Validity of a fast automated 3d spine reconstruction measurements for biplanar radiographs: SOSORT 2024 award winner.

PURPOSE: To validate a fast 3D biplanar spinal radiograph reconstruction method with automatic extract curvature parameters using artificial intelligence (AI). METHODS: Three-hundred eighty paired, posteroanterior and lateral, radiographs from the EOS X-ray system of children with adolescent idiopathic scoliosis were randomly selected from the database. For the AI model development, 304 paired images were used for training; 76 pairs were employed for testing. The validation was evaluated by comparing curvature parameters, including Cobb angles (CA), apical axial vertebral rotation (AVR), kyphotic angle (T1-T12 KA), and lordotic angle (L1-L5 LA), to manual measurements from a rater with 8 years of scoliosis experience. The mean absolute differences ± standard deviation (MAD ± SD), the percentage of measurements within the clinically acceptable errors, the standard error of measurement (SEM), and the inter-method intraclass correlation coefficient ICC[2,1] were calculated. The average reconstruction speed of the 76 test images was recorded. RESULTS: Among the 76 test images, 134 and 128 CA were exported automatically and measured manually, respectively. The MAD ± SD for CA, AVR at apex, KA, and LA were 3.3° ± 3.5°, 1.5° ± 1.5°, 3.3° ± 2.6° and 3.5° ± 2.5°, respectively, and 98% of these measurements were within the clinical acceptance errors. The SEMs and the ICC[2,1] for the compared parameters were all less than 0.7° and > 0.94, respectively. The average time to display the 3D spine and report the measurements was 5.2 ± 1.3 s. CONCLUSION: The developed AI algorithm could reconstruct a 3D scoliotic spine within 6 s, and the automatic curvature parameters were accurately and reliably extracted from the reconstructed images.

Validity and accuracy of automatic cobb angle measurement on 3D spinal ultrasonographs for children with adolescent idiopathic scoliosis: SOSORT 2024 award winner.

PURPOSE: Ultrasonography for scoliosis is a novel imaging method that does not expose children with adolescent idiopathic scoliosis (AIS) to radiation. A single ultrasound scan provides 3D spinal views directly. However, measuring ultrasonograph parameters is challenging, time-consuming, and requires considerable training. This study aimed to validate a machine learning method to measure the coronal curve angle on ultrasonographs automatically. METHODS: A total of 144 3D spinal ultrasonographs were extracted to train and validate a machine learning model. Among the 144 images, 70 were used for training, and 74 consisted of 144 curves for testing. Automatic coronal curve angle measurements were validated by comparing them with manual measurements performed by an experienced rater. The inter-method intraclass correlation coefficient (ICC2,1), standard error of measurement (SEM), and percentage of measurements within clinical acceptance (≤ 5°) were analyzed. RESULTS: The automatic method detected 125/144 manually measured curves. The averages of the 125 manual and automatic coronal curve angle measurements were 22.4 ± 8.0° and 22.9 ± 8.7°, respectively. Good reliability was achieved with ICC2,1 = 0.81 and SEM = 1.4°. A total of 75% (94/125) of the measurements were within clinical acceptance. The average measurement time per ultrasonograph was 36 ± 7 s. Additionally, the algorithm displayed the predicted centers of laminae to illustrate the measurement. CONCLUSION: The automatic algorithm measured the coronal curve angle with moderate accuracy but good reliability. The algorithm's quick measurement time and interpretability can make ultrasound a more accessible imaging method for children with AIS. However, further improvements are needed to bring the method to clinical use.

Developing a Chatbot to Support Individuals With Neurodevelopmental Disorders: Tutorial.

Families of individuals with neurodevelopmental disabilities or differences (NDDs) often struggle to find reliable health information on the web. NDDs encompass various conditions affecting up to 14% of children in high-income countries, and most individuals present with complex phenotypes and related conditions. It is challenging for their families to develop literacy solely by searching information on the internet. While in-person coaching can enhance care, it is only available to a minority of those with NDDs. Chatbots, or computer programs that simulate conversation, have emerged in the commercial sector as useful tools for answering questions, but their use in health care remains limited. To address this challenge, the researchers developed a chatbot named CAMI (Coaching Assistant for Medical/Health Information) that can provide information about trusted resources covering core knowledge and services relevant to families of individuals with NDDs. The chatbot was developed, in collaboration with individuals with lived experience, to provide information about trusted resources covering core knowledge and services that may be of interest. The developers used the Django framework (Django Software Foundation) for the development and used a knowledge graph to depict the key entities in NDDs and their relationships to allow the chatbot to suggest web resources that may be related to the user queries. To identify NDD domain-specific entities from user input, a combination of standard sources (the Unified Medical Language System) and other entities were used which were identified by health professionals as well as collaborators. Although most entities were identified in the text, some were not captured in the system and therefore went undetected. Nonetheless, the chatbot was able to provide resources addressing most user queries related to NDDs. The researchers found that enriching the vocabulary with synonyms and lay language terms for specific subdomains enhanced entity detection. By using a data set of numerous individuals with NDDs, the researchers developed a knowledge graph that established meaningful connections between entities, allowing the chatbot to present related symptoms, diagnoses, and resources. To the researchers' knowledge, CAMI is the first chatbot to provide resources related to NDDs. Our work highlighted the importance of engaging end users to supplement standard generic ontologies to named entities for language recognition. It also demonstrates that complex medical and health-related information can be integrated using knowledge graphs and leveraging existing large datasets. This has multiple implications: generalizability to other health domains as well as reducing the need for experts and optimizing their input while keeping health care professionals in the loop. The researchers' work also shows how health and computer science domains need to collaborate to achieve the granularity needed to make chatbots truly useful and impactful.

Leveraging Knowledge Graphs and Natural Language Processing for Automated Web Resource Labeling and Knowledge Mobilization in Neurodevelopmental Disorders: Development and Usability Study.

BACKGROUND: Patients and families need to be provided with trusted information more than ever with the abundance of online information. Several organizations aim to build databases that can be searched based on the needs of target groups. One such group is individuals with neurodevelopmental disorders (NDDs) and their families. NDDs affect up to 18% of the population and have major social and economic impacts. The current limitations in communicating information for individuals with NDDs include the absence of shared terminology and the lack of efficient labeling processes for web resources. Because of these limitations, health professionals, support groups, and families are unable to share, combine, and access resources. OBJECTIVE: We aimed to develop a natural language-based pipeline to label resources by leveraging standard and free-text vocabularies obtained through text analysis, and then represent those resources as a weighted knowledge graph. METHODS: Using a combination of experts and service/organization databases, we created a data set of web resources for NDDs. Text from these websites was scraped and collected into a corpus of textual data on NDDs. This corpus was used to construct a knowledge graph suitable for use by both experts and nonexperts. Named entity recognition, topic modeling, document classification, and location detection were used to extract knowledge from the corpus. RESULTS: We developed a resource annotation pipeline using diverse natural language processing algorithms to annotate web resources and stored them in a structured knowledge graph. The graph contained 78,181 annotations obtained from the combination of standard terminologies and a free-text vocabulary obtained using topic modeling. An application of the constructed knowledge graph is a resource search interface using the ordered weighted averaging operator to rank resources based on a user query. CONCLUSIONS: We developed an automated labeling pipeline for web resources on NDDs. This work showcases how artificial intelligence-based methods, such as natural language processing and knowledge graphs for information representation, can enhance knowledge extraction and mobilization, and could be used in other fields of medicine.

Deciphering the Diversity of Mental Models in Neurodevelopmental Disorders: Knowledge Graph Representation of Public Data Using Natural Language Processing.

BACKGROUND: Understanding how individuals think about a topic, known as the mental model, can significantly improve communication, especially in the medical domain where emotions and implications are high. Neurodevelopmental disorders (NDDs) represent a group of diagnoses, affecting up to 18% of the global population, involving differences in the development of cognitive or social functions. In this study, we focus on 2 NDDs, attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD), which involve multiple symptoms and interventions requiring interactions between 2 important stakeholders: parents and health professionals. There is a gap in our understanding of differences between mental models for each stakeholder, making communication between stakeholders more difficult than it could be. OBJECTIVE: We aim to build knowledge graphs (KGs) from web-based information relevant to each stakeholder as proxies of mental models. These KGs will accelerate the identification of shared and divergent concerns between stakeholders. The developed KGs can help improve knowledge mobilization, communication, and care for individuals with ADHD and ASD. METHODS: We created 2 data sets by collecting the posts from web-based forums and PubMed abstracts related to ADHD and ASD. We utilized the Unified Medical Language System (UMLS) to detect biomedical concepts and applied Positive Pointwise Mutual Information followed by truncated Singular Value Decomposition to obtain corpus-based concept embeddings for each data set. Each data set is represented as a KG using a property graph model. Semantic relatedness between concepts is calculated to rank the relation strength of concepts and stored in the KG as relation weights. UMLS disorder-relevant semantic types are used to provide additional categorical information about each concept's domain. RESULTS: The developed KGs contain concepts from both data sets, with node sizes representing the co-occurrence frequency of concepts and edge sizes representing relevance between concepts. ADHD- and ASD-related concepts from different semantic types shows diverse areas of concerns and complex needs of the conditions. KG identifies converging and diverging concepts between health professionals literature (PubMed) and parental concerns (web-based forums), which may correspond to the differences between mental models for each stakeholder. CONCLUSIONS: We show for the first time that generating KGs from web-based data can capture the complex needs of families dealing with ADHD or ASD. Moreover, we showed points of convergence between families and health professionals' KGs. Natural language processing-based KG provides access to a large sample size, which is often a limiting factor for traditional in-person mental model mapping. Our work offers a high throughput access to mental model maps, which could be used for further in-person validation, knowledge mobilization projects, and basis for communication about potential blind spots from stakeholders in interactions about NDDs. Future research will be needed to identify how concepts could interact together differently for each stakeholder.

Applying Machine Learning and Point-Set Registration to Automatically Measure the Severity of Spinal Curvature on Radiographs.

OBJECTIVE: Measuring the severity of the lateral spinal curvature, or Cobb angle, is critical for monitoring and making treatment decisions for children with adolescent idiopathic scoliosis (AIS). However, manual measurement is time-consuming and subject to human error. Therefore, clinicians seek an automated measurement method to streamline workflow and improve accuracy. This paper reports on a novel machine learning algorithm of cascaded convolutional neural networks (CNN) to measure the Cobb angle on spinal radiographs automatically. METHODS: The developed method consisted of spinal column segmentation using a CNN, vertebra localization and segmentation using iterative vertebra body location coupled with another CNN, point-set registration to correct vertebra segmentations, and Cobb angle measurement using the final segmentations. Measurement performance was evaluated with the circular mean absolute error (CMAE) and percentage within clinical acceptance ([Formula: see text]) between automatic and manual measurements. Analysis was separated by curve severity to identify any potential systematic biases using independent samples Student's t-tests. RESULTS: The method detected 346 of the 352 manually measured Cobb angles (98%), with a CMAE of 2.8° and 91% of measurements within the 5° clinical acceptance. No statistically significant differences were found between the CMAEs of mild ([Formula: see text]), moderate (25°-45°), and severe ([Formula: see text]) groups. The average measurement time per radiograph was 17.7±10.2s, improving upon the estimated average of 30s it takes an experienced rater to measure. Additionally, the algorithm outputs segmentations with the measurement, allowing clinicians to interpret measurement results. DISCUSSION/CONCLUSION: The developed method measured Cobb angles on radiographs automatically with high accuracy, quick measurement time, and interpretability, suggesting clinical feasibility.

Using machine learning to automatically measure kyphotic and lordotic angle measurements on radiographs for children with adolescent idiopathic scoliosis.

Measuring the kyphotic angle (KA) and lordotic angle (LA) on lateral radiographs is important to truly diagnose children with adolescent idiopathic scoliosis. However, it is a time-consuming process to measure the KA because the endplate of the upper thoracic vertebra is normally difficult to identify. To save time and improve measurement accuracy, a machine learning algorithm was developed to automatically extract the KA and LA. The accuracy and reliability of the T1-T12 KA, T5-T12 KA, and L1-L5 LA were reported. A convolutional neural network was trained using 100 radiographs with data augmentation to segment the T1-L5 vertebrae. Sixty radiographs were used to test the method. Accuracy and reliability were reported using the percentage of measurements within clinical acceptance (≤9°), standard error of measurement (SEM), and inter-method intraclass correlation coefficient (ICC2,1). The automatic method detected 95 % (57/60), 100 %, and 100 % for T1-T12 KA, T5-T12 KA, and L1-L5 LA, respectively. The clinical acceptance rate, SEM, and ICC2,1 for T1-T12 KA, T5-T12 KA, and L1-L5 LA were (98 %, 0.80°, 0.91), (75 %, 4.08°, 0.60), and (97 %, 1.38°, 0.88), respectively. The automatic method measured quickly with an average of 4 ± 2 s per radiograph and illustrated how measurements were made on the image, allowing verifications by clinicians.

Automated Method for Growing Rod Length Measurement on Ultrasound Images in Children With Early Onset Scoliosis.

OBJECTIVE: To develop and validate machine learning algorithms to automatically extract the rod length of the magnetically controlled growing rod from ultrasound images (US) in a pilot study. METHODS: Two machine-learning (ML) models, called the "Boundary model" and "Rod model," were developed to identify specific rod segments on ultrasound images. The models were developed utilizing Mask Regional Convolutional Neural Networks (Mask RCNN). Ninety US images were acquired from 23 participants who had early onset scoliosis (EOS) surgeries; among those, 70 were used for model development, including training and validation, and 20 were used for testing by comparing the AI-based vs. manual measurements. RESULTS: The average precision (AP) of the ML models was 88.5% and 60.2%, respectively. The inter-method correlation coefficient (ICC) was 0.98, and the mean absolute difference ± standard deviation (MAD ± SD) between AI and manual measurements was 0.86 ± 1.0 mm. The Bland-Altman analysis showed no bias, and 90% of the data were within the 95% confidence interval. The automated method was reliable, accurate, and fast. Measurements were displayed in 4.6 seconds after the US image was inputted. CONCLUSION: This was the first AI-based method to measure the MCGR rod length on US images automatically.

Validity of machine learning algorithms for automatically extract growing rod length on radiographs in children with early-onset scoliosis.

The magnetically controlled growing rod technique is an effective surgical treatment for children who have early-onset scoliosis. The length of the instrumented growing rods is adjusted regularly to compensate for the normal growth of these patients. Manual measurement of rod length on posteroanterior spine radiographs is subjective and time-consuming. A machine learning (ML) system using a deep learning approach was developed to automatically measure the adjusted rod length. Three ML models-rod model, 58 mm model, and head-piece model-were developed to extract the rod length from radiographs. Three-hundred and eighty-seven radiographs were used for model development, and 60 radiographs with 118 rods were separated for final testing. The average precision (AP), the mean absolute difference (MAD) ± standard deviation (SD), and the inter-method correlation coefficient (ICC[2,1]) between the manual and artificial intelligence (AI) adjustment measurements were used to evaluate the developed method. The AP of the 3 models were 67.6%, 94.8%, and 86.3%, respectively. The MAD ± SD of the rod length change was 0.98 ± 0.88 mm, and the ICC[2,1] was 0.90. The average time to output a single rod measurement was 6.1 s. The developed AI provided an accurate and reliable method to detect the rod length automatically.

Human intelligence-based metaverse for co-learning of students and smart machines.

This paper proposes a Human Intelligence (HI)-based Computational Intelligence (CI) and Artificial Intelligence (AI) Fuzzy Markup Language (CI&AI-FML) Metaverse as an educational environment for co-learning of students and machines. The HI-based CI&AI-FML Metaverse is based on the spirit of the Heart Sutra that equips the environment with teaching principles and cognitive intelligence of ancient words of wisdom. There are four stages of the Metaverse: preparation and collection of learning data, data preprocessing, data analysis, and data evaluation. During the data preparation stage, the domain experts construct a learning dictionary with fuzzy concept sets describing different terms and concepts related to the course domains. Then, the students and teachers use the developed CI&AI-FML learning tools to interact with machines and learn together. Once the teachers prepare relevant material, students provide their inputs/texts representing their levels of understanding of the learned concepts. A Natural Language Processing (NLP) tool, Chinese Knowledge Information Processing (CKIP), is used to process data/text generated by students. A focus is put on speech tagging, word sense disambiguation, and named entity recognition. Following that, the quantitative and qualitative data analysis is performed. Finally, the students' learning progress, measured using progress metrics, is evaluated and analyzed. The experimental results reveal that the proposed HI-based CI&AI-FML Metaverse can foster students' motivation to learn and improve their performance. It has been shown in the case of young students studying Software Engineering and learning English.

Validation of an artificial intelligence-based method to automate Cobb angle measurement on spinal radiographs of children with adolescent idiopathic scoliosis.

BACKGROUND: Accurately measuring the Cobb angle on radiographs is crucial for diagnosis and treatment decisions for adolescent idiopathic scoliosis (AIS). However, manual Cobb angle measurement is time-consuming and subject to measurement variation, especially for inexperienced clinicians. AIM: This study aimed to validate a novel artificial-intelligence-based (AI) algorithm that automatically measures the Cobb angle on radiographs. DESIGN: This is a retrospective cross-sectional study. SETTING: The population of patients attended the Stollery Children's Hospital in Alberta, Canada. POPULATION: Children who: 1) were diagnosed with AIS, 2) were aged between 10 and 18 years old, 3) had no prior surgery, and 4) had a radiograph out of brace, were enrolled. METHODS: A total of 330 spinal radiographs were used. Among those, 130 were used for AI model development and 200 were used for measurement validation. Automatic Cobb angle measurements were validated by comparing them with manual ones measured by a rater with 20+ years of experience. Analysis was performed using the standard error of measurement (SEM), inter-method intraclass correlation coefficient (ICC2,1), and percentage of measurements within clinical acceptance (≤5°). Subgroup analysis was conducted by severity, region, and X-ray system to identify any systematic biases. RESULTS: The AI method detected 346 of 352 manually measured curves (mean±standard deviation: 24.7±9.5°), achieving 91% (316/346) of measurements within clinical acceptance. Excellent reliability was obtained with 0.92 ICC and 0.79° SEM. Comparable performance was found throughout all subgroups, and no systematic biases in performance affecting any subgroup were discovered. The algorithm measured each radiograph approximately 18s on average which is slightly faster than the estimated measurement time of an experienced rater. Radiographs taken by the EOS X-ray system were measured more quickly on average than those taken by a conventional digital X-ray system (10s vs. 26s). CONCLUSIONS: An AI-based algorithm was developed to measure the Cobb angle automatically on radiographs and yielded reliable measurements quickly. The algorithm provides detailed images on how the angles were measured, providing interpretability that can give clinicians confidence in the measurements. CLINICAL REHABILITATION IMPACT: Employing the algorithm in practice could streamline clinical workflow and optimize measurement accuracy and speed in order to inform AIS treatment decisions.

Developing a cluster-based approach for deciphering complexity in individuals with neurodevelopmental differences.

Objective: Individuals with neurodevelopmental disorders such as global developmental delay (GDD) present both genotypic and phenotypic heterogeneity. This diversity has hampered developing of targeted interventions given the relative rarity of each individual genetic etiology. Novel approaches to clinical trials where distinct, but related diseases can be treated by a common drug, known as basket trials, which have shown benefits in oncology but have yet to be used in GDD. Nonetheless, it remains unclear how individuals with GDD could be clustered. Here, we assess two different approaches: agglomerative and divisive clustering. Methods: Using the largest cohort of individuals with GDD, which is the Deciphering Developmental Disorders (DDD), characterized using a systematic approach, we extracted genotypic and phenotypic information from 6,588 individuals with GDD. We then used a k-means clustering (divisive) and hierarchical agglomerative clustering (HAC) to identify subgroups of individuals. Next, we extracted gene network and molecular function information with regard to the clusters identified by each approach. Results: HAC based on phenotypes identified in individuals with GDD revealed 16 clusters, each presenting with one dominant phenotype displayed by most individuals in the cluster, along with other minor phenotypes. Among the most common phenotypes reported were delayed speech, absent speech, and seizure. Interestingly, each phenotypic cluster molecularly included several (3-12) gene sub-networks of more closely related genes with diverse molecular function. k-means clustering also segregated individuals harboring those phenotypes, but the genetic pathways identified were different from the ones identified from HAC. Conclusion: Our study illustrates how divisive (k-means) and agglomerative clustering can be used in order to group individuals with GDD for future basket trials. Moreover, the result of our analysis suggests that phenotypic clusters should be subdivided into molecular sub-networks for an increased likelihood of successful treatment. Finally, a combination of both agglomerative and divisive clustering may be required for developing of a comprehensive treatment.

Using machine learning to automatically measure axial vertebral rotation on radiographs in adolescents with idiopathic scoliosis.

Adolescent idiopathic scoliosis is a 3D lateral spinal curvature coupled with axial vertebral rotation (AVR). Measuring AVR during clinic is important because it affects treatment options and predicts the risk of scoliosis progression. However, manual measurements are time consuming and have high inter-rater and intra-rater errors. This study aimed to develop a machine learning algorithm based on convolutional neural networks (CNNs) to automatically calculate AVR on posteroanterior radiographs using three different segmentations including spinal column, individual vertebra, and pedicles. Separate labeling and training processes were performed on each of the developed segmentation algorithms. The final machine learning software was tested on 221 vertebrae from 17 spinal radiographs. An experienced rater with over 25 years of experience measured the 221 vertebral rotations manually. By comparing the manual and the fully automatic measurements, 81% (178/221) of the automatic measurements were within the clinical acceptance error (±5°). The mean absolute difference and the standard deviation between the manual and automatic measurements was 4.3° ± 5.7°. Based on the Bland-Altman plot, the manual and automatic measurements had a strong correlation and no bias. The error did not relate to the severity of the rotation. This method is fully automatic, and the result is comparable to others.

Convolutional Neural Network to Segment Laminae on 3D Ultrasound Spinal Images to Assist Cobb Angle Measurement.

A recent innovation in scoliosis monitoring is the use of ultrasonography, which provides true 3D information in one scan and does not emit ionizing radiation. Measuring the severity of scoliosis on ultrasonographs requires identifying lamina pairs on the most tilted vertebrae, which is difficult and time-consuming. To expedite and automate measurement steps, this paper detailed an automatic convolutional neural network-based algorithm for identifying the laminae on 3D ultrasonographs. The predicted laminae were manually paired to measure the lateral spinal curvature on the coronal view, called the Cobb angle. In total, 130 spinal ultrasonographs of adolescents with idiopathic scoliosis recruited from a scoliosis clinic were selected, with 70 for training and 60 for testing. Data augmentation increased the effective training set size to 140 ultrasonographs. Semi-automatic Cobb measurements were compared to manual measurements on the same ultrasonographs. The semi-automatic measurements demonstrated good inter-method reliability (ICC3,1 = 0.87) and performed better on thoracic (ICC3,1 = 0.91) than lumbar curves (ICC3,1 = 0.81). The mean absolute difference and standard deviation between semi-automatic and manual was 3.6° ± 3.0°. In conclusion, the semi-automatic method to measure the Cobb angle on ultrasonographs is feasible and accurate. This is the first algorithm that automates steps of Cobb angle measurement on ultrasonographs.

Centroid-based Distance Loss Function for Lamina Segmentation in 3D Ultrasound Spine Volumes.

Ultrasound imaging of the spine to diagnose the severity of scoliosis is a recent development in the field, offering 3D information that does not require a complicated procedure of reconstruction, unlike with radiography. Determining the severity of scoliosis on ultrasound volumes requires labelling vertebral features called laminae. To increase accuracy and reduce time spent on this task, this paper reported a novel custom centroid-based distance loss function for lamina segmentation in 3D ultrasound volumes, using convolutional neural networks (CNN). A comparison between the custom and two standard loss functions was performed by fitting a CNN with each loss function. The results showed that the custom loss network performed the best in terms of minimization of the distances between the centroids in the ground truth and the centroids in the predicted segmentation. On average, the custom network improved on the total distance between predicted and true centroids by 33 voxels (22%) when compared with the second best performing network, which used the Dice loss. In general, this novel custom loss function allowed the network to detect two more laminae on average in the lumbar region of the spine that the other networks tended to miss.

Multilabel associative classification categorization of MEDLINE articles into MeSH keywords.

The specific characteristic of classification of medical documents from the MEDLINE database is that each document is assigned to more than one category, which requires a system for multilabel classification. Another major challenge was to develop a scalable method capable of dealing with hundreds of thousand of documents. We proposed a novel system for automated classification of MEDLINE documents to MeSH keywords based on the recently developed data mining algorithm called ACRI, which was modified to accommodate multilabel classification. Five different classification configurations in conjunction with different methods of measuring classification quality were proposed and tested. The extensive experimental comparison showed superiority of methods based on reoccurrence of words in an article over nonrecurrent-based associative classification. The achieved relatively high value of macro F1 (46%) demonstrates the high quality of the proposed system for this challenging dataset. Accuracy of the proposed classifier, defined as the ratio of the sum of TP and TN examples to the total number of examples, reached 90%. Three scenarios were proposed based on the performed tests and different possible objectives. If a goal is to classify the largest number of documents, a configuration that maximizes micro F1 should be chosen. On the other hand, if a system is to work well for categories with a small number of documents, a configuration that maximizes macro F1 is more suitable. A tradeoff can be obtained by using a configuration that optimizes the average between macro and micro F1.

OR/AND neurons and the development of interpretable logic models.

In this paper, we are concerned with the concept of fuzzy logic networks and logic-based data analysis realized within this framework. The networks under discussion are homogeneous architectures comprising of OR/AND neurons originally introduced by Hirota and Pedrycz. Being treated here as generic processing units, OR/AND neurons are neurofuzzy constructs that exhibit well-defined logic characteristics and are endowed with a high level of parametric flexibility and come with significant interpretation abilities. The composite logic nature of the logic neurons becomes instrumental in covering a broad spectrum of logic dependencies whose character spread in-between between those being captured by plain and and or logic descriptors (connectives). From the functional standpoint, the developed network realizes a logic approximation of multidimensional mappings between unit hypercubes, that is transformations from [0, 1]n to [0, 1]m. The way in which the structure of the network has been formed is highly modular and becomes reflective of a general concept of decomposition of logic expressions and Boolean functions (as being commonly encountered in two-valued logic). In essence, given a collection of input variables, selected is their subset and transformed into new composite variable, which in turn is used in the consecutive module of the network. These intermediate synthetic variables are the result of the successive problem (mapping) decomposition. The development of the network is realized through genetic optimization. This helps address important issues of structural optimization (where we are concerned with a selection of a subset of variables and their allocation within the network) and reaching a global minimum when carrying out an extensive parametric optimization (adjustments of the connections of the neurons). The paper offers a comprehensive and user-interactive design procedure including a simple pruning mechanism whose intention is to enhance the interpretability of the network while reducing its size. The experimental studies comprise of three parts. First, we demonstrate the performance of the network on Boolean data (that leads to some useful comparative observations considering a wealth of optimization tools available in two-valued logic and digital systems). Second, we discuss synthetic multivalued data that helps focus on the approximation abilities of the network. Finally, show the generation of logic expressions describing selected data sets coming from the machine learning repository.

xGENIA: A comprehensive OWL ontology based on the GENIA corpus.

UNLABELLED: The GENIA ontology is a taxonomy that was developed as a result of manual annotation of a subset of MEDLINE, the GENIA corpus. Both the ontology and corpus have been used as a benchmark to test and develop biological information extraction tools. Recent work shows, however, that there is a demand for a more comprehensive ontology that would go along with the corpus. We propose a complete OWL ontology built on top of the GENIA ontology utilizing the GENIA corpus. The proposed ontology includes elements such as the original taxonomy of categories, biological entities as individuals, relations between individuals using verbs and verb nominalizations as object properties, and links to the UMLS Metathesaurus concepts. AVAILABILITY: http://www.ece.ualberta.ca/~rrak/ontology/xGENIA/