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 415 records · Page 23Linked to original sources

PubMed2026

Development and preliminary validation of plasma cell-free DNA methylation-based diagnostic prediction model for colorectal cancer detection.

BACKGROUND: Colorectal cancer (CRC) is a common malignancy associated with genetic and epigenetic alterations. Several methylation biomarkers have been investigated for non-invasive CRC detection; however, their reported performance varies across clinical settings, and the detection of early-stage or precancerous disease and discrimination from non-malignant colorectal conditions remain challenging. This exploratory study aimed to identify reproducible CRC-associated plasma cell-free DNA (cfDNA) methylation regions and to develop and preliminarily evaluate diagnostic prediction model for distinguishing CRC from healthy controls and benign samples. METHODS: Public CRC tissue methylation datasets from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) were analyzed to identify reproducible CRC-associated methylation alterations. Plasma cfDNA methylation was profiled using methyl-CpG-binding-domain enrichment followed by paired-end sequencing in patients with CRC, patients with colorectal polyps, and healthy controls. After quality-control filtering, 30 CRC and healthy-control samples were randomly allocated at the participant level in a 7:3 ratio to a development set comprising 10 patients with CRC and 11 healthy controls and a held-out test set comprising 4 patients with CRC and 5 healthy controls. Hypermethylated regions were selected using least absolute shrinkage and selection operator (LASSO) logistic regression. The 12-region model was evaluated in the held-out test set and subsequently applied to 10 colorectal polyp samples without refitting or recalibration. RESULTS: Tissue methylation analysis identified reproducible CRC-associated alterations across independent datasets. In the plasma development set, 707 differentially methylated regions (DMRs) were identified between CRC and healthy-control samples, including 324 hypermethylated and 383 hypomethylated regions. LASSO regression selected a 12-region hypermethylation signature. In the held-out test set, the model achieved an area under the curve (AUC) of 0.85 [95% confidence interval (CI): 0.579-1.000]. At the development-set-derived threshold, sensitivity was 75.0% (3/4), specificity was 60.0% (3/5), and accuracy was 66.7% (6/9). When the original model was applied to colorectal polyp samples, model scores were significantly higher in both CRC and polyp samples than in healthy controls, while CRC samples showed a tendency toward higher scores than polyp samples. CONCLUSIONS: This exploratory study identified a 12-region plasma cfDNA hypermethylation signature associated with CRC and developed a LASSO-based diagnostic prediction model that showed preliminary discrimination between CRC and healthy controls in a small held-out test set. By integrating tissue methylation evidence with plasma cfDNA profiling, this study expands the repertoire of candidate region-level methylation markers for blood-based CRC detection.

Colorectal cancer (CRC)↗

PubMedDate not supplied

A chemical class-based approach to predictive model generation.

We make a quantitative comparison of two distinct approaches to predictive model generation in the context of diverse screening data. In the default approach, a single recursive partitioning model is constructed using all of the training data at one time. In the "class-based" approach, the same data are first partitioned into homogeneous, scaffold-based classes, and models are constructed within each class independently. Both approaches are tested on the identical set of hold-out data, using a formal protocol that includes consensus scoring to handle the multiple class-based models. The entire process is performed using three different descriptor sets and is repeated using five separate random trials, such that the trial-averaged prediction rates for the two approaches can be quantitatively compared. We find that although the predictive performances of the class-based and default approaches are similar, the former has at least two distinct advantages. The first is greater interpretability, in that chemists can more easily extract useful structure-activity information from the models. The second is greater reliability, allowing models to be applied with increased confidence to unseen data in virtual-screening applications.

Journal Article↗

PubMed1971

Prediction models for 90Sr in shed deciduous teeth and infant bone.

Shed deciduous teeth were collected in 1966-69 in Denmark, the Faroes and Greenland from children born in the period 1953-63. 235 samples of crowns were analysed for 90Sr. The 90Sr levels in deciduous tooth crowns were related to the fall-out rate and the accumulated fall-out. The tooth levels in children born in 1950-62 could be described with the same equation as the 90Sr bone levels in 1-yr-old infants born in 1962-68. The prediction models for 90Sr in teeth and bones showed that for given amount of fall-out the Faroese levels became nearly twice as high as the Danish. The maximum teeth and bone levels were found in children born in 1963, where the Faroese level was estimated from the prediction model to be 24 pCi 90Sr/g Ca.

Bone and Bones↗

PubMed2006

Predictive model for growth of Clostridium perfringens in cooked cured pork.

Mathematical models have been developed and used for predicting growth of foodborne pathogens in various food matrices. However, these early models either used microbiological media or other model systems to develop the predictive models. Some of these models have been shown to be inaccurate for applications in meat and specific food matrices, especially under dynamic conditions, such as constantly changing temperatures that are encountered during food processing. The objective of this investigation was to develop a model for predicting growth of Clostridium perfringens from spore inocula in cured pork ham. Isothermal growth of C. perfringens at various temperatures from 10 to 48.9 degrees C were evaluated using a methodology that employed a numerical technique to solve a set of differential equations. The estimated theoretical minimum and maximum growth temperatures of C. perfringens in cooked cured pork were 13.5 and 50.6 degrees C, respectively. The kinetic and growth parameters obtained from this study can be used in evaluating growth of C. perfringens from spore populations during dynamically changing temperature conditions such as those encountered in meat processing. Further, this model can be successfully used to design microbiologically "safe" cooling regimes for cured pork hams and similar products.

Animals↗

PubMed2001

A noninvasive estimation of hypernasality using a linear predictive model.

The pronunciation of a speaker with a defective soft palate is marked by hypernasality and an operation may be necessary to repair the defective soft palate to reduce this hypernasality. An assessment of hypernasality is necessary to quantify the effect of the surgery. The current clinical methods for assessing hypernasality are uncomfortable or require expensive equipment. In this paper, a new quantitative method is proposed to estimate hypernasality. This method requires only a microphone and a personal computer equipped with a sound card. Zeros in the frequency response of the vocal tract system are one of the major characteristics of hypernasality. The proposed method made use of the fact that a linear predictive model with a typical order for the human vocal tract system is not accurate when the vocal tract system has zeros in its frequency response. Hypernasality was estimated by comparing the distance between the sequences of linear predictive cepstrum of low- and high-order linear predictive models. The proposed method provides a better correlation (0.58) with nasalance measured by a nasometer than Teager method (0.44) for all the data. Furthermore, the proposed method showed higher correlation of 0.84 than 0.71 of the Teager method for data with a nasalance higher than 35%. Since the proposed method needs only digitized speech data, it is much less invasive and provides an easy and cost-effective evaluation of hypernasality.

Biomedical Engineering↗

PubMed2004

Evaluation of a Clostridium perfringens predictive model, developed under isothermal conditions in broth, to predict growth in ground beef during cooling.

Proper temperature control is essential in minimizing Clostridium perfringens germination, growth, and toxin production. The U.S. Department of Agriculture (USDA) Food Safety and Inspection Service (FSIS) offers two options for the cooling of meat products: follow a standard time-temperature schedule or validate that alternative cooling regimens result in no more than a 1-log(10) CFU/g increase of C. perfringens and no growth of Clostridium botulinum. A mathematical model developed by Juneja et al. (Food Microbiol. 16:335-349, 1999) may be helpful in determining if the C. perfringens performance standard has been achieved, but this model has not been extensively validated. The objective of this study was to validate the Juneja 1999 model in ground beef under a variety of changing temperature and temperature abuse situations. The Juneja 1999 model consistently underpredicted growth of C. perfringens during exponential cooling of ground beef. The model also underpredicted growth of C. perfringens in ground beef cooled at two different rates. The results presented here show generally good agreement with published data on the growth of C. perfringens in similar products. The model error may be due to faster-than-expected exponential growth rates in ground beef during cooling or an error in the mathematical formulation of the model.

Animals↗

PubMed1998

Predictive model for the diagnosis of intraabdominal abscess.

RATIONALE AND OBJECTIVES: The authors investigated the use of an artificial neural network (ANN) to aid in the diagnosis of intraabdominal abscess. MATERIALS AND METHODS: An ANN was constructed based on data from 140 patients who underwent abdominal and pelvic computed tomography (CT) between January and December 1995. Input nodes included data from clinical history, physical examination, laboratory investigation, and radiographic study. The ANN was trained and tested on data from all 140 cases by using a round-robin method and was compared with linear discriminate analysis. A receiver operating characteristic curve was generated to evaluate both predictive models. RESULTS: CT examinations in 50 cases were positive for abscess. This finding was confirmed by means of laboratory culture of aspirations from CT-guided percutaneous drainage in 38 patients, ultrasound-guided percutaneous drainage in five patients, surgery in five patients, and characteristic appearance on CT scans without aspiration in two patients. CT scans in 90 cases were negative for abscess. The sensitivity and specificity of the ANN in predicting the presence of intraabdominal abscess were 90% and 51%, respectively. Receiver operating characteristic analysis showed no statistically significant difference in performance between the two predictive models. CONCLUSION: The ANN is a useful tool for determining whether an intraabdominal abscess is present. It can be used to set priorities for CT examinations in order to expedite treatment in patients believed to be more likely to have an abscess.

Abdominal Abscess↗

PubMed1987

Keeping juvenile delinquents in school: a prediction model.

The purpose of this study was to test an empirically based prediction model of school dropout on a sample of 137 juvenile delinquents, some who have dropped out and some who have remained in school. The specific factors among the many found in previous research that are salient for predicting whether delinquent youths will drop out or remain in school were determined. An important finding of this study is that it required only four factors to yield a high level of prediction: misbehavior in school, disliking school, the negative influence of peers with respect to dropping out and getting into trouble, and a marginal or weak relationship with parents. The four factors identified create a model that is directly applicable to prevention strategies and is extremely parsimonious.

Adolescent↗

PubMed2026

ToxiVerse: chemical bioprofiling, toxicity data sharing and customizable predictive modeling.

MOTIVATION: Chemical toxicity assessment is critical for drug development and environmental safety. Computational models have emerged as a promising alternative to animal testing and now play a significant role in efficiently evaluating new chemicals. To address the urgent need for user-friendly machine learning tools in computational toxicology, we developed ToxiVerse, a public web-based platform. RESULTS: ToxiVerse provides automatic chemical bioprofiling, curated toxicity datasets, and a predictive modeling interface designed for researchers who lack programming expertise. The platform comprises three integrated modules: (i) Bioprofiler, which provides chemical descriptors by combining chemical-bioactivity data from PubChem assays with a machine learning-based data gap-filling procedure; (ii) Database, which hosts ∼50 000 curated chemicals covering diverse toxicity endpoints; and (iii) Cheminformatics, which enables dataset upload, chemical curation, and automatic generation of quantitative structure-activity relationship models for toxicity prediction. AVAILABILITY: The tool is accessible at www.toxiverse.com, and source code is available at https://github.com/zhu-research-group/toxiverse.

Quantitative Structure-Activity Relationship↗

PubMedDate not supplied

Impact of zoledronic acid on renal function in patients with cancer: Clinical significance and development of a predictive model.

Zoledronic acid is a potent bisphosphonate licensed for the treatment of myeloma and bone metastases from solid tumors. Renal deterioration is the most significant toxicity associated with zoledronic acid. We attempted to define the incidence and clinical significance of renal deterioration in patients receiving zoledronic acid and to develop a risk-factor profile for this treatment sequela. This study is a retrospective analysis of all patients who received zoledronic acid at Fox Chase Cancer Center, Philadelphia, Pa, between 1/10/02 and 1/30/04. Data recorded included patient demographics, tumor characteristics, comorbid illnesses, concomitant medications, cancer therapy, number of zoledronic acid doses administered, and serial creatinine measurements. In total, 3,115 evaluable doses of zoledronic acid were administered to 446 patients (median, 4 doses; mean, 6.98 doses; range, 1-28 doses) at a dose of 4 mg over 15 minutes every 3-4 weeks. Of these 446 patients, 42 experienced renal deterioration (median rise in creatinine level, 1.0 mg/dL; range, 0.5-4.4 mg/dL), requiring discontinuation of zoledronic acid therapy in 8 cases. No patient required dialysis and no patient died as a result of zoledronic acid-induced renal dysfunction. On multivariable analysis, predictive factors for the development of renal deterioration were patient age, a diagnosis of myeloma or renal cell cancer, cumulative number of doses, concomitant therapy with a nonsteroidal anti-inflammatory drug, and current or prior therapy with cisplatin. Using these factors, we constructed a predictive model with an area under the receiver operating characteristic curve of 0.75. The incidence of clinically significant renal deterioration in patients treated with zoledronic acid is low.We present a predictive model for decision support when estimating this risk.

Acute Kidney Injury↗

PubMed2004

Prediction models for evaluation of total-body bone mass with dual-energy X-ray absorptiometry among children and adolescents.

OBJECTIVE: The performance of dual-energy x-ray absorptiometry (DXA) in identifying children with decreased bone mass is increasing, but there is no consensus regarding how to interpret the results. The World Health Organization diagnostic categories for normal, osteopenia, and osteoporosis, based on T scores, are not applicable to children and adolescents who have not yet reached peak bone mass. The pediatric reference standards provided by DXA manufacturers have been questioned. Bone mineral density determined with DXA is "areal" density (a 2-dimensional measurement of a 3-dimensional structure), and its misleading nature among growing and maturing children is well recognized. Few published pediatric reference values for bone mineral density measured with DXA include factors that are known to affect the results besides age and gender. Our objective was to develop an algorithm for the evaluation of bone mass among children that included known determinants of bone mass and of its measurement with DXA. METHODS: Height, weight, pubertal status, and total-body bone mineral content, total-body bone area, and total-body bone mineral density measured with DXA were recorded for an ethnically diverse group of healthy pediatric subjects (n = 1218; age: 6-18 years). Prediction models for bone measurements were developed and validated with healthy pediatric subjects and then applied to children with medical disorders. RESULTS: There was a significant gender effect, as well as an interaction between gender and ethnicity. Separate models were developed for log total-body bone mineral content, log total-body bone area, and 1/total-body bone mineral density for girls and boys. The variability explained for each measurement increased from level 1, including age and ethnicity (76-86%), to level 2, including age, ethnicity, height, and weight (84-97%), and to level 3, including age, ethnicity, height, weight, and bone area (89-99%). Pubertal stage was an additional significant predictor of bone measurements but increased the explained variability by only 0.1% with height and weight in the models. The values predicted with each model were not different from measured values for the validation group but were different for patients with medical disorders, with different patterns according to the diagnoses. CONCLUSIONS: These models, including known determinants of bone mass and of bone measurements with DXA, provide an evaluation of pediatric bone mass that proceeds in steps from level 1 to level 3. The outcomes were different for patients at risk for compromised bone mass, compared with healthy children, with specific patterns for each medical disorder. We propose an algorithm for evaluation of bone measurements that follows levels 1 to 3. Our findings suggest that application of this algorithm to well-characterized groups of pediatric patients could identify disease-specific features of DXA results. We recommend this approach as a basis for consensus regarding the clinical evaluation of pediatric bone mass, and we suggest that it could lead to meaningful classification of pediatric bone disorders, investigation of pathophysiologic processes, and development of appropriate interventions.

Absorptiometry, Photon↗

PubMed2006

Successful validation of a survival prediction model in patients with metastases in the spinal column.

PURPOSE: The Dutch Bone Metastases Study Group developed a survival prediction model in patients with symptomatic spinal bone metastases to guide the treating physician. The objective of this study was to validate the Dutch model and compare with our previously developed survival model at the Rapid Response Radiotherapy Program (RRRP model). METHODS AND MATERIALS: The following prognostic factors were extracted from a prospective database in an outpatient palliative radiotherapy clinic: Karnofsky Performance Scores (KPS), primary cancer site, and visceral involvement for the Dutch model; primary cancer site, site of metastases, KPS, fatigue, appetite, and shortness of breath scores in the Edmonton Symptom Assessment Scale for the RRRP model. Patients were assigned scores according to each model. The survival probabilities were generated and calibration was performed for each model. RESULTS: A total of 231 patients with spinal bone metastases from 1999 and 2002 were included in the analysis. The survival probabilities were similar to those in the original models. The calibration comparing actual survival with predicted survival from the Dutch and RRRP models gave R2 values of 0.90 and 0.86, respectively. CONCLUSION: The two models were successfully validated. The Dutch model using three clinical prognostic factors was easier to administer.

Adult↗

PubMed2000

Mathematical modelling of insect neuropeptide potencies. Are quantitatively predictive models possible?

The potencies of natural adipokinetic hormones and synthetic variants have been determined in Locusta migratoria using the lipid mobilisation assay in vivo, and/or the acetate uptake assay in vitro. These data are combinations of previously published and unpublished data (a total of sixty-nine analogues), and form data sets for the construction of mathematical models of the hormone potencies. The sequence variations of amino acids in both natural and artificial adipokinetic hormone analogues were described using continuous descriptor scales z(1)', z(2)', and z(3)', each previously published scale being derived from various properties of the amino acids. By means of these z'-scales and partial least squares regression we attempted to model the potencies in Locusta migratoria of adipokinetic hormones in the two assays. Correlations (r(2) values) between predicted and actual potencies of the different peptides were up to 0.73. We discuss the potential of the partial least squares method for formulating quantitative relationships between different hormone structures and their potencies, and describe how the procedure might be used in structure-activity prediction with the construction of an optimised peptide data set.

Amino Acid Sequence↗

PubMed1996

Final height prediction models for pubertal boys.

Accurate adult height prediction is of clinical importance in assessing the need for pharmacological intervention and in the evaluation of the outcome of therapy. The methods currently in use are subject to a wide range of error, one source of which is the use of bone age (BA) measurements. We have developed a computer model for predicting adult height in pubertal boys without using BA determinations. The model is based on the existing Infancy-Childhood-Puberty model and calculates the onset of the pubertal growth spurt. Predicted adult height was assessed using this new model and four others in a group of normal boys and in a group of short normal boys receiving growth hormone. Calculated final heights by all the methods were not significantly different. Incorporation of paternal height into the prediction equations increased the accuracy of the prediction. It was concluded that our new model is as accurate as existing methods of predicting final height that involve assessing BA.

Adolescent↗

PubMed2025

Genetic mapping and predictive modeling of paralog synthetic lethality.

Paralogs are abundant in the human genome and thought to be a primary source of synthetic lethality, yet the vast paralogome remains largely uncharacterized. A digenic screen of 36,648 paralogous pairs in the human genome revealed that synthetic lethalities were infrequent and varied in penetrance in different tumor backgrounds. We hypothesized that the variable penetrance of synthetic lethalities resulted from complex polygenic interactions with different cellular contexts. A machine learning classifier of a subset of paralog pairs tested across 49 cancer models revealed that endogenous perturbations in related pathways predicted paralog synthetic lethality. Further, predictive modeling of paralog synthetic lethality showed that the strength of synthetic lethal interactions was largely due to the overlap and essentiality of the protein-protein interaction networks shared by the paralog pairs. Collectively, this study tested 36,648 digenic paralog interactions and delineated the key feature classes that underlie the heterogeneity of paralog synthetic lethalities.

Humans↗

PubMed1992

A comparative investigation of hepatic clearance models: predictions of metabolite formation and elimination.

Liver clearance models serve to improve our understanding of the relationships between the physiological determinants and hepatic clearance and predict changes in the disposition of substrates when homeostasis of the organ is perturbed. Their ability to describe metabolism was presently extended to the sequential formation and elimination of primary (M1), secondary (M2), and tertiary (M3) metabolites during a single passage of drug (P) across the liver, under steady state and first-order conditions. The well-stirred model is distinct from other models in that metabolite formation and elimination is independent of enzymic distributions, the number of steps involved in metabolite formation, and the intrinsic clearances of the precursors. This model predicts that the extraction ratio of a formed primary metabolite derived from drug (E[M1, P]) is identical to that for the preformed primary metabolite (E[M1]), and that the extraction ratios of a secondary metabolite derived from drug (E[M2, P]) and primary metabolite (E[M2, M1]) or preformed secondary metabolite (E[M2]) are identical. For the more physiologically acceptable, parallel-tube and dispersion models, metabolite sequential elimination is highly influenced by the intrinsic clearances of the precursors and the enzymic distributions that mediate removal of precursor species and the metabolites. Furthermore, the extent of sequential metabolism recedes as the number of steps involved for metabolite formation increases. These models predict that E[M1, P] less than E[M1], and E[M2, P] less than E[M2, M1] less than E[M2], with the magnitude of the changes being less for the dispersion model than for the parallel-tube model. Competing pathways that divert substrate from entering the sequential pathway were found to exert only minimal influence on the sequential pathway.

Liver↗

PubMed1994

A prediction model of performance in level II fieldwork in physical disabilities.

OBJECTIVES: A prediction model of performance in physical disabilities fieldwork was generated with grades received in the occupational therapy curriculum and in prerequisite courses. METHOD: Grades included those from functional anatomy, neuroanatomy, physical disabilities lecture, physical disabilities clinic, and prerequisite anatomy and physiology courses. Sampling was done collectively over graduated occupational therapy classes from 1987 to 1992 at the University of Puget Sound. A multiple regression analysis was performed and prediction equations were generated for each subscale of the Fieldwork Evaluation for the Occupational Therapist. Equations for combinations of the subscale categories were also produced. RESULTS: Adjusted R2 values were found to be less than 10% in all equations. CONCLUSION: This poor ability of grades to predict fieldwork performance suggests that future investigation be focused on variables other than grades. Such variables might include student motivation, rapport between the student and fieldwork supervisor, and hospital experience in physical disabilities.

Educational Measurement↗

PubMed2004

Monitoring organ donor rates: a predictive model based on routinely available data in France applied to the year 2002.

Temporal trends in organ donor harvesting rates are subject to variability. It is important to detect variations as early as possible using current data. We developed a predictive model for monitoring harvesting activity using the number of donors harvested monthly between 1996 and 2001. A Poisson model was used to predict the number of donors harvested each month along with their confidence intervals. This model also updates, on a monthly basis, the predicted number of donors for the current year. During 2002, the number of donors observed each month followed the predicted monthly variations, but a significant increase was observed in March and May. These models can be used by transplantation agencies for monitoring purposes and for the evaluation of organ donation programmes.

France↗