XGBoost Machine-learning Model Research Articles

Machine learning approach for detection of valvular heart disease through digital cardiac auscultation: results from multi-center prospective cross-sectional study

Abstract Background Cardiac auscultation, an essential bedside diagnostic tool, often identifies significant valvular heart disease through murmurs. However, its accuracy is contingent upon the clinician's expertise, leading to a growing dependence on expensive imaging techniques. This study aimed to develop and validate a machine learning model for detecting valvular heart disease from cardiac auscultation. Methods The digital cardiac auscultation and associated echocardiograms were prospectively collected from three sites between May 1, 2022, and Dec 31, 2022. We trained, validated, and externally tested a machine learning based model to classify aortic stenosis, mitral stenosis, aortic regurgitation, mitral regurgitation, tricuspid regurgitation, oveall valvular heart disease from cardiac auscultation, age, sex, and comorbidity. We condcted training, and internal testing using datasets for eXtreme Gradient Boosting (XGBoost) machine learning model from hospital one and hospital two. The dataset from hospital three was employed for external testing. We evaluated the area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), accuracy, sensitivity, specificity. Result We selected the cardiac auscultation and echocardiograms of a total of 4,321 patients, excluding those without valvular heart disease information, congenital heart disease, a history of valvular operation, and cardiac auscultation could not be interpreted. The diagnostic performance of heart murmurs for valvular heart disease across the three datasets generally demonstrated high sensitivity and PPV. Specifically, the sensitivity for aortic stenosis was 89.1%, mitral stenosis 88.8%, aortic regurgitation 88.5%, mitral regurgitation 89.8%, tricuspid regurgitation 90.1%, and for any valvular heart disease, it was 95.0%. However, the NPV was consistently lower, with values of 16.4%, 14.2%, 12.2%, 23.1%, 26.2%, and 65.3% for the respective conditions. In XGBoost machine learning model, the AUROC values for internal testing (N=1,403), along with their 95% confidence intervals, were as follows: aortic stenosis (0.93, 0.88–0.97), mitral stenosis (0.91, 0.81–0.97), aortic regurgitation (0.84, 0.79–0.90), mitral regurgitation (0.94, 0.90–0.98), tricuspid regurgitation (0.81, 0.75–0.87), and overall valvular heart disease (0.86, 0.82–0.89). For external testing (N=814), the AUROC values were: aortic stenosis (0.90, 0.83–0.96), mitral stenosis (0.88, 0.79–0.95), aortic regurgitation (0.94, 0.93–0.96), mitral regurgitation (0.93, 0.92–0.95), tricuspid regurgitation (0.89, 0.87–0.91), and overall valvular heart disease (0.92, 0.90–0.94). Conclusion The machine learning based model can accurately classify valvular heart diseases using information from digital cardiac auscultation.Figure 1.Study FlowFigure 2.AUC curve

Delta-CT radiomics based model for predicting postoperative anastomotic leakage following radical resection of esophageal squamous cell carcinoma.

To predict postoperative anastomotic leakage (AL) following radical resection of esophageal squamous cell carcinoma (ESCC) based on clinical data and preoperative enhanced Computed tomography(CT) radiomics of the esophagus. We retrospectively analyzed the clinicopathological and radiological data of 213 patients with ESCC who received radical resection at Xiangyang No.1 People's Hospital from July 2011 to February 2024. 3D slicer software was used in combination with Lasso extraction and 10-fold cross-validation to extract texture parameters from contrast-enhanced CT images and generate Delta-Radscores. Several models were built using logistic regression to predict postoperative AL in ESCC. In the training set, the univariate analysis confirmed that duration of surgery, surgical method, delta radscore 1, delta radscore 2, contrast enhancement patterns, peripheral lymph node metastasis, post thoracotomy pulmonary infection(PTPI), and hot pot were risk factors for ESCC-AL (P<0.05 for both). The multivariate analysis showed that delta radscore 1, delta radscore 2, PTPI, and hot pot were independent risk factors for AL (P<0.05 for all). These results were verified by the XGboost machine learning model. The combinational model based on all of the above risk factors [AUC 0.900, OR 0.0282, 95%CI 0.841-0.943] outperformed either the clinical model[AUC 0.759, OR 0.0392, 95%0.683-0.825,P<0.05] or the imaging model[AUC 0.869, OR 0.0335, 95%0.804-0.918,P=0.1277] alone in predictive efficacy. The decision curve proved that the combinational model had a higher clinical net benefit. The nomogram generated via the combinational model simplified the predictive process. The same predictions were verified in the testing set. Delta radscore 1, delta radscore 2, PTPI, and hot pot were related to ESCC-AL. The novel nomogram created using enhanced CT radiomics informed perioperative management and improved the survival quality of ESCC patients.

The Impact of AI Industry Growth on U.S. AI Sector Stocks: A Machine Learning Analysis

The rapid development of artificial intelligence (AI) since 2020 has significantly impacted the U.S. stock market, necessitating a deeper understanding of its influence on AI-related stocks. This study aims to analyze and predict the returns of the Global X Robotics &amp; Artificial Intelligence ETF (BOTZ) as a proxy for AI industry performance. Employing Random Forest and XGBoost machine learning models, we trained on over a thousand data points to forecast BOTZ ETF returns. Our research reveals that AI-focused stocks and ETFs have outperformed the broader market since 2020, driven by increased AI adoption across industries, substantial research and development investments, and shifting investor sentiment towards tech-centric portfolios. The machine learning models demonstrated promising results in capturing complex market dynamics and providing reliable predictions. This study underscores the potential of integrating machine learning with financial analysis, offering valuable insights for investors and stakeholders in navigating the evolving landscape of AI-influenced markets.

Artificial intelligence in prostate cancer: The potential of machine learning models and neural networks to predict biochemical recurrence after robot-assisted radical prostatectomy

ABSTRACT Introduction: This study aimed to evaluate the usefulness of machine learning (ML) and neural network (NN) models versus traditional statistical methods for estimating biochemical recurrence (BCR) in men following robot-assisted radical prostatectomy (RARP). Methods: Patients who underwent RARP from November 2011 to July 2022 were taken in the study. Patients with BCR were assigned to Group 2, whereas those without BCR were placed in Group 1. Preoperative and postoperative parameters, together with demographic data, were recorded in the database. This study used one NN, the radial basis function NN (RBFNN), and two ML approaches, the K-nearest neighbor and XGboost ML models, to predict BCR. Results: Following the application of exclusion criteria, 516 patients were deemed eligible for the study. Of those, 234 (45.3%) developed BCR, and 282 (54.7%) did not. The results showed that the median follow-up period was 24 (15–42) months, and the median BCR diagnosis was 12.23 ± 15.58 months. The area under the curve (AUC) for the Cox proportional hazard analysis was 0.77. The receiver-operating characteristic curves (AUCs) for the XGBoost and K closest neighbor models were 0.82 and 0.69, respectively. The RBFNN’s AUC was 0.82. Conclusions: The classical statistical model was outperformed by XGBoost and RBFNN models in predicting BCR.

Explainable artificial intelligence for the interpretation of ensemble learning performance in algal bloom estimation.

Chlorophyll-a (Chl-a) concentrations, a key indicator of algal blooms, were estimated using the XGBoost machine learning model with 23 variables, including water quality and meteorological factors. The model performance was evaluated using three indices: root mean square error (RMSE), RMSE-observation standard deviation ratio (RSR), and Nash-Sutcliffe efficiency. Nine datasets were created by averaging 1hour data to cover time frequencies ranging from 1hour to 1month. The dataset with relatively high observation frequencies (1-24 h) maintained stability, with an RSR ranging between 0.61 and 0.65. However, the model's performance declined significantly for datasets with weekly and monthly intervals. The Shapley value (SHAP) analysis, an explainable artificial intelligence method, was further applied to provide a quantitative understanding of how environmental factors in the watershed impact the model's performance and is also utilized to enhance the practical applicability of the model in the field. The number of input variables for model construction increased sequentially from 1 to 23, starting from the variable with the highest SHAP value to that with the lowest. The model's performance plateaued after considering five or more variables, demonstrating that stable performance could be achieved using only a small number of variables, including relatively easily measured data collected by real-time sensors, such as pH, dissolved oxygen, and turbidity. This result highlights the practicality of employing machine learning models and real-time sensor-based measurements for effective on-site water quality management. PRACTITIONER POINTS: XAI quantifies the effects of environmental factors on algal bloom prediction models The effects of input variable frequency and seasonality were analyzed using XAI XAI analysis on key variables ensures cost-effective model development.

Towards high stiffness and ductility-The Mg-Al-Y alloy design through machine learning

In traditional trial-and-error method, enhancing the Young's modulus of magnesium alloys while maintaining a favorable ductility has consistently been a challenge. It is a need to explore more efficient and expedited methods to design magnesium alloys with high modulus and ductility. In this study, machine learning (ML) and assisted microstructure control methods are used to design high modulus magnesium alloys. Six key features that influence stiffness and ductility have been extracted in this ML model based on abundant data from literature sources. As a result, predictive models for Young's modulus and elongation are established, with errors less than 2.4% and 4.5% through XGBoost machine learning model, respectively. Within the given range of six features, the magnesium alloys can be fabricated with the Young's modulus exceeding 50 GPa and an elongation surpassing 6%. As a validation, Mg-Al-Y alloys were experimentally prepared to meet the criteria of six features, achieving Young's modulus of 51.5 GPa, and the elongation of 7%. Moreover, the SHapley Additive exPlanation (SHAP) is introduced to boost the model interpretability. This indicates that balancing the volume fraction of reinforcement, the most important feature, is key to achieve Mg-Al-Y alloys with high Young's modulus and favorable elongation through the two models. Enhancing reinforcement dispersion and reducing the size of reinforcement and grain can further improve the elongation of high-stiffness Mg alloy.

Predicting the risk of diabetes complications using machine learning and social administrative data in a country with ethnic inequities in health: Aotearoa New Zealand

BackgroundIn the age of big data, linked social and administrative health data in combination with machine learning (ML) is being increasingly used to improve prediction in chronic disease, e.g., cardiovascular diseases (CVD). In this study we aimed to apply ML methods on extensive national-level health and social administrative datasets to assess the utility of these for predicting future diabetes complications, including by ethnicity.MethodsFive ML models were used to predict CVD events among all people with known diabetes in the population of New Zealand, utilizing nationwide individual-level administrative data.ResultsThe Xgboost ML model had the best predictive power for predicting CVD events three years into the future among the population with diabetes (N = 145,600). The optimization procedure also found limited improvement in prediction by ethnicity (using area under the receiver operating curve, [AUC]). The results indicated no trade-off between model predictive performance and equity gap of prediction by ethnicity (that is improving model prediction and reducing performance gaps by ethnicity can be achieved simultaneously). The list of variables of importance was different among different models/ethnic groups, for example: age, deprivation (neighborhood-level), having had a hospitalization event, and the number of years living with diabetes.Discussion and conclusionsWe provide further evidence that ML with administrative health data can be used for meaningful future prediction of health outcomes. As such, it could be utilized to inform health planning and healthcare resource allocation for diabetes management and the prevention of CVD events. Our results may suggest limited scope for developing prediction models by ethnic group and that the major ways to reduce inequitable health outcomes is probably via improved delivery of prevention and management to those groups with diabetes at highest need.

Machine Learning Elucidates Electrophysiological Properties Predictive of Multi- and Single-Firing Human and Mouse Dorsal Root Ganglia Neurons.

Human and mouse dorsal root ganglia (hDRG and mDRG) neurons are important tools in understanding the molecular and electrophysiological mechanisms that underlie nociception and drive pain behaviors. One of the simplest differences in firing phenotypes is that neurons are single-firing (exhibit only one action potential) or multi-firing (exhibit 2 or more action potentials). To determine if single- and multi-firing hDRG neurons exhibit differences in intrinsic properties, firing phenotypes, and AP waveform properties, and if these properties could be used to predict multi-firing, we measured 22 electrophysiological properties by whole-cell patch-clamp electrophysiology of 94 hDRG neurons from six male and four female donors. We then analyzed the data using several machine learning models to determine if these properties could be used to predict multi-firing. We used 1,000 iterations of Monte Carlo cross-validation to split the data into different train and test sets and tested the logistic regression, k-nearest neighbors, random forest, support vector classifier, and XGBoost machine learning models. All models tested had a >80% accuracy on average, with support vector classifier, and XGBoost performing the best. We found that several properties correlated with multi-firing hDRG neurons and together could be used to predict multi-firing neurons in hDRG including a long decay time, a low rheobase, and long first spike latency. We also found that the hDRG models were able to predict multi-firing with 90% accuracy in mDRG neurons. Understanding these properties could be beneficial in the elucidation of targets on peripheral sensory neurons related to pain.

Combined influence of nutritional and inflammatory status and breast cancer: findings from the NHANES

BackgroundPrevious studies have hinted at the benefits of following an anti-inflammatory diet for potentially reducing breast cancer prevalence. However, the combined influence of diet and inflammation on breast cancer remains unclear.MethodsThe advanced lung cancer inflammation index (ALI) was used to assess inflammation and nutritional status. Statistical methods, such as multivariable logistic regression, eXtreme Gradient Boosting (XGBoost) model, and subgroup analysis, were employed to analyze the impact of ALI on prevalence of BC. Additionally, a two-piece-wise logistic regression model with smoothing was used to determine the ALI threshold for BC prevalence. The study aimed to understand the mechanistic association between ALI levels and BC development.ResultsThe mean (SD) age of the study population was 50.0 (17.7) years, with 40.0% of individuals classified as obese. Comparing ALI tertiles to the lowest tertile, the odds ratios (95% CI) for breast cancer (BC) were 0.78 (0.62, 0.98) and 0.68 (0.52, 0.87) for T2-T3. The XGBoost machine learning model was employed to assess the importance of selected factors, revealing ALI as one of the top five variables influencing BC. Subgroup analysis identified a correlation between ALI, alcohol consumption, and menopausal status. Additionally, ALI levels were associated with decreased estradiol (E2) levels, increased total testosterone (TT)/E2 ratio, and TT/sex hormone-binding globulin (SHBG) ratio.ConclusionThis study indicates a potential protective effect of ALI levels against breast cancer, possibly related to sex hormone disruption. The findings support the use of optimal therapeutic strategies for preventing breast cancer.

Machine Learning Predicts Patients With New-onset Diabetes at Risk of Pancreatic Cancer.

New-onset diabetes represent a high-risk cohort to screen for pancreatic cancer. Develop a machine model to predict pancreatic cancer among patients with new-onset diabetes. A retrospective cohort of patients with new-onset diabetes was assembled from multiple health care networks in the United States. An XGBoost machine learning model was designed from a portion of this cohort (the training set) and tested on the remaining part of the cohort (the test set). Shapley values were used to explain the XGBoost's model features. Model performance was compared with 2 contemporary models designed to predict pancreatic cancer among patients with new-onset diabetes. In the test set, the XGBoost model had an area under the curve of 0.80 (0.76 to 0.85) compared with 0.63 and 0.68 for other models. Using cutoffs based on the Youden index, the sensitivity of the XGBoost model was 75%, the specificity was 70%, the accuracy was 70%, the positive predictive value was 1.2%, and the negative predictive value was >99%. The XGBoost model obtained a positive predictive value of at least 2.5% with a sensitivity of 38%. The XGBoost model was the only model that detected at least 50% of patients with cancer one year after the onset of diabetes. All 3 models had similar features that predicted pancreatic cancer, including older age, weight loss, and the rapid destabilization of glucose homeostasis. Machine learning models isolate a high-risk cohort from those with new-onset diabetes at risk for pancreatic cancer.

Leading role of Saharan dust on tropical cyclone rainfall in the Atlantic Basin.

Tropical cyclone rainfall (TCR) extensively affects coastal communities, primarily through inland flooding. The impact of global climate changes on TCR is complex and debatable. This study uses an XGBoost machine learning model with 19-year meteorological data and hourly satellite precipitation observations to predict TCR for individual storms. The model identifies dust optical depth (DOD) as a key predictor that enhances performance evidently. The model also uncovers a nonlinear and boomerang-shape relationship between Saharan dust and TCR, with a TCR peak at 0.06 DOD and a sharp decrease thereafter. This indicates a shift from microphysical enhancement to radiative suppression at high dust concentrations. The model also highlights meaningful correlations between TCR and meteorological factors like sea surface temperature and equivalent potential temperature near storm cores. These findings illustrate the effectiveness of machine learning in predicting TCR and understanding its driving factors and physical mechanisms.

Blood pressure response index and clinical outcomes in patients with septic shock: a multicenter cohort study

Sepsis is a leading cause of mortality in intensive care units and vasoactive drugs are widely used in septic patients. The cardiovascular response of septic shock patients during resuscitation therapies and the relationship of the cardiovascular response and clinical outcome has not been clearly described. We included adult patients admitted to the ICU with sepsis from Peking Union Medical College Hospital (internal), Medical Information Mart for Intensive Care IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD). The Blood Pressure Response Index (BPRI) was defined as the ratio between the mean arterial pressure and the vasoactive-inotropic score. BRRI was compared with existing risk scores on predicting in-hospital death. The relationship between BPRI and in-hospital mortality was calculated. A XGBoost's machine learning model identified the features that influence short-term changes in BPRI. There were 2139, 9455, and 4202 patients in the internal, MIMIC-IV and eICU-CRD cohorts, respectively. BPRI had a better AUROC for predicting in-hospital mortality than SOFA (0.78 vs. 0.73, p=0.01) and APS (0.78 vs. 0.74, p=0.03) in the internal cohort. The estimated odds ratio for death per unit decrease in BPRI was 1.32 (95% CI 1.20-1.45) when BPRI was below 7.1 vs. 0.99 (95% CI 0.97-1.01) when BPRI was above 7.1 in the internal cohort; similar relationships were found in MIMIC-IV and eICU-CRD. Respiratory support and latest cumulative 12-h fluid balance were intervention-related features influencing BPRI. BPRI is an easy, rapid, precise indicator of the response of patients with septic shock to vasoactive drugs. It is a comparable and even better predictor of prognosis than SOFA and APS in sepsis and it is simpler and more convenient in use. The application of BPRI could help clinicians identify potentially at-risk patients and provide clues for treatment. Fundings for the Beijing Municipal Natural Science Foundation; the National High Level Hospital Clinical Research Funding; the CAMS Innovation Fund for Medical Sciences (CIFMS) from Chinese Academy of Medical Sciences and the National Key R&D Program of China, Ministry of Science and Technology of the People's Republic of China.

P-194 Developing a classification system for euploid embryos: leveraging morphology grades and biopsy day to accurately rank them based on ongoing pregnancy potential

Abstract Study question Can morphology grades and day of trophectoderm (TE) biopsy be utilized to accurately rank euploid blastocysts according to their potential for ongoing pregnancy (OP)? Summary answer The proposed ranking system categorized euploid blastocysts accurately in terms of their ongoing pregnancy potential. What is known already Implementing a ranking for embryo selection within a pool is a valuable optimization strategy. Many studies have documented the importance of inner cell mass (ICM) and trophectoderm (TE) grading, as well as the day (D) at which blastocysts are biopsied on clinical outcomes. However, literature sparks controversy on clinical findings in relation to blastocyst quality. This is primarily because it reports a diversity in blastocyst grade-ranking systems, and none of them accounting for the day of biopsy. Enhancing consistency and comparability across various research studies could be achieved by establishing a standardized approach for qualitatively classifying and ranking euploid blastocysts. Study design, size, duration This retrospective cohort study included 2209 single euploid frozen embryo transfers (SeFET) between 2017 and 2023. Blastocyst (BL) expansion, TE and ICM were assessed before biopsy according to Gardner’s criteria. Only blastocysts graded ≥BL3CC were biopsied on D5, D6 or D7. Classification models (in-house, logistic regression, gradient boost) were assessed for their calibration, i.e., correct prediction of ongoing pregnancy (OP) probability. Participants/materials, setting, methods In-house ranking system categorized euploid transferred blastocysts (BL3-BL6) as ‘Top-quality’ for blastocysts AA/AB/BA on D5; ‘Good-quality’ for blastocysts BB on D5 and AA/AB/BA/BB on D6; ‘Fair-quality’ for AC/BC/CA/CB on D5, BC on D6 and AA/AB/BA/BB on D7; and ‘Poor-quality’ for blastocysts CC on D5, AC/CA/CB/CC on D6 and CA/CB/AC/BC/CC on D7. The in-house classification ranking system was compared to other developed models to evaluate whether performance could be increased. Main results and the role of chance A total of 406 blastocysts were ranked as Top-quality (100% D5), 1323 as Good-quality (51.3% D5 and 48.7% D6), 190 Fair-quality (57.9% D5, 36.3% D6 and 5.8% D7) and 290 as Poor-quality (12.8% D5, 73.8% D6 and 13.4% D7). The ongoing pregnancy rate was significantly higher for blastocysts ranked as Top compared to Good, Fair and Poor-quality (58.9%, 52.2%, 35.8% and 26.6%, respectively). Miscarriage rates were significantly associated with ranking quality (20.9%, 24.3%, 30.6% and 39.4% for Top, Good, Fair and Poor-quality blastocysts, respectively). We further developed two new classification ranking systems using logistic regression model and XGBoost machine learning model. But the new models provided similar AUC and calibration slope (CS) values as the in-house ranking system (AUC [CS]: 0.604 ± 0.0167 [0.962 ± 0.213] and 0.601 ± 0.0177 [0.949 ± 0.219] vs.0.597 ± 0.015 [0.980 ± 0.230] for logistic regression, XGBoost versus in-house model, respectively). Limitations, reasons for caution The present embryo classification ranking system may not be extrapolated to non-PGT-A cycles. Wider implications of the findings Different grade-ranking systems of blastocysts keep being reported in the different publications. Reaching a consensus to rank euploid blastocysts qualitatively, as the hereby proposed classification, may improve consistency and comparability across different research studies. Crucially, the present ranking-system aids embryo selection for transfer from available pool. Trial registration number not applicable

Ultrasound contrast-enhanced radiomics model for preoperative prediction of the tumor grade of clear cell renal cell carcinoma: an exploratory study

BackgroundThis study aims to explore machine learning(ML) methods for non-invasive assessment of WHO/ISUP nuclear grading in clear cell renal cell carcinoma(ccRCC) using contrast-enhanced ultrasound(CEUS) radiomics.MethodsThis retrospective study included 122 patients diagnosed as ccRCC after surgical resection. They were divided into a training set (n = 86) and a testing set(n = 36). CEUS radiographic features were extracted from CEUS images, and XGBoost ML models (US, CP, and MP model) with independent features at different phases were established. Multivariate regression analysis was performed on the characteristics of different radiomics phases to determine the indicators used for developing the prediction model of the combined CEUS model and establishing the XGBoost model. The training set was used to train the above four kinds of radiomics models, which were then tested in the testing set. Radiologists evaluated tumor characteristics, established a CEUS reading model, and compared the diagnostic efficacy of CEUS reading model with independent characteristics and combined CEUS model prediction models.ResultsThe combined CEUS radiomics model demonstrated the best performance in the training set, with an area under the curve (AUC) of 0.84, accuracy of 0.779, sensitivity of 0.717, specificity of 0.879, positive predictive value (PPV) of 0.905, and negative predictive value (NPV) of0.659. In the testing set, the AUC was 0.811, with an accuracy of 0.784, sensitivity of 0.783, specificity of 0.786, PPV of 0.857, and NPV of 0.688.ConclusionsThe radiomics model based on CEUS exhibits high accuracy in non-invasive prediction of ccRCC. This model can be utilized for non-invasive detection of WHO/ISUP nuclear grading of ccRCC and can serve as an effective tool to assist clinical decision-making processes.

Machine learning elucidates electrophysiological properties predictive of multi- and single-firing human and mouse dorsal root ganglia neurons.

Human and mouse dorsal root ganglia (hDRG and mDRG) neurons are important tools in understanding the molecular and electrophysiological mechanisms that underlie nociception and drive pain behaviors. One of the simplest differences in firing phenotypes is that neurons are single-firing (exhibit only one action potential) or multi-firing (exhibit 2 or more action potentials). To determine if single- and multi-firing hDRG exhibit differences in intrinsic properties, firing phenotypes, and AP waveform properties, and if these properties could be used to predict multi-firing, we measured 22 electrophysiological properties by whole-cell patch-clamp electrophysiology of 94 hDRG neurons from 6 male and 4 female donors. We then analyzed the data using several machine learning models to determine if these properties could be used to predict multi-firing. We used 1000 iterations of Monte Carlo Cross Validation to split the data into different train and test sets and tested the Logistic Regression, k-Nearest Neighbors, Random Forest, Supported Vector Classification, and XGBoost machine learning models. All models tested had a greater than 80% accuracy on average, with Supported Vector Classification and XGBoost performing the best. We found that several properties correlated with multi-firing hDRG neurons and together could be used to predict multi-firing neurons in hDRG including a long decay time, a low rheobase, and long first spike latency. We also found that the hDRG models were able to predict multi-firing with 90% accuracy in mDRG. Targeting the neuronal properties that lead to multi-firing could elucidate better targets for treatment of chronic pain.

Spinach genomes reveal migration history and candidate genes for important crop traits.

Spinach (Spinacia oleracea) is an important leafy crop possessing notable economic value and health benefits. Current genomic resources include reference genomes and genome-wide association studies. However, the worldwide genetic relationships and the migration history of the crop remained uncertain, and genome-wide association studies have produced extensive gene lists related to agronomic traits. Here, we re-analysed the sequenced genomes of 305 cultivated and wild spinach accessions to unveil the phylogeny and history of cultivated spinach and to explore genetic variation in relation to phenotypes. In contrast to previous studies, we employed machine learning methods (based on Extreme Gradient Boosting, XGBoost) to detect variants that are collectively associated with agronomic traits. Variant-based cluster analyses revealed three primary spinach groups in the Middle East, Asiaand Europe/US. Combining admixture analysis and allele-sharing statistics, migration routes of spinach from the Middle East to Europe and Asia are presented. Using XGBoost machine learning models we predict genomic variants influencing bolting time, flowering time, petiole color, and leaf surface texture and propose candidate genes for each trait. This study enhances our understanding of the history and phylogeny of domesticated spinach and provides valuable information on candidate genes for future genetic improvement of the crop.

Performance optimization of Bloch surface wave based devices using an XGBoost machine learning model

Bloch surface wave (BSW) based photonic devices have attracted significant interest for bio-sensing, spectroscopy, and light manipulation applications due to their ability to confine light at dielectric interfaces. However, optimizing the geometry of BSW structures to achieve desired optical properties can be computationally expensive using conventional simulation methods for multi-parameter design spaces. In this work, we develop machine learning models based on the gradient boosting algorithm XGBoost to predict key optical characteristics of BSW devices and expedite the design process. Finite element method simulations are used to generate a dataset relating BSW structures’ excitation angle, sensitivity, and spectral response to their geometric parameters, including thickness, porosity, and surrounding refractive index. This dataset trains and validates different XGBoost regression models for photonic structure optimization. Our results demonstrate that a model utilizing deep decision trees achieves the highest predictive accuracy, with a mean absolute error of 0.09° in estimating the excitation angle for new structures. We apply this optimized model to uncover the thickness-porosity combinations, enabling a maximum sensitivity of 171-degree/RIU. This machine learning approach provides a powerful tool for the inverse design and performance enhancement of BSW photonic structures beyond the capabilities of conventional simulation-based optimization.

A machine learning approach to predict daptomycin exposure from two concentrations based on Monte Carlo simulations.

Daptomycin is a concentration-dependent lipopeptide antibiotic for which exposure/effect relationships have been shown. Machine learning (ML) algorithms, developed to predict the individual exposure to drugs, have shown very good performances in comparison to maximum a posteriori Bayesian estimation (MAP-BE). The aim of this work was to predict the area under the blood concentration curve (AUC) of daptomycin from two samples and a few covariates using XGBoost ML algorithm trained on Monte Carlo simulations. Five thousand one hundred fifty patients were simulated from two literature population pharmacokinetics models. Data from the first model were split into a training set (75%) and a testing set (25%). Four ML algorithms were built to learn AUC based on daptomycin blood concentration samples at pre-dose and 1 h post-dose. The XGBoost model (best ML algorithm) with the lowest root mean square error (RMSE) in a 10-fold cross-validation experiment was evaluated in both the test set and the simulations from the second population pharmacokinetic model (validation). The ML model based on the two concentrations, the differences between these concentrations, and five other covariates (sex, weight, daptomycin dose, creatinine clearance, and body temperature) yielded very good AUC estimation in the test (relative bias/RMSE = 0.43/7.69%) and validation sets (relative bias/RMSE = 4.61/6.63%). The XGBoost ML model developed allowed accurate estimation of daptomycin AUC using C0, C1h, and a few covariates and could be used for exposure estimation and dose adjustment. This ML approach can facilitate the conduct of future therapeutic drug monitoring (TDM) studies.

Next-generation non-linear and collapse prediction models for short- to long-period systems via machine learning methods

Since the 1960 s, a cornerstone of earthquake engineering has been estimating the non-linear response of structures based just on lateral strength, modal properties, and the anticipated seismic demand. Over the years, several studies have quantified this empirical relationship and integrated it within seismic design and assessment methodologies. These have been widely accepted for practical application and adopted in building codes worldwide. While these models work reasonably well, there are still areas in which improvements can be made, especially concerning their robust quantification of uncertainty. This is mainly due to the amount of data used to quantify these empirical relationships, the choice of functional forms during the fitting, the model fitting and testing process, and how the ground motion shaking intensity is characterised. This study tackles these issues via the non-linear analysis of single-degree-of-freedom oscillators to train several machine learning (ML) models. This was to examine the accuracy and applicability of such models within a seismic engineering context and explore potential gains in quantifying the non-linear response of structures via next-generation intensity measures, namely average spectral acceleration, Saavg. The results show that the Decision Tree and XGBoost models worked well across a broad range of periods, accurately predicting collapse and non-collapse responses. Appraising these with existing models showed a notable improvement all around. It indicates that the models based on data-driven ML approaches represent a positive step and can be seamlessly integrated with seismic analysis methodologies utilised worldwide. Subsequently, a Python-based library of these XGBoost ML models was developed and made available online to foster practical application.

DNA Methylation Profiling Enables Accurate Classification of Nonductal Primary Pancreatic Neoplasms

Background and aimsCytological and histopathological diagnosis of non-ductal pancreatic neoplasms can be challenging in daily clinical practice while it is crucial for therapy and prognosis. The cancer methylome is successfully used as a diagnostic tool in other cancer entities. Here, we investigate if methylation profiling can improve the diagnostic work-up of pancreatic neoplasms. MethodsDNA methylation data were obtained for 301 primary tumors spanning six primary pancreatic neoplasms and 20 normal pancreas controls. Neural Network, Random Forest, and XGBoost machine learning models were trained to distinguish between tumor types. Methylation data of 29 non-pancreatic neoplasms (n = 3708) were used to develop an algorithm capable of detecting neoplasms of non-pancreatic origin. ResultsAfter benchmarking three state-of-the-art machine learning models, the Random Forest model emerged as the best classifier with 96.9% accuracy. All classifications received a probability score reflecting the confidence of the prediction. Increasing the score threshold, improved the Random Forest classifier performance up to 100% with 87% of samples with scores surpassing the cutoff. Using a logistic regression model, detection of non-pancreatic neoplasms achieved an area under the curve (AUC) of > 0.99. Analysis of biopsy specimens showed concordant classification with their paired resection sample. ConclusionPancreatic neoplasms can be classified with high accuracy based on DNA methylation signatures. Additionally, non-pancreatic neoplasms are identified with near perfect precision. In summary, methylation profiling can serve as a valuable adjunct in the diagnosis of pancreatic neoplasms with minimal risk for misdiagnosis, even in the pre-operative setting.