An unsupervised feature learning framework for basal cell carcinomaimage analysis
Conclusions The proposed UFL-representation-based approach outperforms state-of-the-art methods for BCC detection. Thanks to its visual interpretation layer, the method is able to highlight discriminative tissue regions providing a better diagnosis support. Among the different UFL strategies tested, TICA-learned features exhibited the best performance thanks to its ability to capture low-level invariances, which are inherent to the nature of the problem. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - May 1, 2015 Category: Bioinformatics Source Type: research

Sentiment analysis in medical settings: New opportunities and challenges
Conclusions Medical sentiment concerns the patient's health status, medical conditions and treatment. Its analysis and extraction from texts has multiple applications, even for clinical narratives that remained so far unconsidered. Given the varying usage and meanings of terms, sentiment analysis from medical documents requires a domain-specific sentiment source and complementary context-dependent features to be able to correctly interpret the implicit sentiment. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - May 1, 2015 Category: Bioinformatics Source Type: research

Automatic evidence quality prediction to support evidence-based decision making
Conclusions The experiments suggest that our structured text classification framework achieves evaluation results comparable to those of human performance. Our overall classification approach and evaluation technique are also highly portable and can be used for various evidence grading scales. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 23, 2015 Category: Bioinformatics Source Type: research

Assessment of surveys for the management of hospital clinical pharmacy services
Conclusions We show how the OrdEval algorithm can exploit the information hidden in the ordering of class and attribute values, and their inherent correlation using a small sample of highly relevant respondents. The visualization of the outputs turns out highly useful in our clinical pharmacy research case study. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 23, 2015 Category: Bioinformatics Source Type: research

Abstraction networks for terminologies: Supporting management of “big knowledge”
Conclusions The “big knowledge” challenge constitutes the use and maintenance of terminological structures that comprise tens of thousands to millions of concepts and their attendant complexity. The notion of abstraction network has been introduced as a tool in helping to overcome this challenge, thus enhancing the usefulness of terminologies. Abstraction networks have been shown to be applicable to a variety of existing biomedical terminologies, and these alternative structural views hold promise for future expanded use with additional terminologies. Graphical abstract Highlights (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 18, 2015 Category: Bioinformatics Source Type: research

A semi-supervised learning framework for biomedical event extraction based on hidden topics
Conclusion The results suggest that by incorporating un-annotated data, the proposed framework indeed improves the performance of the state-of-the-art event extraction system and the similarity between sentences might be precisely described by hidden topics and structures of the sentences. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 10, 2015 Category: Bioinformatics Source Type: research

Abstraction networks for terminologies: supporting managementof “big knowledge”
Conclusions The “big knowledge” challenge constitutes the use and maintenance of terminological structures that comprise tens of thousands to millions of concepts and their attendant complexity. The notion of abstraction network has been introduced as a tool in helping to overcome this challenge, thus enhancing the usefulness of terminologies. Abstraction networks have been shown to be applicable to a variety of existing biomedical terminologies, and these alternative structural views hold promise for future expanded use with additional terminologies. Graphical abstract Highlights (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 3, 2015 Category: Bioinformatics Source Type: research

A comparative analysis of the density of the SNOMED CT conceptual content for semantic harmonization
Conclusion These results show that structure-based algorithmic methods can be used to identify potential concepts to enrich SNOMED CT and the four reference terminologies. The comparative analysis has the future potential of supporting terminology authoring by suggesting new content to improve content coverage and semantic harmonization between terminologies. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 3, 2015 Category: Bioinformatics Source Type: research

A semi-supervised learning framework for biomedical eventextraction based on hidden topics
Conclusion: The results suggest that by incorporating un-annotated data, the proposed framework indeed improves the performance of the state-of-the-art event extraction system and the similarity between sentences might be precisely described by hidden topics and structures of the sentences. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - April 1, 2015 Category: Bioinformatics Source Type: research

Automatic negation detection in narrative pathology reports
Conclusions A machine-learning-based approach has potential advantages for negation detection, and may be preferable for the task. To improve the overall performance, one of the possible solutions is to apply different approaches to each section in the reports. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - March 24, 2015 Category: Bioinformatics Source Type: research

Predicting protein complexes from weighted protein–protein interaction graphs with a novel unsupervised methodology: Evolutionary enhanced Markov clustering
Conclusions EE-MC is by design able to overcome intrinsic limitations of existing methodologies such as their inability to handle weighted PPI networks, their constraint to assign every protein in exactly one cluster and the difficulties they face concerning the parameter tuning. This fact was experimentally validated and moreover, new potentially true human protein complexes were suggested as candidates for further validation using experimental techniques. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - March 11, 2015 Category: Bioinformatics Source Type: research

Solving challenges in inter- and trans-disciplinary working teams: lessons from the surgical technology field
Conclusions All actors in trans- and inter-disciplinary teams need to be interested in cooperation. This will lead to a common view on patients and technology models. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 25, 2015 Category: Bioinformatics Source Type: research

DrugNet: Network-based drug–disease prioritization by integrating heterogeneous data
Conclusions Our methodology suggests that new drugs can be repositioned by generating ranked lists of drugs based on a given disease query or vice versa. Our study shows that the simultaneous integration of information about diseases, drugs and targets can lead to a significant improvement in drug repositioning tasks. DrugNet is available as a web tool from http://genome2.ugr.es/drugnet/ (accessed 23.09.14). Matlab source code is also available on the website. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 20, 2015 Category: Bioinformatics Source Type: research

Ontology for assessment studies of human–computer-interaction in surgery
Conclusions The investigation model and its ontological implementation provide a modular guideline for study planning, implementation and documentation within the area of HCI research in surgery. This guideline helps to navigate through the whole study process in the form of a kind of standard or good clinical practice, based on the involved foundational frameworks. Furthermore, it allows to acquire the structured description of the applied assessment methods within a certain surgical domain and to consider this information for own study design or to perform a comparison of different studies. The investigation model and th...
Source: Artificial Intelligence in Medicine - February 19, 2015 Category: Bioinformatics Source Type: research

Predicting protein complexes from weighted protein-protein interaction graphs with a novel unsupervised methodology: evolutionary enhanced Markov clustering
Conclusions EE-MC is by design able to overcome intrinsic limitations of existing methodologies such as their inability to handle weighted PPI networks, their constraint to assign every protein in exactly one cluster and the difficulties they face concerning the parameter tuning. This fact was experimentally validated and moreover, new potentially true human protein complexes were suggestedas candidates for further validation using experimental techniques. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 19, 2015 Category: Bioinformatics Source Type: research

Outcome quality assessment by surgical process compliance measures in laparoscopic surgery
Conclusions We conclude that high process compliance supports good quality outcomes and, therefore, excellent patient care. We also showed that a deviation from best training processes led to a decreased outcome quality. This is relevant for identifying requirements for surgical processes, for generating feedback for the surgeon with regard to human factors and for inducing changes in the workflow in order to improve the outcome quality. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 19, 2015 Category: Bioinformatics Source Type: research

Solving challenges in inter- and transdisciplinary working teams: lessons from the surgical technology field
Conclusions All actors in trans- and interdisciplinary teams need to be interested in cooperation. This will lead to a common view on patients and technology models. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 18, 2015 Category: Bioinformatics Source Type: research

Machine learning in computational docking
Conclusions We conclude with open questions and potential future research directions that can be pursued in smart computational docking; using molecular features of different nature (geometrical, energy terms, pharmacophore), advanced ML techniques (e.g., deep learning), combining more than one ML models. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - February 17, 2015 Category: Bioinformatics Source Type: research

Ontology for assessment studies of human-computer-interaction in surgery
Conclusions The investigation model and its ontological implementation provide a modular guideline for study planning, implementation and documentation within the area of HCI research in surgery. This guideline helps to navigate through the whole study process in the form of a kind of standard or good clinical practice, based on the involved foundational frameworks. Furthermore, it allows to acquire the structured description of the applied assessment methods within a certain surgical domain and to consider this information for own study design or to perform a comparison of different studies. The investigation model and th...
Source: Artificial Intelligence in Medicine - January 14, 2015 Category: Bioinformatics Source Type: research

DrugNet: network-based drug-disease prioritization by integrating heterogeneous data
Conclusions Our methodology suggests that new drugs can be repositioned by generating ranked lists of drugs based on a given disease query or vice versa. Our study shows that the simultaneous integration of information about diseases, drugs and targets can lead to a significant improvement in drug repositioning tasks. DrugNet is available as a web tool from http://genome2.ugr.es/drugnet/ (accessed: 23 September 2014). Matlab source code is also available on the website. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - January 14, 2015 Category: Bioinformatics Source Type: research

Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores
Conclusion Using a classification grid based on the predicted patient mortality and prolonged stay, allows more accurate modeling of the patient LOS. The detailed models allow to support the decisions made by physicians in an ICU setting. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - January 8, 2015 Category: Bioinformatics Source Type: research

Classifying GABAergic interneurons with semi-supervised projected model-based clustering
Conclusions The applied semi-supervised clustering method can accurately discriminate among CB, HT, LB, and MA interneuron types while discovering potential subtypes, and is therefore useful for neuronal classification. The discovery of potential subtypes suggests that some of these types are more heterogeneous that previously thought. Finally, axonal variables seem to be more relevant than dendritic ones for distinguishing among the CB, HT, LB, and MA interneuron types. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - January 8, 2015 Category: Bioinformatics Source Type: research

Improving the Mann–Whitney statistical test for feature selection: An approach in breast cancer diagnosis on mammography
Conclusions The experimental results indicated that uFilter method statistically outperformed the U-test method and it demonstrated similar, but not superior, performance than traditional feature selection methods (CHI2 discretization, IG, 1Rule and Relief). The uFilter method revealed competitive and appealing cost-effectiveness results on selecting relevant features, as a support tool for breast cancer CADx methods especially in unbalanced datasets contexts. Finally, the redundancy analysis as a complementary step to the uFilter method provided us an effective way for finding optimal subsets of features without decreasin...
Source: Artificial Intelligence in Medicine - January 1, 2015 Category: Bioinformatics Source Type: research

Predictive modelling of survival and length of stay incritically ill patients using sequential organ failure scores
Conclusion Using a classification grid based on the predicted patient mortality and prolonged stay, allows more accurate modeling of the patient LOS. The detailed models allow to support the decisions made by physicians in an ICU setting. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - January 1, 2015 Category: Bioinformatics Source Type: research

Application of a two-stage fuzzy neural network to a prostate cancer prognosis system
Conclusions The proposed two-stage FNN is able to learn the relationship between the clinical features and the prognosis of prostate cancer. Once the clinical data are known, the prognosis of prostate cancer patient can be predicted. Furthermore, unlike artificial neural networks, it is much easier to interpret the training results of the proposed network since they are in the form of fuzzy IF-THEN rules. These rules are very important for medical doctors. This can dramatically assist medical doctors to make decisions. Graphical abstract (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 30, 2014 Category: Bioinformatics Source Type: research

Improved cosine similarity measures of simplified neutrosophic sets for medical diagnoses
Conclusions the improved cosine measures of SNSs based on cosine function can overcome some drawbacks of existing cosine similarity measures of SNSs in vector space, and then their diagnosis method is very suitable for handling the medical diagnosis problems with simplified neutrosophic information and demonstrates the effectiveness and rationality of medical diagnoses. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 27, 2014 Category: Bioinformatics Source Type: research

Clinical time series prediction: Toward a hierarchical dynamical system framework
Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 20, 2014 Category: Bioinformatics Source Type: research

Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data
Conclusion The CART analyses have shown that features extracted from three types of physiological measurements; forced expiratory volume in one second (FEV1), arterial oxygen saturation (SPO2) and weight have the most predictive power in stratifying the patients condition. This CART algorithm for early detection could trigger the initiation of timely treatment, thereby potentially reducing exacerbation severity and recovery time and improving the patient's health. This study highlights the potential usefulness of automated analysis of home telehealth data in the early detection of exacerbation events among COPD patients. (...
Source: Artificial Intelligence in Medicine - December 19, 2014 Category: Bioinformatics Source Type: research

Development of electroencephalographic pattern classifiers for real and imaginary thumb and index finger movements of one hand
Conclusion This work supports the feasibility of the approach, which is presumed suitable for one-hand finger movement (real and imaginary) decoding. These results could be applied in the elaboration of multiclass BCI systems. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 19, 2014 Category: Bioinformatics Source Type: research

Adaptive dynamic programming algorithms for sequential appointment scheduling with patient preferences
Conclusions System parameters are adaptively updated as bookings are confirmed. The proposed appointment scheduling system could certainly contribute to better patient satisfaction level during the booking periods. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 18, 2014 Category: Bioinformatics Source Type: research

Self-focusing therapeutic gene delivery with intelligent gene vector swarms: Intra-swarm signalling through receptor transgene expression in targeted cells
Conclusions It is hoped that proposed self-focusing cell-targeted gene vector swarms with receptor-mediated intra-swarm signalling could be particularly effective in ‘top-up’ gene delivery scenarios, achieving high-level and sustained expression of therapeutic transgenes that are prone to shut-down through degradation and silencing. Crucially, in contrast to low-precision ‘general location’ vector guidance by diffusible chemo-attractants, ear-marking non-diffusible receptors can provide high-accuracy targeting of therapeutic vector particles to the specific cell, which has undergone a ‘success...
Source: Artificial Intelligence in Medicine - December 18, 2014 Category: Bioinformatics Source Type: research

Improving the Mann-Whitney statistical test for feature selection: An approach in breast cancer diagnosis on mammography
Conclusions The experimental results indicated that uFilter method statistically outperformed the U-Test method and it demonstrated similar, but not superior, performance than traditional feature selection methods (CHI2 discretization, IG, 1Rule and Relief). The uFilter method revealed competitive and appealing cost-effectiveness results on selecting relevant features, as a support tool for breast cancer CADx methods especially in unbalanced datasets contexts. Finally, the redundancy analysis as a complementary step to the uFilter method provided us an effective way for finding optimal subsets of features without decreasin...
Source: Artificial Intelligence in Medicine - December 12, 2014 Category: Bioinformatics Source Type: research

A short-term operating room surgery scheduling problem integrating multiple nurses roster constraints
Conclusion The ACO approach proposed in this paper efficiently solves the surgery scheduling problem with daily nurse roster while providing a shortened end time and relatively balanced resource allocations. It also supports the advantage of integrating the surgery scheduling with the nurse scheduling and the efficiency of systematic optimization considering a complete three-stage surgery flow and resources involved. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 12, 2014 Category: Bioinformatics Source Type: research

Brain-controlled applications using dynamic P300 speller matrices
Conclusions In this study we presented a multimedia application and an efficient web browser implemented for control with a BCI. Significance Both applications provide access to important areas of modern information retrieval and entertainment. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 11, 2014 Category: Bioinformatics Source Type: research

Recognizing lexical and semantic change patterns in evolving life science ontologies to inform mapping adaptation
Conclusions The experimental evaluations conducted with real life science ontologies showed the effectiveness of our approach to accurately characterize ontology evolution at the level of concept attributes. This investigation confirmed the relevance of the proposed change patterns to support decisions on mapping adaptation. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - December 7, 2014 Category: Bioinformatics Source Type: research

Transductive domain adaptive learning for epileptic electroencephalogram recognition
Conclusion The proposed transfer-learning-based method has better classification accuracy and adaptability than the conventional methods in classifying EEG signals for epilepsy detection. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

NICeSim: An open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making
Conclusions The significant accuracy demonstrated by our predictive model shows that NICeSim might be used for hypothesis testing to minimize in vivo experiments. We observed that the model delivers predictions that are in very good agreement with the literature, demonstrating that NICeSim might be an important tool for supporting decision making in medical practice. Other very important characteristics of NICeSim are its flexibility and dynamism. NICeSim is flexible because it allows the inclusion and deletion of variables according to the requirements of a particular study. It is also dynamic because it trains a just-in-...
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

From decision to shared-decision: Introducing patients’ preferences into clinical decision analysis
Conclusions This study shows that the tool is potentially able to overcome some of the main barriers perceived by physicians in the adoption of SDM. In parallel, the development of the framework increases the involvement of patients in the process of care focusing on the centrality of individual patients. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Operation room tool handling and miscommunication scenarios: An object-process methodology conceptual model
Conclusion The detailed conceptual model of the tools handling subsystem of the operation performed in an OR focuses on the details of the communication and the interactions taking place between the surgeon and the surgical technician during an operation, with the objective of pinpointing the exact circumstances in which errors can happen. Exact and concise specification of the communication events in general and the surgical instrument requests in particular is a prerequisite for a methodical analysis of the various modes of errors and the circumstances under which they occur. This has significant potential value in both ...
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Non-linear temporal scaling of surgical processes
Conclusions NLTS is an effective and efficient method to find a multiple alignment of a set of surgeries. NLTS realigns a set of sequences along their intrinsic timeline, which makes it possible to extract standards of surgical practices. Supplementary material The computer code implementing the proposed methods. Graphical abstract Highlights (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Intra-axiom redundancies in SNOMED CT
Conclusions Our analysis revealed that redundant elements are continuously introduced and removed, and that redundant elements may be overlooked when concept definitions are corrected. Applying our redundancy detection method to remove intra-axiom redundancies from the stated form of SNOMED CT and to point knowledge modellers to newly introduced redundancies can support creating and maintaining a redundancy-free version of SNOMED CT. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Clinical time series prediction: towards a hierarchical dynamical system framework
Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Approaching the axiomatic enrichment of the Gene Ontology from a lexical perspective
Conclusions We think that our results support the claim that our lexical approach can contribute to the axiomatic enrichment of biomedical ontologies and that it can provide new insights into the engineering of biomedical ontologies. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 18, 2014 Category: Bioinformatics Source Type: research

Channel selection and classification of electroencephalogram signals: An artificial neural network and genetic algorithm-based approach
Conclusions We demonstrate that GNMM is able to perform effective channel selections/reductions, which not only reduces the difficulty of data collection, but also greatly improves the generalization of the classifier. An important step that affects the effectiveness of GNMM is the pre-processing method. In this paper, we also highlight the importance of choosing an appropriate time window position. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 15, 2014 Category: Bioinformatics Source Type: research

Detecting and resolving inconsistencies between domain experts’ different perspectives on (classification) tasks
Conclusion This study has shown that under some circumstances, it is possible for domain experts to achieve a high degree of correlation between 2 perspectives of the same task. The experts agreed that the immediate feedback provided by INSIGHT was a significant contribution to this successful outcome. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 15, 2014 Category: Bioinformatics Source Type: research

Identifying significant edges in graphical models of molecular networks
Conclusion Current studies use structure learning algorithms in conjunction with ad hoc thresholds for identifying significant associations in graphical abstractions of biological pathways and signalling mechanisms. Such an ad hoc choice can have pronounced effect on attributing biological significance to the associations in the resulting network and possible downstream analysis. The statistically motivated approach presented in this study has been shown to outperform ad hoc thresholds and is expected to alleviate spurious conclusions of significant associations in such graphical abstractions. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 15, 2014 Category: Bioinformatics Source Type: research

User-centered design in brain–computer interfaces—A case study
Conclusion The user's performance on the first BCI paradigm would typically have excluded her from further ERP-based BCI studies. However, this study clearly shows that, with the numerous paradigms now at our disposal, the pursuit for a functioning BCI system should not be stopped after an initial failed attempt. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - November 15, 2014 Category: Bioinformatics Source Type: research

Fuzzy logic-based diagnostic algorithm for implantable cardioverter defibrillators
Conclusion The paper presents a fuzzy logic-based control algorithm for ICD. Its main advantages are: simplicity and ability to decrease the rate of occurrence of inappropriate therapies. The algorithm can work in real time (i.e. update the diagnosis after every RR-interval) with very limited computational resources. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - October 12, 2014 Category: Bioinformatics Source Type: research

Improving predictive models of glaucoma severity by incorporating quality indicators
Conclusions Results showed that classification modelling is not negatively affected by the inclusion of less reliable tests in the training process. This means that less reliable tests do not subtract useful information from a model trained using only completely reliable data. Future work will be devoted to exploring new quantitative thresholds to ensure high quality testing and low re-test rates. This could assist doctors in tuning patient follow-up and therapeutic plans, possibly slowing down disease progression. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - October 12, 2014 Category: Bioinformatics Source Type: research

Supervised machine learning-based classification of oral malodor based on the microbiota in saliva samples
Conclusions Using T-RF proportions and frequencies, models to classify the presence of methyl mercaptan, a volatile sulfur-containing compound that causes oral malodor, were developed. SVM classifiers successfully classified the presence of methyl mercaptan with high specificity, and this classification is expected to be useful for screening saliva for oral malodor before visits to specialist clinics. Classification by a SVM and an ANN does not require the identification of the oral microbiota species responsible for the malodor, and the ANN also does not require the proportions of T-RFs. (Source: Artificial Intelligence in Medicine)
Source: Artificial Intelligence in Medicine - October 12, 2014 Category: Bioinformatics Source Type: research