PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “clinical prediction model”

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 19 recordsLinked to original sources
PubMed1989

Future imperfect: the limitations of clinical prediction models and the limits of clinical prediction.

Stepwise regression procedures are often used to identify a small set of variables that serve as important predictors of clinical outcome and to construct prediction models based on those variables. Several theoretical and practical limitations of this process are discussed and highlighted with a variety of examples from published reports. Wider appreciation of these limitations should encourage the development of more relevant models, and thereby improve the quality of clinical prediction.

Models, Statistical↗
PubMed1999

History and physical examination to estimate the risk of ectopic pregnancy: validation of a clinical prediction model.

STUDY OBJECTIVE: To prospectively validate a clinical prediction model for ectopic pregnancy (EP). METHODS: Prospective cohort with 14-month derivation and 12-month validation phases. All hemodynamically stable, first-trimester patients with abdominal pain or vaginal bleeding who presented to a military teaching hospital emergency department underwent follow-up until an outcome of intrauterine pregnancy (IUP) or EP was established. Patients were separated into the high-risk group, defined as having either peritoneal signs or definite cervical motion tenderness; intermediate-risk group, defined as the presence of pain or tenderness, other than midline cramping, plus absence of fetal heart tones, and absence of tissue visible at the cervical os; and low-risk group (neither high- nor intermediate-risk) using recursive partitioning. RESULTS: Summarizing both phases, 915 patients had 845 (93%) IUPs and 70 (7.6%) EPs, with 18 (1.9%) lost to follow-up. The clinical prediction model classified 75 (8.2%) into the high-risk group (sensitivity 31%, 95% confidence interval [CI] 21% to 44%; specificity 94%, 95% CI 92% to 95%); and 644 (70%) in the intermediate-risk group (sensitivity 98%, 95% CI 89% to 100%; specificity 25%, 95% CI 22% to 29%). The remaining 196 (21%) patients who met neither high-risk nor intermediate-risk criteria were classified into the low-risk group. On the basis of EP prevalence of 7.7%, the risk of EP was less than 1% (95% CI 0% to 3%) for the low-risk group, 7% (95% CI 5% to 10%) for the intermediate-risk group, and 29% (95% CI 19% to 41%) for the high-risk group. CONCLUSION: This clinical prediction model is useful for estimating the risk of EP in first-trimester patients, particularly when ancillary testing is equivocal or not readily available.

Adult↗
PubMed1999

Solitary pulmonary nodules: clinical prediction model versus physicians.

OBJECTIVE: To determine whether a clinical prediction model developed to identify malignant lung nodules based on clinical data and radiologic lung nodule characteristics could predict a malignant lung nodule diagnosis with higher accuracy than physicians. MATERIAL AND METHODS: One hundred cases were obtained by using a stratified random sample from a retrospective cohort of 629 patients with newly discovered 4- to 30-mm radiologically indeterminate solitary pulmonary nodules (SPNs) on chest radiography. A chest radiologist, pulmonologist, thoracic surgeon, and general internist made predictions of a malignant lesion and recommendations for management (thoracotomy, transthoracic needle aspiration biopsy, or observation) on the basis of radiologic and clinical data used to develop the clinical prediction rule. The predictions of a malignant lung nodule were compared with the probability of malignant involvement from a previously validated clinical prediction model to identify malignant nodules on the basis of three clinical characteristics (age, smoking status, and history of cancer greater than or equal to 5 years previously) and three radiologic characteristics (nodule diameter, spiculation, and upper lobe location). RESULTS: Receiver operating characteristic analysis showed no significant difference between the logistic model and the physicians' predictions. Calibration curves revealed that physicians overestimated the probability of a malignant lesion in patients with low risk of malignant disease by the prediction rule; this finding suggests a potential for the decision rule to improve the management of patients with SPNs that are likely to be benign. CONCLUSION: The prediction model was not better than physicians' predictions of malignant SPNs. The prediction rule may have potential to improve the management of patients with SPNs that are likely to be benign.

Diagnosis, Differential↗
PubMed1998

Derivation of a clinical prediction model for the emergency department diagnosis of ectopic pregnancy.

OBJECTIVE: To derive a clinical prediction model for estimating the pretest probability of ectopic pregnancy in ED patients with first-trimester abdominal pain or vaginal bleeding. METHODS: All hemodynamically stable first-trimester patients presenting to the ED of a tertiary care military teaching hospital over a 14-month period with a chief complaint of abdominal pain and/or vaginal bleeding had clinical data coded prior to determining outcome. They were then followed longitudinally until a criterion standard pregnancy outcome was established. RESULTS: Of the 486 patients enrolled, 280 (58%) had viable intrauterine pregnancies, 167 (34%) had nonviable intrauterine pregnancies, and 39 (8%) had ectopic pregnancies. Using a recursive partitioning model, a high-risk group was derived (that was separated from intermediate and low-risk groups), consisting of patients with abdominal peritoneal signs or definite cervical motion tenderness, with a sensitivity of 31% (95% CI: 17-48%), a specificity of 93% (95% CI: 90-95%), a positive likelihood ratio of 4.3, and a negative likelihood ratio of 0.74. A low-risk group, consisting of patients with either fetal heart tones or tissue at the cervical os, or the absence of pain other than midline menstrual-like cramping and lacking any pelvic tenderness, was differentiated from an intermediate-risk group, with a sensitivity of 96% (95% CI: 81-100%), a specificity of 22% (95% CI: 18-26%), a positive likelihood ratio of 1.2, and a negative likelihood ratio of 0.17. CONCLUSION: A clinical prediction model for estimating the probability of ectopic pregnancy in ED patients has been derived. It may prove to have practical clinical application for estimating pretest probability of ectopic pregnancy as well as assisting in medical decision making when laboratory and ultrasonographic findings are nondiagnostic. Clinical application should await prospective validation in an independent sample.

Abdominal Pain↗
PubMed2006

Prognostic index score and clinical prediction model of local regional recurrence after mastectomy in breast cancer patients.

PURPOSE: To develop clinical prediction models for local regional recurrence (LRR) of breast carcinoma after mastectomy that will be superior to the conventional measures of tumor size and nodal status. METHODS AND MATERIALS: Clinical information from 1,010 invasive breast cancer patients who had primary modified radical mastectomy formed the database of the training and testing of clinical prognostic and prediction models of LRR. Cox proportional hazards analysis and Bayesian tree analysis were the core methodologies from which these models were built. To generate a prognostic index model, 15 clinical variables were examined for their impact on LRR. Patients were stratified by lymph node involvement (<4 vs. >or =4) and local regional status (recurrent vs. control) and then, within strata, randomly split into training and test data sets of equal size. To establish prediction tree models, 255 patients were selected by the criteria of having had LRR (53 patients) or no evidence of LRR without postmastectomy radiotherapy (PMRT) (202 patients). RESULTS: With these models, patients can be divided into low-, intermediate-, and high-risk groups on the basis of axillary nodal status, estrogen receptor status, lymphovascular invasion, and age at diagnosis. In the low-risk group, there is no influence of PMRT on either LRR or survival. For intermediate-risk patients, PMRT improves LR control but not metastases-free or overall survival. For the high-risk patients, however, PMRT improves both LR control and metastasis-free and overall survival. CONCLUSION: The prognostic score and predictive index are useful methods to estimate the risk of LRR in breast cancer patients after mastectomy and for estimating the potential benefits of PMRT. These models provide additional information criteria for selection of patients for PMRT, compared with the traditional selection criteria of nodal status and tumor size.

Adult↗
PubMed2006

Do clinical prediction models improve concordance of treatment decisions in reproductive medicine?

OBJECTIVE: To assess whether the use of clinical prediction models improves concordance between gynaecologists with respect to treatment decisions in reproductive medicine. DESIGN: We constructed 16 vignettes of subfertile couples by varying fertility history, postcoital test, sperm motility, follicle-stimulating hormone level and Chlamydia antibody titre. SETTING: Thirty-five gynaecologists estimated three probabilities, i.e. the 1-year probability of spontaneous pregnancy, the pregnancy chance after intrauterine insemination (IUI) and the pregnancy chance after in vitro fertilisation (IVF). Subsequently they proposed therapeutic regimens for these 16 fictional couples, i.e. expectant management, IUI or IVF. Three months later, the participant gynaecologists again had to propose therapeutic regimes for the same 16 fictional cases but this time accompanied by pregnancy chances obtained from prediction models: predictions on spontaneous pregnancy, IUI and IVF. POPULATION: Thirty-five gynaecologists working in academic and nonacademic hospitals in the Netherlands. METHODS: Setting section. Main outcome measures The concordance between gynaecologists of probability estimates, expressed as interclass correlation coefficient (ICC) and the concordance between gynaecologists of treatment decisions, analysed by calculating Cohen's kappa (kappa). RESULTS: The gynaecologists differed widely in estimating pregnancy chances (ICC: 0.34). Furthermore, there was a huge variation in the proposed therapeutic regimens (kappa: 0.21). The treatment decisions made by gynaecologists were consistent with the ranking of their probability estimates. When prediction models were used, the concordance (kappa) for treatment decisions increased from 0.21 to 0.38. The number of gynaecologists counselling for expectant management increased from 39 to 51%, whereas counselling for IVF dropped from 23 to 14%. CONCLUSION: Gynaecologists differed widely in their estimation of prognosis in 16 fictional cases of subfertile couples. Their therapeutic regimens showed likewise huge variation. After confrontation with prediction models in the same 16 fictional cases, the proposed therapeutic regimens showed only slightly better concordance. Therefore a simple introduction of validated prediction models is insufficient to introduce concordant management between doctors.

Adult↗
PubMed2005

Applicability of clinical prediction models in acute myocardial infarction: a comparison of traditional and empirical Bayes adjustment methods.

INTRODUCTION: Several clinical prediction models have been developed to predict outcome after acute myocardial infarction. Updating to local circumstances may be required to make such models better applicable. We aimed to compare traditional and empirical Bayes (EB) methods to perform such updating. METHODS: We focused on 16 geographical regions within the GUSTO-I trial, which included 40,830 patients with acute myocardial infarction; of whom, 2851 (7.0%) had died by 30 days. Differences in mortality between regions were studied with traditional adjustment for case mix in logistic regression models and with EB methods. These methods updated predictions for new patients while accounting for the uncertainty in the traditionally estimated mortality differences. RESULTS: The case mix in the regions differed with respect to important predictive characteristics such as age, presence of shock, and anterior infarct location (all P < .001). These differences did not explain regional differences in 30-day mortality, which varied between 80% and 120% with traditional analyses (P < .01). The EB estimates for regional differences were much smaller (between 93% and 107%). CONCLUSIONS: Statistically significant differences in case mix and 30-day mortality were noted between geographical regions. The practical implications of this heterogeneity were, however, limited when model predictions were updated with EB methods.

Bayes Theorem↗
PubMed1998

Development of a clinical prediction model for an ordinal outcome: the World Health Organization Multicentre Study of Clinical Signs and Etiological agents of Pneumonia, Sepsis and Meningitis in Young Infants. WHO/ARI Young Infant Multicentre Study Group.

This paper describes the methodologies used to develop a prediction model to assist health workers in developing countries in facing one of the most difficult health problems in all parts of the world: the presentation of an acutely ill young infant. Statistical approaches for developing the clinical prediction model faced at least two major difficulties. First, the number of predictor variables, especially clinical signs and symptoms, is very large, necessitating the use of data reduction techniques that are blinded to the outcome. Second, there is no uniquely accepted continuous outcome measure or final binary diagnostic criterion. For example, the diagnosis of neonatal sepsis is ill-defined. Clinical decision makers must identify infants likely to have positive cultures as well as to grade the severity of illness. In the WHO/ARI Young Infant Multicentre Study we have found an ordinal outcome scale made up of a mixture of laboratory and diagnostic markers to have several clinical advantages as well as to increase the power of tests for risk factors. Such a mixed ordinal scale does present statistical challenges because it may violate constant slope assumptions of ordinal regression models. In this paper we develop and validate an ordinal predictive model after choosing a data reduction technique. We show how ordinality of the outcome is checked against each predictor. We describe new but simple techniques for graphically examining residuals from ordinal logistic models to detect problems with variable transformations as well as to detect non-proportional odds and other lack of fit. We examine an alternative type of ordinal logistic model, the continuation ratio model, to determine if it provides a better fit. We find that it does not but that this model is easily modified to allow the regression coefficients to vary with cut-offs of the response variable. Complex terms in this extended model are penalized to allow only as much complexity as the data will support. We approximate the extended continuation ratio model with a model with fewer terms to allow us to draw a nomogram for obtaining various predictions. The model is validated for calibration and discrimination using the bootstrap. We apply much of the modelling strategy described in Harrell, Lee and Mark (Statist. Med. 15, 361-387 (1998)) for survival analysis, adapting it to ordinal logistic regression and further emphasizing penalized maximum likelihood estimation and data reduction.

Chi-Square Distribution↗
PubMed2005

Clinical prediction model to characterize pulmonary nodules: validation and added value of 18F-fluorodeoxyglucose positron emission tomography.

BACKGROUND: The added value of 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) scanning as a function of pretest risk assessment in indeterminate pulmonary nodules is still unclear. OBJECTIVE: To obtain an external validation of the prediction model according to Swensen and colleagues, and to quantify the potential added value of FDG-PET scanning as a function of its operating characteristics in relation to this prediction model, in a population of patients with radiologically indeterminate pulmonary nodules. DESIGN, SETTING, AND PATIENTS: Between August 1997 and March 2001, all patients with an indeterminate solitary pulmonary nodule who had been referred for FDG-PET scanning were retrospectively identified from the database of the PET center at the VU University Medical Center. RESULTS: One hundred six patients were eligible for the study, and 61 patients (57%) proved to have malignant nodules. The goodness-of-fit statistic for the model (according to Swensen) indicated that the observed proportion of malignancies did not differ from the predicted proportion (p = 0.46). PET scan results, which were classified using the 4-point intensity scale reading, yielded an area under the evaluated receiver operating characteristic curve of 0.88 (95% confidence interval [CI], 0.77 to 0.91). The estimated difference of 0.095 (95% CI, -0.003 to 0.193) between the PET scan results classified using the 4-point intensity scale reading and the area under the curve (AUC) from the Swensen prediction was not significant (p = 0.058). The PET scan results, when added to the predicted probability calculated by the Swensen model, improves the AUC by 13.6% (95% CI, 6 to 21; p = 0.0003). CONCLUSION: The clinical prediction model of Swensen et al was proven to have external validity. However, especially in the lower range of its estimates, the model may underestimate the actual probability of malignancy. The combination of visually read FDG-PET scans and pretest factors appears to yield the best accuracy.

Aged↗
PubMed2003

Gene expression profiling in clinically localized prostate cancer: a four-gene expression model predicts clinical behavior.

PURPOSE: New diagnostic and prognostic molecular markers are required for prostate cancer, one of the most common male malignancies in Western countries. Gene expression profiling may help to identify genes involved in prostate carcinogenesis, yield clinical biomarkers, and improve tumor classification. EXPERIMENTAL DESIGN: To identify fundamental differences between normal and neoplastic prostate tissue, we used real-time quantitative RT-PCR assays to quantify the mRNA expression of 291 selected genes in samples of normal prostate and of well-documented primary, clinically localized prostate tumors. RESULTS: Forty-six genes showed significantly different expression in tumors relative to normal prostate. The dysregulated genes belong notably to the extracellular membrane and extracellular membrane remodeling categories and are involved in angiogenesis. Furthermore, we obtained a four-gene (XLKD1/LYVE1, CGA, F2R/PAR1, and BCL-G) model that discriminated between the seven patients with and the seven patients without relapse, independently of stage and grade. CONCLUSIONS: Some dysregulated genes are good candidates for use as molecular markers and/or therapeutic targets. Furthermore, differential gene expression profiling of clinically localized prostate tumors from relapsing and nonrelapsing patients identified a set of four genes with a pattern of expression that defines a molecular signature that could predict the clinical behavior of this disease.

Aged↗
PubMed2005

Simple clinical variables predict liver histology in hepatitis C: prospective validation of a clinical prediction model.

OBJECTIVE: A recent single-center multivariate analysis of hepatitis C (HCV) patients showed that having any two criteria: 1) ferritin > or =200 microg/l and 2) spider nevi and/or albumin < or = 35 g/l predicted grade 2 or greater histological inflammation; the presence of any two of the following criteria: spider nevi, platelets < or =150 x 109/l, palpable splenomegaly and/or albumin < or =35 g/l predicted stage 2 or greater histological fibrosis. Absence of predictors also predicted a lack of inflammation and fibrosis. Our aim was prospectively to validate this clinical prediction model using an independent multicenter sample. MATERIAL AND METHODS: Eighty-one patients with previously untreated active chronic HCV underwent physical examination, laboratory investigation, and liver biopsy. Biopsies were read, in blinded fashion, by a single pathologist, using a modified Hytiroglou (1995) scale. The clinical scoring system was correlated with histology; likelihood ratios (LRs), Fisher's exact p-values, and receiver operating characteristics (ROCs) were calculated. RESULTS: Data recording was complete in 77 and 38 patients regarding fibrotic stage and inflammatory grade, respectively. For fibrosis, 3/3 patients with any three criteria (LR 17, positive predictive value (PPV) 100%), 4/5 patients with any two criteria (LR 5.1), and 15/47 with no criteria (LR 0.6, negative predictive value (NPV) 68%) had stage 2 or greater fibrosis on biopsy (p=0.01). For inflammation, 5/5 patients with both criteria (LR 15, PPV 100%), and 8/19 patients with no criteria (LR 0.5, NPV 58%) had moderate-severe inflammation on liver biopsy (p=0.036). When missing variables were assumed to be normal, recalculated LRs were almost identical. An alanine aminotransferase (ALAT) level <60 U/l may increase the NPVs. CONCLUSIONS: This independent multicenter data set has validated our published model which uses simple clinical variables accurately and significantly to predict hepatic fibrosis and inflammation in HCV patients.

Adult↗
PubMed2003

Mathematical model predicts clinical ocular motor syndromes.

Clinical ocular motor syndromes were compared with ocular motor syndromes simulated by a mathematical model of the vestibuloocular reflex. The mathematical sensorimotor feedforward model of otolith control of three-dimensional binocular eye position is based on relevant anatomical connections of the vestibuloocular reflex from the utricles to extraocular eye muscles. This is the first attempt to simulate static ocular motor syndromes for unilateral utricular or vestibular nerve failure, lesions of the vestibular nucleus, and lesions of the ascending vestibuloocular reflex pathways. Comparison of the predicted syndromes with those found in patients with unilateral disorders of the vestibular nerve (herpes zoster neuritis), the vestibular nucleus (medullary infarction), and the medial longitudinal fasciculus (pontine infarction) showed good agreement as regards the direction of horizontal, vertical, and torsional eye deviations. The ability of the model to simulate complete or incomplete failures of single elements or entire pathways allows us to pose direct clinical questions about as yet unknown ocular motor syndromes or about the localization of the damage as well as the mechanism involved in syndromes already known.

Aged↗
PubMed2000

Clinical prediction model for differentiation of disseminated Histoplasma capsulatum and Mycobacterium avium complex infections in febrile patients with AIDS.

BACKGROUND: Disseminated infection with Histoplasma capsulatum and Mycobacterium avium complex (MAC) in patients with AIDS are frequently difficult to distinguish clinically. METHODS: We retrospectively compared demographic information, other opportunistic infections, medications, symptoms, physical examination findings and laboratory parameters at the time of hospital presentation for 32 patients with culture documented disseminated histoplasmosis and 58 patients with disseminated MAC infection. RESULTS: Positive predictors of histoplasma infection by univariate analysis included lactate dehydrogenase level, white blood cell (WBC) count, platelet count, alkaline phosphatase level, and CD4 cell count. By multivariate logistic regression analysis, those characteristics that remained significant included a lactate dehydrogenase value > or =500 U/L (risk ratio [RR], 42; 95% confidence interval [CI], 18.53-97.5; p < .001), alkaline phosphatase < or =300 U/L (RR, 9.35; 95% CI, 2.61-33.48; p = .008), WBC < or =4.5 x 10(6)/L (RR, 21.29; 95% CI, 6.79-66.75; p = .008), and CD4 cell count (RR, 0.958; 95% CI, 0.946-0.971; p = .001). CONCLUSIONS: A predictive model for distinguishing disseminated histoplasmosis from MAC infection was developed using lactate dehydrogenase and alkaline phosphatase levels as well as WBC count. This model had a sensitivity of 83%, a specificity of 91%, and a misclassification rate of 13%.

AIDS-Related Opportunistic Infections↗
PubMed2026

Machine learning-based clinical prediction model and multi-omics integration for assessing pancreatic cancer risk in new-onset diabetes.

BACKGROUND: Given that pancreatic cancer (PC) is typically diagnosed at an advanced stage but is often preceded by new-onset diabetes mellitus (NODM), providing a window for early detection, we sought to develop and validate an interpretable machine-learning model integrated with multi-omics profiling to identify early biomarkers of NODM-associated PC. METHODS: In a population-based cohort, individuals with NODM-associated PC and NODM without PC were identified and randomly divided (70:30) into training and validation sets after feature selection. Eight machine learning (ML) classifiers were compared using fivefold cross-validation, and model performance was evaluated in terms of discrimination, calibration, and decision curve&#x2013;based clinical utility. We evaluated interpretability using the Shapley additive explanations (SHAP) analyses. Mechanistically, Olink proteomic profiling and metabolomics were analyzed through clinical classifications and model-defined risk strata. RESULTS: Categorical boosting achieved the best performance in the independent validation set (AUROC&#x2009;=&#x2009;0.844). The NODM cohort was stratified into high- (n&#x2009;=&#x2009;2,362) and low-risk (n&#x2009;=&#x2009;5,030) groups, and internal validation together with SHAP analyses demonstrated consistent model performance and identified clinically interpretable predictors. Proteomic and metabolomic analyses under clinical and risk-based grouping identified 39 overlapping differentially expressed proteins and 145 overlapping metabolites with enriched across 11 shared KEGG pathways. Cross-platform validation highlighted PLTP, CRTAC1, and ITGAV as serum biomarkers with a strong potential for early NODM-PC detection. CONCLUSIONS: We developed an interpretable ML framework centered on NODM enables practical risk stratification for early PC detection by multi-omics and provides a pathway of ML-based triage followed by biomarker confirmation for earlier detection and diagnosis.

Humans↗
PubMed2006

Predicting 5-fluorouracil chemosensitivity of liver metastases from colorectal cancer using primary tumor specimens: three-gene expression model predicts clinical response.

We identified genes related to 5-fluorouracil (5-FU) sensitivity in colorectal cancer and utilized these genes for predicting the 5-FU sensitivity of liver metastases. Eighty-one candidate genes involved in 5-FU resistance in gastric and colon cancer cell lines were previously identified using a cDNA microarray. In this study, the mRNA expression levels of these 81 selected genes and the genes of 5-FU-related enzymes, including thymidylate synthase (TS), dihydropyrimidine dehydrogenase (DPD) and orotate phosphoribosyltransferase (OPRT), were measured using real-time quantitative RT-PCR assays of surgically resected materials from primary colorectal tumors in 22 patients. Clinical responses were estimated by evaluating the effects of 5-FU-based hepatic artery injection (HAI) chemotherapy for synchronous liver metastases. Four genes (TNFRSF1B, SLC35F5, NAG-1 and OPRT) had significantly different expression profiles in 5-FU-nonresponding and responding tumors (p < 0.05). A "Response Index" system using three genes (TNFRSF1B, SLC35F5 and OPRT) was then developed using a discriminate analysis; the results were well correlated with the individual chemosensitivities. Among the 11 cases with positive scores in our response index, 9 achieved a reduction in their liver metastases after 5-FU-based chemotherapy, whereas only 1 of the 11 cases with negative scores responded well to chemotherapy. Our "Response Index" system, consisting of TNFRSF1B, SLC35F5 and OPRT, has great potential for predicting the efficacy of 5-FU-based chemotherapy against liver metastases from colorectal cancer.

Aged↗