Boosting predictive models and augmenting patient data with relevant genomic and pathway information.

The recurrence of low-stage lung cancer poses a challenge due to its unpredictable nature and diverse patient responses to treatments. Personalized care and patient outcomes heavily rely on early relapse identification, yet current predictive models, despite their potential, lack comprehensive genetic data. This inadequacy fuels our research focus-integrating specific genetic information, such as pathway scores, into clinical data. Our aim is to refine machine learning models for more precise relapse prediction in early-stage non-small cell lung cancer. To address the scarcity of genetic data, we employ imputation techniques, leveraging publicly available datasets such as The Cancer Genome Atlas (TCGA), integrating pathway scores into our patient cohort from the Cancer Long Survivor Artificial Intelligence Follow-up (CLARIFY) project. Through the integration of imputed pathway scores from the TCGA dataset with clinical data, our approach achieves notable strides in predicting relapse among a held-out test set of 200 patients. By training machine learning models on enriched knowledge graph data, inclusive of triples derived from pathway score imputation, we achieve a promising precision of 82% and specificity of 91%. These outcomes highlight the potential of our models as supplementary tools within tumour, node, and metastasis (TNM) classification systems, offering improved prognostic capabilities for lung cancer patients. In summary, our research underscores the significance of refining machine learning models for relapse prediction in early-stage non-small cell lung cancer. Our approach, centered on imputing pathway scores and integrating them with clinical data, not only enhances predictive performance but also demonstrates the promising role of machine learning in anticipating relapse and ultimately elevating patient outcomes.

Machine Learning-Assisted Recurrence Prediction for Patients With Early-Stage Non-Small-Cell Lung Cancer.

PURPOSE: Stratifying patients with cancer according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to use machine learning to estimate probability of relapse in patients with early-stage non-small-cell lung cancer (NSCLC)? MATERIALS AND METHODS: For predicting relapse in 1,387 patients with early-stage (I-II) NSCLC from the Spanish Lung Cancer Group data (average age 65.7 years, female 24.8%, male 75.2%), we train tabular and graph machine learning models. We generate automatic explanations for the predictions of such models. For models trained on tabular data, we adopt SHapley Additive exPlanations local explanations to gauge how each patient feature contributes to the predicted outcome. We explain graph machine learning predictions with an example-based method that highlights influential past patients. RESULTS: Machine learning models trained on tabular data exhibit a 76% accuracy for the random forest model at predicting relapse evaluated with a 10-fold cross-validation (the model was trained 10 times with different independent sets of patients in test, train, and validation sets, and the reported metrics are averaged over these 10 test sets). Graph machine learning reaches 68% accuracy over a held-out test set of 200 patients, calibrated on a held-out set of 100 patients. CONCLUSION: Our results show that machine learning models trained on tabular and graph data can enable objective, personalized, and reproducible prediction of relapse and, therefore, disease outcome in patients with early-stage NSCLC. With further prospective and multisite validation, and additional radiological and molecular data, this prognostic model could potentially serve as a predictive decision support tool for deciding the use of adjuvant treatments in early-stage lung cancer.

Synergy between imputed genetic pathway and clinical information for predicting recurrence in early stage non-small cell lung cancer.

OBJECTIVE: Lung cancer exhibits unpredictable recurrence in low-stage tumors and variable responses to different therapeutic interventions. Predicting relapse in early-stage lung cancer can facilitate precision medicine and improve patient survivability. While existing machine learning models rely on clinical data, incorporating genomic information could enhance their efficiency. This study aims to impute and integrate specific types of genomic data with clinical data to improve the accuracy of machine learning models for predicting relapse in early-stage, non-small cell lung cancer patients. METHODS: The study utilized a publicly available TCGA lung cancer cohort and imputed genetic pathway scores into the Spanish Lung Cancer Group (SLCG) data, specifically in 1348 early-stage patients. Initially, tumor recurrence was predicted without imputed pathway scores. Subsequently, the SLCG data were augmented with pathway scores imputed from TCGA. The integrative approach aimed to enhance relapse risk prediction performance. RESULTS: The integrative approach achieved improved relapse risk prediction with the following evaluation metrics: an area under the precision-recall curve (PR-AUC) score of 0.75, an area under the ROC (ROC-AUC) score of 0.80, an F1 score of 0.61, and a Precision of 0.80. The prediction explanation model SHAP (SHapley Additive exPlanations) was employed to explain the machine learning model's predictions. CONCLUSION: We conclude that our explainable predictive model is a promising tool for oncologists that addresses an unmet clinical need of post-treatment patient stratification based on the relapse risk while also improving the predictive power by incorporating proxy genomic data not available for specific patients.

Extraction, Labeling, Clustering, and Semantic Mapping of Segments From Clinical Notes.

This work is motivated by the scarcity of tools for accurate, unsupervised information extraction from unstructured clinical notes in computationally underrepresented languages, such as Czech. We introduce a stepping stone to a broad array of downstream tasks such as summarisation or integration of individual patient records, extraction of structured information for national cancer registry reporting or building of semi-structured semantic patient representations that can be used for computing patient embeddings. More specifically, we present a method for unsupervised extraction of semantically-labeled textual segments from clinical notes and test it out on a dataset of Czech breast cancer patients, provided by Masaryk Memorial Cancer Institute (the largest Czech hospital specialising exclusively in oncology). Our goal was to extract, classify (i.e. label) and cluster segments of the free-text notes that correspond to specific clinical features (e.g., family background, comorbidities or toxicities). Finally, we propose a tool for computer-assisted semantic mapping of segment types to pre-defined ontologies and validate it on a downstream task of category-specific patient similarity. The presented results demonstrate the practical relevance of the proposed approach for building more sophisticated extraction and analytical pipelines deployed on Czech clinical notes.

Performance Level and Strike Type during Ground and Pound Determine Impact Characteristics and Net Force Variability.

The evaluation of strike impact is important for optimal training, conditioning and tactical use. Therefore, the aim of this study was to evaluate ground and pound strikes, in terms of net force variability, across genders and performance levels. Eighty-one participants, professional men (n = 8, 37 ± 6 years, 195 ± 7 cm, 113 ± 27 kg), advanced men (n = 47, 26 ± 8 years, 180 ± 7 cm, 76 ± 11 kg), and advanced women (n = 26, 21 ± 1 years, 167 ± 6 cm, 61 ± 7 kg) performed three strikes from a kneeling position into a force plate on the ground. The elbow strike resulted in the highest impulse and the palm strike in the highest peak force for all three categories. These results support the recommendation that has previously been made to teach the palm strike to beginners and advanced tactical and combat athletes. The direct punch and elbow strike net force were characterized by a double peak curve, where the first peak variability explained 70.2-84% of the net force. The second peak was pronounced in professional men during elbow strikes, which explained 16% of net force variability. The strike type determines the impact net force and its characteristics, where palm strike is typical by highest peak impact tolerance and elbow strike by double force peak with high net force impulse.

Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding.

The scarcity of high-quality annotations in many application scenarios has recently led to an increasing interest in devising learning techniques that combine unlabeled data with labeled data in a network. In this work, we focus on the label propagation problem in multilayer networks. Our approach is inspired by the heat diffusion model, which shows usefulness in machine learning problems such as classification and dimensionality reduction. We propose a novel boundary-based heat diffusion algorithm that guarantees a closed-form solution with an efficient implementation. We experimentally validated our method on synthetic networks and five real-world multilayer network datasets representing scientific coauthorship, spreading drug adoption among physicians, two bibliographic networks, and a movie network. The results demonstrate the benefits of the proposed algorithm, where our boundary-based heat diffusion dominates the performance of the state-of-the-art methods.

An Artificial Intelligence-Based Tool for Data Analysis and Prognosis in Cancer Patients: Results from the Clarify Study.

BACKGROUND: Artificial intelligence (AI) has contributed substantially in recent years to the resolution of different biomedical problems, including cancer. However, AI tools with significant and widespread impact in oncology remain scarce. The goal of this study is to present an AI-based solution tool for cancer patients data analysis that assists clinicians in identifying the clinical factors associated with poor prognosis, relapse and survival, and to develop a prognostic model that stratifies patients by risk. MATERIALS AND METHODS: We used clinical data from 5275 patients diagnosed with non-small cell lung cancer, breast cancer, and non-Hodgkin lymphoma at Hospital Universitario Puerta de Hierro-Majadahonda. Accessible clinical parameters measured with a wearable device and quality of life questionnaires data were also collected. RESULTS: Using an AI-tool, data from 5275 cancer patients were analyzed, integrating clinical data, questionnaires data, and data collected from wearable devices. Descriptive analyses were performed in order to explore the patients' characteristics, survival probabilities were calculated, and a prognostic model identified low and high-risk profile patients. CONCLUSION: Overall, the reconstruction of the population's risk profile for the cancer-specific predictive model was achieved and proved useful in clinical practice using artificial intelligence. It has potential application in clinical settings to improve risk stratification, early detection, and surveillance management of cancer patients.

Analysis of the Contact Area for Three Types of Upper Limb Strikes.

Performance in strike combat sports is mostly evaluated through the values of the net force, acceleration, or speed to improve efficient training procedures and/or to assess the injury. There are limited data on the upper limb striking area, which can be a useful variable for contact pressure assessment. Therefore, the aim of this study was to determine the contact area of the upper limb in three different strike technique positions. A total of 38 men and 38 women (n = 76, 27.3 ± 8.5 years of age, 73.9 ± 13.8 kg of body weight, 173.3 ± 8.4 cm of body height) performed a static simulation of punch with a fist, palm strike, and elbow strike, where three segments of the right upper limb were scanned. The analysis of 684 images showed a correlation (r = 0.634) between weight and punch technique position in men and significant differences in elbow strike (p < 0.001) and palm strike (p < 0.0001) between women and men. In both groups, the palm demonstrated the largest area and the elbow the smallest one. These data may be used to evaluate strike contact pressure in future studies in forensic biomechanics and assessment of injury in combat sports and self-defense.

Biological applications of knowledge graph embedding models.

Complex biological systems are traditionally modelled as graphs of interconnected biological entities. These graphs, i.e. biological knowledge graphs, are then processed using graph exploratory approaches to perform different types of analytical and predictive tasks. Despite the high predictive accuracy of these approaches, they have limited scalability due to their dependency on time-consuming path exploratory procedures. In recent years, owing to the rapid advances of computational technologies, new approaches for modelling graphs and mining them with high accuracy and scalability have emerged. These approaches, i.e. knowledge graph embedding (KGE) models, operate by learning low-rank vector representations of graph nodes and edges that preserve the graph's inherent structure. These approaches were used to analyse knowledge graphs from different domains where they showed superior performance and accuracy compared to previous graph exploratory approaches. In this work, we study this class of models in the context of biological knowledge graphs and their different applications. We then show how KGE models can be a natural fit for representing complex biological knowledge modelled as graphs. We also discuss their predictive and analytical capabilities in different biology applications. In this regard, we present two example case studies that demonstrate the capabilities of KGE models: prediction of drug-target interactions and polypharmacy side effects. Finally, we analyse different practical considerations for KGEs, and we discuss possible opportunities and challenges related to adopting them for modelling biological systems.

Mechanical characterization and modeling of knitted textile implants with permanent set.

Textile-based implant (mesh) treatment is considered as a standard of care for abdominal wall hernia repair. Computational models and simulations have appeared as one of the most promising approach to investigate biomechanics related to hernia repair and to improve clinical outcomes. This paper presents a novel anisotropic hypo-elastoplastic constitutive model specifically established for surgical knitted textile implants. The major mechanical characteristics of these materials such as anisotropy and permanent set have been reproduced. For the first time ever, we report an extensive mechanical characterization of one of these meshes, including cyclic uniaxial tension, planar equibiaxial tension and plunger type testing. These tests highlight the complex mechanical behavior with strong nonlinearity, anisotropy and permanent set. The novel anisotropic hypo-elasto-plastic constitutive model has been identified based on the tensile experiments and validated successfully against the data of the plunger experiment. In the future, implementation of this characterization and modeling approach to additional surgical knitted textiles should be the direction to follow in order to develop clinical decision support software for abdominal wall repair.

Accurate prediction of kinase-substrate networks using knowledge graphs.

Phosphorylation of specific substrates by protein kinases is a key control mechanism for vital cell-fate decisions and other cellular processes. However, discovering specific kinase-substrate relationships is time-consuming and often rather serendipitous. Computational predictions alleviate these challenges, but the current approaches suffer from limitations like restricted kinome coverage and inaccuracy. They also typically utilise only local features without reflecting broader interaction context. To address these limitations, we have developed an alternative predictive model. It uses statistical relational learning on top of phosphorylation networks interpreted as knowledge graphs, a simple yet robust model for representing networked knowledge. Compared to a representative selection of six existing systems, our model has the highest kinome coverage and produces biologically valid high-confidence predictions not possible with the other tools. Specifically, we have experimentally validated predictions of previously unknown phosphorylations by the LATS1, AKT1, PKA and MST2 kinases in human. Thus, our tool is useful for focusing phosphoproteomic experiments, and facilitates the discovery of new phosphorylation reactions. Our model can be accessed publicly via an easy-to-use web interface (LinkPhinder).

Upper Limb Strikes Reactive Forces in Mix Martial Art Athletes during Ground and Pound Tactics.

Athletes of mixed martial arts use a ground and pound strategy with the strikes in the dominant ground position. The aim of this study was to compare the average peak force (Fpeak) among three punches and to estimate the probability of achieving a skull bone fracture force of 5.1 kN for each type of strike in male and female athletes. A total of 60 males and 31 females (26 ± 8 years, 75 ± 20 kg, 177 ± 11 cm) practicing professional self-defense at the advanced and professional levels performed 15 strikes on a force plate. The analyses of 1360 trials showed significant differences among the strikes Fpeak in females (p < 0.01) and males (p < 0.01). Straight punches had lower Fpeak than palm strikes and elbow strikes in both genders, and palm strikes had higher Fpeak than elbow strikes in females. No difference was observed between palm strikes and elbow strikes in males (p = 0.09). The ground and pound strikes resulted in higher impacts than previously reported strikes in the standing position. Male athletes can deliver a Fpeak above 5.1 kN with a probability of 36% with elbow and palm strikes. Such forces can cause head injury; therefore, the use of these strikes in competition should be carefully considered.

Predicting Polypharmacy Side-effects Using Knowledge Graph Embeddings.

Polypharmacy is the use of drug combinations and is commonly used for treating complex and terminal diseases. Despite its effectiveness in many cases, it poses high risks of adverse side effects. Polypharmacy side-effects occur due to unwanted interactions of combined drugs, and they can cause severe complications to patients which results in increasing the risks of morbidity and leading to new mortalities. The use of drug polypharmacy is currently in its early stages; thus, the knowledge of their probable side-effects is limited. This encouraged multiple works to investigate machine learning techniques to efficiently and reliably predict adverse effects of drug combinations. In this context, the Decagon model is known to provide state-of-the-art results. It models polypharmacy side-effect data as a knowledge graph and formulates finding possible adverse effects as a link prediction task over the knowledge graph. The link prediction is solved using an embedding model based on graph convolutions. Despite its effectiveness, the Decagon approach still suffers from a high rate of false positives. In this work, we propose a new knowledge graph embedding technique that uses multi-part embedding vectors to predict polypharmacy side-effects. Like in the Decagon model, we model polypharmacy side effects as a knowledge graph. However, we perform the link prediction task using an approach based on tensor decomposition. Our experimental evaluation shows that our approach outperforms the Decagon model with 12% and 16% margins in terms of the area under the ROC and precision recall curves, respectively.

Discovering protein drug targets using knowledge graph embeddings.

MOTIVATION: Computational approaches for predicting drug-target interactions (DTIs) can provide valuable insights into the drug mechanism of action. DTI predictions can help to quickly identify new promising (on-target) or unintended (off-target) effects of drugs. However, existing models face several challenges. Many can only process a limited number of drugs and/or have poor proteome coverage. The current approaches also often suffer from high false positive prediction rates. RESULTS: We propose a novel computational approach for predicting drug target proteins. The approach is based on formulating the problem as a link prediction in knowledge graphs (robust, machine-readable representations of networked knowledge). We use biomedical knowledge bases to create a knowledge graph of entities connected to both drugs and their potential targets. We propose a specific knowledge graph embedding model, TriModel, to learn vector representations (i.e. embeddings) for all drugs and targets in the created knowledge graph. These representations are consequently used to infer candidate drug target interactions based on their scores computed by the trained TriModel model. We have experimentally evaluated our method using computer simulations and compared it to five existing models. This has shown that our approach outperforms all previous ones in terms of both area under ROC and precision-recall curves in standard benchmark tests. AVAILABILITY AND IMPLEMENTATION: The data, predictions and models are available at: drugtargets.insight-centre.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Facilitating prediction of adverse drug reactions by using knowledge graphs and multi-label learning models.

Timely identification of adverse drug reactions (ADRs) is highly important in the domains of public health and pharmacology. Early discovery of potential ADRs can limit their effect on patient lives and also make drug development pipelines more robust and efficient. Reliable in silico prediction of ADRs can be helpful in this context, and thus, it has been intensely studied. Recent works achieved promising results using machine learning. The presented work focuses on machine learning methods that use drug profiles for making predictions and use features from multiple data sources. We argue that despite promising results, existing works have limitations, especially regarding flexibility in experimenting with different data sets and/or predictive models. We suggest to address these limitations by generalization of the key principles used by the state of the art. Namely, we explore effects of: (1) using knowledge graphs-machine-readable interlinked representations of biomedical knowledge-as a convenient uniform representation of heterogeneous data; and (2) casting ADR prediction as a multi-label ranking problem. We present a specific way of using knowledge graphs to generate different feature sets and demonstrate favourable performance of selected off-the-shelf multi-label learning models in comparison with existing works. Our experiments suggest better suitability of certain multi-label learning methods for applications where ranking is preferred. The presented approach can be easily extended to other feature sources or machine learning methods, making it flexible for experiments tuned toward specific requirements of end users. Our work also provides a clearly defined and reproducible baseline for any future related experiments.

Characterization of the anisotropic mechanical behavior of human abdominal wall connective tissues.

Abdominal wall sheathing tissues are commonly involved in hernia formation. However, there is very limited work studying mechanics of all tissues from the same donor which prevents a complete understanding of the abdominal wall behavior and the differences in these tissues. The aim of this study was to investigate the differences between the mechanical properties of the linea alba and the anterior and posterior rectus sheaths from a macroscopic point of view. Eight full-thickness human anterior abdominal walls of both genders were collected and longitudinal and transverse samples were harvested from the three sheathing connective tissues. The total of 398 uniaxial tensile tests was conducted and the mechanical characteristics of the behavior (tangent rigidities for small and large deformations) were determined. Statistical comparisons highlighted heterogeneity and non-linearity in behavior of the three tissues under both small and large deformations. High anisotropy was observed under small and large deformations with higher stress in the transverse direction. Variabilities in the mechanical properties of the linea alba according to the gender and location were also identified. Finally, data dispersion correlated with microstructure revealed that macroscopic characterization is not sufficient to fully describe behavior. Microstructure consideration is needed. These results provide a better understanding of the mechanical behavior of the abdominal wall sheathing tissues as well as the directions for microstructure-based constitutive model.

Using Drug Similarities for Discovery of Possible Adverse Reactions.

We propose a new computational method for discovery of possible adverse drug reactions. The method consists of two key steps. First we use openly available resources to semi-automatically compile a consolidated data set describing drugs and their features (e.g., chemical structure, related targets, indications or known adverse reaction). The data set is represented as a graph, which allows for definition of graph-based similarity metrics. The metrics can then be used for propagating known adverse reactions between similar drugs, which leads to weighted (i.e., ranked) predictions of previously unknown links between drugs and their possible side effects. We implemented the proposed method in the form of a software prototype and evaluated our approach by discarding known drug-side effect links from our data and checking whether our prototype is able to re-discover them. As this is an evaluation methodology used by several recent state of the art approaches, we could compare our results with them. Our approach scored best in all widely used metrics like precision, recall or the ratio of relevant predictions present among the top ranked results. The improvement was as much as 125.79% over the next best approach. For instance, the F1 score was 0.5606 (66.35% better than the next best method). Most importantly, in 95.32% of cases, the top five results contain at least one, but typically three correctly predicted side effect (36.05% better than the second best approach).

Material model calibration from planar tension tests on porcine linea alba.

The purpose of this study was to determine biomechanical properties of linea alba subjected to transverse planar tension and to compare its behavior at different locations of the abdominal wall. Samples of linea alba from five different porcine abdominal walls were tested in planar tension. During these tests, strain maps were measured for the first time ever using the stereo-digital image correlation (S-DIC) technique. The strain maps were used to derive the properties of different hyperelastic material models. It was shown that the Ogden model and the Holzapfel-Gasser-Ogden model are appropriate to reproduce the response in planar tension. The linea alba located above the umbilicus was significantly more compliant than below the umbilicus. This difference which is reported for the first time here is consistent with the tissue microstructure and it is discussed within the perspective of clinically-relevant numerical simulations.

SKIMMR: facilitating knowledge discovery in life sciences by machine-aided skim reading.

Background. Unlike full reading, 'skim-reading' involves the process of looking quickly over information in an attempt to cover more material whilst still being able to retain a superficial view of the underlying content. Within this work, we specifically emulate this natural human activity by providing a dynamic graph-based view of entities automatically extracted from text. For the extraction, we use shallow parsing, co-occurrence analysis and semantic similarity computation techniques. Our main motivation is to assist biomedical researchers and clinicians in coping with increasingly large amounts of potentially relevant articles that are being published ongoingly in life sciences. Methods. To construct the high-level network overview of articles, we extract weighted binary statements from the text. We consider two types of these statements, co-occurrence and similarity, both organised in the same distributional representation (i.e., in a vector-space model). For the co-occurrence weights, we use point-wise mutual information that indicates the degree of non-random association between two co-occurring entities. For computing the similarity statement weights, we use cosine distance based on the relevant co-occurrence vectors. These statements are used to build fuzzy indices of terms, statements and provenance article identifiers, which support fuzzy querying and subsequent result ranking. These indexing and querying processes are then used to construct a graph-based interface for searching and browsing entity networks extracted from articles, as well as articles relevant to the networks being browsed. Last but not least, we describe a methodology for automated experimental evaluation of the presented approach. The method uses formal comparison of the graphs generated by our tool to relevant gold standards based on manually curated PubMed, TREC challenge and MeSH data. Results. We provide a web-based prototype (called 'SKIMMR') that generates a network of inter-related entities from a set of documents which a user may explore through our interface. When a particular area of the entity network looks interesting to a user, the tool displays the documents that are the most relevant to those entities of interest currently shown in the network. We present this as a methodology for browsing a collection of research articles. To illustrate the practical applicability of SKIMMR, we present examples of its use in the domains of Spinal Muscular Atrophy and Parkinson's Disease. Finally, we report on the results of experimental evaluation using the two domains and one additional dataset based on the TREC challenge. The results show how the presented method for machine-aided skim reading outperforms tools like PubMed regarding focused browsing and informativeness of the browsing context.

Rheological properties of myometrium: experimental quantification and mathematical modeling.

This work answers some questions related to detection of rheological properties of soft tissues exemplified in myometrium, stressed by external tensile force. In the first stage of the experiment the tissue samples were ciclically stressed and response loops were recorded. This test proved severe plastical deformation of samples, which is not usually being stated for living tissues. In addition to course, growth and stabilizing this deformation also energetical losses of individual hysteresis loops of the response were evaluated. In the second stage of the experiment the tissue samples were exposed to a loading force changed in step-wise manner in four steps. The sample response to each force step was processed and evaluated separately to obtain basic properties of used model. In next step, the changes in model characteristics were obtained and evaluated for each element in subsequent force steps. By reason of following easier interpretation, the quite simple visco-elastic model, defined by differential equation with analytic solution, is used. The results prove necessary to introduce in model both spring and damper constants dependent on the magnitude of the loading force and one damper with even time dependent constant. The interindividual variability of characteristic values of the model elements is surprisingly low. On the other side, they are strongly dependent on load magnitude. Complete mathematical model of uterine wall tissue is obtained by amending the principal equation by formulas describing changes in individual components of the model.