ML Models Research Articles

Identification of four novel acute‐on‐chronic liver failure clusters with distinct clinical trajectories and mortality using machine learning methods

SummaryBackground and AimsMachine learning (ML) can identify the hidden patterns without hypothesis in heterogeneous diseases like acute‐on‐chronic live failure (ACLF). We employed ML to describe and predict yet unknown clusters in ACLF.MethodsClinical data of 1568 patients with ACLF from a tertiary care centre (2015–2023) were subjected to distance‐, density‐ and model‐based clustering algorithms. Final model was selected on best cluster separation, viz. Silhouette width and Dunn's index (for distance‐ or density‐based algorithms) and minimum BIC (for model‐based algorithms). Cluster assignments, patient trajectories and survival were analysed through inferential statistics. Supervised ML models were trained in 70% data that predicted clusters in remaining 30% data followed by an temporal validation.ResultsThe cohort was male‐predominant (87%), aged 44.3 years, with alcohol‐associated hepatitis (62.9%) and survival of 50.5%. Due to poor performance of distance‐ and density‐based algorithms and better explainability, the latent class model (LCM) was selected for exploration. LCM revealed four clusters with distinct trajectories, reversibility and survival (independent of MELD, CLIF‐C ACLF and AARC scores). Cluster1 had patients with none/one organ failure and highest reversibility. Cluster2 had females with viral hepatitis and two organ failures. More‐than‐one acute precipitant, severity, infections, organ failures and irreversibility escalated from clusters 1 to 4. Circulatory and renal failures critically influenced cluster assignments. Incorporating clusters to CLIF‐C ACLF, infection and ACLF definition improved the discriminative accuracy of CLIF‐C‐ACLF by 11%. Extreme gradient boost and decision trees could predict clusters with AUCs of 0.989 (0.979–0.995) and 0.875 (0.865–0.890). MELD, CLIF‐C‐OF, haemoglobin, lactate, CLIF‐C‐ACLF and ALT were critical variables for cluster prediction. Clusters with distinct survival were documented in a temporal validation cohort.ConclusionsML for the first time could identify clusters with distinct phenotypes, trajectories and outcomes in ACLF. Stratification into clusters can address heterogeneity, guide prognosis, recruitment in trials, resource allocation and liver transplant discussions in ACLF.

Numerical and machine learning models for concentrically and eccentrically loaded CFST columns confined with FRP wraps

AbstractPrevious research largely concentrated on predicting load‐carrying capacities of concrete‐filled steel tubes (CFST) confined with fiber‐reinforced polymer (FRP) wraps under pure concentric loads, neglecting the more complex failure mechanisms that occur under real‐life eccentric loading conditions. This study, therefore, employs both finite element modeling (FEM) and machine learning methods to accurately predict the load‐bearing capacities under both concentric and eccentric loading conditions. This research analyzed a comprehensive dataset comprising 128 experimental tests and an equivalent number of FEM simulations designed to evaluate their eccentric performance. These models have been thoroughly generated and validated against existing literature. Additionally, the developed ML models, particularly a hybrid deep learning model, demonstrated significant predictive accuracy, with an average R2 value of 0.969 across all model folds. Partial dependence analysis further highlighted the significant influence of concrete strength and the interactive effects of steel tube area and FRP wrap thickness on the load‐carrying capacity of the columns. Furthermore, to enhance cost‐efficiency and resource management compared with traditional laboratory testing, a user‐friendly graphical user interface (GUI) has been developed and hosted on an open‐source platform such as GitHub. This interface supports real‐time, precise predictive capabilities and promotes a collaborative environment for ongoing model refinement and improvement.

Abstract C017: Race-Specific Patterns of Vaginal Microbiome and HPV Infections Predict Risk of Precancerous Cervical Lesions

Abstract Background: Our previous research indicated that high-grade squamous intraepithelial lesions (HSIL), precursors to cervical cancer (CCa), are influenced by the vaginal microbiome (VMB) differentially by self-reported race. VMB enriched for certain anti-inflammatory Lactobacillus species confer protection against the risk of HSIL for white, but not Black women. Black women exhibit greater VMB diversity (associated with HPV tumorigenesis) and a lower prevalence of anti-inflammatory Lactobacillus species. But not all Black women with diverse VMB develop HSIL. Objective: Given HPV's essential role in cervical cancer, we aimed to assess the influence of sociodemographic, clinical, and microecological HPV attributes on HSIL risk within the context of the vaginal microbiome's variation by race. Methods: The VMB and HPV profiles of 1,168 women were analyzed alongside over 100 sociodemographic and clinical variables. Spearman’s correlation, Point-Biserial Correlation, chi-squared tests, and machine learning models, were employed to evaluate associations between sociodemographic, clinical, and microecological variables with HSIL, with a particular focus on the impact of race on these relationships. Results: The cohort was predominantly Black (72%), showing no significant race-based differences in HPV positivity (45%). However, HSIL incidence was nearly twice as high in Black (7%) compared to White women (4%). Women with HSIL had a higher prevalence of non-Lactobacillus-dominant VMB (68% vs. 51%) and were more likely to be HPV+ (73% vs. 44%) than those without HSIL. Co-infection with multiple HPV strains was associated with a higher risk of CIN3. Specifically, HPV16, HPV56, HPV58, HPV33, and HPV42 infections were significantly associated with higher CIN3 risks. The random forest model identified the relative abundance of Lactobacillus crispatus as the most essential factor in predicting CIN3 risk, followed by the number of HPV strains per sample. However, differential abundance analysis specifically indicated lower L. crispatus levels were associated with HSIL in white but not Black women. Conversely, HPV abundance was only associated with HSIL in Black women. Additionally, Black patients with 2 or more HPV co-infections had a higher likelihood of being diagnosed with CIN3+ compared to white counterparts. ML models highlighted different HPV-specific HSIL predictors by race: HPV number, and HPV 56, 16, and 33 in Blacks; sexual partners, HPV 90, 56, and 16 in whites. Conclusions: Our findings reveal race-specific interplays among individual risk factors, HPV infection, and VMB composition in HSIL development. The identification of key microbial and viral predictors highlights the importance of personalized approaches in preventing and managing HSIL, particularly among racially diverse populations. Citation Format: Katherine Y. Tossas, Bin Zhu, Katarzyna Tyc, Myrna Serrano, Jerome Strauss, Gregory Buck. Race-Specific Patterns of Vaginal Microbiome and HPV Infections Predict Risk of Precancerous Cervical Lesions [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr C017.

Explainable ensemble learning graphical user interface for predicting rebar bond strength and failure mode in recycled coarse aggregate concrete

Novel study deploys robust machine learning algorithms using newly built comprehensive dataset to predict reinforcing rebar-to-recycled coarse aggregate concrete (RCA) bond strength and failure mode. Prior investigations have solely concentrated on bond strength, resulting in a limited comprehension of the bond failure pattern. Considering the increasing significance of sustainable construction methods, it is crucial to examine both the failure pattern and bond strength to expand the versatility of RCA in various reinforced concrete structures. Accordingly, XGBoost, CatBoost, Random Forest, and LightGBM were trained for this purpose. Model performance was appraised using various statistical metrics, while failure classification performance was assessed using accuracy, recall, and precision indicators. Model performance was ranked using Copeland's algorithm. Feature importance was quantified using SHAP. Coefficient of determination of 0.91 was achieved by XGBoost in predicting bond strength, outperforming other nine analytical models in literature. Failure mode was predicted with accuracy of 94% by CatBoost, XGBoost, and LightGBM. Embedment length and compressive strength features had greatest influence on bond strength and failure mode, respectively. User-friendly graphical interface was developed to harvest ML models in real-world engineering practice. Online free access accurately assigns to any given combination of input features corresponding accurate rebar bond strength and failure mode.

Influence of Preprocessing Methods of Automated Milking Systems Data on Prediction of Mastitis with Machine Learning Models

Missing data and class imbalance hinder the accurate prediction of rare events such as dairy mastitis. Resampling and imputation are employed to handle these problems. These methods are often used arbitrarily, despite their profound impact on prediction due to changes caused to the data structure. We hypothesize that their use affects the performance of ML models fitted to automated milking systems (AMSs) data for mastitis prediction. We compare three imputations—simple imputer (SI), multiple imputer (MICE) and linear interpolation (LI)—and three resampling techniques: Synthetic Minority Oversampling Technique (SMOTE), Support Vector Machine SMOTE (SVMSMOTE) and SMOTE with Edited Nearest Neighbors (SMOTEEN). The classifiers were logistic regression (LR), multilayer perceptron (MLP), decision tree (DT) and random forest (RF). We evaluated them with various metrics and compared models with the kappa score. A complete case analysis fitted the RF (0.78) better than other models, for which SI performed best. The DT, RF, and MLP performed better with SVMSMOTE. The RF, DT and MLP had the overall best performance, contributed by imputation or resampling (SMOTE and SVMSMOTE). We recommend carefully selecting resampling and imputation techniques and comparing them with complete cases before deciding on the preprocessing approach used to test AMS data with ML models.

Reliability-Based Design for Strip-Footing Subjected to Inclined Loading Using Hybrid LSSVM ML Models

Reliability-Based Design for Strip-Footing Subjected to Inclined Loading Using Hybrid LSSVM ML Models

Image recommendation for social media marketing in maternity and baby care product industry – a machine learning approach

PurposeThe digital marketing landscape is rapidly evolving, but the integration of visual content still heavily depends on human expertise. Driven by the quest for innovative marketing strategies that resonate with family-oriented consumers, this study seeks to bridge this gap by applying machine learning to analyze visual content in the maternity and baby care product sector.Design/methodology/approachThis study incorporates a range of machine learning techniques – including open science framework feature detection, panoptic segmentation, customized instance segmentation, and face detection calculation methods – to analyze and predict the appeal of images, thereby enhancing user engagement and parent-child intimacy.FindingsThe exploration of various ML models, such as DT, LightGBM, RIPPER algorithm, and CNNs, has offered a comparative analysis that addresses a methodological gap in the existing literature, which frequently depends on isolated model evaluations. According to our quadrant analysis with respect to engagement rate and parent-child intimacy, the selection of a model for real-world applications depends on balancing performance and interpretability.Originality/valueThe proposed system offers a series of actionable recommendations designed to enhance customer engagement and foster brand loyalty. This study contributes to image design in maternity and baby care marketing and provides analytical insights for recommendation systems.

Machine learning prediction of dye adsorption by hydrochar: Parameter optimization and experimental validation

In response to escalating global wastewater issues, particularly from dye contaminants, many studies have begun using hydrochar to adsorb dye from wastewater. However, the relationship between the preparation conditions of hydrochar, the properties of hydrochar, experimental conditions, types of dyes, and equilibrium adsorption capacity (Q) has not yet been fully explored. This study conducted a comprehensive assessment using twelve distinct ML models. The Gradient Boosting Regressor (GBR) model exhibited superior performance with R² (0.9629) and RMSE (0.1166) in the test dataset, marking it as the most effective among the evaluated models. Moreover, this study also proved the feasibility of the GBR model through stability testing and residual analysis. A feature importance analysis prioritized the variables as follows: experimental conditions (41.5 %), properties of hydrochar (26.0 %), preparation conditions (18.1 %), and type of dye (14.4 %). Meanwhile, experimental conditions (C0 > 30 mmol/g, pH > 8, and higher solvent temperatures) and hydrochar properties (the BET surface area > 2000 m²/g, an (O+N)/C molar ratio < 0.6, and an H/C molar ratio of approximately 0.06) show higher Q for dyes. Experimental validation of the GBR model confirmed its practical utility with a suitable predictive accuracy (R² = 0.8704). Moreover, the study developed a Python-based GUI that has integrated the best GBR models to facilitate researchers' ongoing application and improvement of this predictive model. This study not only underscores the efficacy of ML in enhancing the understanding of dye adsorption by hydrochar but also sets a precedent for future research on sustainable contaminants removal through bio-based adsorbents.

Explainable artificial intelligence models for predicting pregnancy termination among reproductive-aged women in six east African countries: machine learning approach

Pregnancy termination remains a complex and sensitive issue with approximately 45% of abortions worldwide being unsafe, and 97% of abortions occurring in developing countries. Unsafe pregnancy terminations have implications for women’s reproductive health. This research aims to compare black box models in their prediction of pregnancy termination among reproductive-aged women and identify factors associated with pregnancy termination using explainable artificial intelligence (XAI) methods. We used comprehensive secondary data on reproductive-aged women’s demographic and socioeconomic data from the Demographic Health Survey (DHS) from six countries in East Africa in the analysis. This study implemented five black box ML models, Bagging classifier, Random Forest, Extreme Gradient Boosting (XGB) Classifier, CatBoost Classifier, and Extra Trees Classifier on a dataset with 338,904 instances and 18 features. Additionally, SHAP, Eli5, and LIME XAI techniques were used to determine features associated with pregnancy termination and Statistical analysis were employed to understand the distribution of pregnancy termination. The results demonstrated that machine learning algorithms were able to predict pregnancy termination on DHS data with an overall accuracy ranging from 79.4 to 85.6%. The ML classifier random forest achieved the highest result, with an accuracy of 85.6%. Based on the results of the XAI tool, the most contributing factors for pregnancy termination are wealth index, current working experience, and source of drinking water, sex of household, education level, and marital status. The outcomes of this study using random forest is expected to significantly contribute to the field of reproductive healthcare in East Africa and can assist healthcare providers in identifying individuals’ countries at greater risk of pregnancy termination, allowing for targeted interventions and support.

Improving soil moisture prediction with deep learning and machine learning models

Reliable soil moisture (SM) data is critical for effective water resources management, yet its accurate measurement and prediction remain challenging. This study was conducted to develop a deep learning regression network for sub-hourly SM prediction and compare its performance with traditional machine learning models, including the eXtreme gradient boosting (XGB), light gradient-boosting (LGB), cat boosting (CB), random forest (RF), k-nearest neighbors (kNN), and long short-term memory (LSTM) models. Sub-hourly SM, electrical conductivity (EC), soil temperature (ST), and weather parameters were collected during research experiments conducted for two years (2020–2021 and 2021–2022) at the Tropical Research and Education Center (TREC), University of Florida. A network of SM sensors and a weather station were installed at the experimental site with 24 plots of green beans and sweet corn under full and three deficit irrigation treatments with three replications. Model performance metrics such as coefficient of determination (r2) and global performance indicator (GPI) were used to evaluate the performance of the models. Results showed that all MLs and DL models performed more than satisfactorily in simulating SM of green beans and sweet corn plots. The testing average r2 and GPI of MLs were 0.83 and 0.02 (green beans) and 0.85 and 0.02 (sweet corn). However, XGB and LGB models outperformed the remaining ML and DL models. The testing r2 and GPI of XGB were 0.86 and 0.014 for green beans, whereas 0.88 and 0.015 for sweet corn. The r2 and GPI values for the LGB were 0.85 and 0.014 for green beans, while 0.88 and 0.015 for sweet corn. Even though DL model took longer and resources to be trained, its performance was not as accurate as that of XGB and LGB models. However, the performance of DL was better than the LSTM model. The r2 and RMSE of the LSTM model were 0.68 and 0.02cm 3 cm-3 for green beans and 0.75 and 0.02cm 3 cm-3 for sweet corn, respectively. Whereas the r2 and RMSE of DL were 0.84 and 0.015cm 3 cm-3 (green beans) and 0.85 and 0.02 cm 3 cm-3 (sweet corn). The ML and DL models performed better in simulating SM of sweet corn plots than green beans. Overall, these results confirmed that the ML and DL models could be alternative tools for SM prediction for agricultural fields, with potential applications for irrigation scheduling and water resources management.

Modeling health outcomes of air pollution in the Middle East by using support vector machines and neural networks

This study investigates the impact of air pollution on health outcomes in Middle Eastern countries, a region facing severe environmental challenges. As such, these are important in an effort to add up to policy-level as well as interventional changes that can be put in practice in the area of public health. Numeration analysis and association with health parameters was carried out by using Analytical tools such as, AIR Data, ARIMA,ANN, SVM and Exponential smoothing. Amongst the models, Support Vector Machine came again on top, with high accuracy yielding Mean Absolute Percentage Error of approximately 1%. Mortality of Air pollution in Qat from the case of Mortality of Air Pollution in Qatar is 959 while Auto regressive Integrated Moving average is 11.096, Exponential Smoothing 9.892 and Artificial Neural Networks are the source of inspiration for the development of this paper 4.61. The above perceptions indicate that there is need to adapt modeling strategies depending on the context and establish that it is possible to implement ML models in public health planning basket. This paper publishes the methodological frameworks for the purpose of modeling and analysis of the EHDs and serves as policy prescription for the policy makers to intending to reduce the effects of air borne pollution on health.

Prediction and optimization framework of shear strength of reinforced concrete flanged shear wall based on machine learning and non-dominated sorting genetic algorithm-II

Reinforced concrete (RC) flanged shear wall has good lateral strength and stiffness, which has been widely used in building structures. Due to the coupling effect of many factors such as wall section shape, shear span ratio, so the shear performance evaluation of flanged wall is still very limited. This paper proposed a prediction framework for the shear capacity of RC flanged shear walls. A database containing 14 input variables, 1 output variable and 153 samples was constructed to evaluate the prediction accuracy of 11 existing design methods. The Pearson coefficient was used to preliminarily analyze the correlation between variables. The grid search was used to optimize the hyperparameters of 4 machine learning models, and six statistical indicators ( R2, R, RMSE, SD, MAE, and MAPE) were used to comprehensively compare the prediction results of the ML models to determine the best model. On this basis, SHapley Additive exPlanations (SHAP) was used to enhance the interpretability of the prediction models, and the mechanism of the input variables on the shear capacity was quantified. A graphical user interface (GUI) was proposed to guide the engineering design. A multi-objective model (MOO) was established to analyze the trade-off between shear performance and cost, thereby determining the best optimal scheme. The results show that the prediction accuracy of the ML models is better than the existing design methods. The XGB model has the best prediction performance, with R2, R, RMSE are 0.99, 0.99, 118.96, respectively. The SHAP method can effectively enhance the interpretability of the ML models, and tw, lw and f ′c are the key parameters affecting the shear capacity of the flanged shear wall.

Harnessing Machine Learning to Predict Methadone Overdose Risk: Insights from Illinois's SUDORS Data

Knowledge of decedent characteristics associated with methadone involvement in unintentional drug overdose deaths can help to inform efforts to intervene in these deaths. ML models with existing data, offer a cost-effective means to help create effective interventions. In this study, we aim to develop an optimized ML algorithm for predicting overdose death patterns due to methadone using data from Illinois's State Unintentional Drug Overdose Reporting System (SUDORS). We utilized IL SUDORS 2019-2022 data for training (n = 11931) with selected indicators (n = 28). To address the imbalance in non-methadone-related deaths, we applied the Synthetic Minority Oversampling Technique. Next, we assessed various machine learning models, including logistic regression, support vector machine, random forest, neural network, and ridge regression. Model performance was evaluated using metrics such as accuracy, precision, area under the precision-recall curve (AUPRC), etc. Utilizing separate training (n = 15813), validation (n = 3388), and test (n = 3389) datasets, the Random Forest Model outperforms all other models with 92% accuracy, 91% precision, 93% recall, and 0.97 AUPRC. Notably, these outcomes were achieved using primarily demographic indicators. Through analyzing partial dependence plots, we were able to see how changes in each indicator dynamically influence methadone-related fatalities. This study demonstrates the potential of ML models in identification of methadone involvement in unintentional drug overdose deaths and contributes to the knowledge base for the prevention of these deaths. Leveraging SUDORS data, the Random Forest Model exhibited exceptional performance, highlighting its value for healthcare professionals, prevention and harm reduction specialists, and policymakers.

Prediction of poststroke independent walking using machine learning: a retrospective study

BackgroundAccurately predicting the walking independence of stroke patients is important. Our objective was to determine and compare the performance of logistic regression (LR) and three machine learning models (eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest (RF)) in predicting walking independence at discharge in stroke patients, as well as to explore the variables that predict prognosis.Methods778 (80% for the training set and 20% for the test set) stroke patients admitted to China Rehabilitation Research Center between February 2020 and January 2023 were retrospectively included. The training set was used for training models. The test set was used to validate and compare the performance of the four models in terms of area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.ResultsAmong the three ML models, the AUC of the XGBoost model is significantly higher than that of the SVM and RF models (P < 0.001, P = 0.024, respectively). There was no significant difference in the AUCs between the XGBoost model and the LR model (0.891 vs. 0.880, P = 0.560). The XGBoost model demonstrated superior accuracy (87.82% vs. 86.54%), sensitivity (50.00% vs. 39.39%), PPV (73.68% vs. 73.33%), NPV (89.78% vs. 87.94%), and F1 score (59.57% vs. 51.16%), with only slightly lower specificity (96.09% vs. 96.88%). Together, the XGBoost model and the stepwise LR model identified age, FMA-LE at admission, FAC at admission, and lower limb spasticity as key factors influencing independent walking.ConclusionOverall, the XGBoost model performed best in predicting independent walking after stroke. The XGBoost and LR models together confirm that age, admission FMA-LE, admission FAC, and lower extremity spasticity are the key factors influencing independent walking in stroke patients at hospital discharge.Trial registrationNot applicable.

An innovative method for improving rainfall prediction in Gujarat state through a fusion model DWT, 1DCNN and LSTM

In countries like India where agriculture is a major industry, accurate prediction of rainfall is crucial. The ability to forecast rainfall helps in planning crop cultivation and has a positive impact on both local and national economies. Nevertheless, conventional statistical techniques prove inadequate for forecasting precipitation over extended periods of time owing to the erratic characteristics inherent in climate phenomena. To address this issue, various ML models such as Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Discrete Wavelet Transform, have been explored for precipitation prediction. Large-scale data analysis and overcoming intricate challenges have become achievable through the utilization of deep learning, which has proven to be a potent approach. It combines the advantages of multiple methodologies and algorithms in order to develop accurate precipitation forecasting models. In this study, researchers treated rainfall time series as signals and used the Discrete Wavelet Transform method along with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network methods to analyze and reconstruct these signals. The research employed a dataset acquired from the Indian Meteorological Department and NASA, covering the years 1901 to 2022. This extensive collection comprised diverse meteorological parameters such as relative humidity, wet bulb temperature, Surface Pressure, soil dampness levels, relative humidity, temperatures (min and max), wind speed data in addition to rainfall records. The fusion of these three methods - DWT-CNN-LSTM deep model - consistently demonstrated excellent performance in key evaluation metrics such as MAE and RMSE. This approach achieved remarkable results in accurately predicting precipitation patterns for Gujarat State over the specified time period.

Analysis of 27 supervised machine learning models for the co-gasification assessment of peanut shell and spent tea residue in an open-core downdraft gasifier

The producer gas (PG) obtained through thermochemical processing of the various renewable biomass types contributes to Sustainable Development Goal-7 (SDG-7). Hence, this study examined 27 supervised and multiple-input single-output ML models in terms of performance metrics and accuracy to predict CO, H2, CH4, and CO2 compositions, as well as PG's HHV in the co-gasification of peanut shell (PS) and spent tea residue (STR). Multiple trial experiments were tested with various equivalence ratios (ERs) and mixing ratios (MRs) on a 90 m3/h gas-yield open-core, down-draft gasifier with air as the gasification medium. About 18 models were chosen after evaluating their performance metrics in estimating relevant parameters. The accuracy of those models is assessed based on 12 sample runs with varying ER and MR. The findings revealed that 16 models from the linear, neural network, support vector machine, Gaussian process, tree, and ensemble categories were reliable ML models. The chosen 16 models' R2 values for CO, H2, CH4, CO2, and HHVPG are above 0.931, 0.937, 0.962, 0.806, and 0.971, respectively, with the exception of TRE. Additionally, the models demonstrated a prediction accuracy of >95 % for all of the investigated parameters in the co-gasification of PS and STR when compared to random experimental runs.

Multi-property prediction and high-throughput screening of polyimides: An application case for interpretable machine learning

Polyimide (PI), as a high-performance polymer widely used in aerospace, optoelectronics, microelectronics, etc., the properties it focused on in different areas of application were diverse. However, most of the past machine learning studies in polyimide property prediction were focused only on the prediction of a single property. This study focused on four major categories of properties of polyimide, including thermal (Tg, Td5, Td10, and CTE), mechanical (Ts and TM), dielectric (ε), and optical (λcutoff, T400, nav, and Δn), totaling eleven properties. PI data synthesized from previous studies were collected. MorGan fingerprints, improved MorGan fingerprints, RDkit and Mordred descriptors were selected as feature representations. Four ML models such as DNN, RF, XGBoost and BT were also built. Collectively, 176 machine learning models were trained for 11 predictions of properties. The performance and generalization ability of the models were confirmed by experimental validation, external validation and leave-one-out cross-validation. SHAP analysis was used to explain the optimal model for each property prediction from a physicochemical point of view and structural aspects, and three PIs with different structures were designed accordingly. Finally, a high-throughput virtual screening of nearly 7.6 million polyimides was performed based on the trained model. SA_scores was used to evaluate the ease of synthesis of each PI, and finally high-performance PIs with potential and easy to synthesize were selected for each field. This study could be expected to provide a guideline and a design framework for the application of PIs in various fields in the future.

Lifestyle Profiling Using Wearables and Prediction of Glucose Metabolism in Individuals with Normoglycemia or Prediabetes.

This study examined the relationship between lifestyles (diet, sleep, and physical activity) and glucose responses at a personal level. 36 healthy adults in the Bay Area were monitored for their lifestyles and glucose levels using wearables and continuous glucose monitoring (NCT03919877). Gold-standard metabolic tests were conducted to phenotype metabolic characteristics. Through the lifestyle data (2,307 meals, 1,809 nights, and 2,447 days) and 231,206 CGM readings from metabolically-phenotyped individuals with normoglycemia or prediabetes, we found: 1) eating timing was associated with hyperglycemia, muscle insulin resistance (IR), and incretin dysfunction, whereas nutrient intakes were not; 2) timing of increased activity in muscle IS and IR participants was associated with differential benefits of glucose control; 3) Integrated ML models using lifestyle factors predicted distinct metabolic characteristics (muscle, adipose IR or incretin dysfunction). Our data indicate the differential impact of lifestyles on glucose regulation among individuals with different metabolic phenotypes, highlighting the value of personalized lifestyle modifications.

On discovery of novel hub genes for ER+ and TN breast cancer types through RNA seq data analyses and classification models

Breast cancer (BC) is a malignant neoplasm which is classified into various types defined by underlying molecular factors such as estrogen receptor positive (ER+), progesterone receptor positive (PR+), human epidermal growth factor positive (HER2+) and triple negative (TNBC). Early detection of ER+ and TNBC is crucial in the choice of diagnosis and appropriate treatment strategy. Here we report the key genes associated to ER+ and TNBC using RNA-Seq analysis and machine learning models. Three ER+ and TNBC RNA seq datasets comprising 164 patients in-toto were selected for standard NGS hierarchical data processing and data analyses protocols. Enrichment pathway analysis and network analysis was done and finally top hub genes were identified. To come with a reliable classifier which could distinguish the distinct transcriptome patterns associated to ER+ and TNBC, ML models were built employing Naïve Bayes, SVM and kNN. 1730 common DEG’s exhibiting significant logFC values with 0.05 p-value threshold were identified. A list of top ten hub genes were screened on the basis of maximal clique centrality (MCC) which included CDC20, CDK1, BUB1, AURKA, CDCA8, RRM2, TTK, CENPF, CEP55 and NDC80.These genes were found to be involved in crucial cell cycle pathways. k-Nearest Neighbor (kNN) model was observed to be best classifier with accuracy 84%, specificity 66% and sensitivity 95% to differentiate between ER+ and TNBC RNA-Seq transcriptomes. Our screened list of 10 hub genes can thus help unearth novel molecular signatures implicated in ER+ and TNBC onset, prognosis and design of novel protocols for breast cancer diagnostics and therapeutics.

Enhanced Tobacco Yield Prediction Using Spatial Information and Exogenous Variable-driven Machine Learning Models

Remote sensing technology has been essential in studying the relationship between tobacco canopy spectral characteristics and biomass yield. This study has been conducted in Garnepudi, Andhra Pradesh, employed satellite imagery obtained between 2015 and 2023 to extract vegetation indices (VI’s). Accurately predicting yield is crucial for India's economy. This study investigates the efficacy of various predictive models for tobacco yield forecasting using multiple vegetation indices: Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Soil Adjusted Vegetation Index (SAVI), Modified Soil Adjusted Vegetation Index (MSAVI), Leaf Area Index (LAI) and Leaf Surface Water Index (LSWI). The models assessed include traditional parametric approaches (ARIMAX, MLR), machine learning techniques (ANN, SVR, RFR), and advanced ensemble methods like XGBoost. The results highlight XGBoost as the most accurate model, consistently delivering the lowest error metrics, including RMSE and MAE, across all vegetation indices. Specifically, XGBoost achieved the best performance with LAI showing RMSE of 86.657, MAE of 58.324, sMAPE of 14.354, MASE of 1.001, and QL of 29.162 respectively. They exhibited lower error metrics, as compare to the statistical and ML models underscoring their effectiveness and potential in tobacco yield prediction. This study highlights the significant role of remote sensing technology in capturing crop development patterns and accurately forecasting tobacco yield, thereby offering valuable insights for agricultural planning and decision-making. The study also addresses challenges such as data quality and model generalization, providing a comprehensive view of the research impact and future directions.