Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Cancer 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 199 records · Page 11Linked to original sources
PubMed2006

Nomogram predictive of cancer specific survival in patients undergoing partial or total amputation for squamous cell carcinoma of the penis.

PURPOSE: We created the first nomograms to predict cancer specific survival probabilities of patients with squamous cell carcinoma of the penis, clustering prognostic information from the most commonly used clinical and pathological variables. MATERIALS AND METHODS: We retrospectively collected clinical and pathological data from 175 patients who had undergone surgery for squamous cell carcinoma of the penis from 1980 to 2002 at 11 urological centers in northeastern Italy. A logistic regression model was used to construct the nomogram. RESULTS: At a median followup of 24 months, 101 patients (57.7%) were alive and disease-free while 74 (42.3%) died of penile cancer. According to multivariate analyses, 2 models predictive of cancer specific survival probability were generated. The first model was based on the pathological findings of the primary tumor after penectomy and on the clinical stage of groin lymph nodes, while the second model included the pathological data of the primary tumor and groin lymph nodes. The concordance index was 0.728 for the first model and 0.747 for the second. Calibration appeared to be good in both models. CONCLUSIONS: In this article we propose 2 models to predict the 5-year cancer specific survival probabilities of patients with squamous cell carcinoma of the penis. Both models showed good discriminating power and calibration in predicting patient 5-year cancer specific survival. These nomograms could improve the quality of prognostic data provided to patients and support physicians in planning treatment.

Aged↗
PubMed1997

[Systemic scleroderma and cancer. Search for predictive factors of cancer in 123 patients with scleroderma].

Several studies have suggested an increased risk of cancer in patients with systemic sclerosis, but the potential risk factors for these cancers remain unknown. The aim of this study was to identify, among patients with systemic sclerosis, factors associated with the development of cancer, with attention to clinical (age, sex, cutaneous sclerosis), immunological (antinuclear antibodies, anticentromere antibodies, anti-Scl-70 antibodies) and histological (pulmonary fibrosis) features. We retrospectively studied 123 patients with systemic sclerosis. The median follow-up period was 4 years. Fourteen cases of cancer (11.3%) were found (lung n = 3, breast n = 2, ovarian n = 2, skin n = 1, thyroid n = 1, rectum n = 1, uterine cervix n = 1, larynx n = 1, pancreas n = 1, myelodysplasia n = 1). The characteristics of systemic sclerosis were similar in patients with and patients without cancer. Yet, the three cases of lung cancers occurred in association with CREST syndromes and anticentromere antibodies.

Adolescent↗
PubMed2026

A Foundation Model Based CT Biomarker for Non-Invasive Prediction of Response to Neoadjuvant Immunochemotherapy in Non-Small Cell Lung Cancer.

Predicting pathological complete response (pCR) to neoadjuvant immunochemotherapy in non-small cell lung cancer (NSCLC) is clinically important yet remains challenging. Here, we introduce a foundation model-derived computed tomography (CT) imaging biomarker established from a multi-center cohort of 702 patients. Specifically, we developed and validated a non-invasive baseline CT-based model for risk stratification of pathological response. To address scanner and protocol heterogeneity, we first built a 3D Vision Mamba-based CT super-resolution model trained on 2494 cases for image standardization. We then fine-tuned a lung cancer-specific CT foundation model from a pretrained 3D model (VoCo) using 6643 chest CT scans. Finally, we constructed a multi-task Swin Transformer that jointly performs risk stratification and segments tumors to generate the imaging biomarker. Across five centers, the model achieved consistently strong generalization (AUC: 0.75-0.87) for pCR prediction. Genomic analysis revealed that the biomarker was independent of tumor mutational burden but significantly associated with TP53 mutations, suggesting an association with a radiogenomic phenotype related to this alteration. Together, these results demonstrate a generalizable and biologically meaningful foundation model-based biomarker for non-invasive risk stratification of pathological response in NSCLC.

Female↗
PubMed2006

GammaH2AX in cancer cells: a potential biomarker for cancer diagnostics, prediction and recurrence.

Current advances in cancer biology have identified major pathways involved in tumorigenesis. The association of DNA damage with premalignant stages of tumor progression, genome instability and further oncogenic transformation opens the possibility of using common DNA damage markers for early cancer detection, prediction, prognosis, therapeutics and possibly for cancer prevention. Perhaps the most sensitive DNA damage marker is gammaH2AX formation in the chromatin flanking the free DNA double-stranded ends in double-strand breaks (DSBs) and eroded telomeres, both present during oncogenic transformation. Our group and others found elevated endogenous levels of in various human cancer cell lines, premalignant lesions and solid tumors. These data suggest that increased DNA damage is a general characteristic of cancer development. GammaH2AX-based assay can be applied to human biopsies, aspirates and, possibly, to mononuclear cells of the peripheral blood. We propose that detection of gammaH2AX could benefit for the early cancer screening and to ascertain the efficiency of clinical treatment involving chemo- and radiotherapeutic protocols.

Adolescent↗
PubMed2005

Empirical evaluation of prediction intervals for cancer incidence.

BACKGROUND: Prediction intervals can be calculated for predicting cancer incidence on the basis of a statistical model. These intervals include the uncertainty of the parameter estimates and variations in future rates but do not include the uncertainty of assumptions, such as continuation of current trends. In this study we evaluated whether prediction intervals are useful in practice. METHODS: Rates for the period 1993-97 were predicted from cancer incidence rates in the five Nordic countries for the period 1958-87. In a Poisson regression model, 95% prediction intervals were constructed for 200 combinations of 20 cancer types for males and females in the five countries. The coverage level was calculated as the proportion of the prediction intervals that covered the observed number of cases in 1993-97. RESULTS: Overall, 52% (104/200) of the prediction intervals covered the observed numbers. When the prediction intervals were divided into quartiles according to the number of cases in the last observed period, the coverage level was inversely proportional to the frequency (84%, 52%, 46% and 26%). The coverage level varied widely among the five countries, but the difference declined after adjustment for the number of cases in each country. CONCLUSION: The coverage level of prediction intervals strongly depended on the number of cases on which the predictions were based. As the sample size increased, uncertainty about the adequacy of the model dominated, and the coverage level fell far below 95%. Prediction intervals for cancer incidence must therefore be interpreted with caution.

Adolescent↗
PubMed2003

[Cutaneous necrosis is predictive of cancer in adult dermatomyositis].

INTRODUCTION: Adult dermatomyositis is associated with cancer in 15 p. 100 to 50 p. 100 of cases and, hence, investigations should be systematically performed to search for cancer. A number of predictive factors have been reported. The aim of our study was to search for predictive factors of cancer, among adults with dermatomyositis. METHODS: We prospectively assessed 26 adults presenting with dermatomyositis, hospitalised in our department of dermatology from January 1993 to June 2000. The parameters assessed were: association with a cancer, age, gender, cutaneous necrosis, muscular weakness, electromyographic abnormalities, erythrocyte sedimentation rate, and muscular enzyme levels. RESULTS: Mean age was of 52 years and sex ratio (M/F) was of 0.53. Cancers were diagnosed in eight cases (31 p. 100) (mean age: 59.5 years; sex ratio=1; cancer localization: lung (2), breast (2), ovary, endometrium, bladder, and melanoma). Five patients in the cancer group had cutaneous necrosis and only 2 in the without cancer (p=0.01; PPV=71.4 p.100). Elevation of muscular enzyme was also associated with cancer. CONCLUSION: Our report demonstrates that cutaneous necrosis is closely associated with cancer and it suggests that in selected patients with dermatomyositis and cutaneous necrosis, more exhaustive and repeated investigations should be performed to search for cancer. The interest of elevation in muscular enzyme as a predictive factor of cancer is discussed.

Adult↗
PubMed1999

Some elements of prognosis in terminal cancer.

Predicting the survival of terminal cancer patients is a difficult task. To better understand this difficulty, we divide prognostication into two distinct elements: foreseeing and foretelling. Foreseeing is a physician's silent cognitive estimate about a patient's illness. Foretelling is the physician's communication of that prediction to the patient or significant others. In this article, we review the impact of each element of prognosis on physicians' overall prognostic accuracy. We show that physicians often make unwitting, large, and generally optimistic errors in foreseeing patients' prognoses. They also may make more conscious, but equally large, optimistic errors in foretelling prognoses to patients. The net effect is that patients may become twice removed from the truth about their illness, both times toward a falsely optimistic prognosis. We also describe the possible consequences of these optimistic prognostic errors. Finally, we review techniques that may improve physicians' prognostic accuracy. We conclude that part of the challenge of providing humane, compassionate end-of-life care to cancer patients may involve accurately foreseeing and foretelling their prognoses.

Bias↗
PubMed2003

Multiclass classification of microarray data with repeated measurements: application to cancer.

Prediction of the diagnostic category of a tissue sample from its gene-expression profile and selection of relevant genes for class prediction have important applications in cancer research. We have developed the uncorrelated shrunken centroid (USC) and error-weighted, uncorrelated shrunken centroid (EWUSC) algorithms that are applicable to microarray data with any number of classes. We show that removing highly correlated genes typically improves classification results using a small set of genes.

Algorithms↗
PubMedDate not supplied

Copy number of cancer genes predict tumor grade and survival of pancreatic cancer patients.

Pancreatic cancer is on the increase. While means of early diagnosis are being sought, it continues to present late. Prognostication is based on patient and tumor characteristics, including expression or mutation of cancer-related genes. Few studies have examined the impact of the amplification of these genes on the outcome of pancreatic cancer. We have now used a non-radioisotopic slot-blot technique to relate gene copy numbers of p53, c-myc and K-ras to tumor grade and survival. Outcomes were corrected for patient characteristics, tumor location and TNM staging. The Kaplan-Meier test for likelihood of survival showed that increase in copy number of the two oncogenes and loss of p53 were associated with non-significant reduction in survival. When these variations in cancer gene copy numbers were, however, examined by logistic regression analysis in the context of patient and tumor characteristics, survival was negatively related to K-ras amplification (p = 0.0291). Tumor grade, but not survival was positively related to loss of p53 gene copy (p = 0.0131) as well as c-myc amplification (p = 0.0248). Thus using a simple non-radioisotopic technique for the detection of cancer gene copy number in association with patients and disease characteristics, we could predict survival on the one hand and tumor behavior on the other. Such information could be used to plan initial and follow-up therapy.

Adult↗
PubMed2006

Endogenous steroid hormone concentrations and risk of breast cancer: does the association vary by a woman's predicted breast cancer risk?

PURPOSE: To examine whether the associations of endogenous estrogens and testosterone with breast cancer risk differ between high- and low-risk women, as determined by the Gail model and the Rosner and Colditz model, and by family history of breast cancer. METHODS: We conducted a prospective nested case-control study within the Nurses' Health Study. From 1989 or 1990 until June 2000, blood samples were collected, 418 breast cancer patient cases were identified, and two controls (total n = 817) were matched to each case. We classified women as high or low risk based on their family history of breast cancer, their 5-year Gail risk score, and their 5-year Rosner and Colditz risk score. Multivariate relative risks (RR) and 95% CI were calculated by unconditional logistic regression, adjusting for matching and breast cancer risk factors. RESULTS: Estrone sulfate was statistically significantly associated with breast cancer risk among women with low (< 1.66%) and high (> or = 2.52%; 75th percentile) Gail predicted risk (fourth v first quartile RR = 3.6; 95% CI, 1.9 to 7.0; RR = 2.5; 95% CI, 1.2 to 5.1, respectively). Testosterone results were similar across strata of predicted risk, with two times the risk in the fourth (v first) quartile. Estradiol appeared more strongly associated with breast cancer in women with higher predicted risk (RR = 4.5; 95% CI, 2.1 to 9.5) compared with women with lower risk (RR = 2.1; 95% CI, 1.2 to 3.6), but differences were not statistically significant. Results were similar across predicted Rosner and Colditz risk scores. CONCLUSION: These data suggest that higher levels of endogenous estrogens and testosterone are associated with increased breast cancer risk, regardless of predicted risk or family history of breast cancer.

Adult↗
PubMedDate not supplied

Prediction of cancer outcome with microarrays: a multiple random validation strategy.

BACKGROUND: General studies of microarray gene-expression profiling have been undertaken to predict cancer outcome. Knowledge of this gene-expression profile or molecular signature should improve treatment of patients by allowing treatment to be tailored to the severity of the disease. We reanalysed data from the seven largest published studies that have attempted to predict prognosis of cancer patients on the basis of DNA microarray analysis. METHODS: The standard strategy is to identify a molecular signature (ie, the subset of genes most differentially expressed in patients with different outcomes) in a training set of patients and to estimate the proportion of misclassifications with this signature on an independent validation set of patients. We expanded this strategy (based on unique training and validation sets) by using multiple random sets, to study the stability of the molecular signature and the proportion of misclassifications. FINDINGS: The list of genes identified as predictors of prognosis was highly unstable; molecular signatures strongly depended on the selection of patients in the training sets. For all but one study, the proportion misclassified decreased as the number of patients in the training set increased. Because of inadequate validation, our chosen studies published overoptimistic results compared with those from our own analyses. Five of the seven studies did not classify patients better than chance. INTERPRETATION: The prognostic value of published microarray results in cancer studies should be considered with caution. We advocate the use of validation by repeated random sampling.

Gene Expression Profiling↗
PubMed1998

Cancer predisposition, radiosensitivity and the risk of radiation-induced cancers. IV. Prediction of risks in relatives of cancer-predisposed individuals.

Individuals carrying cancer-predisposing germline mutations are known to be at a higher risk for cancers than those who do not carry them. This is also true of their biological relatives because they have a higher probability of being carriers of such mutant genes than unrelated individuals in the population. Further, there are now sufficient grounds for assuming that cancer-predisposed individuals may also be at a higher risk for cancers induced by ionizing radiation. In our earlier work, we examined the impact of this heterogeneity (with respect to cancer predisposition and radiosensitivity differentials) on risks of radiation-induced cancer at the population level. This paper is focused on the question of risks of radiation-induced cancer in relatives of cancer-predisposed individuals. Using an autosomal dominant model of cancer predisposition and radiosensitivity developed earlier and applying it to breast cancer risks associated with mutations in the BRCA1 gene, we show that: (1) The risk ratio (i.e. the ratio of risk of radiation-induced cancer in relatives to that in unrelated individuals) in the population increases with the degree of biological relatedness of the relative, being higher for close than for distant relatives; incomplete penetrance of the mutant gene "dilutes" this risk ratio. (2) The proportion of excess radiation-induced cancers in relatives (i.e. the attributable fraction) is higher than in unrelated individuals. (3) In relatives, the proportion of excess cancers due to radiosensitivity differentials alone depends on the strength of predisposition, the radiosensitivity differentials assumed, the radiation dose, the proportion of cancers due to predisposition, the mutant gene frequency and the penetrance of the mutant gene. This is in contrast to the situation for unrelated individuals, for whom the above-mentioned proportion is dependent on the first three but not on the last three of these factors. Further, even when the proportion of excess cancers is small, most of it is due to radiosensitivity differential alone both in unrelated individuals and in relatives. (4) For values of predisposition strength and radiosensitivity differential <10, even when the estimated frequency of a mutant BRCA1 gene is 0.0047 and the proportion of breast cancers due to these mutations is 38% (as is the case for Ashkenazi Jewish women under age 30), the increase in breast cancer risks is only marginal even for first-degree relatives. (5) These findings support the conclusion that increases in radiation risks to relatives (compared to those in unrelated individuals), to be detectable epidemiologically, will occur only when the mutant alleles are common and the strength of predisposition and radiosensitivity differentials are conjointly dramatic.

Breast Neoplasms↗
PubMed1995

[Changes and trend prediction in cancer morbidity of urban residents in Beijing].

Data from a long-term cancer morbidity registry and notification system were analyzed dynamically. A theoretical model of grey system was established based on time-series changes in cancer morbidities to predict its trend by the year of 2001 in Beijing. Results show cancer morbidities in Beijing will increase yearly from 1991 to 2001, and overall morbidity rate of malignant tumor will increase to 179.9/100,000 from 162.5/100,000. Proportions of malignant tumor in different sites will change greatly. Morbidities of lung cancer and breast cancer will increase rapidly, of liver and colon-rectal cancer shoes an increasing trend, too, of esophageal and cervical cancer will decline steadily, and of stomach cancer will begin to decline. All these facts laid a scientific basis for the study on cancer prevention and control.

Breast Neoplasms↗
PubMed2004

Family cancer histories predictive of a high risk of hereditary non-polyposis colorectal cancer associate significantly with a genomic rearrangement in hMSH2 or hMLH1.

Hereditary non-polyposis colorectal cancer (HNPCC) results from inactivating germline mutations in a set of DNA-mismatch-repair genes, of which the most clinically relevant are hMSH2 and hMLH1. Computer-assisted pedigree risk assessment tools are available to assist in the calculation of an individual's likelihood of bearing such a deleterious mutation. One such tool, cancergene version 3.4 (http://www3.utsouthwestern.edu/cancergene) was used to assess the risk of a deleterious mutation in the genes hMSH2 and/or hMLH1 in a series of probands selected from a panel of 67 South-western Ontario kindred previously identified as likely candidates for HNPCC by established clinical criteria. A DNA sample isolated from peripheral blood leukocytes obtained from each of these probands was examined for genomic rearrangement using the multiplex ligation-dependent probe amplification (MLPA) method. Of the individuals calculated to have a risk of >50% of a hMSH2 or hMLH1 gene mutation by the CancerGene risk assessment tool, 69% (9/13) were shown to have a genomic rearrangement resulting in the deletion of one or more exons of one of these two genes. Family cancer histories predictive of a high risk of HNPCC significantly associate with a genomic rearrangement in hMSH2 or hMLH1.

Adaptor Proteins, Signal Transducing↗
PubMed2006

Neuro-fuzzy modeling: an accurate and interpretable method for predicting bladder cancer progression.

PURPOSE: New methods are required to improve the prediction of cancer progression as traditional statistical tests have limited accuracy. Accurate predictions would allow physicians to offer specific treatment according to individual patient risk. While predictive improvements are obtained using ANN, the hidden nature of these networks prevents insight and has hindered their widespread implementation. NFM is an alternate form of artificial intelligence using fuzzy logic (which is a multivalued logic which provides reasoning under uncertainty). By defuzzification the NFM rule base becomes transparent to overcome the black box nature of ANN. MATERIALS AND METHODS: Combinations of clinicopathological (tumor stage and grade, patient age, gender, and smoking status) and molecular (immunohistochemical expression of p53 and methylation status of 11 loci) data from 117 patients were used to develop and compare predictive models of tumor progression using NFM, ANN and LR. RESULTS: NFM (88% to 100% sensitivity, 97% to 100% specificity and 94% to 100% accuracy) predicted the presence and timing of cancer progression more accurately than ANN (81% to 87%, 95% to 100% and 89% to 90%, p = 0.002) and LR 3%, 61% to 72% and 47% to 53%, p = 0.00005). NFM was able to interrogate the clinicopathological and molecular data, and select the most important parameters (age, grade, stage, smoking, methylation) for progression prediction. CONCLUSIONS: Intelligent systems and molecular biomarkers improved the accuracy of cancer progression predictions. NFM appeared superior to ANN in terms of accuracy, sensitivity, specificity and transparency. The use of NFM in routine clinical practice warrants further validation.

Aged↗
PubMed1996

Initial prognostic factors in small-cell lung cancer patients predicting quality of life during chemotherapy. Swiss Group for Clinical Cancer Research (SAKK).

The question of whether initial prognostic factors in small-cell lung cancer patients have a predictive value for patients' quality of life (QL) during chemotherapy is addressed in the context of a randomised clinical trial comparing early and late alternating chemotherapy (SAKK protocol 15/84). The relative impact of initial tumour stage and performance status, previous weight loss, sex and age on patient-rated QL was analysed over six chemotherapy cycles in 124-130 patients (according to available QL data) with more than 400 questionnaires. Fatigue/malaise, personal functioning, emotional and general well-being were prospectively selected as QL indicators. Predefined summary measures (average QL score over chemotherapy cycles, 'minimum', 'maximum' and 'final' improvement) were analysed separately by scale in various patient groups. General linear models adjusted for treatment arm and response were used to confirm the univariate findings. Within the overall sample, the average QL scores over six cycles were predicted by initial prognostic factors. Patients with poor prognostic factors reported worse QL. Within a limited sample (with baseline QL), patients with poor prognostic factors reported worse QL at baseline and greater improvement under treatment. Graphical comparison of QL patterns over cycles showed permanent discrimination by levels of prognostic factors. The impact of initial prognostic factors was consistently confirmed in the three analyses. Levels of performance status and weight loss best discriminated QL. Initial tumour stage, performance status and previous weight loss can predict QL in small-cell lung cancer during chemotherapy, even after controlling for response to treatment. Our results may contribute to clinical decision-making with regard to the intensity of chemotherapy and QL outcome, especially in patients with extensive disease.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed2004

Flexible dose-response models for Japanese atomic bomb survivor data: Bayesian estimation and prediction of cancer risk.

Generalised absolute risk models were fitted to the latest Japanese atomic bomb survivor cancer incidence data using Bayesian Markov Chain Monte Carlo methods, taking account of random errors in the DS86 dose estimates. The resulting uncertainty distributions in the relative risk model parameters were used to derive uncertainties in population cancer risks for a current UK population. Because of evidence for irregularities in the low-dose dose response, flexible dose-response models were used, consisting of a linear-quadratic-exponential model, used to model the high-dose part of the dose response, together with piecewise-linear adjustments for the two lowest dose groups. Following an assumed administered dose of 0.001 Sv, lifetime leukaemia radiation-induced incidence risks were estimated to be 1.11 x 10(-2) Sv(-1) (95% Bayesian CI -0.61, 2.38) using this model. Following an assumed administered dose of 0.001 Sv, lifetime solid cancer radiation-induced incidence risks were calculated to be 7.28 x 10(-2) Sv(-1) (95% Bayesian CI -10.63, 22.10) using this model. Overall, cancer incidence risks predicted by Bayesian Markov Chain Monte Carlo methods are similar to those derived by classical likelihood-based methods and which form the basis of established estimates of radiation-induced cancer risk.

Algorithms↗
PubMed2006

Predicting colorectal cancer risk in patients with rectal bleeding.

BACKGROUND: Rectal bleeding is an important symptom of colorectal cancer but has low predictive value in primary care. AIM: To determine which characteristics of rectal bleeding, along with other factors, are predictive of colorectal cancer. DESIGN OF STUDY: Observation study of patients with rectal bleeding referred to an open-access diagnostic clinic. SETTING: Primary care, southern England. METHOD: Symptom data were collected, using a self-completed questionnaire. Logistic regression techniques were used to determine predictors of colorectal cancer. RESULTS: There were 604 patients in the study and 22 (3.6%, 95% confidence interval [CI] = 2.0% to 5.2%) were diagnosed with colorectal cancer. Significant predictors of colorectal cancer were found to be age (<50 years: odds ratio [OR] = 1; 50-69 years: OR = 5.1, 95% CI = 1.4 to 18.6; > or = 70 years: OR = 8.2, 95% CI = 2.1 to 31.8) and blood mixed with the stool (Likelihood ratio [LR] 1.5; adjusted OR = 3.8; 95% CI = 1.4 to 10.5). Presence of haemorrhoids associated with bright red bleeding not mixed with stool reduced the likelihood of cancer (OR = 0.4, 95% CI = 0.1 to 1.2) but did not eliminate it--a cancer was present in 2% of patients with these symptoms. CONCLUSION: Patient-reported type of rectal bleeding as an isolated symptom has insufficient diagnostic value to be useful in general practice. By studying referred patients, we may even have overestimated its value. At best, it could be useful as a component of a composite symptom score to guide referral decisions.

Aged↗