Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “prediction scoring”

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.

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

At least 37 records · Page 2Linked to original sources
PubMed2026

A multi-scale fusion model based on multi-phase contrast-enhanced CT for predicting pancreatic cancer resectability.

Purpose.Develop a multi-scale fusion model (MSFM) based on multi-phase contrast-enhanced computed tomography (CECT) to predict pancreatic cancer (PC) resectability, thereby assisting expert decision-making.Methods.This retrospective study enrolled 280 patients with PC from four institutions, which were randomly divided into a training cohort (202 patients) and an independent test cohort (78 patients). Three-phase CECT images (arterial, venous, and delayed phases) were used for modeling. The MSFM comprises two sub-networks: (1) a multi-phase fusion network for extracting cross-phase shared fusion features, (2) a phase-specific branch network for capturing phase-specific features; and a post-fusion strategy to generate the final predictive score by integrating the shared fusion features and three groups of phase-specific features. Additionally, a human-machine fusion deep learning model (HMfDL) was constructed by fusing the predictive score of the MSFM with expert assessments.Results.In the independent test, the MSFM achieved an AUC (area under the receiver operating characteristic curve) of 0.8385 (95% CI: 0.7521-0.9249), accuracy of 84.62%, sensitivity of 72.00%, and specificity of 90.57%. This performance outperformed single-phase models (AUC range: 0.7638-0.7781), two-phase models (AUC range: 0.7826-0.7864), and ten states-of-the-art classifiers (AUC range: 0.7404-0.7796). The HMfDL further improved the performance, reaching an AUC of 0.8626 (95% CI: 0.7853-0.9400), accuracy of 91.03%, sensitivity of 80.00%, and specificity of 96.23%. Notably, the HMfDL corrected 58.82% of misdiagnosis made by experts.Conclusions. The MSFM effectively fuses multi-phase CECT to enable highly accurate predictions of PC resectability, and provides valuable support for expert decision-making through HMfDL.

Humans↗
PubMed1978

Sex-related differences in response to practice on a visual-spatial test and generalization to a related test.

93 first graders (mean age 6.5 years) were given a pretest and posttest on half of the items from the Children's Embedded Figures Test. Half of the children were randomly assigned to a training condition and received a brief training procedure on visual-spatial disembedding prior to the administration of the posttest. Children in the control condition received no training. The performance of girls improved significantly more from pretest to posttest than the performance of boys. Boys and girls showed similar beneficial effects of training in addition to the benefit of direct practice. The tendency that was observed for boys to perform higher than girls on the pretest, p less than .10, was not evident on the posttest. Scores on the pretest predicted scores on a different measure of visual-spatial ability only for children in the control group. The results are interpreted in terms of current theories of sex differences in visual-spatial perception.

Child↗
PubMed1979

Environmental influences on vocational interest development in adolescents from adoptive and biological families.

Family influences on vocational interest development were studied by hypothesizing that parents with similar interests are more likely to have adolescents who also develop those interests than are parents whose interests are very divergent. In order to unconfound genetic and environmental influences, the 844 parents and adolescent children in 114 biologically related and 101 adoptive families completed the Strong-Campbell Interest Inventory. Parent-child interest difference scores were regressed on parent-parent difference scores (PPDIF), a dummy variable for family type, and the interaction between family type and PPDIF. For all parent-child pairs except mother-son, greater PPDIF scores predicted greater parent-child difference scores (indicating influence of family environment), and there was no family type X PPDIF interaction (indicating that the environmental influence was operating in both biological and adoptive families). Evidence of genetic variance in interest sytyes was also confirmed.

Adolescent↗
PubMed2026

Digital profiling of dysarthria in late- and early-onset Parkinson's disease.

BackgroundDigital speech analysis affords robust markers of Parkinson's disease (PD). However, most studies target late-onset PD (LOPD), neglecting early-onset PD (EOPD) -an increasingly prevalent subtype. This proof-of-concept study tackles such gap.MethodsWe used machine learning to discriminate persons with EOPD (with symptom onset before age 50) and LOPD (with symptom onset after age 50) from healthy controls (HCs) through prosodic and articulatory features from natural speech.ResultsMaximal classification between patients and HCs was afforded by combined prosodic and articulation features in LOPD (AUC&#x2009;=&#x2009;0.90) and by articulation alone in EOPD (AUC&#x2009;=&#x2009;0.79), with chance-level discrimination between patient groups (AUC&#x2009;=&#x2009;0.55). Motor severity (MDS-UPDRS-III) scores predicted by these features correlated with actual motor severity scores in both LOPD (r&#x2009;=&#x2009;0.52, p&#x2009;<&#x2009;0.001) and EOPD (r&#x2009;=&#x2009;0.27, p&#x2009;<&#x2009;0.001).ConclusionsDigital speech markers offer markers of PD irrespective of age of onset.Plain language summary titleVoice recordings capture motor symptoms in Parkinson's disease irrespective of age of onset.

Humans↗
PubMed2026

Machine learning vs. traditional methods for predicting postoperative cardiac complications after non-cardiac surgery: a systematic review and Bayesian network meta-analysis.

INTRODUCTION: Accurate prediction of peri-operative cardiac complications is critical to optimise pre-operative decision-making. Traditional risk prediction scores, such as the Revised Cardiac Risk Index, show only modest discrimination. Machine learning can model complex, non-linear relationships but their predictive performance compared with traditional scores remains unclear. METHODS: We performed a systematic review and Bayesian network meta-analysis. The primary outcome was postoperative adverse cardiac events following non-cardiac surgery. Prediction models were assessed relative to the Revised Cardiac Risk Index. As many studies evaluated multiple versions of each model type, the highest performing ('best version') and lowest performing ('worst version') results were analysed. Models were ranked using the surface under the cumulative ranking curve (SUCRA). RESULTS: Thirteen studies evaluating 54 models and 927,113 patients were included. Machine learning approaches generally outperformed traditional risk scores. Automated machine learning ranked highest (SUCRA 96.6) showed the greatest improvement in the best version analysis (mean difference (MD) 0.28 (95%CrI 0.16-0.40)) and remained superior in the sensitivity analysis (MD 0.30 (95%CrI 0.14-0.45)). Gradient boosting models showed superior performance over the Revised Cardiac Risk Index across analysis (best version: MD 0.20 (95%CrI 0.14-0.26), worst version: MD 0.18 (95%CrI 0.12-0.25), SUCRA 82.4). The Gupta Perioperative Risk for Myocardial Infarction or Cardiac Arrest score outperformed the Revised Cardiac Risk Index in the best version analysis (MD 0.16 (95%CrI 0.01-0.32)). Between-study heterogeneity was low. None of the included studies externally validated their machine learning models and only six were judged to be at low risk of bias. DISCUSSION: Most machine learning models showed better discrimination than traditional risk scores, with automated machine learning and gradient boosting models ranking highest. However, study quality, calibration reporting and absence of external validation limit immediate clinical adoption. Prospective, multicentre evaluation is required before integration of these models into peri-operative practice.

Humans↗
PubMed2026

Evolution of tumor subclones and T-cell dynamics underlie variable ibrutinib responses in Waldenstr&#xf6;m macroglobulinemia.

To elucidate the molecular basis underlying differential responses and resistance to ibrutinib in Waldenstr&#xf6;m macroglobulinemia (WM), we conducted a prospective phase 2 trial of ibrutinib monotherapy in treatment-na&#xef;ve patients. A total of 74 sequential bone marrow (BM) aspirates from 17 patients, collected from baseline through 48 treatment cycles, were profiled using single-cell multiomics. BM cells were segregated primarily into B-cell/plasma cell and T-cell compartments. Longitudinal clonal tracking of malignant B cells/plasma cells identified 3 distinct evolutionary patterns: evolution (early clone contraction with late clone expansion and increasing genomic complexity), devolution (early clone expansion with late clone contraction and genomic simplification), and no evolution (stable clonal architecture). The evolution pattern was strongly associated with disease progression, whereas devolution correlated with durable clinical response. Transcriptomic profiling of resistant clones enabled development and validation of the Waldenstr&#xf6;m ibrutinib prediction (WIP) score, which predicted treatment response at baseline. Within the WIP signature, LYN emerged as a key regulator; LYN knockdown or inhibition significantly increased WM cell sensitivity to ibrutinib, suggesting a rational combination strategy. In parallel, GZMB+ CD8+ effector-memory T cells expanded after treatment in patients with progressive disease and coexisted with tumor evolution. These cells exhibited persistently impaired cytotoxic programs (eg, GNLY), a dedifferentiated memory-like state, elevated PDCD1 expression, and reduced T-cell receptor diversity. Together, this study provides, to our knowledge, the first single-cell framework of tumor clonal evolution and T-cell dysfunction under ibrutinib in WM, introduces the WIP score as a predictive biomarker for treatment response, and identifies actionable tumor-intrinsic and immune mechanisms driving resistance. This trial was registered at www.ClinicalTrials.gov as NCT02604511.

Aged↗
PubMed2026

Variance Polygenic Scores (vPGS) as a Tool for Studying Gene-Environment Interactions Associated With Refractive Error.

PURPOSE: Conventional polygenic scores predict an individual's phenotype based on their genetics. By contrast, variance polygenic scores (vPGS) quantify genetic predisposition to phenotypic variance. We tested the hypothesis that a vPGS for refractive error can identify individuals with increased susceptibility to environmental risk factors for myopia. METHODS: Six vPGS construction strategies were evaluated in UK Biobank participants: three variance heterogeneity genome-wide association study (vGWAS) methods and two reweighting schemes. vPGS performance was assessed using two metrics: (i) "Diff"-difference in phenotypic variance in vPGS decile ten versus one; (ii) Spearman correlation of phenotypic variance versus vPGS decile. The optimal vPGS was used to test for vPGS &#xd7; time spent reading or vPGS &#xd7; time spent outdoors interactions in children aged 15 years (ALSPAC cohort; n = 3471). RESULTS: Of the vGWAS methods, conditional quantile regression outperformed SCAMPI and Levene's Test. Of the re-weighting schemes, LDpred2 outperformed pruning and thresholding. In an independent sample of UK Biobank participants (n = 19,470), the top-performing vPGS successfully stratified individuals into groups with increasing variance in refractive error, even after adjusting for a conventional PGS (Diff: 2.55, 95% confidence interval [CI], 1.64-3.47; Spearman correlation = 0.87; 95% CI, 0.43-0.93). However, in ALSPAC participants, there was minimal support for vPGS interactions with time reading (P = 0.80) or time outdoors (P = 0.89). CONCLUSIONS: A novel vPGS successfully stratified individuals into groups with relatively high or low genetic susceptibility to refractive error variance. However, the vPGS could not identify individuals at enhanced risk from lifestyle risk factors for myopia.

Humans↗
PubMed1979

Prediction of symptoms and illness behaviour from measures of life change and verbalized depressive themes.

A new measure of depressiveness in speech content and the Schedule of Recent Experiences are used to predict illness reports and clinic use in two samples of subjects. The results suggest that the more life change the subjects reported, the more depressiveness they verbalized, and that both life change and depressiveness scores predict illness reports and health service users. Multivariate combinations of the measures of life change and depressivenss gave better predictions than either measure alone, and the measure of depressiveness for the most part gave somewhat better predictions than the life change measure. This suggest that it is important to quantify reactions to life events. In addition, it suggests that the two longstanding currents of interest in psychosomatic medicine which concern the importance of life events on the one hand and of affective and intrapsychic events on the other can profitably be integrated.

Adolescent↗
PubMed2026

NCBoost v2: a classifier for non-coding single-nucleotide variants in Mendelian diseases.

MOTIVATION: The current diagnostic rate of rare diseases through whole-genome sequencing has stabilized at around 30% on average, highlighting the need for improved computational scores to identify pathogenic variants. In 2019, we developed NCBoost, a supervised-learning approach that mined a comprehensive set of sequence constraint features and proved particularly well suited to identifying high-effect pathogenic non-coding variants in genetic diseases. Since its first release, the substantial increase in the number of variants available for training, as well as the enhanced capacity to detect purifying selection signals from large-scale genome sequencing projects, motivated an update of NCBoost. RESULTS: We implemented NCBoost v2, a pathogenicity score for non-coding single-nucleotide variants, trained on the largest set of curated pathogenic variants in monogenic Mendelian diseases available to date. It leverages conservation features computed from recent large-scale genomic consortia such as Zoonomia and gnomAD, and incorporates recent splice-altering predictive scores. NCBoost v2 outperformed alternative state-of-the-art methods in a variety of scenarii, providing more consistent scores across non-coding genomic regions and fine-tuning the scoring of pathogenic splice-altering variants in Mendelian disease genes. AVAILABILITY AND IMPLEMENTATION: NCBoost v2 software is implemented in Python 3.10 and is freely available under the GNU General Public License Version 3 at https://doi.org/10.5281/zenodo.16029049 and https://github.com/RausellLab/NCBoost-2, together with precomputed scores for the human genome assembly GRCh38.

Polymorphism, Single Nucleotide↗
PubMed2025

A simple approach for multiple observations improves power to detect genetic effects and genomic prediction accuracy.

Many datasets, including widely used biobanks, have more than one observation of numerous phenotypes for at least a portion of their sample. The majority of GWAS utilize only a single observation per individual, even when more than one observation may be available, and apply a standard model in which the additive allelic effect being estimated is assumed to be constant across the age or time range in the sample. Here, we test a set of simple approaches to utilize multiple observations per individual, under this same assumption. We find that utilizing the mean or median of the available observations rather than a single observation improves power to detect associated loci and enriched gene sets and yields higher out-of-sample polygenic score prediction accuracy. Despite growing biobanks, many deeply phenotyped samples are relatively small but have multiple observations. While explicitly modeling age- or time-dependent genetic effects can estimate time- or age-specific genetic effects, most GWAS apply a standard, additive-only model; a simple approach of using the mean or median can improve power by reducing "noise" in the phenotype, utilize standard, optimized software, and be particularly impactful for smaller samples, including samples of diverse genetic ancestry currently existing in widely used biobanks.

Journal Article↗
PubMed2024

Exploring novel MYH7 gene variants using in silico analyses in Korean patients with cardiomyopathy.

BACKGROUND: Pathogenic variants of MYH7, which encodes the beta-myosin heavy chain protein, are major causes of dilated and hypertrophic cardiomyopathy. METHODS: In this study, we used whole-genome sequencing data to identify MYH7 variants in 397 patients with various cardiomyopathy subtypes who were participating in the National Project of Bio Big Data pilot study in Korea. We also performed in silico analyses to predict the pathogenicity of the novel variants, comparing them to known pathogenic missense variants. RESULTS: We identified 27 MYH7 variants in 41 unrelated patients with cardiomyopathy, consisting of 20 previously known pathogenic/likely pathogenic variants, 2 variants of uncertain significance, and 5 novel variants. Notably, the pathogenic variants predominantly clustered within the myosin motor domain of MYH7. We confirmed that the novel identified variants could be pathogenic, as indicated by high prediction scores in the in silico analyses, including SIFT, Mutation Assessor, PROVEAN, PolyPhen-2, CADD, REVEL, MetaLR, MetaRNN, and MetaSVM. Furthermore, we assessed their damaging effects on protein dynamics and stability using DynaMut2 and Missense3D tools. CONCLUSIONS: Overall, our study identified the distribution of MYH7 variants among patients with cardiomyopathy in Korea, offering new insights for improved diagnosis by enriching the data on the pathogenicity of novel variants using in silico tools and evaluating the function and structural stability of the MYH7 protein.

Humans↗
PubMed1979

The safest place of birth: further evidence.

The distribution of births for each place of delivery was studied with a composite antenatal prediction score, incorporating the most important risk factors, which was developed for the second volume of British Births 1970. Although consultant hospitals are seen to have the greatest share of births at moderate and high risk, this is not sufficient to account for the whole amount by which perinatal mortality in these hospitals exceeds that in other places of delivery.

Delivery, Obstetric↗
PubMed2025

Multidrug resistance and recurrence in urinary bacteraemia among cancer patients.

BACKGROUND: Urinary tract infections (UTI) in oncological patients can lead to bacteraemia (bUTI), increasing morbidity and mortality. This study assessed the characteristics, outcomes and recurrence of bUTI in oncological patients. METHODS: A retrospective cohort study was conducted at Hospital Clinic, Barcelona, from 2008 to 2019. All episodes of bUTI in oncological patients were analysed. Multivariable regression models identified independent risk factors for multidrug-resistant (MDR) Gram-negative bacilli (GNB), recurrent bUTI and related mortality. RESULTS: A total of 561 bUTI episodes were identified in 478 oncological patients. Urinary tract involvement due to neoplasm was present in 62.2%, and 59.4% had urinary tract instrumentation. Prior UTI-related admission without bacteraemia was reported in 63.8%. Following bUTI, oncological treatment was delayed in 47% and stopped in 33.6% of cases. GNB caused 87.3% of episodes, with Escherichia coli and Klebsiella spp. being the most common pathogens. Enterococcus spp. and Pseudomonas aeruginosa were frequent, particularly in patients with urinary instrumentation. MDR-GNB caused 19.6% of episodes, and 23.4% of cases received inappropriate empirical antibiotic therapy (IEAT). Recurrent bUTI occurred in 14.0% of patients. A simple predictive score efficiently identified patients at high risk of recurrence. Thirty-day mortality was 15.3%, and bUTI-related mortality was 10.7%, with absence of fever, septic shock and carbapenemase-producing Enterobacterales linked to higher related mortality. CONCLUSION: bUTI in oncological patients is predominantly caused by GNB, with high rates of MDR isolates and high mortality. IEAT is common, and recurrence is significant, highlighting the need for targeted preventive strategies and optimized empirical therapy.

Humans↗
PubMed1978

Parental treatment, children's temperament, and the risk of childhood behavioral problems: 2. Initial temperament, parental attitudes, and the incidence and form of behavioral problems.

Childhood behavioral problems are found to be related to both early temperament and parental behavior, in that first-year temperament scores predicted mild (but not more severe) problems. A parental pathology scale discriminated more severe cases among girls only; more severe cases among boys were accompanied by negative temperament changes. For both sexes, the form of subsequent behavioral problems was associated with first-year temperament patterns.

Adaptation, Psychological↗
PubMed2025

Polygenic Risk Scores for Preeclampsia Prediction Beyond Gold-Standard Clinical Models in Multiethnic Populations.

BACKGROUND: Preeclampsia is a major cause of maternal and fetal mortality and morbidity. Early risk stratification enables timely preventative therapy in high-risk women. Polygenic risk scores (PGS) improve prediction in complex diseases, but their added value for preeclampsia remains unclear, particularly in comparison to gold-standard first-trimester prediction models and across non-European ancestries. METHODS: We evaluated the performance of both a preeclampsia and systolic blood pressure PGS in 2 prospective pregnancy cohorts with detailed phenotyping: the Fetal Medicine Foundation study (n=5207; 2127 cases) and the Pregnancy Outcome Prediction study (n=3659; 228 cases). Risk models included (1) clinical factors; (2) clinical factors plus PGS; (3) advanced model including first-trimester mean arterial pressure, PAPP-A (pregnancy-associated plasma protein-A), and uterine artery pulsatility index; and (4) advanced model plus PGS. Discriminative performance, measured by the area under the receiver operating characteristic curve, was assessed overall and by ancestry. RESULTS: The preeclampsia PGS was independently associated with preeclampsia (odds ratio per SD, 1.24 [95% CI, 1.17-1.31]; P<0.001). It modestly improved prediction over clinical models (area under the receiver operating characteristic curve 0.746 versus 0.750; P=0.017) but not over the advanced model (area under the receiver operating characteristic curve 0.817 versus 0.818; P=0.326). The systolic blood pressure PGS showed stronger performance, improving prediction over both models in women of European ancestry. No improvement was observed with either score in women of African ancestry. CONCLUSIONS: PGSs for preeclampsia and SBP provide modest added predictive value beyond clinical risk factors in European ancestry women. Limited utility in African ancestry women reflects underrepresentation in the genome-wide association studies used to develop current scores. As cohort sizes grow and models are refined, PGSs may become important tools for equitable risk stratification in maternal health.

Adult↗