Augmenting Embedding with Domain Knowledge for Oral Disease Diagnosis Prediction

2018 ◽  
pp. 236-250
Author(s):  
Guangkai Li ◽  
Songmao Zhang ◽  
Jie Liang ◽  
Zhanqiang Cao ◽  
Chuanbin Guo
Keyword(s):  
Domain Knowledge ◽  
Disease Diagnosis ◽  
Oral Disease

A Hybrid Model for Rice Disease Diagnosis Using Entropy Based Neuro Genetic Algorithm

Fuzzy Systems ◽  
2017 ◽  
pp. 273-291
Author(s):  
K. Lavanya ◽  
M.A. Saleem Durai ◽  
N.Ch.S.N. Iyengar
Keyword(s):  
Domain Knowledge ◽  
Back Propagation ◽  
Search Space ◽  
Disease Diagnosis ◽  
Complex Nature ◽  
Disease Prediction ◽  
Rice Disease ◽  
Consistent Performance ◽  
Diagnostic Symptoms ◽  
Target Data

Disease prediction is often characterized by a high degree of fuzziness and uncertainty. This may reside in the imperfect and complex nature of symptoms that aids in diagnosis.. For precise rice disease diagnosis, domain knowledge of expertise pathologists along with clinically screened database of crop symptoms is considered as knowledge base. The hybrid method pre treats the crop symptoms for removal of noise and redundancy. It forms as target data for rice disease diagnostic model. The Entropy assisted GEANN algorithm reduces the n- dimensionality of diagnostic symptoms and optimizes the target data search space for higher accuracy. Finally the neuro fuzzy system make way for prediction of diseases based on the rules derived from qualitative interpretation of crop symptoms uniqueness. The algorithm is tested for real time case studies of Vellore district, Tamilnadu, India and the results evolved consistent performance against regression, back propagation algorithm and fuzzy network in disease prediction.

scholarly journals Dynamic Changes in the Subgingival Microbiome and Their Potential for Diagnosis and Prognosis of Periodontitis

mBio ◽  
2015 ◽  
Vol 6 (1) ◽  
Author(s):  
Baochen Shi ◽  
Michaela Chang ◽  
John Martin ◽  
Makedonka Mitreva ◽  
Renate Lux ◽  
...  
Keyword(s):  
Disease Progression ◽  
Clinical Examination ◽  
Disease Diagnosis ◽  
Taxonomic Composition ◽  
Oral Disease ◽  
Dynamic Changes ◽  
Diagnosis And Prognosis ◽  
Microbiome Profile ◽  
Before And After

ABSTRACTThe human microbiome influences and reflects the health or disease state of the host. Periodontitis, a disease affecting about half of American adults, is associated with alterations in the subgingival microbiome of individual tooth sites. Although it can be treated, the disease can reoccur and may progress without symptoms. Without prognostic markers, follow-up examinations are required to assess reoccurrence and disease progression and to determine the need for additional treatments. To better identify and predict the disease progression, we aim to determine whether the subgingival microbiome can serve as a diagnosis and prognosis indicator. Using metagenomic shotgun sequencing, we characterized the dynamic changes in the subgingival microbiome in periodontitis patients before and after treatment at the same tooth sites. At the taxonomic composition level, the periodontitis-associated microorganisms were significantly shifted from highly correlated in the diseased state to poorly correlated after treatment, suggesting that coordinated interactions among the pathogenic microorganisms are essential to disease pathogenesis. At the functional level, we identified disease-associated pathways that were significantly altered in relative abundance in the two states. Furthermore, using the subgingival microbiome profile, we were able to classify the samples to their clinical states with an accuracy of 81.1%. Follow-up clinical examination of the sampled sites supported the predictive power of the microbiome profile on disease progression. Our study revealed the dynamic changes in the subgingival microbiome contributing to periodontitis and suggested potential clinical applications of monitoring the subgingival microbiome as an indicator in disease diagnosis and prognosis.IMPORTANCEPeriodontitis is a common oral disease. Although it can be treated, the disease may reoccur without obvious symptoms. Current clinical examination parameters are useful in disease diagnosis but cannot adequately predict the outcome of individual tooth sites after treatment. A link between the subgingival microbiota and periodontitis was identified previously; however, it remains to be investigated whether the microbiome can serve as a diagnostic and prognostic indicator. In this study, for the first time, we characterized the subgingival microbiome of individual tooth sites before and after treatment using a large-scale metagenomic analysis. Our longitudinal study revealed changes in the microbiota in taxonomic composition, cooccurrence of subgingival microorganisms, and functional composition. Using the microbiome profiles, we were able to classify the clinical states of subgingival plaque samples with a high accuracy. Follow-up clinical examination of sampled sites indicates that the subgingival microbiome profile shows promise for the development of diagnostic and prognostic tools.

scholarly journals Big data management with machine learning inscribed by domain knowledge for health care

2017 ◽  
Vol 6 (4) ◽  
pp. 98 ◽  
Author(s):  
EPhzibah E.P. ◽  
Sujatha R
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Big Data ◽  
Data Management ◽  
Domain Knowledge ◽  
Disease Diagnosis ◽  
Computing Methods ◽  
Support Vector ◽  
Vector Method ◽  
Medical Practitioners

In this work, a framework that helps in the disease diagnosis process with big-data management and machine learning using rule based, instance based, statistical, neural network and support vector method is given. Concerning this, big-data that contains the details of various diseases are collected, preprocessed and managed for classification. Diagnosis is a day-to-day activity for the medical practitioners and is also a decision-making task that requires domain knowledge and expertise in the specific field. This framework suggests different machine learning methods to aid the practitioner to diagnose disease based on the best classifier that is identified in the health care system. The framework has three main segments like big-data management, machine learning and input/output details of the patient. It has been already proved in the literature that the computing methods do help in disease diagnosis, provided the data about that particular disease is available in the data center. Thus this framework will provide a source of confidence and satisfaction to the doctors, as the model generated is based on the accuracy of the classifier compared to other classifiers.

Handbook of Oral Disease: Diagnosis and Management

BDJ ◽  
2002 ◽  
Vol 192 (7) ◽  
pp. 416-417
Author(s):  
A. Qualtrough ◽  
S. Greening ◽  
Dr J.M. Thomason ◽  
G. Smith
Keyword(s):  
Disease Diagnosis ◽  
Oral Disease ◽  
Diagnosis And Management

scholarly journals Saliva: Physiology and Diagnostic Potential in Health and Disease

2010 ◽  
Vol 10 ◽  
pp. 434-456 ◽  
Author(s):  
Sebastien J. C. Farnaud ◽  
Ourania Kosti ◽  
Stephen J. Getting ◽  
Derek Renshaw
Keyword(s):  
Communicable Disease ◽  
Systemic Disease ◽  
Disease Diagnosis ◽  
Antimicrobial Activities ◽  
Human Saliva ◽  
The Body ◽  
Viable Alternative ◽  
Indirect Detection ◽  
Oral Disease ◽  
Diagnostic Potential

Saliva has been described as the mirror of the body. In a world of soaring healthcare costs and an environment where rapid diagnosis may be critical to a positive patient outcome, saliva is emerging as a viable alternative to blood sampling. In this review, we discuss the composition and various physiological roles of saliva in the oral cavity, including soft tissue protection, antimicrobial activities, and oral tissue repair. We then explore saliva as a diagnostic marker of local oral disease and focus particularly on oral cancers. The cancer theme continues when we focus on systemic disease diagnosis from salivary biomarkers. Communicable disease is the focus of the next section where we review the literature relating to the direct and indirect detection of pathogenic infections from human saliva. Finally, we discuss hormones involved in appetite regulation and whether saliva is a viable alternative to blood in order to monitor hormones that are involved in satiety.

scholarly journals Clinical Evaluation of Pathognomonic Salivary Protease Fingerprinting for Oral Disease Diagnosis

2021 ◽  
Vol 11 (9) ◽  
pp. 866
Author(s):  
Garrit Koller ◽  
Eva Schürholz ◽  
Thomas Ziebart ◽  
Andreas Neff ◽  
Roland Frankenberger ◽  
...  
Keyword(s):  
Disease Status ◽  
Disease Diagnosis ◽  
Matrix Metalloproteases ◽  
Supervised Machine Learning ◽  
Oral Disease ◽  
Peptide Cleavage ◽  
Disease States ◽  
Substrate Cleavage ◽  
Specific Activities ◽  
Learning Analysis

Dental decay (Caries) and periodontal disease are globally prevalent diseases with significant clinical need for improved diagnosis. As mediators of dental disease-specific extracellular matrix degradation, proteases are promising analytes. We hypothesized that dysregulation of active proteases can be functionally linked to oral disease status and may be used for diagnosis. To address this, we examined a total of 52 patients with varying oral disease states, including healthy controls. Whole mouth saliva samples and caries biopsies were collected and subjected to analysis. Overall proteolytic and substrate specific activities were assessed using five multiplexed, fluorogenic peptides. Peptide cleavage was further described by inhibitors targeting matrix metalloproteases (MMPs) and cysteine, serine, calpain proteases (CSC). Proteolytic fingerprints, supported by supervised machine-learning analysis, were delineated by total proteolytic activity (PepE) and substrate preference combined with inhibition profiles. Caries and peridontitis showed increased enzymatic activities of MMPs with common (PepA) and divergent substrate cleavage patterns (PepE), suggesting different MMP contribution in particular disease states. Overall, sensitivity and specificity values of 84.6% and 90.0%, respectively, were attained. Thus, a combined analysis of protease derived individual and arrayed substrate cleavage rates in conjunction with inhibitor profiles may represent a sensitive and specific tool for oral disease detection.

A Hybrid Model for Rice Disease Diagnosis Using Entropy Based Neuro Genetic Algorithm

2016 ◽  
Vol 7 (2) ◽  
pp. 52-69
Author(s):  
K. Lavanya ◽  
M.A. Saleem Durai ◽  
N.Ch.S.N. Iyengar
Keyword(s):  
Domain Knowledge ◽  
Back Propagation ◽  
Search Space ◽  
Disease Diagnosis ◽  
Complex Nature ◽  
Diagnostic Model ◽  
Disease Prediction ◽  
Back Propagation Algorithm ◽  
Rice Disease ◽  
Target Data

Disease prediction is often characterized by a high degree of fuzziness and uncertainty. This may reside in the imperfect and complex nature of symptoms that aids in diagnosis.. For precise rice disease diagnosis, domain knowledge of expertise pathologists along with clinically screened database of crop symptoms is considered as knowledge base. The hybrid method pre treats the crop symptoms for removal of noise and redundancy. It forms as target data for rice disease diagnostic model. The Entropy assisted GEANN algorithm reduces the n- dimensionality of diagnostic symptoms and optimizes the target data search space for higher accuracy. Finally the neuro fuzzy system make way for prediction of diseases based on the rules derived from qualitative interpretation of crop symptoms uniqueness. The algorithm is tested for real time case studies of Vellore district, Tamilnadu, India and the results evolved consistent performance against regression, back propagation algorithm and fuzzy network in disease prediction.

Sign in / Sign up

Export Citation Format

Share Document