Ontology-based feature engineering in machine learning workflows for heterogeneous epilepsy patient records

Efficient management of pulmonary embolism diagnosis using a two-step interconnected machine learning model based on electronic health records data

Pulmonary Embolism (PE) is a life-threatening clinical disease with no specific clinical symptoms and Computed Tomography Angiography (CTA) is used for diagnosis. Clinical decision support scoring systems like Wells and rGeneva based on PE risk factors have been developed to estimate the pre-test probability but are underused, leading to continuous overuse of CTA imaging. This diagnostic study aimed to propose a novel approach for efficient management of PE diagnosis using a two-step interconnected machine learning framework directly by analyzing patients' Electronic Health Records data. First, we performed feature importance analysis according to the result of LightGBM superiority for PE prediction, then four state-of-the-art machine learning methods were applied for PE prediction based on the feature importance results, enabling swift and accurate pre-test diagnosis. Throughout the study patients' data from different departments were collected from Sina educational hospital, affiliated with the Tehran University of medical sciences in Iran. Generally, the Ridge classification method obtained the best performance with an F1 score of 0.96. Extensive experimental findings showed the effectiveness and simplicity of this diagnostic process of PE in comparison with the existing scoring systems. The main strength of this approach centered on PE disease management procedures, which would reduce avoidable invasive CTA imaging and be applied as a primary prognosis of PE, hence assisting the healthcare system, clinicians, and patients by reducing costs and promoting treatment quality and patient satisfaction.

Early detection of mild cognitive impairment through neuropsychological tests in population screenings: a decision support system integrating ontologies and machine learning

Machine learning (ML) methodologies for detecting Mild Cognitive Impairment (MCI) are progressively gaining prevalence to manage the vast volume of processed information. Nevertheless, the black-box nature of ML algorithms and the heterogeneity within the data may result in varied interpretations across distinct studies. To avoid this, in this proposal, we present the design of a decision support system that integrates a machine learning model represented using the Semantic Web Rule Language (SWRL) in an ontology with specialized knowledge in neuropsychological tests, the NIO ontology. The system's ability to detect MCI subjects was evaluated on a database of 520 neuropsychological assessments conducted in Spanish and compared with other well-established ML methods. Using the F2 coefficient to minimize false negatives, results indicate that the system performs similarly to other well-established ML methods (F2TE2  = 0.830, only below bagging, F2BAG  = 0.832) while exhibiting other significant attributes such as explanation capability and data standardization to a common framework thanks to the ontological part. On the other hand, the system's versatility and ease of use were demonstrated with three additional use cases: evaluation of new cases even if the acquisition stage is incomplete (the case records have missing values), incorporation of a new database into the integrated system, and use of the ontology capabilities to relate different domains. This makes it a useful tool to support physicians and neuropsychologists in population-based screenings for early detection of MCI.

Reconstruction of Eriocheir sinensis Protein-Protein Interaction Network Based on DGO-SVM Method

Eriocheir sinensis is an economically important aquatic animal. Its regulatory mechanisms underlying many biological processes are still vague due to the lack of systematic analysis tools. The protein-protein interaction network (PIN) is an important tool for the systematic analysis of regulatory mechanisms. In this work, a novel machine learning method, DGO-SVM, was applied to predict the protein-protein interaction (PPI) in E. sinensis, and its PIN was reconstructed. With the domain, biological process, molecular functions and subcellular locations of proteins as the features, DGO-SVM showed excellent performance in Bombyx mori, humans and five aquatic crustaceans, with 92-96% accuracy. With DGO-SVM, the PIN of E. sinensis was reconstructed, containing 14,703 proteins and 7,243,597 interactions, in which 35,604 interactions were associated with 566 novel proteins mainly involved in the response to exogenous stimuli, cellular macromolecular metabolism and regulation. The DGO-SVM demonstrated that the biological process, molecular functions and subcellular locations of proteins are significant factors for the precise prediction of PPIs. We reconstructed the largest PIN for E. sinensis, which provides a systematic tool for the regulatory mechanism analysis. Furthermore, the novel-protein-related PPIs in the PIN may provide important clues for the mechanism analysis of the underlying specific physiological processes in E. sinensis.

Dermoscopy Differential Diagnosis Explorer (D3X) Ontology to Aggregate and Link Dermoscopic Patterns to Differential Diagnoses: Development and Usability Study

BACKGROUND

Dermoscopy is a growing field that uses microscopy to allow dermatologists and primary care physicians to identify skin lesions. For a given skin lesion, a wide variety of differential diagnoses exist, which may be challenging for inexperienced users to name and understand.

OBJECTIVE

In this study, we describe the creation of the dermoscopy differential diagnosis explorer (D3X), an ontology linking dermoscopic patterns to differential diagnoses.

METHODS

Existing ontologies that were incorporated into D3X include the elements of visuals ontology and dermoscopy elements of visuals ontology, which connect visual features to dermoscopic patterns. A list of differential diagnoses for each pattern was generated from the literature and in consultation with domain experts. Open-source images were incorporated from DermNet, Dermoscopedia, and open-access research papers.

RESULTS

D3X was encoded in the OWL 2 web ontology language and includes 3041 logical axioms, 1519 classes, 103 object properties, and 20 data properties. We compared D3X with publicly available ontologies in the dermatology domain using a semiotic theory-driven metric to measure the innate qualities of D3X with others. The results indicate that D3X is adequately comparable with other ontologies of the dermatology domain.

CONCLUSIONS

The D3X ontology is a resource that can link and integrate dermoscopic differential diagnoses and supplementary information with existing ontology-based resources. Future directions include developing a web application based on D3X for dermoscopy education and clinical practice.

A machine learning approach to classifying New York Heart Association (NYHA) heart failure

According to the European Society of Cardiology, globally the number of patients with heart failure nearly doubled from 33.5 million in 1990 to 64.3 million in 2017, and is further projected to increase dramatically in this decade, still remaining a leading cause of morbidity and mortality. One of the most frequently applied heart failure classification systems that physicians use is the New York Heart Association (NYHA) Functional Classification. Each NYHA class describes a patient's symptoms while performing physical activities, delivering a strong indicator of the heart performance. In each case, a NYHA class is individually determined routinely based on the subjective assessment of the treating physician. However, such diagnosis can suffer from bias, eventually affecting a valid assessment. To tackle this issue, we take advantage of the machine learning approach to develop a decision-tree, along with a set of decision rules, which can serve as additional blinded investigator tool to make unbiased assessment. On a dataset containing 434 observations, the supervised learning approach was initially employed to train a Decision Tree model. In the subsequent phase, ensemble learning techniques were utilized to develop both the Voting Classifier and the Random Forest model. The performance of all models was assessed using 10-fold cross-validation with stratification.The Decision Tree, Random Forest, and Voting Classifier models reported accuracies of 76.28%, 96.77%, and 99.54% respectively. The Voting Classifier led in classifying NYHA I and III with 98.7% and 100% accuracy. Both Random Forest and Voting Classifier flawlessly classified NYHA II at 100%. However, for NYHA IV, Random Forest achieved a perfect score, while the Voting Classifier reported 90%. The Decision Tree showed the least effectiveness among all the models tested. In our opinion, the results seem satisfactory in terms of their supporting role in clinical practice. In particular, the use of a machine learning tool could reduce or even eliminate the bias in the physician's assessment. In addition, future research should consider testing other variables in different datasets to gain a better understanding of the significant factors affecting heart failure.

Ontology-based decision support systems for diabetes nutrition therapy: A systematic literature review

Diabetes is a non-communicable disease that has reached epidemic proportions, affecting 537 million people globally. Artificial Intelligence can support patients or clinicians in diabetes nutrition therapy - the first medical therapy in most cases of Type 1 and Type 2 diabetes. In particular, ontology-based recommender and decision support systems can deliver a computable representation of experts' knowledge, thus delivering patient-tailored nutritional recommendations or supporting clinical personnel in identifying the most suitable diet. This work proposes a systematic literature review of the domain ontologies describing diabetes in such systems, identifying their underlying conceptualizations, the users targeted by the systems, the type(s) of diabetes tackled, and the nutritional recommendations provided. This review also delves into the structure of the domain ontologies, highlighting several aspects that may hinder (or foster) their adoption in recommender and decision support systems for diabetes nutrition therapy. The results of this review process allow to underline how recommendations are formulated and the role of clinical experts in developing domain ontologies, outlining the research trends characterizing this research area. The results also allow for identifying research directions that can foster a preeminent role for clinical experts and clinical guidelines in a cooperative effort to make ontologies more interoperable - thus enabling them to play a significant role in the decision-making processes about diabetes nutrition therapy.

Cerebral Spinal Fluid Volumetrics and Paralimbic Predictors of Executive Dysfunction in Congenital Heart Disease: A Machine Learning Approach Informing Mechanistic Insights

The relationship between increased cerebral spinal fluid (CSF) ventricular compartments, structural and microstructural dysmaturation, and executive function in patients with congenital heart disease (CHD) is unknown. Here, we leverage a novel machine-learning data-driven technique to delineate interrelationships between CSF ventricular volume, structural and microstructural alterations, clinical risk factors, and sub-domains of executive dysfunction in adolescent CHD patients. We trained random forest regression models to predict measures of executive function (EF) from the NIH Toolbox, the Delis-Kaplan Executive Function System (D-KEFS), and the Behavior Rating Inventory of Executive Function (BRIEF) and across three subdomains of EF - mental flexibility, working memory, and inhibition. We estimated the best parameters for the random forest algorithm via a randomized grid search of parameters using 10-fold cross-validation on the training set only. The best parameters were then used to fit the model on the full training set and validated on the test set. Algorithm performance was measured using root-mean squared-error (RMSE). As predictors, we included patient clinical variables, perioperative clinical measures, microstructural white matter (diffusion tensor imaging- DTI), and structural volumes (volumetric magnetic resonance imaging- MRI). Structural white matter was measured using along-tract diffusivity measures of 13 inter-hemispheric and cortico-association fibers. Structural volumes were measured using FreeSurfer and manual segmentation of key structures. Variable importance was measured by the average Gini-impurity of each feature across all decision trees in which that feature is present in the model, and functional ontology mapping (FOM) was used to measure the degree of overlap in feature importance for each EF subdomain and across subdomains. We found that CSF structural properties (including increased lateral ventricular volume and reduced choroid plexus volumes) in conjunction with proximate cortical projection and paralimbic-related association white matter tracts that straddle the lateral ventricles and distal paralimbic-related subcortical structures (basal ganglia, hippocampus, cerebellum) are predictive of two-specific subdomains of executive dysfunction in CHD patients: cognitive flexibility and inhibition. These findings in conjunction with combined RF models that incorporated clinical risk factors, highlighted important clinical risk factors, including the presence of microbleeds, altered vessel volume, and delayed PDA closure, suggesting that CSF-interstitial fluid clearance, vascular pulsatility, and glymphatic microfluid dynamics may be pathways that are impaired in CHD, providing mechanistic information about the relationship between CSF and executive dysfunction.

Identification of Key Elements in Prostate Cancer for Ontology Building via a Multidisciplinary Consensus Agreement

BACKGROUND

Clinical data collection related to prostate cancer (PCa) care is often unstructured or heterogeneous among providers, resulting in a high risk for ambiguity in its meaning when sharing or analyzing data. Ontologies, which are shareable formal (i.e., computable) representations of knowledge, can address these challenges by enabling machine-readable semantic interoperability. The purpose of this study was to identify PCa-specific key data elements (KDEs) for standardization in clinic and research.

METHODS

A modified Delphi method using iterative online surveys was performed to report a consensus agreement on KDEs by a multidisciplinary panel of 39 PCa specialists. Data elements were divided into three themes in PCa and included (1) treatment-related toxicities (TRT), (2) patient-reported outcome measures (PROM), and (3) disease control metrics (DCM).

RESULTS

The panel reached consensus on a thirty-item, two-tiered list of KDEs focusing mainly on urinary and rectal symptoms. The Expanded Prostate Cancer Index Composite (EPIC-26) questionnaire was considered most robust for PROM multi-domain monitoring, and granular KDEs were defined for DCM.

CONCLUSIONS

This expert consensus on PCa-specific KDEs has served as a foundation for a professional society-endorsed, publicly available operational ontology developed by the American Association of Physicists in Medicine (AAPM) Big Data Sub Committee (BDSC).