SEARCH · Search PubMed

Results for “Model selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

957 recordsLinked to original sources

PubMed2026

Nipocalimab Phase 3 Dose Selection for Severe Hemolytic Disease of the Fetus and Newborn.

Nipocalimab, a neonatal Fc receptor (FcRn) blocker, is under evaluation for severe hemolytic disease of the fetus and newborn (HDFN). In the Phase 2 UNITY trial, weekly intravenous antenatal treatment with nipocalimab at dose regimens of 30 and 45 mg/kg prevented fetal anemia requiring intrauterine transfusion (IUT) in 54% of high-risk pregnancies and delayed the need for IUTs versus their previous pregnancies in the remaining 46% of pregnancies. This analysis aimed to select a weekly dose regimen of nipocalimab for the Phase 3 study in severe HDFN (NCT05912517) that maintains FcRn blockade throughout antenatal treatment, including with an unplanned dosing delay of up to 3 days. Observed pharmacokinetic/pharmacodynamic (PK/PD) data from UNITY (i.e., nipocalimab concentrations, FcRn occupancy, and serum IgG) were analyzed using a model-based approach. A PK/PD model originally developed in nonpregnant participants was updated to incorporate gestational weight gain. Nipocalimab PK and FcRn occupancy were described by a two-compartment model with nonlinear, dose-dependent PK, which captured longitudinal PK, FcRn occupancy, and IgG profiles during dosing and return toward baseline postpartum after discontinuation. Both 30 and 45 mg/kg achieved ∼80%-85% reductions in maternal IgG; however, 30 mg/kg showed greater variability in predose trough concentrations, increasing the risk of falling below concentrations required for full FcRn occupancy across antenatal treatment. Simulations incorporating PK/PD variability indicated that 45 mg/kg weekly per current weight maintained full FcRn occupancy in >95% of pregnant individuals, even with dosing delays up to 3 days. Exploratory exposure-response analyses supported 45 mg/kg for the Phase 3 HDFN study.

Humans↗

PubMed2026

Statistical test to compare the linkage model and the admixture model based on central limit results.

In the Admixture Model, the probability that an individual carries a certain allele at a specific marker depends on the allele frequencies in K ancestral populations and the proportion of the individual's genome originating from these populations. The markers are assumed to be independent. The Linkage Model is a Hidden Markov Model that extends the Admixture Model by incorporating linkage between neighboring loci. We prove consistency and asymptotic normality of maximum likelihood estimators for the ancestry of individuals in the Linkage Model, complementing earlier results by (Pfaff et al., 2004; Pfaffelhuber and Rohde, 2022; Heinzel, 2025) for the Admixture Model. These results are used to prove that a statistical test that allows for model selection between the Admixture Model and the Linkage Model is an asymptotic level-α-test. Finally, we demonstrate the practical relevance of our results by applying the test to real-world data from The 1000 Genomes Project Consortium (2015).

Genetic Linkage↗

PubMed2026

Penalized Cumulative Probability Model for a Continuous Outcome Subject to Detection Limits.

Mixed-type outcome data occur when the outcome variable's distribution is a mixture of both continuous and discrete ordinal variables. Such mixed-type outcomes are common in biomedical, psychological, and the health sciences, particularly for variables having either a detection or quantitation limit. When interest lies in identifying a combination of genomic features associated with a mixed-type outcome, any method used would require a variable selection strategy for high-dimensional data. Unfortunately, few variable selection methods exist for modeling a mixed-type outcome when the covariate space is high dimensional. This study develops a high-dimensional penalized cumulative probability model (CPM), to allow for the identification of genomic features associated with mixed-type outcome of interest. We demonstrated how such model may be estimated using the iterative penalization procedure-the generalized monotone incremental forward stagewise (GMIFS) algorithm. The Model-X knockoffs procedure was combined with the estimation algorithm to control the false discovery rates (FDR) when performing variable selection. Through extensive simulation studies, our penalized CPM was shown to outperform alternative methods in terms of controlled variable selection performance by achieving high statistical power with the FDR being controlled at the target level. We demonstrate the utility of our method by applying it to predict estimated glomeruli filtration rate (eGFR) in kidney transplant recipients at 24 months post-transplant using baseline gene expression data as predictors. Our CPM model identified five genes associated with this mixed-type outcome which have important links to renal disease, which may provide prognostic guidance for kidney transplantation recipients.

Models, Statistical↗

PubMed2026

Clinical applications of digital twin technology in In Vitro Fertilisation.

BACKGROUND: Digital twin technology, originating from aerospace and manufacturing industries, has emerged as a transformative tool in healthcare. In vitro fertilisation (IVF) faces persistent challenges including suboptimal embryo selection, unpredictable treatment outcomes, and limited personalisation of protocols. Despite advances in assisted reproductive technology, existing literature exhibits fragmentation: artificial intelligence applications in embryo selection, ovarian stimulation, and endometrial assessment have been developed independently without systematic integration into comprehensive treatment frameworks. Digital twin technology offers unprecedented opportunities to create virtual replicas of biological systems, enabling real-time monitoring, predictive modelling, and personalised treatment strategies. AIM: This narrative review aims to critically examine the current applications of digital twin technology in IVF, evaluate its potential benefits and limitations, synthesize existing evidence into an integrative conceptual model, and identify future directions for implementation in reproductive medicine. METHOD: A comprehensive narrative review was conducted using PubMed, Scopus, Web of Science, and IEEE Xplore databases. A narrative review approach was selected over systematic review to accommodate the heterogeneity of evidence types in this emerging field, including theoretical frameworks, simulation studies, and proof-of-concept implementations that would be excluded from systematic reviews. Search terms included "digital twin," "IVF," "in vitro fertilisation," "assisted reproductive technology," "embryo selection," and "predictive modelling." Studies published between 2015 and 2025 were included, focusing on original research articles, systematic reviews, and proof-of-concept studies describing digital twin applications in reproductive medicine. RESULTS: Digital twin technology in IVF demonstrates significant potential across multiple domains including embryo development simulation, ovarian response prediction, endometrial receptivity modelling, and personalised stimulation protocols. Current applications integrate artificial intelligence, machine learning algorithms, time-lapse imaging, and omics data to create comprehensive virtual models. Early evidence suggests improvements in embryo selection accuracy, ovarian response prediction, and treatment protocol optimization, though large-scale randomized controlled trials remain limited. Implementation challenges include data integration complexity, computational requirements, regulatory considerations, and validation requirements. CONCLUSION: Digital twin technology represents a paradigm shift in IVF practice, offering personalised, predictive, and precision medicine approaches. This review synthesizes existing evidence to propose an integrative conceptual model for digital twin implementation across the IVF treatment spectrum, identifies critical knowledge gaps, and establishes research priorities to advance clinical translation. Despite current limitations, continued advancement promises improved success rates and patient outcomes.

Humans↗

PubMed2026

Selective monitoring of trace-level catechin and myricetin in herbal and aqueous matrices using magnetic MIP-DSPME: Optimization via design of experiments.

A novel dispersive solid-phase microextraction approach utilizing a magnetic molecularly imprinted polymer (MMIP) integrated with HPLC-UV detection was developed for the concurrent quantification of catechin and myricetin in herbal extracts and aqueous samples. The sorbent was engineered as a core-shell nanocomposite, consisting of a selective polymer layer deposited onto Fe3O4@SiO2-APTMS magnetic nanoparticles. Dual-template imprinting using catechin and myricetin generated complementary binding cavities within the polymer framework. Experimental variables influencing extraction were systematically screened and subsequently optimized. A Plackett-Burman design was first applied to identify the most influential factors, with pH and sorption time identified as the dominant variables. These parameters were subsequently fine-tuned using a central composite design, and the optimization process was completed in only 30 experimental runs. The sorption characteristics of the imprinted sorbent (MMIP) were compared with those of its non-imprinted counterpart (MNIP). The MMIP demonstrated markedly higher maximum binding capacities (Qmax), reaching 119.3 mg g-1 for myricetin and 112.1 mg g-1 for catechin, whereas the corresponding values for the MNIP were 32.55 and 32.08 mg g-1, respectively. Moreover, the affinity constants (KL = 0.760-0.950 L mg-1) were approximately 2.3-fold higher for the MMIP, confirming its stronger and more selective interactions with the target analytes. The selectivity coefficients for the targeted flavonoids relative to structurally related compounds, including ferulic acid, p-coumaric acid, melatonin, and curcumin, exceeded 3.5 for the MMIP, whereas the corresponding values for the MNIP were close to 1.1, demonstrating the high molecular recognition capability of the imprinted sorbent. Method validation demonstrated limits of detection (LODs) of 0.33-0.59 ng mL-1 and limits of quantification (LOQs) of 1.10-1.96 ng mL-1, and excellent linearity over the concentration range of 5.0-5500 ng mL-1 (R2 > 0.998). The method achieved recoveries of 93.96% to 105.69% with RSDs below 5.5%, while the preconcentration factors ranged from 209 to 229. Furthermore, the sorbent retained more than 95% of its extraction efficiency after four consecutive reuse cycles and more than 80% after six cycles, demonstrating excellent stability and reusability. The proposed method was successfully applied to the analysis of six medicinal plant extracts and water samples, showing negligible matrix interference and superior sensitivity, selectivity, and operational simplicity compared with conventional solid-phase extraction methods.

Flavonoids↗

PubMed2026

Analyzing salinity tolerance in grass carp (Ctenopharyngodon idella): Insights from genome-wide association study and genomic selection.

Grass carp (Ctenopharyngodon idella) is one of the most widely cultured freshwater fish species globally. However, the expansion of its farming scale faces severe limitation owing to freshwater scarcity; therefore, the development of strains with greater salinity tolerance is key for expanding production using brackish water resources. To investigate the genetic basis of salinity tolerance in grass carp, a genome-wide association study (GWAS) was conducted using 200 individuals representing extreme phenotypes, namely salinity-tolerant and salinity-sensitive groups. In total, 17 single nucleotide polymorphisms (SNPs) related to salinity tolerance were detected, which were distributed across 11 chromosomes. Through gene annotation, 38 candidate genes were obtained from these loci. Enrichment analysis revealed these candidate genes are primarily implicated in key biological processes, including osmotic regulation, energy metabolism, and stress responses. Analyses of different SNP densities revealed that the 5 K SNP density panel can balance prediction accuracy and computational efficiency. The BayesA model achieved the highest prediction accuracy under the GWAS_Evenly selection strategy, with substantial reductions in mean absolute error and mean square error. This study reveals the genetic mechanisms of salinity tolerance in grass carp, which might be optimized through genomic selection, and provides insights for selectively breeding new varieties with greater salinity tolerance.

Animals↗

PubMed2026

Effect of Semaglutide on the Inflammatory Biomarker High-Sensitivity CRP in Patients With Established Cardiovascular Disease and Overweight or Obesity in SELECT: A Prespecified Secondary Analysis.

BACKGROUND: In SELECT (Semaglutide Effects on Heart Disease and Stroke in Patients With Overweight or Obesity), among 17 604 patients with known atherosclerotic cardiovascular disease and overweight or obesity, but not diabetes, randomization to the glucagon-like peptide-1 receptor agonist semaglutide significantly reduced the primary outcome of major adverse cardiovascular events (MACE; cardiovascular death, nonfatal myocardial infarction, or nonfatal stroke) compared with placebo (mean follow-up, 39.8 months). Inflammation, as indicated by plasma hsCRP (high-sensitivity C-reactive protein) level, is implicated as a biomarker predicting cardiovascular risk in obesity and atherosclerotic cardiovascular disease. SELECT provides a unique opportunity to study the relationship among hsCRP, obesity, weight loss, and MACE outcomes in semaglutide versus placebo groups. METHODS: In this prespecified SELECT substudy, we evaluated whether baseline hsCRP levels predicted MACE risk and examined the relationships between changes in hsCRP levels and time to first MACE, baseline body weight, weight loss, and other clinical measures among treatment groups over time (104, 208 weeks) using multiple approaches, including Cox modeling. RESULTS: Baseline hsCRP level, which was similar in the semaglutide (geometric mean 1.96 mg/L) and placebo (geometric mean 1.91 mg/L) groups, was prognostic of future MACE. The risk of MACE increased across baseline hsCRP level <2, 2-<10, and ≥10 mg/L subgroups, including significant associations with cardiovascular and all-cause death. Semaglutide reduced hsCRP levels (-37.8% [104 weeks]) and risk of MACE across all hsCRP subgroups. Greater reductions in ratio-to-baseline hsCRP with semaglutide were associated with greater weight loss, but preceded major weight loss, evident by 4 and 8 weeks, and occurred among those without weight loss. Semaglutide-associated changes in hsCRP were independent of low-density lipoprotein cholesterol levels, statin use, and atherosclerotic cardiovascular disease entry criteria. hsCRP reductions were found to be prognostic of decreased risk of MACE. Modeling suggests decreased inflammation as contributing in part to the benefits seen with semaglutide in SELECT. CONCLUSIONS: In SELECT, hsCRP data at baseline and in response to treatment with semaglutide support inflammation as a potential prognostic factor associated with cardiovascular risk in these generally well-treated patients with atherosclerotic cardiovascular disease and overweight or obesity but not diabetes. These findings suggest that the MACE reduction observed with semaglutide versus placebo in SELECT may have partially involved a decrease in inflammation. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT03574597.

Humans↗

PubMed2026

Metagenome-scale modeling to assess microbiome metabolic complementarity for precision microbiota transplantation therapies.

Fecal microbiota transplantation (FMT) holds therapeutic promise beyond recurrent Clostridioides difficile infection, but clinical outcomes remain unpredictable and donor-selection strategies remain limited, in part because the role of donor‒recipient metabolic interactions in shaping the post-FMT community remains poorly understood. Here, we leverage metagenome-scale metabolic modeling to quantify metabolic niche complementarity between donor and recipient microbiomes and predict post-FMT community composition. Using MICOM-derived metabolic models, we show that donor genomes whose metabolic flux profiles are more dissimilar from the recipient community colonize at significantly higher rates in a murine FMT model. In a human IBS trial, the same metric predicted post-FMT community composition via leave-one-out cross-validation and captured known disease-associated alterations in short-chain fatty acid, sulfur, and gas metabolism. We then performed 2,548 in silico FMT simulations between IBS-D/M patients and donors from the OpenBiome biobank to evaluate personalized donor screening, identifying super-donors characterized by high taxonomic diversity, broad metabolic niche coverage, and community interaction networks dominated by cross-feeding rather than competition. Together, these results support metabolic niche complementarity as a potential determinant of post-FMT community composition and provide a mechanistic basis for evaluating donor-recipient metabolic compatibility. This framework offers a scalable approach for generating testable hypotheses for personalized donor selection.

Fecal Microbiota Transplantation↗

PubMed2026

The effect of olfactory training and odor exposure on visual selective attention.

Olfactory training (OT) is a well-established, non-invasive intervention that improves olfactory function by repeated, structured exposure to odorants. Beyond sensory outcomes, it also influences multiple aspects of cognition. Yet, its influence on attention, a fundamental process underlying many cognitive domains, remains unclear. This study examined the impact of a 12-week OT program on visual selective attentional performance and the effect of on-task odor exposure. Ninety-four healthy participants were initially included, and randomized into OT or placebo groups. Participants completed the d2 Test of Attention simultaneously with and without odor exposure in a randomized sequence at baseline, post-training, and a follow-up four weeks after stopping the training. The d2 test measures commission errors, omission errors, and concentration performance. Ninety-three participants (OT=51, placebo=42) completed baseline measurement, 74 (OT=39, placebo=35) returned for post-training session, and 57 participants (OT=29, placebo=28) returned for the follow-up appointment. Results showed that OT did not significantly improve d2 test performance. In the primary model, on-task PEA exposure reduced commission errors compared to the odorless condition, suggesting a possible transient effect of olfactory input on the inhibitory control in the context of the d2 attentional test. This effect, however, was no longer significant once the follow-up data were included and should be regarded as preliminary. Overall, these findings raise the possibility of a distinction between relatively long-term OT and short-term odor exposure: while OT did not improve visual selective attention, brief on-task odor exposure may transiently enhance inhibitory control during attentional tasks, a possibility that remains to be confirmed.

Humans↗

PubMed2026

Construction of precision clinical-proteomics risk model based on machine learning for predicting heart failure in type II diabetes mellitus.

BACKGROUND AND AIMS: Heart failure (HF) is a severe complication in type 2 diabetes mellitus (T2DM), but current risk stratification scores have limited predictive accuracy. We aimed to develop novel prediction tools integrating clinical variables with proteomics to improve risk stratification of hospitalization for HF in T2DM. METHODS AND RESULTS: In this study, we included 2111 UK Biobank participants with T2DM but no prior HF, and profiled 2920 proteins to predict 10-year incident HF hospitalization. Participants were randomly divided into training (70%), tuning (10%), and validation (20%) sets.Three prediction models were developed: a Clinical model based on demographic characteristics, comorbidities, medication use, and laboratory indices; a Protein model based on 40 proteins selected by the Light Gradient Boosting Machine (LGBM); and the Clinical OMics and Protein ASSessment for Heart Failure (COMPASS-HF) model, which integrated both clinical variables and the LGBM-selected proteins. Models were evaluated for area under the curve (AUC), sensitivity, and specificity. During follow-up, 168 participants (7.96%) developed incident HF. The COMPASS-HF model showed better discrimination than the Clinical model, with an AUC of 0.897 (95% CI: 0.850-0.945) versus 0.790 (95% CI: 0.723-0.856). It also demonstrated higher sensitivity (0.882; 95% CI: 0.725-0.967) and consistent performance in subgroups. COMPASS-HF effectively stratified risk of hospitalization for HF, with cumulative incidence rates of 31.9% in the high-risk group and 1.2% in the low-risk group. CONCLUSIONS: By combining clinical and proteomic variables, we developed a high-performance HF prediction model for T2DM, enabling precise risk stratification and informing early intervention strategies.

Humans↗

PubMed2026

Predictive Models for Hypoglycemia Risk in Haemodialysis Patients With Diabetic Kidney Disease: Systematic Review and Meta-Analysis.

AIM: To provide evidence for selecting and developing reliable clinical assessment tools for hypoglycemia in diabetic kidney disease patients during haemodialysis. DESIGN: Review. METHODS: Systematic searches were performed in 9 Chinese and English databases to collect literature regarding the development of hypoglycemia risk prediction models in haemodialysis patients with diabetic kidney disease. Two reviewers independently performed literature screening, data extraction, risk-of-bias assessment, and applicability evaluation. The Prediction Model Risk of Bias Assessment Tool was used to assess the risk of bias and applicability of the included studies. Meta-analysis was conducted using R software. DATA SOURCES: CNKI, Wanfang, VIP, CBM, PubMed, Cochrane Library, EMbase, Web of Science, and CINAHL. The search period covered from the establishment date of each database to December 2025. RESULTS: Six studies, comprising six prediction models, were included. Two studies performed internal validation, and three conducted external validation. All models reported the area under the curve, ranging from 0.813 to 0.866, and calibration measures. Four studies were rated as having a high risk of bias, while all six demonstrated good overall applicability. The meta-analysis showed that the pooled AUC value of the six studies was 0.846 (95% CI: 0.823-0.867). CONCLUSION: Research on hypoglycemia risk prediction models in haemodialysis patients with diabetic kidney disease remains in the developmental stage. Although the included prediction models exhibited satisfactory apparent discriminatory ability and clinical applicability, most of the original studies suffered from a high risk of bias and lacked adequate validation. The true predictive performance and clinical application value of these models remain to be further verified. Accordingly, routine and unconditional clinical application is not recommended at this stage. Future studies should include more high-quality, multicenter external validation and develop models with high generalizability, favourable clinical applicability, and robust predictive performance to facilitate early identification of hypoglycemia risk in this population. IMPACT: This study systematically evaluated the hypoglycemia risk prediction models for diabetic kidney disease patients during haemodialysis, and the research on hypoglycemia risk prediction models for maintenance haemodialysis patients during dialysis is still in the development stage. This study provides a reference for clinical medical staff to select or develop hypoglycemia risk prediction and assessment tools for diabetic kidney disease patients during haemodialysis. REPORTING METHOD: This study was conducted in accordance with the relevant guidelines of the EQUATOR Network and followed the TRIPOD-SRMA Checklist. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution. TRIAL REGISTRATION: PROSPERO: CRD420251243352.

Humans↗

PubMed2026

A systematic review and meta-analysis of visuospatial attentional deficits in Parkinson's patients.

Parkinson's disease (PD) is a neurodegenerative condition primarily characterized by motor deficits, yet cognitive impairments are increasingly recognized. While deficits in executive functioning are well documented even in the absence of cognitive decline, evidence of attentional deficits in PD remains inconsistent, and the role of motor symptom lateralization is unclear. In this systematic review and meta-analysis, we examined visual attention in right-handed, cognitively unimpaired idiopathic PD patients, focusing on the canonical attentional domains (sustained, selective, divided) and processes (alerting, endogenous and exogenous orienting, reorienting), as well as visuospatial bias. Four databases were searched for studies comparing PD patients with healthy controls. Meta-analytic estimates were derived using Hedges' g within random-effects models, and studies that could not be quantitatively integrated were summarized narratively. In addition, studies directly comparing patients with left- and right-predominant motor symptoms (LPD vs. RPD) were reviewed qualitatively. Across 51 studies, PD patients exhibited deficits in sustained, selective, and divided attention. Among attentional processes, only exogenous orienting was impaired, whereas alerting, endogenous orienting, and reorienting were preserved. Findings from the few studies examining visuospatial bias indicated small, context-dependent shifts in spatial attention rather than a consistent directional bias. These findings indicate that PD patients show visual-attentional impairments, particularly under high-demand conditions, while basic alertness and voluntary orienting appear preserved. Exogenous orienting deficits and subtle rightward spatial tendencies in LPD suggest disruption of right-hemisphere attentional networks. These results have implications for early cognitive assessment, rehabilitation strategies, and understanding the neural bases of attentional dysfunction in PD.

Humans↗

PubMed2026

Mul-PheG2P: decoupled learning and prediction-space fusion enables robust and interpretable multi-phenotype genomic prediction.

Genomic prediction of multiple phenotypes is crucial in modern plant breeding; however, existing methods struggle with negative transfer and lack interpretability, particularly across high-dimensional small-sample data and diverse species. To address this, we propose Mul-PheG2P, a novel paradigm based on decoupled learning and predictive space fusion. It employs a two-stage design: first training phenotype-specific encoders using genetic data, then decoupling phenotype-specific learning from cross-phenotype aggregation via an interpretable prediction layer. Mul-PheG2P outperforms existing methods across diverse crop datasets, including maize (Zea mays), wheat (Triticum aestivum), and tomato (Solanum lycopersicum). It provides a multi-scale interpretability chain: at the macro level, it quantifies phenotypic contributions via attention-based weighting; at the micro level, Integrated Gradients reveal the genetic basis of predictions. Notably, the model successfully identified the CCT (CONSTANS, CO-like, and TOC) motif regulating photoperiodism and the SQUAMOSA (SQUAMOSA promoter binding protein) promoter for inflorescence development, confirming its ability to capture functional biological mechanisms. These results highlight the high performance and interpretability of Mul-PheG2P, showcasing its value for low-cost, large-scale screening to advance precision breeding.

Phenotype↗

PubMed2026

Development and validation of a comprehensive prognostic model for 28-day ICU mortality in non-traumatic subarachnoid hemorrhage: an analysis based on the MIMIC-IV database.

BACKGROUND: Due to the complex pathophysiology of non-traumatic subarachnoid hemorrhage (SAH), accurate risk prediction remains a challenge. Our aim is to develop and validate a comprehensive prognostic model that integrates demographic characteristics, vital signs, laboratory parameters, and more, to provide clinical decision-making support in real-world practice. METHODS: We conducted a retrospective cohort study of 785 Non-traumatic subarachnoid hemorrhage patients. The cohort was randomly divided into a training set (n = 549) and a validation set (n = 236). Feature selection was performed using LASSO regression, followed by backward stepwise Cox regression for optimization. A nomogram was constructed based on independent predictive factors, and model performance was assessed using discrimination, calibration, and decision curve analysis. To prevent immortal-time bias, all predictors were anchored to a fixed early (first-24-hour) measurement window, treatment variables were modelled as binary indicators rather than cumulative exposures, and a five-model sensitivity analysis with baseline-severity adjustment was performed. RESULTS: The development of our model followed a systematic approach: first, 15 potential predictive factors were selected via LASSO regression, which were then refined to 12 independent predictors using backward stepwise Cox regression. The final predictive factors included: Ventilation, AHT, Nimodipine 60 mg, Age, SAPS.II, Input amount, Calcium total, Platelet count, White blood cells, Anion gap, pH, and Chloride. The integrated model demonstrated excellent predictive ability for 7-day, 14-day, and 21-day mortality in both the training set (AUC: 0.972, 0.934, 0.898) and the validation set (AUC: 0.968, 0.948, 0.911). Calibration curves and decision curve analysis confirmed the model's reliability and clinical utility across different time points. We constructed a nomogram for individualized risk prediction. Univariate Kaplan-Meier survival analysis demonstrated significant stratification of survival outcomes by each predictor, while restricted cubic spline analysis revealed non-linear relationships between continuous variables and mortality risk. Random survival forest analysis identified the top three predictive factors (Nimodipine 60 mg, Ventilation, AHT) and compared them with our full 12-variable model, confirming superior performance of the integrated model at all time points. At the 28-day primary endpoint, the model achieved a time-dependent AUC of 0.898 (training) and 0.904 (validation); after restricting predictors to the early baseline window, the leakage-controlled model retained good discrimination (validation C-index 0.803). CONCLUSIONS: Our ICU 28-day mortality prognosis model demonstrated robust performance in predicting ICU 28-day mortality in non-traumatic subarachnoid hemorrhage. The model, through the nomogram, provides individualized risk assessment, aiding clinical decision-making and patient stratification.

Humans↗

PubMed2026

Hierarchical modeling of tumor subtypes in cell lines using large-scale genomic datasets.

Cancer cell lines (CLs) are widely used to study tumor biology and drug response, yet their translational relevance is often limited by inaccurate subtype annotations. Existing CL-tumor matching approaches are frequently constrained by flat classification schemes, weak subtype definitions, and the exclusion of normal tissue references, leading to potential confounding of tumor-specific and tissue-of-origin signals. To address these limitations, a hierarchical classification (HC) framework is presented in which CLs are aligned with patient tumors across biological resolutions, from organ to molecular subtype. Gene expression profiles from 802 CLs, 5,612 tumors from The Cancer Genome Atlas (TCGA) , and 8,939 non-cancerous tissues were integrated to separate oncogenic signals from tissue-specific signals. Node-specific features were selected using maximum relevance minimum redundancy, and balanced accuracies of 89% in cross-validation and 75%, and 80% on external datasets were achieved. Through the framework, 43 CLs were reassigned, and clinically relevant underrepresented subtypes were identified.

cancer cell lines↗

PubMed2026

An Assessment of Reliability Estimation Methods for Binomial Health Care Quality Measures.

We evaluated the performance of commonly used methods for estimating the reliability of binomial health care quality measures using simulated datasets spanning a range of performance score means and variances, numbers of entities, and patient sample sizes. For each simulation, reliability was estimated for all selected methods and compared with the known true reliability derived from the simulation parameters, with methods assessed on their accuracy and precision. Logistic regression with reliability estimated on the outcome scale demonstrated the highest accuracy and precision among all methods evaluated. The widely used Adams beta-binomial method performed poorly, although a modification recommended by Nieser and Harris substantially improved its performance. These approaches are applicable only to binomial measures. Among methods that can be applied to both binomial and continuous measures, permutation resampling of the Spearman rank correlation coefficient was the most accurate and precise, outperforming other commonly used approaches. Overall, for binomial quality measures, logistic regression on the outcome scale is the preferred method for reliability estimation, followed closely by the modified beta-binomial approach, while for non-binomial measures, permutation-based Spearman rank correlation appears to be the most suitable method.

Reproducibility of Results↗

PubMed2026

Rational design of high-productivity perfusion processes for CHO Cells: From growth inhibitory strategies to model-driven optimization.

While perfusion culture for Chinese hamster ovary (CHO) cells offers advantages such as continuous operation and flexibility, it suffers from product loss through cell bleeding and difficulties in reaching high productivity due to sustained rapid cell growth. Growth inhibitory strategies are widely used to enhance productivity in fed‑batch processes; however, their practical implementation and comparative effectiveness in perfusion processes remain insufficiently explored. Meanwhile, process development often relies on costly trial‑and‑error approaches. Here, we systematically compared three growth inhibitory strategies in perfusion culture-low cell‑specific perfusion rate (CSPR), sodium butyrate, and mild hypothermia-with respect to cell growth, metabolism, productivity, and product quality. Genome‑scale metabolic flux sampling analysis revealed that low‑CSPR and sodium butyrate induce a convergent up‑regulation of energy metabolism, correlating with greater gains in specific productivity (qp). Building on this insight, we developed a growth‑kinetic model for the combined low‑CSPR + butyrate strategy, incorporating parameter uncertainty. This model‑guided framework enabled the rational design of two distinct high‑productivity perfusion processes: a sustained mode that achieved robust long‑term stability alongside substantial productivity gains, and a high‑intensity mode that pushed qp and daily volumetric titer to their maxima, with increases of up to 108.94% and 190.36%, respectively, in a model CHO cell line with a moderate baseline productivity. Our study provides a proof‑of‑concept framework for perfusion intensification, from strategy selection to rational process design.

Animals↗

PubMed2026

Diagnostic performance of machine learning models for malignant and non-malignant pleural effusion: Systematic review and meta-analysis.

BACKGROUND: Accurately distinguishing malignant pleural effusion (MPE) from non-malignant pleural effusion is clinically important, but the generalisability and methodological quality of machine-learning (ML) models remain uncertain. METHODS: We searched eight databases to 23 April 2026. Diagnostic performance was pooled using random-effects and Reitsma bivariate models, and study quality was assessed using PROBAST+AI. RESULTS: Forty-two studies were included; 17 contributed to the AUC meta-analysis and 14 to the bivariate analysis. The pooled AUC was 0.90 (95 % CI 0.85-0.94; 95 % prediction interval 0.62-0.98), with sensitivity of 0.80 (95 % CI 0.77-0.83) and specificity of 0.87 (95 % CI 0.79-0.92). Only nine studies reported external, temporal or independent validation. Externally validated studies had a lower pooled AUC than studies without external validation (0.83 vs 0.92), with lower specificity observed in the two externally validated studies contributing sensitivity and specificity data. All 42 development assessments had high overall quality concerns, and all 42 model evaluations were judged at high risk of bias. CONCLUSIONS: ML models showed good apparent accuracy for distinguishing MPE from non-MPE, but the evidence was limited by substantial heterogeneity, high risk of bias and scarce external validation. The pooled estimates reflect the average performance of different selected models rather than the expected accuracy of a single clinical test. ML models should be regarded as adjuncts to existing diagnostic pathways until they are confirmed by rigorous multicentre prospective external validation and clinical-impact studies.

Humans↗