Screening Task Research Articles

Evaluation of a time-varying cut-off frequency low-pass filter for assessing knee joint moments and ACL injury risk

ABSTRACT Conventional low-pass filtering of 3D motion capture signals prior to estimating knee joint moments and ACL injury risk has known limitations. This study aimed to evaluate the fractional Fourier filter (FrFF), which employs a time-varying cut-off frequency, for assessing peak knee moments during common ACL injury risk screening tasks. Ground reaction force and motion data were collected from 23 team sport athletes performing 45° unanticipated sidesteps and drop jumps. Peak knee abduction, internal rotation and non-sagittal moments were estimated using inverse dynamics after five different low-pass filter approaches were applied (FrFF vs. four variations of a fourth-order Butterworth filter). The FrFF produced peak knee moments larger than “matched” (i.e. force and motion cut-off frequencies were equivalent) and closer to “unmatched” (i.e. force and motion cut-offs were different) Butterworth filter approaches and removed problems with representing foot-to-ground impact peaks. Participants with larger peak moments were identified as “at risk” of injury irrespective of filter approach, but the FrFF identified “at risk” classifications conventional approaches did not. Preliminary evidence suggests that the FrFF displays enhanced sensitivity to movement strategies that induce high knee loads. This was most evident for sidestepping, with more research warranted to optimise the FrFF for drop jumps.

Accelerating Evidence Synthesis in Observational Studies: Development of a Living Natural Language Processing-Assisted Intelligent Systematic Literature Review System.

Systematic literature review (SLR), a robust method to identify and summarize evidence from published sources, is considered to be a complex, time-consuming, labor-intensive, and expensive task. This study aimed to present a solution based on natural language processing (NLP) that accelerates and streamlines the SLR process for observational studies using real-world data. We followed an agile software development and iterative software engineering methodology to build a customized intelligent end-to-end living NLP-assisted solution for observational SLR tasks. Multiple machine learning-based NLP algorithms were adopted to automate article screening and data element extraction processes. The NLP prediction results can be further reviewed and verified by domain experts, following the human-in-the-loop design. The system integrates explainable articificial intelligence to provide evidence for NLP algorithms and add transparency to extracted literature data elements. The system was developed based on 3 existing SLR projects of observational studies, including the epidemiology studies of human papillomavirus-associated diseases, the disease burden of pneumococcal diseases, and cost-effectiveness studies on pneumococcal vaccines. Our Intelligent SLR Platform covers major SLR steps, including study protocol setting, literature retrieval, abstract screening, full-text screening, data element extraction from full-text articles, results summary, and data visualization. The NLP algorithms achieved accuracy scores of 0.86-0.90 on article screening tasks (framed as text classification tasks) and macroaverage F1 scores of 0.57-0.89 on data element extraction tasks (framed as named entity recognition tasks). Cutting-edge NLP algorithms expedite SLR for observational studies, thus allowing scientists to have more time to focus on the quality of data and the synthesis of evidence in observational studies. Aligning the living SLR concept, the system has the potential to update literature data and enable scientists to easily stay current with the literature related to observational studies prospectively and continuously.

Proteome Aggregation in Cells Derived from Amyotrophic Lateral Sclerosis Patients for Personalized Drug Evaluation.

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disorder that currently lacks effective therapy. Given the heterogeneity of clinical and molecular profiles of ALS patients, personalized diagnostics and pathological characterization represent a powerful strategy to optimize patient stratification, thereby enabling personalized treatment. Immortalized lymphocytes from sporadic and genetic ALS patients recapitulate some pathological hallmarks of the disease, facilitating the fundamental task of drug screening. However, the molecular aggregation of ALS has not been characterized in this patient-derived cellular model. Indeed, protein aggregation is one of the most prominent features of neurodegenerative diseases, and therefore, models to test drugs against personalized pathological aggregation could help discover improved therapies. With this work, we aimed to characterize the aggregation profile of ALS immortalized lymphocytes and test several drug candidates with different mechanisms of action. In addition, we have evaluated the molecular aggregation in motor neurons derived from two hiPSC cell lines corresponding to ALS patients with different mutations in TARDBP. The results provide valuable insight into the different characterization of sporadic and genetic ALS patients' immortalized lymphocytes, their differential response to drug treatment, and the usefulness of proteome homeostasis characterization in patients' cells.

Brain volume loss after cranial irradiation: a controlled comparison study between photon vs proton radiotherapy for WHO grade 2-3 gliomas.

Radiation therapy (RT) is an integral treatment component in patients with glioma but associated with neurotoxicity. Proton RT (PRT), as compared with photon RT (XRT), reduces excess radiation to nontarget tissue. We used a retrospective method to evaluate brain imaging metrics of neurotoxicity after treatment with PRT and XRT for glioma. We analyzed brain volume change in thirty-four patients with WHO grade 2-3 gliomas treated with either PRT (n = 17) or XRT (n = 17). Both groups were carefully matched by demographic/clinical criteria and assessed longitudinally for two years post-radiotherapy. Brain volume change was measured as ventricular volume expansion in the tumor free hemisphere (contralateral to RT target) as a proxy indicator of brain volume loss. We further assessed the impact of volumetric changes on cognition in PRT patients, who completed neuropsychological testing as part of an outcome study. We found significant ventricular volume increases in the contralesional hemisphere in both groups at two years post-RT (F(1, 31) = 18.45, p < 0.000, partial η2 = 0.373), with greater volume change observed in XRT (26.55%) vs. PRT (12.03%) (M = 12.03%, SD = 16.26; F(1,31) = 4.26, p = 0.048, partial η2 = 0.121). Although, there was no group-level change on any cognitive test in PRT treated patients, individual changes on cognitive screening, working memory, processing speed and visual memory tasks correlated with contralesional brain volume loss. This study suggests progressive brain volume loss following cranial irradiation, with greater severity after XRT vs. PRT. Radiation-induced brain volume loss appears to be associated with measurable cognitive changes on an individual level. Prospective studies are warranted to validate these findings and their impacts on long-term cognitive function and quality of life. An improved understanding of the structural and functional consequences of cranial radiation is essential to develop neuroprotective strategies.

EP.04A.09 The Impetus, Formation and Initial Strategic Aims of the UCLCC Screening and Prevention Task Force

EP.04A.09 The Impetus, Formation and Initial Strategic Aims of the UCLCC Screening and Prevention Task Force

Does Parkinson's disease affect verb production in picture descriptions?

Research on Parkinson's disease (PD) has documented significant deficits in verb production, with more robust results in single word retrieval tasks than in connected speech, yet the underlying causes of these deficits are disputable, especially concerning connected speech production. We analyzed picture descriptions provided by 48 individuals with PD and 48 age-matched healthy controls, and examined the percent of nouns and verbs of all words, the number of described events, verbs denoting activity, verbs in active morpho-syntactic patterns, and transitive verbs. Individuals with PD produced a lower percent of verbs than did control participants, but the groups differed in no other variable. Scores on a cognitive screening task associated with the percent of verbs and the number of events. We suggest that verb retrieval in connected speech in PD reflects no specific difficulty with action semantics, but rather the spread of PD pathology into more diffuse verb-specific neural networks.

Enhancing protein-ligand binding affinity prediction through sequential fusion of graph and convolutional neural networks.

Predicting protein-ligand binding affinity is a crucial and challenging task in structure-based drug discovery. With the accumulation of complex structures and binding affinity data, various machine-learning scoring functions, particularly those based on deep learning, have been developed for this task, exhibiting superiority over their traditional counterparts. A fusion model sequentially connecting a graph neural network (GNN) and a convolutional neural network (CNN) to predict protein-ligand binding affinity is proposed in this work. In this model, the intermediate outputs of the GNN layers, as supplementary descriptors of atomic chemical environments at different levels, are concatenated with the input features of CNN. The model demonstrates a noticeable improvement in performance on CASF-2016 benchmark compared to its constituent CNN models. The generalization ability of the model is evaluated by setting a series of thresholds for ligand extended-connectivity fingerprint similarity or protein sequence similarity between the training and test sets. Masking experiment reveals that model can capture key interaction regions. Furthermore, the fusion model is applied to a virtual screening task for a novel target, PI5P4Kα. The fusion strategy significantly improves the ability of the constituent CNN model to identify active compounds. This work offers a novel approach to enhancing the accuracy of deep learning models in predicting binding affinity through fusion strategies.

MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction.

The prediction of drug-target affinity (DTA) plays a crucial role in drug development and the identification of potential drug targets. In recent years, computer-assisted DTA prediction has emerged as a significant approach in this field. In this study, we propose a multi-modal deep learning framework called MMD-DTA for predicting drug-target binding affinity and binding regions. The model can predict DTA while simultaneously learning the binding regions of drug-target interactions through unsupervised learning. To achieve this, MMD-DTA first uses graph neural networks and target structural feature extraction network to extract multi-modal information from the sequences and structures of drugs and targets. It then utilizes the feature interaction and fusion modules to generate interaction descriptors for predicting DTA and interaction strength for binding region prediction. Our experimental results demonstrate that MMD-DTA outperforms existing models based on key evaluation metrics. Furthermore, external validation results indicate that MMD-DTA enhances the generalization capability of the model by integrating sequence and structural information of drugs and targets. The model trained on the benchmark dataset can effectively generalize to independent virtual screening tasks. The visualization of drug-target binding region prediction showcases the interpretability of MMD-DTA, providing valuable insights into the functional regions of drug molecules that interact with proteins.

Evaluating the effectiveness of large language models in abstract screening: a comparative analysis

ObjectiveThis study aimed to evaluate the performance of large language models (LLMs) in the task of abstract screening in systematic review and meta-analysis studies, exploring their effectiveness, efficiency, and potential integration into existing human expert-based workflows.MethodsWe developed automation scripts in Python to interact with the APIs of several LLM tools, including ChatGPT v4.0, ChatGPT v3.5, Google PaLM 2, and Meta Llama 2, and latest tools including ChatGPT v4.0 turbo, ChatGPT v3.5 turbo, Google Gemini 1.0 pro, Meta Llama 3, and Claude 3. This study focused on three databases of abstracts and used them as benchmarks to evaluate the performance of these LLM tools in terms of sensitivity, specificity, and overall accuracy. The results of the LLM tools were compared to human-curated inclusion decisions, gold standard for systematic review and meta-analysis studies.ResultsDifferent LLM tools had varying abilities in abstract screening. Chat GPT v4.0 demonstrated remarkable performance, with balanced sensitivity and specificity, and overall accuracy consistently reaching or exceeding 90%, indicating a high potential for LLMs in abstract screening tasks. The study found that LLMs could provide reliable results with minimal human effort and thus serve as a cost-effective and efficient alternative to traditional abstract screening methods.ConclusionWhile LLM tools are not yet ready to completely replace human experts in abstract screening, they show great promise in revolutionizing the process. They can serve as autonomous AI reviewers, contribute to collaborative workflows with human experts, and integrate with hybrid approaches to develop custom tools for increased efficiency. As technology continues to advance, LLMs are poised to play an increasingly important role in abstract screening, reshaping the workflow of systematic review and meta-analysis studies.

Towards Trustworthy AI-Enabled Decision Support Systems: Validation of the Multisource AI Scorecard Table (MAST)

The Multisource AI Scorecard Table (MAST) is a checklist tool to inform the design and evaluation of trustworthy AI systems based on the U.S. Intelligence Community’s analytic tradecraft standards. In this study, we investigate whether MAST can be used to differentiate between high and low trustworthy AI-enabled decision support systems (AI-DSSs). Evaluating trust in AI-DSSs poses challenges to researchers and practitioners. These challenges include identifying the components, capabilities, and potential of these systems, many of which are based on the complex deep learning algorithms that drive DSS performance and preclude complete manual inspection. Using MAST, we developed two interactive AI-DSS testbeds. One emulated an identity-verification task in security screening, and another emulated a text-summarization system to aid in an investigative task. Each testbed had one version designed to reach low MAST ratings, and another designed to reach high MAST ratings. We hypothesized that MAST ratings would be positively related to the trust ratings of these systems. A total of 177 subject-matter experts were recruited to interact with and evaluate these systems. Results generally show higher MAST ratings for the high-MAST compared to the low-MAST groups, and that measures of trust perception are highly correlated with the MAST ratings. We conclude that MAST can be a useful tool for designing and evaluating systems that will engender trust perceptions, including for AI-DSS that may be used to support visual screening or text summarization tasks. However, higher MAST ratings may not translate to higher joint performance, and the connection between MAST and appropriate trust or trustworthiness remains an open question.

Shading-Guided Manga Screening From Reference.

Manga screening is a critical process in manga production, which still requires intensive labor and cost. Existing manga screening methods either generate simple dotted screentones only or rely on color information and manual hints during screentone selection. Due to the large domain gap between line drawings and screened manga, and the difficulties in generating high-quality, properly selected and shaded screentones, even state-of-the-art deep learning methods cannot convert line drawings to screened manga well. Besides, ambiguity exists in the screening process since different artists may screen differently for the same line drawing. In this article, we propose to introduce shaded line drawing as the intermediate counterpart of the screened manga so that the manga screening task can be decomposed into two sub-tasks, generating shading from a line drawing and replacing shading with proper screentones. The reference image is adopted to resolve the ambiguity issue and provides options and controls on the generated screened manga. We proposed a reference-based shading generation network and a reference-based screentone generation module to achieve the two sub-tasks individually. We conduct extensive visual and quantitative experiments to verify the effectiveness of our system. Results and statistics show that our method outperforms existing methods on the manga screening task.

Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data

Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual screening of organic materials. By fine-tuning the BERT models with data from five virtual screening tasks, the version pretrained with the USPTO–SMILES dataset achieved R2 scores exceeding 0.94 for three tasks and over 0.81 for two others. This performance surpasses that of models pretrained on the small molecule or organic materials databases and outperforms three traditional machine learning models trained directly on virtual screening data. The success of the USPTO–SMILES pretrained BERT model can be attributed to the diverse array of organic building blocks in the USPTO database, offering a broader exploration of the chemical space. The study further suggests that accessing a reaction database with a wider range of reactions than the USPTO could further enhance model performance. Overall, this research validates the feasibility of applying transfer learning across different chemical domains for the efficient virtual screening of organic materials.Scientific contributionThis study verifies the feasibility of applying transfer learning to large language models in different chemical fields to help organic materials perform virtual screening. Through the comparison of transfer learning from different chemical fields to a variety of organic material molecules, the high precision virtual screening of organic materials is realized.

Identification and Validation of New DNA-PKcs Inhibitors through High-Throughput Virtual Screening and Experimental Verification.

DNA-PKcs is a crucial protein target involved in DNA repair and response pathways, with its abnormal activity closely associated with the occurrence and progression of various cancers. In this study, we employed a deep learning-based screening and molecular dynamics (MD) simulation-based pipeline, identifying eight candidates for DNA-PKcs targets. Subsequent experiments revealed the effective inhibition of DNA-PKcs-mediated cell proliferation by three small molecules (5025-0002, M769-1095, and V008-1080). These molecules exhibited anticancer activity with IC50 (inhibitory concentration at 50%) values of 152.6 μM, 30.71 μM, and 74.84 μM, respectively. Notably, V008-1080 enhanced homology-directed repair (HDR) mediated by CRISPR/Cas9 while inhibiting non-homologous end joining (NHEJ) efficiency. Further investigations into the structure-activity relationships unveiled the binding sites and critical interactions between these small molecules and DNA-PKcs. This is the first application of DeepBindGCN_RG in a real drug screening task, and the successful discovery of a novel DNA-PKcs inhibitor demonstrates its efficiency as a core component in the screening pipeline. Moreover, this study provides important insights for exploring novel anticancer therapeutics and advancing the development of gene editing techniques by targeting DNA-PKcs.

Metaheuristics-guided active learning for optimizing reaction conditions of high-performance methane conversion

Converting greenhouse gases into value-added chemical compounds has been widely studied in chemical science and engineering for sustainable industry. In particular, nonoxidative coupling of methane (NOCM) that transforms methane into useful chemical compounds has received great interests because methane is a naturally abundant greenhouse gas. NOCM has received significant attention in sustainable industry for addressing the climate crisis. However, there are complex optimization problems in maximizing the efficiency of the nonoxidative methane conversion. Although conventional data-driven methods have been successfully applied to various engineering problems, a data-driven optimization of NOCM remains a challenging problem because expensive chemical experiments should be performed to collect prior data for model training. To avoid the expensive costs of chemical experiments, we propose an active learning method that performs training data augmentation and model re-training without pre-defined unlabeled experimental data. To this end, we combine active learning with metaheuristic algorithms to perform active learning with statistically augmented data. We applied the proposed method to a high-throughput screening task to discover new reaction conditions of high-performance NOCM, and the high-throughput screening error was significantly reduced by 69.11%.

Feasibility of Stereo EEG Based Brain Computer Interfacing in An Adult and Pediatric Cohort.

Stereoelectroencephalography (sEEG) is a mesoscale intracranial monitoring method which records from the brain volumetrically with depth electrodes. Implementation of sEEG in BCI has not been well-described across a diverse patient cohort. Across eighteen subjects, channels with high frequency broadband (HFB, 65-115Hz) power increases during hand, tongue, or foot movements during a motor screening task were provided real-time feedback based on these HFB power changes to control a cursor on a screen. Seventeen subjects established successful control of the overt motor BCI, but only nine were able to control imagery BCI with ≥ 80% accuracy. In successful imagery BCI, HFB power in the two target conditions separated into distinct subpopulations, which appear to engage unique subnetworks of the motor cortex compared to cued movement or imagery alone. sEEG-based motor BCI utilizing overt movement and kinesthetic imagery is robust across patient ages and cortical regions with substantial differences in learning proficiency between real or imagined movement.

Telomere length in early childhood and its association with attention: a study in 4-6 year old children.

Telomere length (TL), a marker of cellular aging, has been studied in adults with regard to its connection to cognitive function. However, little is known about the association between TL and cognitive development in children. This study investigated the interplay between TL and cognitive functioning in 283 Belgian children aged four to six years of the Environmental Influence on Aging in Early Life (ENVIRONAGE) birth cohort. Child leukocyte TL was measured using qPCR, while cognitive functioning, including attention and memory, was assessed using the Cambridge Neuropsychological Test Automated Battery (CANTAB). Linear regression models were employed to examine the association between TL and cognitive outcomes, adjusting for potential confounders. We found an inverse association between TL and the spatial errors made during the Motor Screening task (p = 0.017), indicating a higher motor accuracy in children with longer telomeres. No significant associations were found between TL and other cognitive outcomes. Our results suggest a specific link between TL and motor accuracy but not with the other cognitive domains.

Benchmarking deep models on retinal fundus disease diagnosis and a large-scale dataset

Retinal fundus imaging contributes to monitoring the vision of patients by providing views of the interior surface of the eyes. Machine learning models greatly aided ophthalmologists in detecting retinal disorders from color fundus images. Hence, the quality of the data is pivotal for enhancing diagnosis algorithms, which ultimately benefits vision care and maintenance. To facilitate further research in this domain, we introduce the Eye Disease Diagnosis and Fundus Synthesis (EDDFS) dataset, comprising 28,877 fundus images. These include 15,000 healthy samples and a diverse range of images depicting various disorders such as diabetic retinopathy, age-related macular degeneration, glaucoma, pathological myopia, hypertension retinopathy, retinal vein occlusion, and Laser photocoagulation. In addition to providing the dataset, we propose a Transformer-joint convolution network for automated eye disease screening. Firstly, a co-attention structure is integrated to capture long-range attention information along with local features. Secondly, a cross-stage feature fusion module is designed to extract multi-level and disease-related information. By leveraging the dataset and our proposed network, we establish benchmarks for disease screening and grading tasks. Our experimental results underscore the network’s proficiency in both multi-label and single-label disease diagnosis, while also showcasing the dataset’s capability in supporting fundus synthesis. (The dataset and code will be available onhttps://github.com/xia-xx-cv/EDDFS_dataset.)

Machine learning models for abstract screening task - A systematic literature review application for health economics and outcome research

ObjectiveSystematic literature reviews (SLRs) are critical for life-science research. However, the manual selection and retrieval of relevant publications can be a time-consuming process. This study aims to (1) develop two disease-specific annotated corpora, one for human papillomavirus (HPV) associated diseases and the other for pneumococcal-associated pediatric diseases (PAPD), and (2) optimize machine- and deep-learning models to facilitate automation of the SLR abstract screening.MethodsThis study constructed two disease-specific SLR screening corpora for HPV and PAPD, which contained citation metadata and corresponding abstracts. Performance was evaluated using precision, recall, accuracy, and F1-score of multiple combinations of machine- and deep-learning algorithms and features such as keywords and MeSH terms.Results and conclusionsThe HPV corpus contained 1697 entries, with 538 relevant and 1159 irrelevant articles. The PAPD corpus included 2865 entries, with 711 relevant and 2154 irrelevant articles. Adding additional features beyond title and abstract improved the performance (measured in Accuracy) of machine learning models by 3% for HPV corpus and 2% for PAPD corpus. Transformer-based deep learning models that consistently outperformed conventional machine learning algorithms, highlighting the strength of domain-specific pre-trained language models for SLR abstract screening. This study provides a foundation for the development of more intelligent SLR systems.

Modern machine‐learning for binding affinity estimation of protein–ligand complexes: Progress, opportunities, and challenges

AbstractStructure‐based drug design is a widely applied approach in the discovery of new lead compounds for known therapeutic targets. In most structure‐based drug design applications, the docking procedure is considered the crucial step. Here, a potential ligand is fitted into the binding site, and a scoring function assesses its binding capability. With the rise of modern machine‐learning in drug discovery, novel scoring functions using machine‐learning techniques achieved significant performance gains in virtual screening and ligand optimization tasks on retrospective data. However, real‐world applications of these methods are still limited. Missing success stories in prospective applications are one reason for this. Additionally, the fast‐evolving nature of the field makes it challenging to assess the advantages of each individual method. This review will highlight recent strides toward improved real world applicability of machine‐learning based scoring, enabling a better understanding of the potential benefits and pitfalls of these functions on a project. Furthermore, a systematic way of classifying machine‐learning based scoring that facilitates comparisons will be presented.This article is categorized under: Data Science &gt; Chemoinformatics Data Science &gt; Artificial Intelligence/Machine Learning Software &gt; Molecular Modeling

CURRICULUM VITAE ANALYSIS USING MACHINE LEARNING ALGORITHM

We describe a system called CV analysis machine, that processes a set of given free-form textual resumes (in English for IT domain), creates a standardized profile for each candidate, and for a given job description, identifies a ranked shortlist of k candidates, along with a matching score for each. The resume scoring function is hand-crafted, hierarchical, and uses domain-knowledge from recruitment experts. We describe a simple neural- network system that automatically learns some weights used in the scoring function, based on feedback about whether the candidate has their grades on each portion and calculate the overall grade of each candidate and find all grades at a time. Companies often receive thousands of resumes for each job posting and employ dedicated screeners to short list qualified applicants. In this paper, we present PROSPECT, a decision support tool to help these screeners shortlist resumes efficiently. Prospect mines resumes to extract salient aspects of candidate profiles like skills, experience in each skill, education details and experience. Extracted information is presented in the form of facets to aid recruiters in the task of screening. We also employ Information Retrieval techniques to rank all applicants for a given job opening. In our experiments we show that extracted information improves our ranking by 30% there by making screening tasks simpler and more efficient. Keywords--e-recruitment,aptitude,personality prediction,credentials,Big five model of Personality