Machine Learning-based Screening Research Articles

Machine learning-based screening of fuel properties for SI and CI engines using a hybrid group extraction method

The design of high-performance fuels is crucial for achieving clean and efficient combustion of engines. In the current study, a framework for machine learning (ML) model-based fuel design is presented to identify compounds with desired properties for internal combustion engine (ICE) applications. Descriptors computed from newly proposed structural and positional-based group extraction method in this study are used as input in ML models due to the simplicity and computational-efficiency. The ML models were trained and validated using publically available experimental data for up to 1135 compounds. The results demonstrated a high level of predictive accuracy, with R2 values generally exceeding 0.99 for 11 physicochemical properties including melting point, boiling point, enthalpy of vaporization, surface tension, dynamic viscosity, low heating value, liquid density, yield sooting index, cetane number, research octane number and motor octane number. Furthermore, by employing the developed ML models to predict new data, a Fuel Property Database containing 1135 fuels with 12 fuel properties is established, enhanced by an interface for a user-friendly Fuel Physicochemical Properties Prediction Tool that facilitates swift property predictions and database expansion. The Pearson correlation coefficient (PCC) approach is subsequently employed to assess the correlation between descriptors and predicted or experimental properties. The strong agreement between the correlations affirms the effective predictive performance of the ML models within the calibrated data range. Additionally, a PCC analysis is conducted to reveal the individual effects of influential factors and their interactions, highlighting significant features like molecular weight size, degree of branching, and functional group content that influence physical and chemical properties, thereby providing valuable insights for fuel design and optimization. Finally, a initial comprehensive data-driven screening was carried out to identify potential fuel candidates that meet the key property limits for combustion applications in both spark-ignition (SI) and compression-ignition (CI) engines.

Malnutrition risk assessment using a machine learning-based screening tool: A multicentre retrospective cohort.

Malnutrition is associated with increased morbidity, mortality, and healthcare costs. Early detection is important for timely intervention. This paper assesses the ability of a machine learning screening tool (MUST-Plus) implemented in registered dietitian (RD) workflow to identify malnourished patients early in the hospital stay and to improve the diagnosis and documentation rate of malnutrition. This retrospective cohort study was conducted in a large, urban health system in New York City comprising six hospitals serving a diverse patient population. The study included all patients aged ≥ 18 years, who were not admitted for COVID-19 and had a length of stay of ≤ 30 days. Of the 7736 hospitalisations that met the inclusion criteria, 1947 (25.2%) were identified as being malnourished by MUST-Plus-assisted RD evaluations. The lag between admission and diagnosis improved with MUST-Plus implementation. The usability of the tool output by RDs exceeded 90%, showing good acceptance by users. When compared pre-/post-implementation, the rate of both diagnoses and documentation of malnutrition showed improvement. MUST-Plus, a machine learning-based screening tool, shows great promise as a malnutrition screening tool for hospitalised patients when used in conjunction with adequate RD staffing and training about the tool. It performed well across multiple measures and settings. Other health systems can use their electronic health record data to develop, test and implement similar machine learning-based processes to improve malnutrition screening and facilitate timely intervention.

Directed Evolution of Near-Infrared Serotonin Nanosensors with Machine Learning-Based Screening

In this study, we employed a novel approach to improve the serotonin-responsive ssDNA-wrapped single-walled carbon nanotube (ssDNA-SWCNT) nanosensors, combining directed evolution and machine learning-based prediction. Our iterative optimization process is aimed at the sensitivity and selectivity of ssDNA-SWCNT nanosensors. In the three rounds for higher serotonin sensitivity, we substantially improved sensitivity, achieving a remarkable 2.5-fold enhancement in fluorescence response compared to the original sequence. Following this, we directed our efforts towards selectivity for serotonin over dopamine in the two rounds. Despite the structural similarity between these neurotransmitters, we achieved a 1.6-fold increase in selectivity. This innovative methodology, offering high-throughput screening of mutated sequences, marks a significant advancement in biosensor development. The top-performing nanosensors, N2-1 (sensitivity) and L1-14 (selectivity) present promising reference sequences for future studies involving serotonin detection.

Development of a pharmaceutical science systematic review process using a semi-automated machine learning tool: Intravenous drug compatibility in the neonatal intensive caresetting.

Our objective was to establish and test a machine learning-based screening process that would be applicable to systematic reviews in pharmaceutical sciences. We used the SPIDER (Sample, Phenomenon of Interest, Design, Evaluation, Research type) model, a broad search strategy, and a machine learning tool (Research Screener) to identify relevant references related to y-site compatibility of 95 intravenous drugs used in neonatal intensive care settings. Two independent reviewers conducted pilot studies, including manual screening and evaluation of Research Screener, and used the kappa-coefficient for inter-reviewer reliability. After initial deduplication of the search strategy results, 27 597 references were available for screening. Research Screener excluded 1735 references, including 451 duplicate titles and 1269 reports with no abstract/title, which were manually screened. The remainder (25 862) were subject to the machine learning screening process. All eligible articles for the systematic review were extracted from <10% of the references available for screening. Moderate inter-reviewer reliability was achieved, with kappa-coefficient ≥0.75. Overall, 324 references were subject to full-text reading and 118 were deemed relevant for the systematic review. Our study showed that a broad search strategy to optimize the literature captured for systematic reviews can be efficiently screened by the semi-automated machine learning tool, Research Screener.

Machine Learning-based Screening of Mn-PNP Catalysts for CO2 Reduction Reaction Using Region-wise Ligand-encoded Feature Matrix

The CO2 reduction reaction is a promising way to reduce CO2 level in the environment and most importantly to produce C1-based chemicals (HCOOH and CH3OH) which can be used as...

Machine Learning-Based Screening for Potential Singlet Fission Chromophores: The Challenge of Imbalanced Data Sets.

Excitation with one photon of a singlet fission (SF) material generates two triplet excitons, thus doubling the solar cell efficiency. Therefore, the SF molecules are regarded as new generation organic photovoltaics, but it is hard to identify them. Recently, it was demonstrated that molecules of low-to-intermediate diradical character (DRC) are potential SF chromophores. This prompts a low-cost strategy for finding new SF candidates by computational high-throughput workflows. We propose a machine learning aided screening for SF entrants based on their DRC. Our data set comprises 469 784 compounds extracted from the PubChem database, structurally rich but inherently imbalanced regarding DRC values. We developed well performing classification models that can retrieve potential SF chromophores. The latter (∼4%) were analyzed by K-means clustering to reveal qualitative structure-property relationships and to extract strategies for molecular design. The developed screening procedure and data set can be easily adapted for applications of diradicaloids in photonics and spintronics.

Machine Learning-Based Screening Solution for COVID-19 Cases Investigation: Socio-Demographic and Behavioral Factors Analysis and COVID-19 Detection

The COVID-19 pandemic has unleashed an unprecedented global crisis, releasing a wave of illness, mortality, and economic disarray of unparalleled proportions. Numerous societal and behavioral aspects have conspired to fuel the rampant spread of COVID-19 across the globe. These factors encompass densely populated areas, adherence to mask-wearing protocols, inadequate awareness levels, and various behavioral and social practices. Despite the extensive research surrounding COVID-19 detection, an unfortunate dearth of studies has emerged to meticulously evaluate the intricate interplay between socio-demographic and behavioral factors and the likelihood of COVID-19 infection. Thus, a comprehensive online-based cross-sectional survey was methodically orchestrated, amassing data from a substantial sample size of 500 respondents. The precisely designed survey questionnaire encompassed various variables encompassing socio-demographics, behaviors, and social factors. The Bivariate Pearson’s Chi-square association test was deftly employed to unravel the complex associations between the explanatory variables and COVID-19 infection. The feature importance approach was also introduced to discern the utmost critical features underpinning this infectious predicament. Four distinct Machine Learning (ML) algorithms, specifically Decision Tree, Random Forest, CatBoost, and XGBoost, were employed to accurately predict COVID-19 infection based on a comprehensive analysis of socio-demographic and behavioral factors. The performance of these models was rigorously assessed using a range of evaluation metrics, including accuracy, recall, precision, ROC-AUC score, and F1 score. Pearson’s Chi-square test revealed a statistically significant association between vaccination status and COVID-19 infection. The use of sanitizer and masks, the timing of infection, and the interval between the first and second vaccine doses were significantly correlated with the likelihood of contracting the COVID-19 virus. Among the ML models tested, the XGBoost classifier demonstrated the highest classification accuracy, achieving an impressive 97.6%. These findings provide valuable insights for individuals, communities, and policymakers to implement targeted strategies aimed at mitigating the impact of the COVID-19 pandemic.

Machine learning-based screening of in-house database to identify BACE-1 inhibitors

Machine learning-based screening of in-house database to identify BACE-1 inhibitors

Automatic Detection of Chronic Insomnia from Polysomnographic and Clinical Variables Using Machine Learning.

Insomnia is defined subjectively by the presence and frequency of specific clinical symptoms and an association with distress. Although sleep study data has shown some weak associations, no objective test can currently be used to predict insomnia. The purpose of this study was to use previously reported and relatively crafted insomnia-related polysomnographic variables in machine learning models to classify groups with and without insomnia. Demographics, diagnosed depression, Epworth Sleepiness Scale (ESS), and features derived from electroencephalography (EEG), arousals, and sleep stages from 3,407 sleep clinic patients (2,617 without insomnia and 790 insomnia patients based on responses to a set of questions) were included in this analysis. The number of features were reduced using pair-wise correlation and recursive feature elimination. Predictive value of three machine learning models (logistic regression, neural network, and support vector machine) was investigated, and the best performance was achieved with logistic regression, yielding a balanced accuracy of 71%. The most important features in predicting insomnia were depression, age, sex, duration of longest arousal, ESS score, and EEG power in theta and sigma bands across all sleep stages. Results indicate potential of machine learning-based screening for insomnia using clinical variables and EEG.

FASDetect as a machine learning-based screening app for FASD in youth with ADHD

Fetal alcohol-spectrum disorder (FASD) is underdiagnosed and often misdiagnosed as attention-deficit/hyperactivity disorder (ADHD). Here, we develop a screening tool for FASD in youth with ADHD symptoms. To develop the prediction model, medical record data from a German University outpatient unit are assessed including 275 patients aged 0–19 years old with FASD with or without ADHD and 170 patients with ADHD without FASD aged 0–19 years old. We train 6 machine learning models based on 13 selected variables and evaluate their performance. Random forest models yield the best prediction models with a cross-validated AUC of 0.92 (95% confidence interval [0.84, 0.99]). Follow-up analyses indicate that a random forest model with 6 variables – body length and head circumference at birth, IQ, socially intrusive behaviour, poor memory and sleep disturbance – yields equivalent predictive accuracy. We implement the prediction model in a web-based app called FASDetect – a user-friendly, clinically scalable FASD risk calculator that is freely available at https://fasdetect.dhc-lab.hpi.de.

Machine Learning Approach for Screening Cochlear Implant Candidates: Comparing With the 60/60 Guideline.

To develop a machine learning-based referral guideline for patients undergoing cochlear implant candidacy evaluation (CICE) and to compare with the widely used 60/60 guideline. Retrospective cohort. Tertiary referral center. 772 adults undergoing CICE from 2015 to 2020. Variables included demographics, unaided thresholds, and word recognition score. A random forest classification model was trained on patients undergoing CICE, and bootstrap cross-validation was used to assess the modeling approach's performance. The machine learning-based referral tool was evaluated against the 60/60 guideline based on ability to identify CI candidates under traditional and expanded criteria. Of 587 patients with complete data, 563 (96%) met candidacy at our center, and the 60/60 guideline identified 512 (87%) patients. In the random forest model, word recognition score; thresholds at 3000, 2000, and 125; and age at CICE had the largest impact on candidacy (mean decrease in Gini coefficient, 2.83, 1.60, 1.20, 1.17, and 1.16, respectively). The 60/60 guideline had a sensitivity of 0.91, a specificity of 0.42, and an accuracy of 0.89 (95% confidence interval, 0.86-0.91). The random forest model obtained higher sensitivity (0.96), specificity (1.00), and accuracy (0.96; 95% confidence interval, 0.95-0.98). Across 1,000 bootstrapped iterations, the model yielded a median sensitivity of 0.92 (interquartile range [IQR], 0.85-0.98), specificity of 1.00 (IQR, 0.88-1.00), accuracy of 0.93 (IQR, 0.85-0.97), and area under the curve of 0.96 (IQR, 0.93-0.98). A novel machine learning-based screening model is highly sensitive, specific, and accurate in predicting CI candidacy. Bootstrapping confirmed that this approach is potentially generalizable with consistent results.

A novel machine learning-based screening identifies statins as inhibitors of the calcium pump SERCA

We report a novel small-molecule screening approach that combines data augmentation and machine learning to identify Food and Drug Administration (FDA)-approved drugs interacting with the calcium pump (Sarcoplasmic reticulum Ca2+-ATPase, SERCA) from skeletal (SERCA1a) and cardiac (SERCA2a) muscle. This approach uses information about small-molecule effectors to map and probe the chemical space of pharmacological targets, thus allowing to screen with high precision large databases of small molecules, including approved and investigational drugs. We chose SERCA because it plays a major role in the excitation-contraction-relaxation cycle in muscle and it represents a major target in both skeletal and cardiac muscle. The machine learning model predicted that SERCA1a and SERCA2a are pharmacological targets for seven statins, a group of FDA-approved 3-hydroxy-3-methylglutaryl coenzyme A reductase inhibitors used in the clinic as lipid-lowering medications. We validated the machine learning predictions by using invitro ATPase assays to show that several FDA-approved statins are partial inhibitors of SERCA1a and SERCA2a. Complementary atomistic simulations predict that these drugs bind to two different allosteric sites of the pump. Our findings suggest that SERCA-mediated Ca2+ transport may be targeted by some statins (e.g., atorvastatin), thus providing a molecular pathway to explain statin-associated toxicity reported in the literature. These studies show the applicability of data augmentation and machine learning-based screening as a general platform for the identification of off-target interactions and the applicability of this approach extends to drug discovery.

Machine learning-based screening for biomarkers of psoriasis and immune cell infiltration

Machine learning-based screening for biomarkers of psoriasis and immune cell infiltration

Machine Learning-Based Screening of Risk Factors and Prediction of Deep Vein Thrombosis and Pulmonary Embolism After Hip Arthroplasty.

Prophylactic anticoagulation is a standard strategy for patients undergoing total hip arthroplasty (THA) to prevent deep venous thromboembolism (DVT) and pulmonary embolism (PE). Nevertheless, some patients still experience these complications during their hospital stay. Current risk assessment methods like the Caprini and Geneva scores are not specifically designed for THA and may not accurately predict DVT or PE postoperatively. This study used machine learning techniques to establish models for early diagnosis of DVT and PE in patients undergoing THA. Data were collected from 1481 patients who received perioperative prophylactic anticoagulation. Model establishment and parameter tuning were performed using a training set and evaluated using a test set. Among the models, extreme gradient boosting (XGBoost) performed the best, with an area under the receiver operating characteristic curve (AUC) of 0.982, sensitivity of 0.913, and specificity of 0.998. The main features used in the XGBoost model were direct and indirect bilirubin, partial activation prothrombin time, prealbumin, creatinine, D-dimer, and C-reactive protein. Shapley Additive Explanations analysis was conducted to further analyze these features. This study presents a model for early diagnosis DVT or PE after THA and demonstrates bilirubin could be a potential predictor in the assessment of DVT or PE. Compared to traditional risk assessment, XGBoost has a high sensitivity and specificity to predict DVT and PE in the clinical setting. Furthermore, the results of this study were converted into a web calculator that can be used in clinical practice.

Machine Learning-Based Models with High Accuracy and Broad Applicability Domains for Screening PMT/vPvM Substances.

Persistent, mobile, and toxic (PMT) substances and very persistent and very mobile (vPvM) substances can transport over long distances from various sources, increasing the public health risk. A rapid and high-throughput screening of PMT/vPvM substances is thus warranted to the risk prevention and mitigation measures. Herein, we construct a machine learning-based screening system integrated with five models for high-throughput classification of PMT/vPvM substances. The models are constructed with 44 971 substances by conventional learning, deep learning, and ensemble learning algorithms, among which, LightGBM and XGBoost outperform other algorithms with metrics exceeding 0.900. Good model interpretability is achieved through the number of free halogen atoms (fr_halogen) and the logarithm of partition coefficient (MolLogP) as the two most critical molecular descriptors representing the persistence and mobility of substances, respectively. Our screening system exhibits a great generalization capability with area under the receiver operating characteristic curve (AUROC) above 0.951 and is successfully applied to the persistent organic pollutants (POPs), prioritized PMT/vPvM substances, and pesticides. The screening system constructed in this study can serve as an efficient and reliable tool for high-throughput risk assessment and the prioritization of managing emerging contaminants.

Machine Learning-Based Screening and Measurement to Measurement Association for Navigation in GNSS Spoofing Environment

Global navigation satellite system (GNSS) provides reliable positioning across the globe. However, GNSS is vulnerable to deliberate interference problem like spoofing, which can cause fake navigation. This article proposes navigation in a GNSS spoofing environment by taking the received power, correlation distortion function, and pseudorange measurement observation space into account. In the proposed approach, both actual and interference measurements are considered a set. Machine learning screens the authentic measurements from the accessible set using parameters such as received power and correlation function distortion. To maintain the track and navigate the GNSS’s time-varying kinematics, we used a combination of the gating technique within the Kalman filter framework and logic-based track management. The machine learning classifiers like support vector machines (SVMs), neural networks (NNs), ensemble, nearest neighbor, and decision trees are explored, and we observe that linear SVM and NN provide a test accuracy of 98.20%. A time-varying position-pull off strategy is considered, and the metrics like position RMSE and track failure are compared with the conventional M-best algorithm. The results show that for four authentic measurements and spoof injections, there are only a few track failures. In contrast, even with an increase in spoof injections, track failures are zero in the case of six authentic measurements.

Development of a Machine Learning-Based Screening Method for Thyroid Nodules Classification by Solving the Imbalance Challenge in Thyroid Nodules Data.

This study aims to show the impact of imbalanced data and the typical evaluation methods in developing and misleading assessments of machine learning-based models for preoperative thyroid nodules screening. A retrospective study. The ultrasonography features for 431 thyroid nodules cases were extracted from medical records of 313 patients in Babol, Iran. Since thyroid nodules are commonly benign, the relevant data are usually unbalanced in classes. It can lead to the bias of learning models toward the majority class. To solve it, a hybrid resampling method called the Smote-was used to creating balance data. Following that, the support vector classification (SVC) algorithm was trained by balance and unbalanced datasets as Models 2 and 3, respectively, in Python language programming. Their performance was then compared with the logistic regression model as Model 1 that fitted traditionally. The prevalence of malignant nodules was obtained at 14% (n = 61). In addition, 87% of the patients in this study were women. However, there was no difference in the prevalence of malignancy for gender. Furthermore, the accuracy, area under the curve, and geometric mean values were estimated at 92.1%, 93.2%, and 76.8% for Model 1, 91.3%, 93%, and 77.6% for Model 2, and finally, 91%, 92.6% and 84.2% for Model 3, respectively. Similarly, the results identified Micro calcification, Taller than wide shape, as well as lack of ISO and hyperechogenicity features as the most effective malignant variables. Paying attention to data challenges, such as data imbalances, and using proper criteria measures can improve the performance of machine learning models for preoperative thyroid nodules screening.

Machine learning-based screening of an epithelial-mesenchymal transition-related long non-coding RNA signature reveals lower-grade glioma prognosis and the tumor microenvironment and predicts antitumor therapy response.

Epithelial-mesenchymal transition (EMT) confers high invasive and migratory capacity to cancer cells, which limits the effectiveness of tumor therapy. Long non-coding RNAs (lncRNAs) can regulate the dynamic process of EMT at different levels through various complex regulatory networks. We aimed to comprehensively analyze and screen EMT-related lncRNAs to characterize lower-grade glioma (LGG) tumor biology and provide new ideas for current therapeutic approaches. We retrieved 1065 LGG samples from the Cancer Genome Atlas and Chinese Glioma Genome Atlas by machine learning algorithms, identified three hub lncRNAs including CRNDE, LINC00665, and NEAT1, and established an EMT-related lncRNA signature (EMTrLS). This novel signature had strong prognostic value and potential clinical significance. EMTrLS described LGG genomic alterations and clinical features including gene mutations, tumor mutational burden, World Health Organization (WHO) grade, IDH status, and 1p/19q status. Notably, stratified analysis revealed activation of malignancy-related and metabolic pathways in the EMTrLS-high cohort. Moreover, the population with increased EMTrLS scores had increased cells with immune killing function. However, this antitumor immune function may be suppressed by increased Tregs and macrophages. Meanwhile, the relatively high expression of immune checkpoints explained the immunosuppressive state of patients with high EMTrLS scores. Importantly, we validated this result by quantifying the course of antitumor immunity. In particular, EMTrLS stratification enabled assessment of the responsiveness of LGG to chemotherapeutic drug efficacy and PD1 blockade. In conclusion, our findings complement the foundation of molecular studies of LGG, provide valuable insight into our understanding of EMT-related lncRNAs, and offer new strategies for LGG therapy.

Machine learning-based screening of MCF-7 human breast cancer cells and molecular docking analysis of essential oils from Ocimum basilicum against breast cancer

A machine learning algorithm-based model is a powerful tool for discovering candidate compounds on the breast cancer cell line MCF-7. Using the Lazy Predict Python package, the “Random Forest” algorithm indicates that the highest accuracy is 83.57% in discovering potential compounds. Essential oils from the leaves and stems of Ocimum basilicum, as identified by GC−MS analysis, are selected as a test dataset. Among them, eight essential oils, including alpha-pinene, trans-beta-ocimene, estragole, alpha-cubebene, gamma-muurolene, delta-cadinol, gamma-cadinene, and beta-ocimene potentially exhibit activity against MCF-7. The anticancer mechanisms of these essential oils are analyzed using molecular docking simulation based on the structure-activity relationship between these candidates and the two protein targets, BRCA1 and BRCA2. This study shows that our model can potentially screen bioactive compounds targeting breast cancer cell line MCF-7 and offer the basis for further research into substances derived from Ocimum basilicum that can potentially be utilized as a novel treatment for breast cancer.

The Impact of Carbon Capture Storage and Utilization on Energy Efficiency, Sustainability, and Production of an Offshore Platform: Thermodynamic and Sensitivity Analyses

Abstract Oil and gas production in FPSOs (floating, production, storage, and offloading) faces a dual challenge: meeting variation in energy demand while decreasing its negative environmental impact. The present article integrates thermodynamic analysis of oil and gas processing plants and screening analysis to determine the most important operational parameters to lower energy demand and increase efficiency and production. Therefore, the main goals of this study are to identify the contribution of the total effect of the operating parameters in an FPSO with CCUS (CO2 capture, utilization, and storage). Twenty-seven thermodynamic and structural design variables are selected as input parameters for the sensitivity analyses. Four machine learning-based screening analysis algorithms such as smooth spline-analysis of variance (SS-ANOVA), PAWN, gradient boosting machine (GBM), and Morris are adapted to achieve the following objectives: (1) overall power consumption of FPSO, (2) CO2 removal efficiency of carbon capture and storage (CCS), (3) power consumption of CCS, and (4) total oil production. The influence of three real crude oil compositions with variations in gas–oil ratio (GOR) and CO2 content is assessed. The combination of thermodynamic and screening analyses showed that the optimal operating pressure parameters of CCS significantly reduce the energy consumption and exergy destruction of the key main and utility plants. Furthermore, the results indicated that total power consumption, CCS efficiency, and CCS power consumption are much more sensitive to the CO2 content of the fluid reservoir than GOR, while the total oil production is influenced only by the GOR content. Finally, for scenarios with high CO2 or GOR content, the effect of design variable interactions is decisive in changing the separation efficiency and/or the compression unit performance.