Multi-modal recommender system for predicting project manager performance within a competency-based framework.

The evaluation of performance using competencies within a structured framework holds significant importance across various professional domains, particularly in roles like project manager. Typically, this assessment process, overseen by senior evaluators, involves scoring competencies based on data gathered from interviews, completed forms, and evaluation programs. However, this task is tedious and time-consuming, and requires the expertise of qualified professionals. Moreover, it is compounded by the inconsistent scoring biases introduced by different evaluators. In this paper, we propose a novel approach to automatically predict competency scores, thereby facilitating the assessment of project managers' performance. Initially, we performed data fusion to compile a comprehensive dataset from various sources and modalities, including demographic data, profile-related data, and historical competency assessments. Subsequently, NLP techniques were used to pre-process text data. Finally, recommender systems were explored to predict competency scores. We compared four different recommender system approaches: content-based filtering, demographic filtering, collaborative filtering, and hybrid filtering. Using assessment data collected from 38 project managers, encompassing scores across 67 different competencies, we evaluated the performance of each approach. Notably, the content-based approach yielded promising results, achieving a precision rate of 81.03%. Furthermore, we addressed the challenge of cold-starting, which in our context involves predicting scores for either a new project manager lacking competency data or a newly introduced competency without historical records. Our analysis revealed that demographic filtering achieved an average precision of 54.05% when dealing with new project managers. In contrast, content-based filtering exhibited remarkable performance, achieving a precision of 85.79% in predicting scores for new competencies. These findings underscore the potential of recommender systems in competency assessment, thereby facilitating more effective performance evaluation process.

Machine learning algorithms using national registry data to predict loss to follow-up during tuberculosis treatment.

BACKGROUND: Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN). METHODS: We performed a retrospective study of all TB cases reported to SINAN between 2015 and 2022; excluding children (< 18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we splitted our data into training (~ 80% data) and test (~ 20%) sets, and then compared the model metrics using the test data set. RESULTS: Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring systems exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity and sensitivity. A user-friendly web calculator app was developed ( https://tbprediction.herokuapp.com/ ) to facilitate implementation. CONCLUSIONS: Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement utilizing schooling level, sex, age, prior TB status, and substance use (drug, alcohol, and/or tobacco). This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.

Proanthocyanidins isolated from the leaves of Ficus glomerata evaluated on the activities of rumen enzymes: in vitro and in silico studies.

Two new proanthocyanidins (2S:3S)-(-)-epicatechin-(4α→8)4-(2R:3R)-(+)-catechin (Compound 1) and (2R, 3R)-3-O-galloyl-(+)-catechin (4ß→8)3-(2R, 3R)-3-O-galloyl-(+)-catechin (Compound 2) were isolated from Ficus glomerata and characterized by ultraviolet spectroscopy (UV), proton nuclear magnetic resonance (1H NMR), 13C NMR, and heteronuclear multiple bond correlation . The bioactivity and drug scores of isolated compounds were predicted using OSIRIS property explorer applications with drug scores of 0.03 (compound 1) and 0.05 (compound 2). Predictive drug scores provided an indication of the compounds' potential to demonstrate desired biological effects. Furthermore, the newly discovered proanthocyanidins tended to interact with protein due to their chemical structure and molecular conformation. With the aim of maintaining this focus, compounds 1 and 2 were subjected to in vitro testing against ruminal enzymes to further explore their potential impact. Both compounds showed significant inhibition activities (p < 0.01) against glutamic oxaloacetic transaminase in both protozoa and bacterial fractions, with an effective concentration (EC50) of 12.30-18.20 mg/mL. The compounds also exhibited significant inhibition (p < 0.01) of ruminal glutamic pyruvic transaminase activity, with EC50 values ranging from 9.77 to 17.38 mg/mL. Furthermore, the inhibition was recorded in R-cellulase between EC50 values of 15.85 and 23.99 mg/mL by both compounds. Additionally, both compounds led to a decrease in protease activity with increasing incubation time and concentration. In conclusion, the results indicate that these novel proanthocyanidins hold the potential to significantly impact rumen enzyme biology. Furthermore, their promising effects suggest that they could be further explored for drug development and other important applications.

Analysis across Taiwan Biobank, Biobank Japan, and UK Biobank identifies hundreds of novel loci for 36 quantitative traits.

Genome-wide association studies (GWASs) have identified tens of thousands of genetic loci associated with human complex traits. However, the majority of GWASs were conducted in individuals of European ancestries. Failure to capture global genetic diversity has limited genomic discovery and has impeded equitable delivery of genomic knowledge to diverse populations. Here we report findings from 102,900 individuals across 36 human quantitative traits in the Taiwan Biobank (TWB), a major biobank effort that broadens the population diversity of genetic studies in East Asia. We identified 968 novel genetic loci, pinpointed novel causal variants through statistical fine-mapping, compared the genetic architecture across TWB, Biobank Japan, and UK Biobank, and evaluated the utility of cross-phenotype, cross-population polygenic risk scores in disease risk prediction. These results demonstrated the potential to advance discovery through diversifying GWAS populations and provided insights into the common genetic basis of human complex traits in East Asia.

Genetic architecture and polygenic risk score prediction of degenerative suspensory ligament desmitis (DSLD) in the Peruvian Horse.

Introduction: Spontaneous rupture of tendons and ligaments is common in several species including humans. In horses, degenerative suspensory ligament desmitis (DSLD) is an important acquired idiopathic disease of a major energy-storing tendon-like structure. DSLD risk is increased in several breeds, including the Peruvian Horse. Affected horses have often been used for breeding before the disease is apparent. Breed predisposition suggests a substantial genetic contribution, but heritability and genetic architecture of DSLD have not been determined. Methods: To identify genomic regions associated with DSLD, we recruited a reference population of 183 Peruvian Horses, phenotyped as DSLD cases or controls, and undertook a genome-wide association study (GWAS), a regional window variance analysis using local genomic partitioning, a signatures of selection (SOS) analysis, and polygenic risk score (PRS) prediction of DSLD risk. We also estimated trait heritability from pedigrees. Results: Heritability was estimated in a population of 1,927 Peruvian horses at 0.22 ± 0.08. After establishing a permutation-based threshold for genome-wide significance, 151 DSLD risk single nucleotide polymorphisms (SNPs) were identified by GWAS. Multiple regions of enriched local heritability were identified across the genome, with strong enrichment signals on chromosomes 1, 2, 6, 10, 13, 16, 18, 22, and the X chromosome. With SOS analysis, there were 66 genes with a selection signature in DSLD cases that was not present in the control group that included the TGFB3 gene. Pathways enriched in DSLD cases included proteoglycan metabolism, extracellular matrix homeostasis, and signal transduction pathways that included the hedgehog signaling pathway. The best PRS predictive performance was obtained when we fitted 1% of top SNPs using a Bayesian Ridge Regression model which achieved the highest mean of R2 on both the probit and logit liability scales, indicating a strong predictive performance. Discussion: We conclude that within-breed GWAS of DSLD in the Peruvian Horse has further confirmed that moderate heritability and a polygenic architecture underlies the trait and identified multiple DSLD SNP associations in novel tendinopathy candidate genes influencing disease risk. Pathways enriched with DSLD risk variants include ones that influence glycosaminoglycan metabolism, extracellular matrix homeostasis, signal transduction pathways.

Brain morphometric features predict depression symptom phenotypes in late-life depression using a deep learning model.

Objectives: Our objective was to use deep learning models to identify underlying brain regions associated with depression symptom phenotypes in late-life depression (LLD). Participants: Diagnosed with LLD (N = 116) and enrolled in a prospective treatment study. Design: Cross-sectional. Measurements: Structural magnetic resonance imaging (sMRI) was used to predict five depression symptom phenotypes from the Hamilton and MADRS depression scales previously derived from factor analysis: (1) Anhedonia, (2) Suicidality, (3) Appetite, (4) Sleep Disturbance, and (5) Anxiety. Our deep learning model was deployed to predict each factor score via learning deep feature representations from 3D sMRI patches in 34 a priori regions-of-interests (ROIs). ROI-level prediction accuracy was used to identify the most discriminative brain regions associated with prediction of factor scores representing each of the five symptom phenotypes. Results: Factor-level results found significant predictive models for Anxiety and Suicidality factors. ROI-level results suggest the most LLD-associated discriminative regions in predicting all five symptom factors were located in the anterior cingulate and orbital frontal cortex. Conclusions: We validated the effectiveness of using deep learning approaches on sMRI for predicting depression symptom phenotypes in LLD. We were able to identify deep embedded local morphological differences in symptom phenotypes in the brains of those with LLD, which is promising for symptom-targeted treatment of LLD. Future research with machine learning models integrating multimodal imaging and clinical data can provide additional discriminative information.

Building CNN-Based Models for Image Aesthetic Score Prediction Using an Ensemble.

In this paper, we propose a framework that constructs two types of image aesthetic assessment (IAA) models with different CNN architectures and improves the performance of image aesthetic score (AS) prediction by the ensemble. Moreover, the attention regions of the models to the images are extracted to analyze the consistency with the subjects in the images. The experimental results verify that the proposed method is effective for improving the AS prediction. The average F1 of the ensemble improves 5.4% over the model of type A, and 33.1% over the model of type B. Moreover, it is found that the AS classification models trained on the XiheAA dataset seem to learn the latent photography principles, although it cannot be said that they learn the aesthetic sense.

Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning.

Drug combinations could trigger pharmacological therapeutic effects (TEs) and adverse effects (AEs). Many computational methods have been developed to predict TEs, e.g. the therapeutic synergy scores of anti-cancer drug combinations, or AEs from drug-drug interactions. However, most of the methods treated the AEs and TEs predictions as two separate tasks, ignoring the potential mechanistic commonalities shared between them. Based on previous clinical observations, we hypothesized that by learning the shared mechanistic commonalities between AEs and TEs, we could learn the underlying MoAs (mechanisms of actions) and ultimately improve the accuracy of TE predictions. To test our hypothesis, we formulated the TE prediction problem as a multi-task heterogeneous network learning problem that performed TE and AE learning tasks simultaneously. To solve this problem, we proposed Muthene (multi-task heterogeneous network embedding) and evaluated it on our collected drug-drug interaction dataset with both TEs and AEs indications. Our experimental results showed that, by including the AE prediction as an auxiliary task, Muthene generated more accurate TE predictions than standard single-task learning methods, which supports our hypothesis. Using a drug pair Vincristine-Dasatinib as a case study, we demonstrated that our method not only provides a novel way of TE predictions but also helps us gain a deeper understanding of the MoAs of drug combinations.

Machine learning algorithms using national registry data to predict loss to follow- up during tuberculosis treatment.

Background: Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN). Methods: We performed a retrospective study of all TB cases reported to SINAN between 2015-2022; excluding children (<18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we split our data into train (~80% data) and test (~20%), and then we compare model metrics using a test data set. Results: Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated and cured. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring system exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity, and sensibility. A user-friendly web calculator app was created (https://tbprediction.herokuapp.com/) to facilitate implementation. Conclusions: Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement. This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.

A Deep Learning Quantification Algorithm for HER2 Scoring of Gastric Cancer.

Gastric cancer is the third most common cause of cancer-related death in the world. Human epidermal growth factor receptor 2 (HER2) positive is an important subtype of gastric cancer, which can provide significant diagnostic information for gastric cancer pathologists. However, pathologists usually use a semi-quantitative assessment method to assign HER2 scores for gastric cancer by repeatedly comparing hematoxylin and eosin (H&E) whole slide images (WSIs) with their HER2 immunohistochemical WSIs one by one under the microscope. It is a repetitive, tedious, and highly subjective process. Additionally, WSIs have billions of pixels in an image, which poses computational challenges to Computer-Aided Diagnosis (CAD) systems. This study proposed a deep learning algorithm for HER2 quantification evaluation of gastric cancer. Different from other studies that use convolutional neural networks for extracting feature maps or pre-processing on WSIs, we proposed a novel automatic HER2 scoring framework in this study. In order to accelerate the computational process, we proposed to use the re-parameterization scheme to separate the training model from the deployment model, which significantly speedup the inference process. To the best of our knowledge, this is the first study to provide a deep learning quantification algorithm for HER2 scoring of gastric cancer to assist the pathologist's diagnosis. Experiment results have demonstrated the effectiveness of our proposed method with an accuracy of 0.94 for the HER2 scoring prediction.

Evaluation and Mitigation of Racial Bias in Clinical Machine Learning Models: Scoping Review.

BACKGROUND: Racial bias is a key concern regarding the development, validation, and implementation of machine learning (ML) models in clinical settings. Despite the potential of bias to propagate health disparities, racial bias in clinical ML has yet to be thoroughly examined and best practices for bias mitigation remain unclear. OBJECTIVE: Our objective was to perform a scoping review to characterize the methods by which the racial bias of ML has been assessed and describe strategies that may be used to enhance algorithmic fairness in clinical ML. METHODS: A scoping review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) Extension for Scoping Reviews. A literature search using PubMed, Scopus, and Embase databases, as well as Google Scholar, identified 635 records, of which 12 studies were included. RESULTS: Applications of ML were varied and involved diagnosis, outcome prediction, and clinical score prediction performed on data sets including images, diagnostic studies, clinical text, and clinical variables. Of the 12 studies, 1 (8%) described a model in routine clinical use, 2 (17%) examined prospectively validated clinical models, and the remaining 9 (75%) described internally validated models. In addition, 8 (67%) studies concluded that racial bias was present, 2 (17%) concluded that it was not, and 2 (17%) assessed the implementation of bias mitigation strategies without comparison to a baseline model. Fairness metrics used to assess algorithmic racial bias were inconsistent. The most commonly observed metrics were equal opportunity difference (5/12, 42%), accuracy (4/12, 25%), and disparate impact (2/12, 17%). All 8 (67%) studies that implemented methods for mitigation of racial bias successfully increased fairness, as measured by the authors' chosen metrics. Preprocessing methods of bias mitigation were most commonly used across all studies that implemented them. CONCLUSIONS: The broad scope of medical ML applications and potential patient harms demand an increased emphasis on evaluation and mitigation of racial bias in clinical ML. However, the adoption of algorithmic fairness principles in medicine remains inconsistent and is limited by poor data availability and ML model reporting. We recommend that researchers and journal editors emphasize standardized reporting and data availability in medical ML studies to improve transparency and facilitate evaluation for racial bias.

Exploring Metrics to Establish an Optimal Model for Image Aesthetic Assessment and Analysis.

To establish an optimal model for photo aesthetic assessment, in this paper, an internal metric called the disentanglement-measure (D-measure) is introduced, which reflects the disentanglement degree of the final layer FC (full connection) nodes of convolutional neural network (CNN). By combining the F-measure with the D-measure to obtain an FD measure, an algorithm of determining the optimal model from many photo score prediction models generated by CNN-based repetitively self-revised learning (RSRL) is proposed. Furthermore, the aesthetics features of the model regarding the first fixation perspective (FFP) and the assessment interest region (AIR) are defined by means of the feature maps so as to analyze the consistency with human aesthetics. The experimental results show that the proposed method is helpful in improving the efficiency of determining the optimal model. Moreover, extracting the FFP and AIR of the models to the image is useful in understanding the internal properties of these models related to the human aesthetics and validating the external performances of the aesthetic assessment.

Multiparametric magnetic resonance imaging for differentiating active from inactive thyroid-associated ophthalmopathy: Added value from magnetization transfer imaging.

PURPOSE: To investigate the feasibility of using magnetization transfer (MT) magnetic resonance imaging for evaluating patients with thyroid-associated ophthalmopathy (TAO), and determine its added value for differentiating active from inactive TAO and predicting clinical activity score (CAS), compared with conventional fat-saturated T2-weighted and diffusion-weighted imaging. METHODS: Orbital MT, fat-saturated T2-weighted, and diffusion-weighted imaging of 60 prospectively enrolled consecutive patients with TAO was analyzed. Simplified histogram parameters (mean, max, min) of magnetization transfer ratio (MTR), signal intensity ratio (SIR), and apparent diffusion coefficient (ADC) at extraocular muscles were calculated for each orbit and compared between the active and inactive groups. RESULTS: Intraclass correlation coefficients of MTRs and SIRs were similar (0.802-0.963 vs 0.812-0.974, respectively), followed by those of ADCs (0.714-0.855). Patients with active TAO showed significantly lower MTRs and higher SIRs and ADCs than those with inactive TAO (P < 0.05). MTRmean achieved the highest area under the curve (AUC) of 0.868 for differentiating active from inactive group, followed by SIRmax (AUC, 0.836). MTRmean also demonstrated a higher and negative correlation with CAS (r = -0.614, P < 0.001) than MTRmax and MTRmin (r = -0.495, P < 0.001; r = -0.243, P = 0.007; respectively). Support vector machine-based analysis revealed that uniting MTRs could prosper concurrently added performance for disease activity differentiation and CAS prediction, compared with merely combining SIRs and ADCs (AUC, 0.933 vs 0.901; r = 0.703 vs. 0.673). CONCLUSIONS: MT imaging could potentially be used as a noninvasive method for differentiating the activity of TAO and predicting CAS, thereby offering added value to conventional SIR and ADC.

Predicting cognitive scores with graph neural networks through sample selection learning.

Analyzing the relation between intelligence and neural activity is of the utmost importance in understanding the working principles of the human brain in health and disease. In existing literature, functional brain connectomes have been used successfully to predict cognitive measures such as intelligence quotient (IQ) scores in both healthy and disordered cohorts using machine learning models. However, existing methods resort to flattening the brain connectome (i.e., graph) through vectorization which overlooks its topological properties. To address this limitation and inspired from the emerging graph neural networks (GNNs), we design a novel regression GNN model (namely RegGNN) for predicting IQ scores from brain connectivity. On top of that, we introduce a novel, fully modular sample selection method to select the best samples to learn from for our target prediction task. However, since such deep learning architectures are computationally expensive to train, we further propose a learning-based sample selection method that learns how to choose the training samples with the highest expected predictive power on unseen samples. For this, we capitalize on the fact that connectomes (i.e., their adjacency matrices) lie in the symmetric positive definite (SPD) matrix cone. Our results on full-scale and verbal IQ prediction outperforms comparison methods in autism spectrum disorder cohorts and achieves a competitive performance for neurotypical subjects using 3-fold cross-validation. Furthermore, we show that our sample selection approach generalizes to other learning-based methods, which shows its usefulness beyond our GNN architecture.

V-Dock: Fast Generation of Novel Drug-like Molecules Using Machine-Learning-Based Docking Score and Molecular Optimization.

We propose a computational workflow to design novel drug-like molecules by combining the global optimization of molecular properties and protein-ligand docking with machine learning. However, most existing methods depend heavily on experimental data, and many targets do not have sufficient data to train reliable activity prediction models. To overcome this limitation, protein-ligand docking calculations must be performed using the limited data available. Such docking calculations during molecular generation require considerable computational time, preventing extensive exploration of the chemical space. To address this problem, we trained a machine-learning-based model that predicted the docking energy using SMILES to accelerate the molecular generation process. Docking scores could be accurately predicted using only a SMILES string. We combined this docking score prediction model with the global molecular property optimization approach, MolFinder, to find novel molecules exhibiting the desired properties with high values of predicted docking scores. We named this design approach V-dock. Using V-dock, we efficiently generated many novel molecules with high docking scores for a target protein, a similarity to the reference molecule, and desirable drug-like and bespoke properties, such as QED. The predicted docking scores of the generated molecules were verified by correlating them with the actual docking scores.

Loneliness is linked to specific subregional alterations in hippocampus-default network covariation.

Social interaction complexity makes humans unique. But in times of social deprivation, this strength risks exposure of important vulnerabilities. Human social neuroscience studies have placed a premium on the default network (DN). In contrast, hippocampus (HC) subfields have been intensely studied in rodents and monkeys. To bridge these two literatures, we here quantified how DN subregions systematically covary with specific HC subfields in the context of subjective social isolation (i.e., loneliness). By codecomposition using structural brain scans of ∼40,000 UK Biobank participants, loneliness was specially linked to midline subregions in the uncovered DN patterns. These association cortex patterns coincided with concomitant HC patterns implicating especially CA1 and molecular layer. These patterns also showed a strong affiliation with the fornix white matter tract and the nucleus accumbens. In addition, separable signatures of structural HC-DN covariation had distinct associations with the genetic predisposition for loneliness at the population level.NEW & NOTEWORTHY The hippocampus and default network have been implicated in rich social interaction. Yet, these allocortical and neocortical neural systems have been interrogated in mostly separate literatures. Here, we conjointly investigate the hippocampus and default network at a subregion level, by capitalizing structural brain scans from ∼40,000 participants. We thus reveal unique insights on the nature of the "lonely brain" by estimating the regimes of covariation between the hippocampus and default network at population scale.

Hybrid Basketball Game Outcome Prediction Model by Integrating Data Mining Methods for the National Basketball Association.

The sports market has grown rapidly over the last several decades. Sports outcomes prediction is an attractive sports analytic challenge as it provides useful information for operations in the sports market. In this study, a hybrid basketball game outcomes prediction scheme is developed for predicting the final score of the National Basketball Association (NBA) games by integrating five data mining techniques, including extreme learning machine, multivariate adaptive regression splines, k-nearest neighbors, eXtreme gradient boosting (XGBoost), and stochastic gradient boosting. Designed features are generated by merging different game-lags information from fundamental basketball statistics and used in the proposed scheme. This study collected data from all the games of the NBA 2018-2019 seasons. There are 30 teams in the NBA and each team play 82 games per season. A total of 2460 NBA game data points were collected. Empirical results illustrated that the proposed hybrid basketball game prediction scheme achieves high prediction performance and identifies suitable game-lag information and relevant game features (statistics). Our findings suggested that a two-stage XGBoost model using four pieces of game-lags information achieves the best prediction performance among all competing models. The six designed features, including averaged defensive rebounds, averaged two-point field goal percentage, averaged free throw percentage, averaged offensive rebounds, averaged assists, and averaged three-point field goal attempts, from four game-lags have a greater effect on the prediction of final scores of NBA games than other game-lags. The findings of this study provide relevant insights and guidance for other team or individual sports outcomes prediction research.

Powerlifting score prediction using a machine learning method.

This research discusses an interesting topic, using artificial intelligence methods to predict the score of powerlifters. We collected the characteristics of powerlifters, and then used the reservoir computing extreme learning machine to build a predictive model. In order to further improve the prediction results, we propose a method to optimize the reservoir computing extreme learning machine using the whale optimization algorithm. Experimental results show that our proposed method can effectively predict the score of powerlifters with the coefficient of determination value is 0.7958 and root-mean-square error of prediction value is 16.73. This provides a reliable basis for experts to judge the results before the competition.

Nomograms and risk score models for predicting survival in rectal cancer patients with neoadjuvant therapy.

BACKGROUND: Colorectal cancer is a common digestive cancer worldwide. As a comprehensive treatment for locally advanced rectal cancer (LARC), neoadjuvant therapy (NT) has been increasingly used as the standard treatment for clinical stage II/III rectal cancer. However, few patients achieve a complete pathological response, and most patients require surgical resection and adjuvant therapy. Therefore, identifying risk factors and developing accurate models to predict the prognosis of LARC patients are of great clinical significance. AIM: To establish effective prognostic nomograms and risk score prediction models to predict overall survival (OS) and disease-free survival (DFS) for LARC treated with NT. METHODS: Nomograms and risk factor score prediction models were based on patients who received NT at the Cancer Hospital from 2015 to 2017. The least absolute shrinkage and selection operator regression model were utilized to screen for prognostic risk factors, which were validated by the Cox regression method. Assessment of the performance of the two prediction models was conducted using receiver operating characteristic curves, and that of the two nomograms was conducted by calculating the concordance index (C-index) and calibration curves. The results were validated in a cohort of 65 patients from 2015 to 2017. RESULTS: Seven features were significantly associated with OS and were included in the OS prediction nomogram and prediction model: Vascular_tumors_bolt, cancer nodules, yN, body mass index, matchmouth distance from the edge, nerve aggression and postoperative carcinoembryonic antigen. The nomogram showed good predictive value for OS, with a C-index of 0.91 (95%CI: 0.85, 0.97) and good calibration. In the validation cohort, the C-index was 0.69 (95%CI: 0.53, 0.84). The risk factor prediction model showed good predictive value. The areas under the curve for 3- and 5-year survival were 0.811 and 0.782. The nomogram for predicting DFS included ypTNM and nerve aggression and showed good calibration and a C-index of 0.77 (95%CI: 0.69, 0.85). In the validation cohort, the C-index was 0.71 (95%CI: 0.61, 0.81). The prediction model for DFS also had good predictive value, with an AUC for 3-year survival of 0.784 and an AUC for 5-year survival of 0.754. CONCLUSION: We established accurate nomograms and prediction models for predicting OS and DFS in patients with LARC after undergoing NT.

A Novel Method for Cancer Subtyping and Risk Prediction Using Consensus Factor Analysis.

Cancer is an umbrella term that includes a range of disorders, from those that are fast-growing and lethal to indolent lesions with low or delayed potential for progression to death. One critical unmet challenge is that molecular disease subtypes characterized by relevant clinical differences, such as survival, are difficult to differentiate. With the advancement of multi-omics technologies, subtyping methods have shifted toward data integration in order to differentiate among subtypes from a holistic perspective that takes into consideration phenomena at multiple levels. However, these integrative methods are still limited by their statistical assumption and their sensitivity to noise. In addition, they are unable to predict the risk scores of patients using multi-omics data. Here, we present a novel approach named Subtyping via Consensus Factor Analysis (SCFA) that can efficiently remove noisy signals from consistent molecular patterns in order to reliably identify cancer subtypes and accurately predict risk scores of patients. In an extensive analysis of 7,973 samples related to 30 cancers that are available at The Cancer Genome Atlas (TCGA), we demonstrate that SCFA outperforms state-of-the-art approaches in discovering novel subtypes with significantly different survival profiles. We also demonstrate that SCFA is able to predict risk scores that are highly correlated with true patient survival and vital status. More importantly, the accuracy of subtype discovery and risk prediction improves when more data types are integrated into the analysis. The SCFA software and TCGA data packages will be available on Bioconductor.