Lasso Model Research Articles

Digital phenotyping of depression during pregnancy using self-report data.

Depression is a common pregnancy complication yet is often under-detected and, subsequently, undertreated. Data collected through mobile health tools may be used to support the identification of depression symptoms in pregnancy. An observational cohort study of 2062 pregnancies collected self-reports of patient history, mood, pregnancy-specific symptoms, and written language using a prenatal support app. These app inputs were used to model depression risk in subsequent 30- and 60-day periods throughout pregnancy. A selective inference lasso modeling approach examined the individual and additive value of each type of patient-reported app input. Depression models ranged in predictive power (AUC value of 0.64-0.83), depending on the type of inputs. The most predictive model included personal history, daily mood, and acute pregnancy-related symptoms (e.g., severe vomiting, cramping). Across models, daily mood was the strongest indicator of depression symptoms in the following month. Models that retained natural language inputs typically improved predictive accuracy and offered insight into the lived context associated with experiencing depression. Our findings are not generalizable beyond a digitally literate patient population that is self-motivated to report data during pregnancy. Simple patient reported data, including sparse language, shared directly via digital tools may support earlier depression symptom identification and a more nuanced understanding of depression context.

Circulating metabolites associate with the QT interval in individuals without prevalent cardiovascular disease

Abstract Background Patients with metabolic syndrome have a higher prevalence of heart-rate corrected QT (QTc) interval prolongation. Despite this the effect of circulating metabolites on the QTc is largely unknown and limited to small studies. Purpose To test for association of circulating metabolites with the QTc interval in the UK Biobank study. Methods Participants were identified from the UK Biobank with same day plasma metabolite profiling and electrocardiograms. All 249 metabolites measured underwent quality control and log transformation to account for rightward skew and zero values. 149 metabolites with inter-correlations >0.7 were excluded. Participants taking QTc-prolonging medication or with a history of ischaemic heart disease or heart failure up to 6 months after the visit, were excluded. Participants were allocated to a training group (N=21,610) or an independent test group (N=5,304), if samples were obtained at recruitment or at a second visit, respectively. In the training group, each metabolite was tested separately for association with the QTc in linear regression analyses, adjusted for clinical covariates (age, sex, fasting time, body mass index (BMI), systolic blood pressure (SBP), smoking status, diabetes, lipid-lowering drug use and dietary factors). Significant metabolites (P<5x10-4) underwent validation in the test group. Sex-stratified analyses were also performed. In the training group, variables in two models underwent regularisation by LASSO regression (10-fold cross-validation) to reduce multicollinearity and downweigh less important variables; 1) clinical variables, 2) clinical variables and validated metabolites. Coefficients were used for QTc prediction in the test group. Significance between the models was evaluated by fisher’s transformation of R-squared statistics. Results In the per metabolite multivariate analysis, 56 metabolites were associated with the QTc interval. 19 metabolites validated in the test group. For 14 of these, absolute effect sizes were >5ms when comparing individuals in the top decile of the metabolite distribution verses the bottom (Figure 1), including the ketone body 3-hydroxybutyrate (9ms), and omega-6 fatty acid to total fatty acid ratio (7.2ms). For associations in males and females separately, significant effect size differences (P<0.05) were observed for 9 metabolites (Figure 2). In the training group, the combined LASSO model selected 17 (of 19) metabolites along with age, sex, SBP and BMI. In the test group, this model R-squared was 0.115 compared with 0.081 for clinical covariates alone, representing a significant 41.9% increase in QTc variation explained (P=0.002). Conclusions This study demonstrates clinically relevant metabolite associations with the QTc in individuals without cardiovascular disease and explain a significant proportion of QTc variation. Further investigation is warranted to test for direct effects on cardiac electrophysiology and proarrhythmic potential.Validated metabolitesSignificant sex differences

Non-lipid metabolomic biomarkers are associated with adverse cardiac remodelling and cardiovascular outcomes

Abstract Background Metabolomics is the detailed profiling of circulating metabolites including carbohydrates, lipids, amino and fatty acids, and ketones, all of which are substrates used in energy metabolism by cardiomyocytes. Purpose The role of cholesterol fractions with cardiovascular risk is well-established. This novel study examines the association between non-lipid circulating metabolites and markers of cardiac remodelling as assessed by cardiovascular magnetic resonance (CMR) imaging. Metabolites associated with adverse remodelling were taken forward to examine their impact on incident cardiovascular disease (CVD); ischaemic heart disease (IHD) and heart failure (HF). Methods This study used data from the UK Biobank. After exclusions (prevalent IHD, HF; outliers), there were a maximum of 34,727 individuals for CMR analyses and 262,536 individuals for incident CVD analysis. For CMR analyses, outcome variables were LV end-diastolic volume (EDV), LV mass, LV mass:volume ratio (MVR), LV global longitudinal strain (GLS) and native T1. Separate regression models were built for each of the 40 scaled metabolite biomarkers. Each model incorporated one metabolite at a time with additional covariates: age, sex, ethnicity, systolic blood pressure, cholesterol medication use, type 2 diabetes, dietary intake, smoking status, fasting time, and time between recruitment and CMR examination. A Bonferroni-corrected significance threshold of 2.4x10-4 was used. To account for correlation between metabolites, Lasso regression with 10 fold cross-validation to identify the most important predictors was performed for LV MVR, LV GLS and native T1 whereby all metabolites and above covariates were included in the model. Metabolite predictors of adverse remodelling were included in an adjusted logistic regression model with incident CVD as an outcome. Results Metabolites demonstrating significant (p < 2.4x10-4) associations with CMR parameters are presented in Fig 1. For higher LV MVR and more positive LV GLS, the metabolites with the largest effect were monounsaturated fatty acids and glycoprotein acetyls. Higher omega-6:omega-3 ratio was associated with higher T1 values. The Lasso model identified 8 important predictors for adverse cardiac remodelling. Of these, two were routine biomarkers (creatinine, glucose). Of the remainder, monounsaturated fatty acids, glycoprotein acetyls and apolipoprotein B:apolipoprotein A1 ratio were significantly associated with increased risk of incident CVD (Fig 2). Current evidence regarding monounsaturated fatty acids in CVD is mixed. Glycoprotein acetyls are implicated in vascular inflammation. Apolipoproteins are thought to be a potential therapeutic target for CVD risk reduction. Conclusion This study demonstrates a role of non-lipid metabolites on subclinical CVD as assessed by adverse remodelling with CMR as well as associations with incident CVD. We highlight potential novel biomarkers for identification of CVD.Metabolite association with LV MVR/GLSMetabolite association with incident CVD

Performance of the Classical Model in Feature Selection Across Varying Database Sizes of Healthcare Data

Machine learning is increasingly being applied to medical research, particularly in selecting predictive modelling variables. By identifying relevant variables, researchers can improve model accuracy and reliability, leading to better clinical decisions and reduced overfitting. Efficient utilization of resources and the validity of medical research findings depend on selecting the right variables. However, few studies compare the performance of classical and modern methods for selecting characteristics in health datasets, highlighting the need for a critical evaluation to choose the most suitable approach. We analysed the performance of six different variable selection methods, which includes stepwise, forward and backward selection using p-value and AIC, LASSO, and Elastic Net. Health-related surveillance data on behaviors, health status, and medical service usage were used across ten databases, with sizes ranging from 10% to 100%, maintaining consistent outcome proportions. Varying database sizes were utilized to assess their impact on prediction models, as they can significantly influence accuracy, overfitting, generalizability, statistical power, parameter estimation reliability, computational complexity, and variable selection. The stepwise and backward AIC model showed the highest accuracy with an Area under the ROC Curve (AUC) of 0.889. Despite its sparsity, the Lasso and Elastic Net model also performed well. The study also found that binary variables were considered more crucial by the Lasso and Elastic Net model. Importantly, the significance of variables remained consistent across different database sizes. The study shows that no major variations in results between the fitness metric of the model and the number of variables in stepwise and backward p-value models, irrespective of the database's size. LASSO and Elastic Net models surpassed other models throughout various database sizes, and with fewer variables.

Integrated analysis of single-cell RNA-seq and bulk RNA-seq revealed key genes for bone metastasis and chemoresistance in prostate cancer.

Prostate cancer (PCa) is a serious malignancy. The main causes of PCa aggravation and death are unexplained resistance to chemotherapy and bone metastases. This study aimed to investigate the molecular mechanisms associated with the dynamic processes of progression, bone metastasis, and chemoresistance in PCa. Through comprehensive analysis of single-cell RNA sequencing (scRNA-seq) data, Gene Expression Omnibus (GEO) tumor progression and metastasis-related genes were identified. These genes were subjected to lasso regression modeling using the Cancer Genome Atlas (TCGA) database. Tartrate-resistant acid phosphatase (TRAP) staining and real-time quantitative PCR (RT-qPCR) were used to evaluate osteoclast differentiation. CellMiner was used to confirm the effect of LDHA on chemoresistance. Finally, the relationship between LDHA and chemoresistance was verified using doxorubicin-resistant PCa cell lines. 7928 genes were identified as genes related to tumor progression and metastasis. Of these, 7 genes were found to be associated with PCa prognosis. The scRNA-seq and TCGA data showed that the expression of LDHA was higher in tumors and associated with poor prognosis of PCa. In addition, upregulation of LDHA in PCa cells induces osteoclast differentiation. Additionally, high LDHA expression was associated with resistance to Epirubicin, Elliptinium acetate, and doxorubicin. Cellular experiments demonstrated that LDHA knockdown inhibited doxorubicin resistance in PCa cells. LDHA may play a potential contributory role in PCa initiation and development, bone metastasis, and chemoresistance. LDHA is a key target for the treatment of PCa.

7515 Plasma proteomic signatures for type 2 diabetes mellitus and related traits in the UK Biobank

Abstract Disclosure: T. Gupte: None. Z. Azizi: None. K. Nzenkue: None. P. Kho: None. M. Chen: None. J. Zhou: None. R. Guarischi-Sousa: None. D.J. Panyard: None. F. Abbasi: None. K. Watson: None. S. Clarke: None. P.S. Tsao: None. T.L. Assimes: None. Background: The plasma proteome holds promise as a future diagnostic and prognostic tool that can accurately reflect complex human traits and disease processes. We assessed the ability of plasma proteins to associate with two primary risk factors of type 2 diabetes mellitus (T2DM) and to predict incident T2DM. Methods: Clinical, genetic, and high-throughput proteomic data from three subcohorts of 5586, 5584, and 36339 individuals in the UK Biobank were analyzed for association with DXA-measured truncal fat, maximum VO2, and incident T2DM, respectively. Exclusion criteria included prevalent T2DM, history of T1DM, or elevated A1c (>48 mmol/mol) values. We used LASSO to assess relative ability of 13 clinical variables including the Q-Diabetes (Q-D) score, 36 polygenic risk scores (PRSs), and 2923 proteins to associate with each trait by comparing variances explained (R2) and AUC statistics between data types. Stability selection with randomized LASSO identified the most robustly associated proteins for each trait. The benefit of proteomic signatures (PSs) over the Q-D score was evaluated through the derivation of Δ AUC values. Separate case-control groups were developed to evaluate T2DM prediction in the adiposity and fitness cohorts. Results: Across all three subcohorts, the mean age was 56.6 years, 54.9% were female, and 5.4% developed T2DM over a median follow-up of 7.7 years. In the adiposity cohort, a protein-only LASSO model explained 73.2% of the variance in truncal fat and GLIPR1, CLMP, LEP, FABP4, and FAM3C were among the top proteins selected. In the fitness cohort, a protein-only LASSO model explained 61.9% of the variance in maximum VO2 and LEP, CD99, AGRN, ELN, and CA14 were among the top proteins selected. LASSO-derived PSs increased the R2 of truncal fat and maximum VO2 over clinical and genetic factors by 13% and 1%, respectively, with the former also improving risk prediction of T2DM over Q-D [Δ AUC: 0.026 (95% CI -0.007, 0.060)]. In the T2DM cohort, a protein-only LASSO model returned an AUC of 0.856 (95% CI 0.840, 0.871) and PLXNB2, PODXL, PLA2G7, FGFR2, and NFASC were among the top proteins selected. We observed a similar improvement in T2DM prediction over Q-D [Δ AUC: 0.015 (95% CI 0.009, 0.023)] when using a PS derived strictly from the T2DM outcome and augmented with non-overlapping proteins associated with fat and fitness. A few proteins (ranging between 15-33 for each trait) identified by stability selection algorithms offered most of the improvement in risk prediction. Conclusion: Plasma PS modestly improves the prediction of T2DM over that possible with clinical and genetic factors. Further studies are warranted to better elucidate the clinical utility of these signatures in predicting T2DM risk over the standard practice of using the Q-D score. Presentation: 6/2/2024

Identification of key genes participating in copper-diethyldithiocarbamate-related cell death process and predicting the development of prostate cancer

Copper (Cu) is used as a cofactor in all organisms, and yet it can be toxic at high intracellular concentrations, causing cell death. Diethyldithiocarbamate (DDC) is a Cu ionophore that can transport Cu effectively into the cell. Copper-diethyldithiocarbamate (Cu-DDC) can treat prostate cancer (PCa) and may correlate with the cell death process. However, the specific Cu-DDC-related cell death genes in PCa are still unknown. Information about the Cu-DDC-related cell death genes was obtained from a previous study. Concurrently, the RNA expression profiles and clinical data were downloaded from public databases such as GEO, TCGA, and CPGEA. Using data from TCGA database, the logistic and lasso regression models were generated using R software. The influence of these genes in affecting PCa progression and prognosis was analyzed. Finally, the expression of these genes was verified in clinical samples. We found five Cu-DDC-related cell death genes associated with the occurrence of PCa from GSE35988, a gene dataset, namely, CDKN2A, PRC1, CDK1, SOX2, and ZNF365. CDKN2A, PRC1, and CDK1 are known to influence PCa patients’ disease-free survival (DFS) status and were overexpressed, whereas SOX2 and ZNF365 were under-expressed in PCa in the different databases. Some of these genes can affect PCa progression. Consistent with the database results, the mRNA and protein expression of CDKN2A, PRC1, and CDK1 was also higher in clinical samples. In conclusion, we identified five hub genes which are important for Cu-DDC-related cell death process that can predict the development of PCa.

Predicting Methanol Space-Time Yield from CO? Hydrogenation Using Machine Learning: Statistical Evaluation of Penalized Regression Techniques

This study investigates the effectiveness of machine learning techniques, specifically penalized regression models Ridge Regression, Lasso Regression, and Elastic Net Regression in predicting methanol space-time yield (STY) from CO? hydrogenation data. Using a dataset derived from Cu-based catalyst research, the study implemented a comprehensive preprocessing approach, including data cleaning, imputation, outlier removal, and normalization. The models were rigorously evaluated through 10-fold cross-validation and tested on unseen data. Ridge Regression outperformed the other models, achieving the lowest Root Mean Squared Error (RMSE) of 0.7706, Mean Absolute Error (MAE) of 0.5627, and Mean Squared Error (MSE) of 0.5938. In comparison, Lasso and Elastic Net Regression models exhibited higher error metrics. Feature importance analysis revealed that Gas Hourly Space Velocity (GHSV) and Molar Masses of Support significantly influence catalytic activity. These findings suggest that Ridge Regression is a promising tool for accurately predicting methanol production, providing valuable insights for optimizing catalytic processes and advancing sustainable practices in chemical engineering.

Optimization of drug solubility inside the supercritical CO2 system via numerical simulation based on artificial intelligence approach

In this research paper, we explored the predictive capabilities of three different models of Polynomial Regression (PR), Extreme Gradient Boosting (XGB), and LASSO to estimate the density of supercritical carbon dioxide (SC-CO2) and the solubility of niflumic acid as functions of the input variables of temperature and pressure. The optimization of hyperparameters for these models is achieved using the innovative Barnacles Mating Optimizer (BMO) algorithm. For SC-CO2 density estimation, PR exhibits remarkable accuracy, showing an R-squared value of 0.99207 for data fitting. XGB performs admirably with an R2 of 0.92673, while LASSO model demonstrates good predictive ability, showing an R2 of 0.81917. Furthermore, we assess the models’ performance in predicting the solubility of niflumic acid. PR exhibits excellent predictive capabilities with an R2 of 0.96949. XGB also delivers strong performance, yielding an R-squared score of 0.92961. LASSO performs well, achieving an R-squared score of 0.82094. The results indicated promising performance of machine learning models and optimizer in estimating drug solubility in supercritical CO2 as the solvent applicable for pharmaceutical industry.

Spatio-temporal modeling to identify factors associated with stunting in Indonesia using a Modified Generalized Lasso

This study investigates the factors associated with stunting prevalence in Indonesia, utilizing a generalized lasso framework with modified penalty matrices to accommodate spatio-temporal data structures. Novel approaches are introduced to construct the penalty matrices, with particular focus on defining neighborhood structures. The proposed method is applied to data from 34 Indonesian provinces, covering the years 2019 to 2023. The primary outcome is stunting prevalence, modeled against nine predictor variables: poverty, exclusive breastfeeding, low birth weight (LBW), high school completion, access to proper sanitation, unmet health service needs, Gross Domestic Product (GDP), calorie consumption, and protein consumption. A total of nine spatio-temporal models were compared, including a modified generalized lasso with three distinct penalty matrices for each two tuning selection methods and a generalized ridge regression with three penalty matrices. Results indicate that the generalized lasso model with a 3-nearest neighbor adjacency matrix outperformed the alternatives. Temporal variations were observed in the effects of exclusive breastfeeding, LBW, high school completion, and unmet health service needs. Positive associations with stunting prevalence were identified for poverty, exclusive breastfeeding, LBW, and unmet health service needs, while negative associations were found for high school completion rates, access to proper sanitation, GDP, calorie intake, and protein consumption. The strongest associations were observed in parts of Sumatra, Sulawesi, and Jakarta. These findings suggest that government interventions aimed at improving education, healthcare access, and poverty reduction may help alleviate stunting in Indonesia, particularly in regions with the greatest need.

Data-driven nexus between malaria incidence and World Bank indicators in the Mekong River during 2000-2022.

The increase in hydro dams in the Mekong River amidst the prevalence of multidrug-resistant malaria in Cambodia has raised concerns about global public health. Political conflicts during Covid-19 pandemic led cross-border movements of malaria cases from Myanmar and caused health care burden in Thailand. While previous publications used climatic indicators for predicting mosquito-borne diseases, this research used globally recognizable World Bank indicators to find the most impactful indicators related with malaria and shed light on the predictability of mosquito-borne diseases. The World Bank datasets of the World Development Indicators and Climate Change Knowledge Portal contain 1494 time series indicators. They were stepwise screened by Pearson and Distance correlation. The sets of five and four contain respectively 19 and 149 indicators highly correlated with malaria incidence which were found similarly among five and four GMS countries. Living areas, ages, career, income, technology accessibility, infrastructural facilities, unclean fuel use, tobacco smoking, and health care deficiency have affected malaria incidence. Tonle Sap Lake, the largest freshwater lake in Southeast Asia, could contribute to the larval habitat. Seven groups of indicator topics containing 92 indicators with not-null datapoints were analyzed by regression models, including Multiple Linear, Ridge, Lasso, and Elastic Net models to choose 7 crucial features for malaria prediction via Long Short Time Memory network. The indicator of people using at least basic sanitation services and people practicing open defecation were health factors had most impacts on regression models. Malaria incidence could be predicted by one indicator to reach the optimal mean absolute error which was lower than 10 malaria cases (per 1,000 population at risk) in the Long Short Time Memory model. However, public health crises caused by political problems should be analyzed by political indexes for more precise predictions.

Lipidomic perturbations of normal-weight adiposity phenotypes and their mediations on diet–adiposity associations

Background & aimsNormal-weight obesity (NWO) and normal-weight central obesity (NWCO) have been linked to higher cardiometabolic risks, but their etiological bases and attributable dietary factors remain unclear. In this study we therefore aimed to identify lipidomic signatures and dietary factors related to NWO and NWCO and to explore the mediation associations of lipids in diet–adiposity associations. MethodsUsing a high-coverage targeted lipidomic approach, we quantified 1245 serum lipids in participants with NWO (n = 150), NWCO (n = 150), or propensity-score-matched normal-weight controls (n = 150) based on the Regional Ethnic Cohort Study in Northwest China. Consumption frequency of 28 major food items was recorded using a food frequency questionnaire. ResultsProfound lipidomic perturbations of NWCO relative to NWO were observed, and 249 (dominantly glycerolipids) as well as 48 (dominantly glycerophospholipids) lipids were exclusively associated with NWCO or NWO. Based on strong lipidomic signatures identified by a LASSO model, phospholipid biosynthesis was the top enriched pathway of NWCO, and sphingolipid metabolism was the top pathway of NWO. Remarkably, sphingolipids were positively associated with NWO and NWCO, but lyso-phosphatidylcholines were negatively associated with them. Rice, fruit juice, and carbonated drink intakes were positively associated with the risk of NWCO. Both global and individual lipidomic signatures, including SE(28:1_22:6) and HexCer(d18:1/20:1), mediated these diet-NWCO associations (mediation proportion: 15.92%–26.10%). ConclusionsDifferential lipidomic signatures were identified for overall and abdominal adiposity accumulation in normal-weight individuals, underlining their core mediation roles in dietary contributions to adiposity deposition.

192 Prediction of fecal starch content of fattening cattle using near-infrared spectroscopy and machine learning

Abstract Starch content in cattle feces can be used to predict starch digestibility. Near-infrared spectroscopy (NIRS) can be used to rapidly and non-chemically predict fecal starch content after a calibration model has been consequentially developed. Recent advancements in machine learning have introduced potent methods for developing optimized models. In addition, diverse preprocessing methods, such as scatter correction and smoothing, are available to eliminate irrelevant variance sources. This study aimed to identify optimal spectral preprocessing and regression methods for predicting fecal starch content using NIR spectra. NIR spectra were measured for 196 fecal samples collected from 9 fattening cattle farms. Fecal starch content on a DM basis was measured using enzymatic reactions and colorimetry. The 196 samples were divided into a calibration set (n = 123), a validation set (n = 29) comprising four farms, and an external validation set (n = 44) comprising five farms that differed from the calibration set. Based on the calibration set, two preprocessing methods were selected using the partial least squares (PLS) model. In method 1, the calibration models were developed by a grid search 5-fold cross validation on the 1,152 preprocessed calibration sets, and preprocessing with the lowest root mean square error (RMSE) of cross-validation among these calibration sets was selected. In method 2, the original calibration set (n = 123) was divided into a calibration set (n = 116) and a preprocessing selection set (n = 7) with different neutral detergent fiber and similar starch contents. After preprocessing, calibration models were developed as described in method 1. The preprocessing selection sets were then predicted by the developed models, and preprocessing with the lowest RMSE among these preprocessing selection sets was selected. Using the preprocessing methods selected in methods 1 and 2, the validation and external validation sets were predicted using seven regression models. As a result, the preprocessing selected by method 1 was in the wavelength range of 400–2500 nm, with robust normal variate (RNV) scatter correction and first-order derivative Savitzky-Golay filtering (2nd order polynomial, 2-nm window size). The preprocessing selected by method 2 had a wavelength range of 1500–2500 nm, RNV scatter correction, and 2nd-order derivative Savitzky-Golay filtering (3rd order polynomial, 25-nm window size). Among the seven regression models, the Lasso model was the most accurate for prediction. The Lasso models based on the preprocessing methods selected by methods 1 and 2 had RMSE of external validation = 2.054% of DM and 1.540% of DM, respectively. The feature importance of the Lasso model based on preprocessing method selected by methods 2 was higher at wavelengths of 1775 nm and 2325 nm. In conclusion, seven models were developed and evaluated based on diverse preprocessing methods using NIRS. The Lasso model exhibited the highest accuracy.

Exploring predictors of medial collateral ligament tears in lateral approach total knee replacement: A retrospective study

BackgroundMedial collateral ligament (MCL) tears are uncommon in total knee replacement (TKR), but they pose significant surgical challenges, affecting recovery and outcomes. This study analyzed 18 (1.3 %) MCL tear cases from 1429 TKR procedures using a lateral subvastus approach. Logistic regression with Lasso regularization was used to assess factors like gender, BMI, and knee alignment. Midsubstance disruptions were the most common. MCL tears were more frequent in females, those with higher BMI, and valgus alignment. The Lasso model achieved an AUC of 0.83 and an F1 score of 0.76. MethodsA retrospective analysis on 1429 TKR cases performed by three experienced surgeons using the Optimotion Implant system and specialized MCL retractors was conducted. The lateral subvastus approach without parapatellar arthrotomy. A hinged knee brace was applied postoperatively and a posterior stabilized insert was used for MCL tears. Demographic data were collected, and a Lasso regression model with data balancing, was employed to identify MCL tear predictors. ResultsAmong the 1429 TKR cases, 18 cases (1.3 %) involved MCL tears. The average age of these patients was 67.3 years (not statistically significant). The average BMI for patients with MCL tears was 36.7, significantly higher than the overall group average of 31.5, suggesting a link between higher BMI and MCL tears. Females were notably more affected, making up 88.9 % of the MCL tear cases compared to 11.1 % of males. Regarding knee alignment, 38.9 % had valgus alignment (p < 0.05), No significant differences were observed in knee flexion or Knee Society Scores (KSS) following MCL tears. ConclusionsGender, BMI, and knee alignment are significant factors influencing the incidence of MCL tears in TKR procedures. The Lasso model effectively identified individuals at higher risk. Preventive measures, including surgeon training and the use of specialized MCL retractors, were implemented. Functional outcomes such as knee flexion and KSS scores did not show significant differences post-MCL tear.

MOY 3 - Development and external validation of the “Global Surgical-Site Infection” (GloSSI) predictive model in adult patients undergoing abdominal surgery

Abstract Aims Identification of patients at high-risk of surgical-site infections (SSI) may allow surgeons to minimise associated morbidity. However, there are significant concerns with the methodological quality and transportability of models previously developed. We aimed to develop a novel score to predict 30-day SSI risk following gastrointestinal surgery across a global context, and externally validate against existing models. Methods This was a secondary analysis of 2 prospective international cohort studies: GlobalSurg-1 (July-November 2014) and GlobalSurg-2 (January-July 2016). Consecutive adults undergoing gastrointestinal surgery were eligible. Model development was performed in GlobalSurg-2 data, with novel and previous scores externally validated in GlobalSurg-1. The primary outcome was 30-day SSI, with two predictive techniques explored: penalised regression (LASSO) and machine learning (XGBOOST). Final model selection based on prognostic accuracy and clinical utility. Results There were 14,019 patients (SSI=12.3%) for derivation, and 8,464 (SSI=11.4%) for external validation. The LASSO model was selected due to similar discrimination to XGBoost (AUC: 0.738, 0.725-0.750 versus 0.737, 0.709-0.765), but greater explainability. The final score included six variables: country income, ASA grade, diabetes, and operative contamination, approach, and duration. Model performance remained good on external validation (AUC: 0.730, 0.715-0.744; calibration-in-the-large: -0.098, slope: 1.008), and demonstrated superior performance to external validation of all previous models. Conclusion The GloSSI score allowed accurate prediction of the risk of SSI with 6 simple variables which are routinely available at the time of surgery across global settings. This can inform use of intraoperative and postoperative interventions to modify the risk of SSI and minimise associated harm.

Machine learning-based prediction of early neurological deterioration after intravenous thrombolysis for stroke: insights from a large multicenter study.

This investigation seeks to ascertain the efficacy of various machine learning models in forecasting early neurological deterioration (END) following thrombolysis in patients with acute ischemic stroke (AIS). Employing data from the Shenyang Stroke Emergency Map database, this multicenter study compiled information on 7,570 AIS patients from 29 comprehensive hospitals who received thrombolytic therapy between January 2019 and December 2021. An independent testing cohort was constituted from 2,046 patients at the First People's Hospital of Shenyang. The dataset incorporated 15 pertinent clinical and therapeutic variables. The principal outcome assessed was the occurrence of END post-thrombolysis. Model development was executed using an 80/20 split for training and internal validation, employing classifiers like logistic regression with lasso regularization (lasso regression), support vector machine (SVM), random forest (RF), gradient-boosted decision tree (GBDT), and multi-layer perceptron (MLP). The model with the highest area under the curve (AUC) was utilized to delineate feature significance. Baseline characteristics showed variability in END incidence between the training (n = 7,570; END incidence 22%) and external validation cohorts (n = 2,046; END incidence 10%; p < 0.001). Notably, all machine learning models demonstrated superior AUC values compared to the reference model, indicating their enhanced predictive capacity. The lasso regression model achieved the highest AUC at 0.829 (95% CI: 0.799-0.86; p < 0.001), closely followed by the MLP model with an AUC of 0.828 (95% CI: 0.799-0.858; p < 0.001). The SVM, RF, and GBDT models also showed commendable AUCs of 0.753, 0.797, and 0.774, respectively. Decision curve analysis revealed that the SVM and MLP models demonstrated a high net benefit. Feature importance analysis emphasized "Onset To Needle Time" and "Admission NIHSS Score" as significant predictors. Our research establishes the MLP and lasso regression as robust tools for predicting early neurological deterioration in acute ischemic stroke patients following thrombolysis. Their superior predictive accuracy, compared to traditional models, highlights the significant potential of machine learning approaches in refining prognosis and enhancing clinical decisions in stroke care management. This advancement paves the way for more tailored therapeutic strategies, ultimately aiming to improve patient outcomes in clinical practice.

Construction of circRNA-mediated ceRNA network and immunoassay for investigating pathogenesis of COPD.

The chronic respiratory condition known as chronic obstructive pulmonary disease (COPD) was one of the main causes of death and disability worldwide. This study aimed to explore and elucidate new targets and molecular mechanisms of COPD by constructing competitive endogenous RNA (ceRNA) networks. GSE38974 and GSE106986 were used to select DEGs in COPD samples and normal samples. Cytoscape software was used to construct and present protein-protein interaction (PPI) network, mRNA-miRNA co-expression network and ceRNA network. The CIBERSORT algorithm and the Lasso model were used to screen the immune infiltrating cells and hub genes associated with COPD, and the correlation between them was analyzed. COPD cell models were constructed in vitro and the expression level of ceRNA network factors mediated by hub gene was detected by reverse transcription-quantitative polymerase chain reaction (RT-qPCR). In this study, 852 differentially expressed genes were screened in the GSE38974 dataset, including 439 upregulated genes and 413 downregulated genes. Gene clustering analysis of PPI network results was performed using the Minimum Common Tumor Data Element (MCODE) in Cytoscape, and seven hub genes were screened using five algorithms in cytoHubba. CCL20 was verified as an important hub gene based on mRNA-miRNA co-expression network, GSE106986 database validation and the analysis of ROC curve results. Finally, we successfully constructed the circDTL-hsa-miR-330-3p-CCL20 network by Cytoscape. Immune infiltration analysis suggested that CCL20 can co-regulate immune cell migration and infiltration through chemokines CCL7 and CXCL3. In vitro experiments, the expression of circDTL and CCL20 was increased, while the expression of hsa-miR-330-3p was decreased in the COPD cell model. By constructing the circDTL-hsa-miR-330-3p-CCL20 network, this study contributes to a better understanding of the molecular mechanism of COPD development, which also provides important clues for the development of new therapeutic strategies and drug targets.

Prediction of medical admissions after psychiatric inpatient hospitalization in bipolar disorder: a retrospective cohort study.

Bipolar Disorder (BD) is a severe mental illness associated with high rates of general medical comorbidity, reduced life expectancy, and premature mortality. Although BD has been associated with high medical hospitalization, the factors that contribute to this risk remain largely unexplored. We used baseline medical and psychiatric records to develop a supervised machine learning model to predict general medical admissions after discharge from psychiatric hospitalization. In this retrospective three-year cohort study of 71 patients diagnosed with BD (mean age=52.19 years, females=56.33%), lasso regression models combining medical and psychiatric records, as well as those using them separately, were fitted and their predictive power was estimated using a leave-one-out cross-validation procedure. The proportion of medical admissions in patients with BD was higher compared with age- and sex-matched hospitalizations in the same region (25.4% vs. 8.48%). The lasso model fairly accurately predicted the outcome (area under the curve [AUC]=69.5%, 95%C.I.=55-84.1; sensitivity=61.1%, specificity=75.5%, balanced accuracy=68.3%). Notably, pre-existing cardiovascular, neurological, or osteomuscular diseases collectively accounted for more than 90% of the influence on the model. The accuracy of the model based on medical records was slightly inferior (AUC=68.7%, 95%C.I. = 54.6-82.9), while that of the model based on psychiatric records only was below chance (AUC=61.8%, 95%C.I.=46.2-77.4). Our findings support the need to monitor medical comorbidities during clinical decision-making to tailor and implement effective preventive measures in people with BD. Further research with larger sample sizes and prospective cohorts is warranted to replicate these findings and validate the predictive model.

Identification and validation of oxidative stress-related diagnostic markers for recurrent pregnancy loss: insights from machine learning and molecular analysis.

It has been recognized that oxidative stress (OS) is implicated in the etiology of recurrent pregnancy loss (RPL), yet the biomarkers reflecting oxidative stress in association with RPL remain scarce. The dataset GSE165004 was retrieved from the Gene Expression Omnibus (GEO) database. From the GeneCards database, a compendium of 789 genes related to oxidative stress-related genes (OSRGs) was compiled. By intersecting differentially expressed genes (DEGs) in normal and RPL samples with OSRGs, differentially expressed OSRGs (DE-OSRGs) were identified. In addition, four machine learning algorithms were employed for the selection of diagnostic markers for RPL. The Receiver Operating Characteristic (ROC) curves for these genes were generated and a predictive nomogram for the diagnostic markers was established. The functions and pathways associated with the diagnostic markers were elucidated, and the correlations between immune cells and diagnostic markers were examined. Potential therapeutics targeting the diagnostic markers were proposed based on data from the Comparative Toxicogenomics Database and ClinicalTrials.gov. The candidate biomarker genes from the four models were further validated in RPL tissue samples using RT-PCR and immunohistochemistry. A set of 20 DE-OSRGs was identified, with 4 genes (KRAS, C2orf69, CYP17A1, and UCP3) being recognized by machine learning algorithms as diagnostic markers exhibiting robust diagnostic capabilities. The nomogram constructed demonstrated favorable predictive accuracy. Pathways including ribosome, peroxisome, Parkinson's disease, oxidative phosphorylation, Huntington's disease, and Alzheimer's disease were co-enriched by KRAS, C2orf69, and CYP17A1. Cell chemotaxis terms were commonly enriched by all four diagnostic markers. Significant differences in the abundance of five cell types, namely eosinophils, monocytes, natural killer cells, regulatory T cells, and T follicular helper cells, were observed between normal and RPL samples. A total of 180 drugs were predicted to target the diagnostic markers, including C544151, D014635, and CYP17A1. In the validation cohort of RPL patients, the LASSO model demonstrated superiority over other models. The expression levels of KRAS, C2orf69, and CYP17A1 were significantly reduced in RPL, while UCP3 levels were elevated, indicating their suitability as molecular markers for RPL. Four oxidative stress-related diagnostic markers (KRAS, C2orf69, CYP17A1, and UCP3) have been proposed to diagnose and potentially treat RPL.

Metafeature Selection via Multivariate Sparse-Group Lasso Learning for Automatic Hyperparameter Configuration Recommendation.

The performance of classification algorithms is mainly governed by the hyperparameter settings deployed in applications, and the search for desirable hyperparameter configurations usually is quite challenging due to the complexity of datasets. Metafeatures are a group of measures that characterize the underlying dataset from various aspects, and the corresponding recommendation algorithm fully relies on the appropriate selection of metafeatures. Metalearning (MtL), aiming to improve the learning algorithm itself, requires development in integrating features, models, and algorithm learning to accomplish its goal. In this article, we develop a multivariate sparse-group Lasso (SGLasso) model embedded with MtL capacity in recommending suitable configurations via learning. The main idea is to select the principal metafeatures by removing those redundant or irregular ones, promoting both efficiency and performance in the hyperparameter configuration recommendation. To be specific, we first extract the metafeatures and classification performance of a set of configurations from the collection of historical datasets, and then, a metaregression task is established through SGLasso to capture the main characteristics of the underlying relationship between metafeatures and historical performance. For a new dataset, the classification performance of configurations can be estimated through the selected metafeatures so that the configuration with the highest predictive performance in terms of the new dataset can be generated. Furthermore, a general MtL architecture combined with our model is developed. Extensive experiments are conducted on 136 UCI datasets, demonstrating the effectiveness of the proposed approach. The empirical results on the well-known SVM show that our model can effectively recommend suitable configurations and outperform the existing MtL-based methods and the well-known search-based algorithms, such as random search, Bayesian optimization, and Hyperband.