (substance)
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 13/23
14. Introduction Materials & methods Results Conclusion
Four rules of redundancy detection
Exists restriction within rolegroup
An exists restriction is redundant within a rolegroup when it is
more general than or equivalent to another exists restriction in
the same rolegroup.
Example: Closed skull fracture with intracranial injury
Closed skull fracture with intracranial injury ≡
Fracture of skull
∃RG(∃Finding site.Intracranial structure
∃Associated morphology.Traumatic abnormality
∃Associated morphology.Closed traumatic abnormality )
Closed traumatic abnormality Traumatic abnormality
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 14/23
15. Introduction Materials & methods Results Conclusion
Four rules of redundancy detection
Rolegroup
A rolegroup is redundant when all its exists restrictions are
more general than or equivalent to those contained in another
rolegroup in the definition of the same concept or a
superconcept.
Example: Brain stem contusion with open intracranial wound
Brain stem contusion with open intracranial wound ≡
Contusion of brain with open intracranial wound
∃RG(∃Associated morphology.Open wound
∃Finding site.Intracranial structure)
∃RG(∃Associated morphology.Open contusion
∃Finding site.Brainstem structure)
Open contusion Open wound
Brainstem structure Intracranial structure
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 15/23
16. Introduction Materials & methods Results Conclusion
Four rules of redundancy detection
Approach
Applied the four rules of redundancy detection to each
concept and recursively all its stated (direct and indirect)
superconcepts in the stated form of SNOMED CT.
Eliminated all identified redundant elements.
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 16/23
17. Introduction Materials & methods Results Conclusion
Detected redundancies
Applying the four rules of redundancy detection, 35,010 of the
296,433 SNOMED CT concepts (12%) were identified to
contain redundant elements in their definitions.
Overview of all identified redundant elements:
Rule All Percentage
rolegroup 50,680 41%
ungrouped exists restriction 13,808 54%
concept 842 0.024%
grouped exists restriction 6 0.00026%
Sum 65,336
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 17/23
18. Introduction Materials & methods Results Conclusion
Categories of concepts with redundancies
finding
procedure
product
body structure
situation
specimen
organism
substance
physical object
Number of Concepts
0
5000
10000
15000
20000
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 18/23
19. Introduction Materials & methods Results Conclusion
Distances
Defined as steps in the concept hierarchy
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 19/23
20. Introduction Materials & methods Results Conclusion
Evaluation of Results
Partial completeness by comparison to Cornet and Abu-Hanna
Cornet and Abu-Hanna (2008) designed a method to identify
underspecified concepts, which can also identify special cases
of redundantly defined concepts.
→We compare the results of the two methods.
Partial completeness: All redundantly defined concepts
identified by applying the Cornet and Abu-Hanna method
must also be identified by the application of the four rules of
redundancy detection.
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 20/23
21. Introduction Materials & methods Results Conclusion
Evaluation of Results
Partial completeness by comparison to Cornet and Abu-Hanna
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 21/23
22. Introduction Materials & methods Results Conclusion
Evaluation of Results
Soundness
Closure of manipulated, redundancy-free version of SNOMED
CT equivalent to closure of original version.
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 22/23
23. Introduction Materials & methods Results Conclusion
Questions?
Overview of redundant
elements in SNOMED CT
Rules could help to
remove existing
redundancies and to
prevent future
redundancies
advantage: explanations!
IHTSDO: redundancy-free
normal forms
Future: Generalisation of
method
Kathrin Dentler and Ronald Cornet — Redundant Elements in SNOMED CT Concept Definitions 23/23