SEARCH · PubMed Health

Results for “predictive modelling”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 1,513 records · Page 84Linked to original sources

PubMed2001

Blazing pathways through genetic mountains.

It is now widely accepted that high-throughput data sources will shed essential understanding on the inner workings of cellular and organism function. One key challenge is to distill the results of such experiments into an interpretable computational form that will be the basis of a predictive model. A predictive model represents the gold standard in understanding a biological system and will permit us to investigate the underlying cause of diseases and help us to develop therapeutics. Here I explore how discoveries can be based on high-throughput data sources and discuss how independent discoveries can be assembled into a comprehensive picture of cellular function.

Animals↗

PubMed2004

Evaluation of Staphylococcus aureus growth potential in ham during a slow-cooking process: use of predictions derived from the U.S. Department of Agriculture Pathogen Modeling Program 6.1 predictive model and an inoculation study.

The U.S. Department of Agriculture has cautioned against slow cooking meat such that the interior temperature increases from 10 degrees C (50 degrees F) to 54.4 degrees C (130 degrees F) in > or = 6 h. During a commercial ham-smoking process, the ham cold point is typically between 10 and 54.4 degrees C for 13 h, but the ham is subsequently exposed to heating sufficient to eliminate vegetative pathogenic bacteria. Thus, production of heat-stable staphylococcal enterotoxin is the primary biological hazard. For this study, uncooked surface and uncooked ground interior ham were inoculated with a three-strain Staphylococcus aureus mixture, exposed to simulated surface and interior slow-cook conditions, respectively, and analyzed periodically using the Baird-Parker agar and 3M Petrifilm Staph Express count plate methods. For the surface and interior conditions, S. aureus numbers increased by no more than 0.1 and 0.7 log units, respectively. Predictions derived from actual time and temperature data and S. aureus growth values from a computer-generated model (Pathogen Modeling Program 6.1, U.S. Department of Agriculture) were for 2.7 (ham surface) and 9.9 to 10.5 (ham interior) generations of S. aureus growth, indicating that use of model-derived growth values would not falsely indicate safe slow cooking of ham. The Baird-Parker method recovered significantly (P < 0.05) greater numbers of S. aureus than the Petrifilm Staph Express method. For hams pumped with brine to attain (i) 18% (wt/wt) weight gain, (ii) > or = 2.3% sodium lactate, (iii) > or = 0.8% sodium chloride, and (iv) 200 ppm ingoing sodium nitrite, slow-cooking critical limits of < or = 4 h between 10 and 34 degrees C, < or = 5 h between 34 and 46 degrees C, and < or = 5 h between 46 and 54.4 degrees C could be considered adequate to ensure safety.

Animals↗

PubMed1995

Tree-structured prediction for censored survival data and the Cox model.

Prediction trees for the analysis of survival data are discussed. It is shown that trees are useful not only in summarizing the prognostic information contained in a set of covariates (prognostic classification), but also in detecting and displaying treatment-covariates interactions (subgroup analysis). The RECPAM approach to tree-growing is outlined; prognostic classification and subgroup analysis are then formulated within the RECPAM framework and on the basis of the Cox proportional hazards models with a priori strata. Two examples of data analysis are presented. The issue of cross-validation is discussed in relation to computationally cheaper model selection criteria.

Algorithms↗

PubMed2005

Toxicity assessment of environmentally relevant pollutant mixtures using a heuristic model.

In this study, 9 chemicals were chosen from a recent report on surface water concentrations of a variety of xenobiotics to test the hypothesis that the toxicity of chemical mixtures could be estimated using a model based on the toxicity of the individual chemicals. Concentration-response curves for the endpoints of lifespan, growth rate, and fecundity were generated for each chemical experimentally using the crustacean, Daphnia magna. From this data, a mathematical model for the combined toxicity of these chemicals was generated that merged the concepts of concentration addition and independent joint action. Toxicity of a mixture was modeled at various levels at which the ratio of the chemicals within the mixture was maintained at that reported for median detected environmental levels. Toxicity of the mixture was then determined experimentally and compared to model predictions. The model accurately predicted the most sensitive endpoint, as well as the lowest toxic effect level of the mixture. Results demonstrated that, for this mixture of chemicals, toxicity was not influenced significantly by interactions among the chemicals and a single constituent dominated toxicity. According to model predictions and experimental results, the median detected environmental concentrations of chemicals constituting this mixture provided no margin of safety.

Animals↗

PubMed2005

An evaluation of evaluative personality terms: a comparison of the big seven and five-factor model in predicting psychopathology.

Two personality models are compared regarding their relationship with personality disorder (PD) symptom counts and with lifetime Axis I diagnoses. These models share 5 similar domains, and the Big 7 model also includes 2 domains assessing self-evaluation: positive and negative valence. The Big 7 model accounted for more variance in PDs than the 5-factor model, primarily because of the association of negative valence with most PDs. Although low-positive valence was associated with most Axis I diagnoses, the 5-factor model generally accounted for more variance in Axis I diagnoses than the Big 7 model. Some predicted associations between self-evaluation and psychopathology were not found, and unanticipated associations emerged. These findings are discussed regarding the utility of evaluative terms in clinical assessment.

Adult↗

PubMed2001

What happens when we relearn part of what we previously knew? Predictions and constraints for models of long-term memory.

Part-set relearning studies examine whether relearning a subset of previously learned items impairs or improves memory for other items in memory that are not relearned. Atkins and Murre have examined part-set relearning using multi-layer networks that learn by optimizing performance on a complete set of items. For this paper, four computer models that learn each item additively and separately were tested using the part-set relearning procedure (Hebbian network, CHARM, MINERVA 2, and SAM). Optimization models predict that part-set relearning should improve memory for items not relearned, while additive models make the opposite prediction. This distinction parallels the relative ability of these models to account for interference phenomena. Part-set relearning provides another source of evidence for choosing between optimization and additive models of long-term memory. A new study suggests that the predictions of the additive models are broadly supported.

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↗

PubMed2001

Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods.

The question of whether two disorders cluster together, or coaggregate, within families often arises. This paper considers how to analyze familial aggregation of two disorders and presents two multivariate logistic regression methods that model both disorder outcomes simultaneously. The first, a proband predictive model, predicts a relative's outcomes (the presence or absence of each of the two disorders) by using the proband's disorder status. The second, a family predictive model derived from the quadratic exponential model, predicts a family member's outcomes by using all of the remaining family members' disorder statuses. The models are more realistic, flexible, and powerful than univariate models. Methods for estimation and testing account for the correlation of outcomes among family members and can be implemented by using commercial software.

Family↗

PubMed1991

Structure prediction and modelling.

Protein structure prediction from sequence remains a major goal in molecular biology. The methods described in this review concentrate on deriving structural information through the detection of similarities between a test sequence and a database of known structures. Such methods are often referred to as knowledge-based strategies reflecting the use of a structural database in the analyses. The past year has seen considerable advances in both the development of automated procedures and their application to protein sequences of outstanding biological interest.

Algorithms↗

PubMed2001

Artificial neural network model to predict biochemical failure after radical prostatectomy.

BACKGROUND: Biochemical failure, defined here as a rise in the serum prostate specific antigen (PSA) concentration to >0.3 ng/mL or the initiation of adjuvant therapy, is thought to be an adverse prognostic factor for men who undergo radical prostatectomy (RP) as definitive treatment for clinically localized cancer of the prostate (CAP). We have developed an artificial neural network (ANN) to predict biochemical failure that may benefit clinicians and patients choosing among the definitive treatment options for CAP. MATERIALS AND METHODS: Clinical and pathologic data from 196 patients who had undergone RP at one institution between 1988 and 1999 were utilized. Twenty-one records were deleted because of missing outcome, Gleason sum, PSA, or clinical stage data. The variables from the 175 remaining records were analyzed for input variable selection using principal component analysis, decision tree analysis, and stepped logistic regression. The selected variables were age, PSA, primary and secondary Gleason grade, and Gleason sum. The records were randomized and split into three bootstrap training and validation sets of 140 records (80%) and 35 records (20%), respectively. RESULTS: Forty-four percent of the patients suffered biochemical failure. The average duration of follow up was 2.5 years (range 0-11.5 years). Forty-two percent of the patients had pathologic evidence of non-organ-confined disease. The average area under the receiver operator characteristic (ROC) curve for the validation sets was 0.75 +/- 0.07. The ANN with the highest area under the ROC curve (0.80) was used for prediction and had a sensitivity of 0.74, a specificity of 0.78, a positive predictive value of 0.71, and a negative predictive value of 0.81. CONCLUSION: These results suggest that ANN models can predict PSA failure using readily available preoperative variables. Such predictive models may offer assistance to patients and physicians deciding on definitive therapy for CaP.

Adjuvants, Pharmaceutic↗

PubMed2006

Prediction of pelvic inflammatory disease among young, single, sexually active women.

OBJECTIVES: To assess prediction strategies for pelvic inflammatory disease (PID). STUDY DESIGN: One thousand one hundred seventy women were enrolled based on a high chlamydial risk score. Incident PID over a median of 3 years was diagnosed by either histologic endometritis or Centers for Disease Control and Prevention criteria. A multivariable prediction model for PID was assessed. RESULTS: Women enrolled using the risk score were young, single, sexually active, and often had prior sexually transmitted infections. Incident PID was common (8.6%). From 24 potential predictors, significant factors included age at first sex, gonococcal/chlamydial cervicitis, history of PID, family income, smoking, medroxyprogesterone acetate use, and sex with menses. The model correctly predicted 74% of incident PID; in validation models, correct prediction was only 69%. CONCLUSIONS: Our data validate a modified chlamydial risk factor scoring system for prediction of PID. Additional multivariable modeling contributed little to prediction. Women identified by a threshold value on the chlamydial risk score should undergo intensive education and screening.

Adolescent↗

PubMed2006

Prediction of adult height in growth-hormone-treated children with growth hormone deficiency.

CONTEXT: Several studies have searched for factors that significantly influence adult height (AH) of children with GH deficiency (GHD) who have been treated with biosynthetic GH, but a prediction model for AH has not yet been presented. OBJECTIVE: Our objective was to develop models for prediction of AH, using information available at the start of GH treatment or after 1 yr of treatment. DESIGN AND SETTING: For this retrospective study, data were collected from the National Registry of Growth Hormone Treatment in Children, which contained data of Dutch children treated with GH. PATIENTS/INTERVENTION: Patients included males born before 1985 and females born before 1987 with either diagnosis of GHD (syndromes, tumors, and other diseases were excluded) or a maximal GH response during provocation tests of less than 11 ng/ml, treated with biosynthetic GH for at least 1 yr. To be able to use the complete group of 342 children for the development of the models, multiple imputation was used for missing values. MAIN OUTCOME MEASURE: We assessed AH sd scores (SDS). RESULTS: Each prediction model contained both target height SDS and current height SDS. The change in height SDS during the first year proved an important predictor for AH. In all models, addition of GH dose was not significant. The percent explained variance, after correction for overfitting, ranged from 37% (prepubertal children, prediction at start) to 60% (pubertal children, prediction after 1 yr). CONCLUSION: The presented prediction models give accurate predictions of AH for children with GHD at start and after 1 yr of GH treatment. They are useful tools in the treatment of these children.

Adolescent↗

PubMed2001

Use of neural network models to predict industrial bioreactor effluent quality.

Engineered bioreactors are useful tools for degrading wastes from crude oil refining facilities. One such bioreactor forms part of the wastewater remediation process used at a refinery in the San Francisco Bay Area. The flow rate and chemical concentrations of the waste vary, and it is necessary to be able to predict the efficiency of the reactor degradation process for this varied input. The complex biological, physical, and chemical processes of the reactor make deterministic modeling unsuitable. Therefore, predictive modeling for this system was performed using a neural network model. A predictive, time-series neural network model requires a complete data set. Often, in the case of a large industrial facility, data are missing. Various techniques can be used to reconstruct missing data, but comparisons of techniques have not been performed for large-scale remediation processes. In this manuscript, four techniques are used for reconstructing missing data to examine which ones provide superior predictive capabilities. It was found that the interpolated and moving average values methods provided the best predictions. The mean and median replacement methods, commonly used in neural network modeling, provided much poorer predictions. Another goal of this study is to determine which water quality parameters are more accurately predicted than others. In this study, pH was the most accurately predicted, while ammonia and total phenolics concentrations were the least accurately predicted.

Ammonia↗

PubMed2006

The significance of endogeneity problems in crash models: an examination of left-turn lanes in intersection crash models.

Crash prediction models are used for a variety of purposes including forecasting the expected future performance of various transportation system segments with similar traits. The influence of intersection features on safety have been examined extensively because intersections experience a relatively large proportion of motor vehicle conflicts and crashes compared to other segments in the transportation system. The effects of left-turn lanes at intersections in particular have seen mixed results in the literature. Some researchers have found that left-turn lanes are beneficial to safety while others have reported detrimental effects on safety. This inconsistency is not surprising given that the installation of left-turn lanes is often endogenous, that is, influenced by crash counts and/or traffic volumes. Endogeneity creates problems in econometric and statistical models and is likely to account for the inconsistencies reported in the literature. This paper reports on a limited-information maximum likelihood (LIML) estimation approach to compensate for endogeneity between left-turn lane presence and angle crashes. The effects of endogeneity are mitigated using the approach, revealing the unbiased effect of left-turn lanes on crash frequency for a dataset of Georgia intersections. The research shows that without accounting for endogeneity, left-turn lanes 'appear' to contribute to crashes; however, when endogeneity is accounted for in the model, left-turn lanes reduce angle crash frequencies as expected by engineering judgment. Other endogenous variables may lurk in crash models as well, suggesting that the method may be used to correct simultaneity problems with other variables and in other transportation modeling contexts.

Accidents, Traffic↗

PubMed2003

In silico ADME prediction: data, models, facts and myths.

A critical review of a very recent work in the field of in silico ADME prediction is presented with emphasis on the work published during the period 2000-2002, and several other review articles are mentioned in order to offer a broader view of the field. We find that not much progress has been made in developing robust and predictive models, and that the lack of accurate data, together with the use of questionable modeling end-points, has greatly hindered the real progress in defining generally applicable models. Due to the largely empirical nature of QSAR/QSPR approaches, general and truly predictive models for complex phenomena, such as absorption and clearance, may still be chimeric. The development of local models for use within focused chemical series may be the most appropriate way of utilizing in silico ADME predictions, once experience and data have been gained on a given project and/or structural class.

Animals↗

PubMed2000

Models for predicting subjective quality of life in individuals with traumatic brain injury.

The objective of this study was to compare the utility of ICIDH-based models and needs-based models for predicting subjective quality of life in individuals with traumatic brain injury (TBI). Using an existing data base of individuals with TBI living in the community, seven predictive models were tested using multiple regression analyses. In comparing adjusted R2 associated with each of seven models, it was concluded that needs-based models using subjective indicators clearly predict more variance in measures of life satisfaction, or subjective well-being, than do either type of model relying on objective measures. It is suggested that, in documenting 'outcomes' of rehabilitation, the degree to which the focal individual's important needs are met defines more directly his/her well-being than do measures of impairment, disability or handicap.

Activities of Daily Living↗

PubMed2004

Making ends meet: a cost comparison of laparoscopic and open radical retropubic prostatectomy.

PURPOSE: We compared the perioperative costs of laparoscopic radical prostatectomy (LRP) and open radical retropubic prostatectomy (RRP) at a metropolitan hospital by developing a detailed computer model. MATERIALS AND METHODS: Our predictive model incorporates institutional cost centers for operative time, operating room consumables, professional fees, hospital room and board, oral analgesics, autologous blood banking, blood transfusion and cystography. Versions with and without pelvic lymphadenectomy (PLND) were evaluated using 1 and 2-way sensitivity analyses. Operative times, lengths of stay and transfusion rates were derived from published series. We also reviewed individual hospital charges for 172 consecutive prostatectomy cases for comparison and validation of model predictions. RESULTS: The model predicted cost premiums for LRP of 14.4% (without PLND) and 17.5% (with PLND). The actual hospital charge premium for LRP and PLND was 18.4%, which differed from the predicted cost premium by less than 1%. The most significant cost centers in order of importance were operative time, length of stay and consumables. To achieve cost equivalence with RRP, operative times would need to average 159 minutes (LRP and PLND) and 174 minutes (LRP alone) holding other factors constant. Cost equivalence could not be achieved by shortening hospital stay alone unless LRP were performed as an outpatient procedure. CONCLUSIONS: Our model predicts the perioperative costs of LRP to be greater than RRP by a factor of less than 1.2x. If disposable instruments and trocars are eliminated, and patients undergoing LRP and PLND are discharged on postoperative day 2, cost equivalence with RRP and PLND can be achieved with operative times of 3.4 hours.

Computer Simulation↗

PubMed2025

Predicting dynamic expression patterns in budding yeast with a fungal DNA language model.

Predicting gene expression from DNA sequence remains challenging due to complex regulatory codes. We introduce a masked DNA language model pretrained on 165 fungal genomes closely related to budding yeast that captures conserved regulatory grammar. Fine-tuning the LM on yeast RNA-seq data-including high-resolution transcriptional regulator induction time courses generated in this study-yielded Shorkie, a model that substantially improves gene expression prediction compared to baselines trained without self-supervision. Shorkie identified canonical transcription factor (TF) binding motifs and tracked their usage across induction experiments. Furthermore, Shorkie accurately predicted variant effects, outperforming leading sequence-to-expression models in cis-eQTL classification and achieving high concordance with massively parallel reporter assays. Interpretability analyses revealed Shorkie's ability to resolve promoter dynamics, splicing signals, and temporal changes in regulatory motif usage. This framework demonstrates that evolutionary-scale pretraining combined with transfer learning substantially improves our ability to decode gene regulation from sequence, providing insights into noncoding variants and regulatory networks.

Journal Article↗