Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Computational prediction”

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 217 records · Page 12Linked to original sources
PubMed2003

Predicting cranial computed tomography results of head injury patients using an artificial neural network.

We conducted this study to determine if artificial neural network modeling would predict cranial computed tomography results in head injury patients using different combinations of clinical variables. 150 consecutive patients admitted to a regional trauma center with head injury were enrolled in the study. The CT was labeled with presence of surgically significant intracranial hematoma (SSIH), if midline shift, obliteration of ambient cistern or basal cistern were found. The best performance of our models to differentiate normal from abnormal cranial CT and detection of SSIH was ideal.

Craniocerebral Trauma↗
PubMed2004

Histologic severity of appendicitis can be predicted by computed tomography.

HYPOTHESIS: A regression model based on computed tomographic (CT) findings alone can accurately predict the histologic severity of acute appendicitis in patients who have a high disease likelihood. DESIGN: Retrospective study. SETTING: Mayo Clinic in Scottsdale, Ariz. PATIENTS: Consecutive sample of 105 patients (50 women and 55 men, aged 15-89 years) undergoing nonincidental appendectomy within 3 days of nonfocused abdominal CT. INTERVENTIONS: Computed tomographic scans and histologic features were retrospectively reinterpreted. Each patient's histologic and CT findings were scored by standardized criteria. An ordinal logistic regression model was constructed with a subset of CT findings that statistically correlated best with the final histologic features. Predicted severity values were then generated from the model. MAIN OUTCOME MEASURE: Agreement between predicted and actual histologic severity, using weighted kappa measurement. RESULTS: Computed tomography variables used in the model were fat stranding, appendix diameter, dependent fluid, appendolithiasis, extraluminal air, and the radiologist's overall confidence score. The weighted kappa measurement of agreement between predicted and actual histologic severity was 0.75, with a 95% confidence interval between the values of 0.59 and 0.90. CONCLUSIONS: Computed tomographic findings, when used with the regression model developed from this pilot study, can accurately predict the histologic severity of acute appendicitis in patients initially seen with a high clinical suspicion of the disease. These findings provide a platform from which to prospectively test the model.

Acute Disease↗
PubMed1987

Suicide risk prediction by computer interview: a prospective study.

A computer interview program that uses a subjective Bayesian probability model to assess suicide risk was evaluated. Predictions made by clinicians for 52 patients were compared with predictions made by the computer for the same patients. The computer was significantly (p = .001) better at predicting attempters, and clinicians were significantly (p = .01) better at predicting nonattempters. An analysis of receiver operating characteristic curves showed that the computer had better overall discrimination, but the difference was nonsignificant.

Decision Making, Computer-Assisted↗
PubMedDate not supplied

Computer-aided prediction of receptor profile for drug-like compounds.

Computer program SIMEST (Similarity Estimating) for prompt estimation of drug-like compounds' interaction with various receptors has been developed. More than 200 kinds of receptor activities (agonists and antagonists) can be predicted analysing new compound's similarity with known ligands. SIMEST consists of two components: (a) database of low-molecular weight ligands (agonists and antagonists) for 106 receptors and (b) similarity estimation module based on original MNA descriptors. The predictive abilities of SIMEST were evaluated on two data sets: (a) about 24,000 biologically active compounds from MDDR-99.2 database; (b) seven well-studied antipsychotic drugs. Average accuracy of prediction was 85.2% for compounds from MDDR and 78.7% for antipsychotic drugs. SIMEST can be effectively applied for predicting possible mechanisms of action and side effects for drug-like substances on the basis of their structural formulae.

Databases, Factual↗
PubMed1989

Computer-assisted predictive mathematical relationship among electroshock voltage and duration and occurrence of convulsion in mice.

A microcomputer program in BASIC for predicting percentage of occurrence of electroshock-induced convulsion in mice was designed. A formula published by the author to express the mathematical relationship among the drug dose, the time, and the biological response was used in this program. Analysis of the actual, and the computer-assisted predicted percentages of occurrence of convulsion has shown that the program is fairly accurate in expressing convulsion response of mice as a function of the voltage and the duration.

Animals↗
PubMed2004

Computational gene prediction using multiple sources of evidence.

This article describes a computational method to construct gene models by using evidence generated from a diverse set of sources, including those typical of a genome annotation pipeline. The program, called Combiner, takes as input a genomic sequence and the locations of gene predictions from ab initio gene finders, protein sequence alignments, expressed sequence tag and cDNA alignments, splice site predictions, and other evidence. Three different algorithms for combining evidence in the Combiner were implemented and tested on 1783 confirmed genes in Arabidopsis thaliana. Our results show that combining gene prediction evidence consistently outperforms even the best individual gene finder and, in some cases, can produce dramatic improvements in sensitivity and specificity.

Arabidopsis↗
PubMed1986

Computer-assisted predictive mathematical relationship among metrazol dose and time and mortality in mice.

A microcomputer program in BASIC for predicting mortality in mice administered metrazol is designed. A formula published by the author to express the mathematical relationship among the drug dose, the time after administration, and the biological response was used in this program. Analysis of the actual and the computer-assisted predicted mortalities has shown that the program is fairly accurate and reliable in expressing tolerance of mice as a function of the dose and the time.

Animals↗
PubMed1989

Three methods compared for estimating the fraction of testosterone and estradiol not bound to sex-hormone-binding globulin.

Here we propose and validate, both theoretically and experimentally, a new technique for measuring the percentage of non-sex-hormone-binding globulin (SHBG) bound to testosterone and estradiol. In this method, SHBG is saturated with 1 mumol of 5 alpha-dihydrotestosterone per liter and the non-protein-bound fraction is subsequently measured in treated and untreated samples by centrifugal ultrafiltration dialysis (CUFD). We compared this technique with two previously published methods for measuring the percentage of albumin-bound steroid--ammonium sulfate precipitation and heat denaturation of SHBG followed by CUFD--and also with previously published computer predictions. The ammonium sulfate precipitation gave results closest to the computer-predicted percentage of albumin-bound testosterone and estradiol. Of the two techniques involving CUFD, the 5 alpha-dihydrotestosterone saturation method was the more reproducible. Results by both CUFD methods were higher than the computer-based predictions for albumin-bound steroid in pregnancy serum, in part perhaps because the CUFD measurements represent the non-SHBG-bound fraction rather than that which is albumin-bound alone.

Ammonium Sulfate↗
PubMed1994

Computer-assisted predictions of the secondary structure in the plant virus single-stranded DNA genome.

Coconut foliar decay virus (CFDV) contains the single-stranded circular DNA molecules of 1291 nucleotides which were found to replicate autonomously in the cells of the diseased palms. The special features of the CFDV DNA sequence, including putative secondary structure and the distribution of the inverted repeat motifs, are investigated with computer-assisted prediction methods. It is evident that the structural principle of the branched series of long and short double helixes interspersed by short non-helical regions is existed for CFDV virion DNA. The total degree of base pairing is near 62%. We have also predicted the presence of several sequence elements formed by inverted repeat motifs which are potentially capable of binding the eukaryotic transcriptional regulatory factors.

Base Sequence↗
PubMed1993

Preoperative abdominopelvic computed tomographic prediction of optimal cytoreduction in epithelial ovarian carcinoma.

PURPOSE: This study was undertaken to assess the ability of computed tomography (CT) to predict the likelihood of optimal primary tumor cytoreduction in women with epithelial ovarian carcinoma. PATIENTS AND METHODS: Fifty-one women with preoperative CT and a histologic diagnosis of epithelial ovarian carcinoma following primary tumor operation by a gynecologic oncologist were identified. Forty-two CT scans were retrospectively analyzed. CT findings of attachment of the omentum to the spleen or disease greater than 2 cm on the diaphragm, liver surface, or parenchyma, pleura, mesentery, gallbladder fossa, or suprarenal paraaortic nodes were coded to represent unresectable disease. CT results were compared with surgical outcome. RESULTS: Twenty-nine of 42 (69%) patients underwent optimal cytoreduction to less than 2 cm residual disease. Successful cytoreduction was accomplished in 23 of 24 patients who fulfilled CT criteria for cytoreduction and six of 18 with CT criteria predictive of inability to perform cytoreduction. CT was highly sensitive for detection of ascites, mesenteric, and omental disease, but was poor for detection of liver involvement, omental attachment to the spleen, gallbladder fossa disease, and peritoneal nodules smaller than 2 cm. The CT findings accurately predicted surgical outcome with a sensitivity of 92.3% and specificity of 79.3%. The positive predictive value was 67% and the negative predictive value was 96%. CONCLUSION: CT scan is an accurate method for the prediction of successful surgical cytoreduction and may have utility in the decision to offer neoadjuvant chemotherapy to certain medically disabled patients, a hypothesis currently under evaluation.

Adult↗
PubMed2006

Potential mRNA degradation targets of hsa-miR-200c, identified using informatics and qRT-PCR.

Using an anchored oligo(dT) based RT-PCR approach we quantified endogenous expression of ten microRNAs in six cell lines. This identified a miRNA, miR-200c, with variable expression, ranging from undetectable in MDA-MB-231 and HT1080 to highly expressed in MCF7. The variable expression provided a model system to investigate endogenous interactions between miRNAs and their computationally predicted targets. As the expression level of the predicted mRNA targets and miR-200c in these lines should have an inverse relationship if cleavage or degradation results from the interaction. To select targets for analysis we used Affymetrix expression data and computational prediction programs. Affymetrix data indicated approximately 3500 candidate mRNAs, absent in MCF7 and present in MDA-MB-231 or HT1080. These targets were cross-referenced against approximately 600 computationally predicted miR-200c targets, identifying twenty potential mRNAs. Expression analysis by qRT-PCR of these targets and an additional ten mRNAs (selected using the prediction program ranking alone) revealed four mRNAs, BIN1, TCF8, RND3 and LHFP with an inverse relationship to miR-200c. Of the remainder, the majority did not appear to be degraded (and may be translational targets) or were undetectable in the cell lines examined. Finally, inhibition of miR-200c using an anti-miRNA 2'-0-Methyl oligonucleotide (AMO) resulted in an increase in expression of one of the targets, the transcription factor TCF8. These results indicate that a single miRNA could directly affect the mRNA levels of an important transcription factor, albeit in a manner specific to cell lines. Further investigation is required to confirm this in vivo and determine any translational effects.

Cell Line↗
PubMed2005

Computational wear prediction of a total knee replacement from in vivo kinematics.

Wear of ultra-high molecular weight polyethylene bearings in total knee replacements remains a major limitation to the longevity of these clinically successful devices. Few design tools are currently available to predict mild wear in implants based on varying kinematics, loads, and material properties. This paper reports the implementation of a computer modeling approach that uses fluoroscopically measured motions as inputs and predicts patient-specific implant damage using computationally efficient dynamic contact and tribological analyses. Multibody dynamic simulations of two activities (gait and stair) with two loading conditions (70-30 and 50-50 medial-lateral load splits) were generated from fluoroscopic data to predict contact pressure and slip velocity time histories for individual elements on the tibial insert surface. These time histories were used in a computational wear analysis to predict the depth of damage due to wear and creep experienced by each element. Predicted damage areas, volumes, and maximum depths were evaluated against a tibial insert retrieved from the same patient who provided the in vivo motions. Overall, the predicted damage was in close agreement with damage observed on the retrieval. The gait and stair simulations separately predicted the correct location of maximum damage on the lateral side, whereas a combination of gait and stair was required to predict the correct location on the medial side. Predicted maximum damage depths were consistent with the retrieval as well. Total computation time for each damage prediction was less than 30 min. Continuing refinement of this approach will provide a robust tool for accurately predicting clinically relevant wear in total knee replacements.

Aged↗
PubMed1990

Structure of donor side components in photosystem II predicted by computer modelling.

Thirty-one and eleven sequences for the photosystem II reaction centre proteins D1 and D2 respectively, were compared to identify conserved single amino acid residues and regions in the sequences. Both proteins are highly conserved. One important difference is that the lumenal parts of the D1 protein are more conserved than the corresponding parts in the D2 protein. The three-dimensional structures around the electron donors tyrosineZ and tyrosineD on the oxidizing side of photosystem II have been predicted by computer modelling using the photosynthetic reaction centre from purple bacteria as a framework. In the model the tyrosines occupy two cavities close to the lumenal surface of the membrane. They are symmetrically arranged around the primary donor P680 and the distances between the centre of the tyrosines and the closest Mg ion in P680 are around 14 A. Both tyrosineZ and tyrosineD are suggested to form a hydrogen bond with histidine 190 from the loop connecting helices C and D in the D1 and D2 proteins, respectively. The Mn cluster in the oxygen evolving complex has been localized by using known and estimated distances from the tyrosine radicals. It is suggested that a binding region for the Mn cluster is constituted by the lumenal ends of helices A and B and the loop connecting them in the D1 protein. This part of the D1 protein contains a large number of strictly conserved carboxylic acid residues and histidines which could participate in the Mn binding. There is little probability that the Mn cluster binds on the lumenal surface of the D2 protein.

Amino Acid Sequence↗
PubMed2003

[The computer simulating prediction method of noise of underground garage in urban residential region].

The model of random point sound source was applied to predict the noise of underground garage in urban residential region with the method of computer simulating. Comparing the predict data and the data of measurement, the precision of this model was good. The model can be applied to predict the influence of the noise of new built underground garage noise, it can offer the reference for the planning department.

Computer Simulation↗
PubMed2004

Multiphasic helical computed tomography predicts subsequent development of severe brain edema in acute ischemic stroke.

OBJECTIVE: To evaluate the use of multiphasic helical computed tomography (CT) in predicting subsequent development of severe brain edema in patients with acute middle cerebral artery (MCA) stroke. DESIGN: Case-control study. SETTING: Tertiary referral hospital. PATIENTS: We studied 31 patients with acute MCA stroke who had a baseline National Institutes of Health Stroke Scale score of 15 or higher within 6 hours of symptom onset. Sequential 4-phasic enhanced helical CT scans were performed after taking precontrast CT scans. The severity of perfusion deficit was graded as "severe" or "moderate" depending on collateral blood flow. MAIN OUTCOME MEASURES: Patients were classified as having severe brain edema if they showed signs of uncal herniation or deterioration with mass effect leading to hemicraniectomy. RESULTS: Severe brain edema developed in 10 patients (32%). Severe perfusion deficit greater than 50% of the presumed MCA territory on multiphasic helical CT was more often found in patients with severe brain edema than in those without (8 of 10 vs 4 of 21, P =.002). In contrast, parenchymal hypodensity greater than 50% on precontrast CT was observed only in 5 patients with severe brain edema (5 of 10 vs 4 of 21, P =.10). Additional involvement of the anterior or posterior cerebral artery territory was found on multiphasic CT (6 of 10 vs 0 of 21, P <.001) and on precontrast CT (4 of 10 vs 0 of 21, P =.007) only in patients with severe brain edema. CONCLUSION: Multiphasic helical CT is more useful than precontrast CT for predicting subsequent severe brain edema in acute MCA stroke based on the findings of severe perfusion deficit greater than 50% of the MCA territory and additional involvement of the anterior or posterior cerebral artery territory.

Academic Medical Centers↗
PubMed2005

Does preoperative multislice computed tomography predict operative times in total endoscopic coronary artery bypass grafting?

OBJECTIVE: Multislice computed tomography (MSCT) is currently discussed as a potential tool for procedure planning in endoscopic heart surgery. We aimed to assess the influence of various thoracic measurements on operative times in arrested heart totally endoscopic coronary artery bypass grafting (AHTECAB). METHODS: 34 patients (aged 59 years, 71% male) scheduled for AHTECAB were examined prospectively with ECG-gated 16-channel MSCT angiography of coronary arteries and internal mammary arteries. All AHTECABs were single LIMA to LAD bypass operations using the Da Vinci telemanipulator and the ESTECH remote access perfusion system. RESULTS: The LIMA-LAD distances were: I (at origin of the first diagonal branch) 4.3 cm (2.5-6.0), II (aortic valve level) 3.7 cm (1.1-6.4), III (mitral valve level) 2.9 cm (0.7-5.0), and IV (basis cordis) 2.3 cm (0.6-4.3). The anterioposterior thoracic diameter was 12.4 cm (8.9-15.6), and the transverse diameter was 24.9 cm (21.1-26.8). LIMA-LAD distances I (P = .025, r = .396) and III (P = .042, r = .356) significantly correlated with the anastomotic time. Increased rotation of the heart to the left was associated with a decreased cardiopulmonary bypass time (p = .016, r = -.451). CONCLUSION: These data suggest that MSCT has the potential to predict operative times in robotic AHTECAB.

Coronary Angiography↗
PubMed2026

Multimodal alignment improves generalizability of genomic biomarker prediction in computational pathology.

Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed multimodal alignment for biomarker learning and generalization (MARBLE), a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach.

CP: computational biology↗
PubMed1997

Can pretreatment computed tomography predict local control in T3 squamous cell carcinoma of the glottic larynx treated with definitive radiotherapy?

PURPOSE: To determine if pretreatment computed tomography (CT) can predict local control in T3 squamous cell carcinoma of the glottic larynx treated with definitive radiotherapy (RT). METHODS AND MATERIALS: Forty-two patients with previously untreated T3 squamous cell carcinoma of the glottic larynx were treated for cure with RT alone; all had a minimum 2-year follow-up. Tumor volumes and extent were determined by consensus of two head and neck radiologists on pretreatment CT studies. A tumor score was calculated and assigned to each primary lesion depending on the extent of laryngeal spread. Sclerosis of any laryngeal cartilage was recorded. The specific CT parameters assessed were correlated with local control. RESULTS: Tumor volume was a significant predictor of local control. For tumors measuring < 3.5 cm3, local control was achieved in 22 of 26 patients (85%), whereas for tumors > or = 3.5 cm3, local control was achieved in 4 of 16 patients (25%) (p = 0.0002). Sensitivity and specificity using this cutpoint were 85% and 75%, respectively. Tumor score as a measure of anatomic extent was also found to be a significant predictor of local control. The local control rate for tumors assigned a low tumor score (< or = 5) was 78% (21 of 27) compared to 33% (5 of 15) for tumors assigned a high tumor score (6, 7, or 8) (p = 0.008). A significant decrease in the local control rate was observed for cancers involving the paraglottic space at the false vocal cord level (14 of 16 [88%] vs. 12/26 [46%]) (p = 0.010), cancers involving the face of the arytenoid (15 of 18 [83%] vs. 11 of 24 [46%]) (p = 0.024), and tumors involving the interarytenoid region (25 of 36 [69%] vs. 1 of 6 [17%]; p = 0.020). There were 12 patients with sclerosis of both the ipsilateral arytenoid and the adjacent cricoid cartilage. These patients showed a significant decrease in local control (4 of 12 [33%]). CONCLUSION: Pretreatment CT can stratify patients with T3 glottic carcinoma into groups more or less likely to be locally controlled with definitive RT. The local control rate for these tumors can be improved using a CT-based tumor profile; the ideal CT profile for a radiocurable T3 glottic larynx carcinoma is volume < 3.5 cm3 and no or single laryngeal cartilage sclerosis.

Carcinoma, Squamous Cell↗