Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients

Bartfay, Emma; Mackillop, W.; Pater, J

doi:10.1111/j.1365-2354.2005.00638.x

Cited by 29 publications

(20 citation statements)

References 33 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example it can be useful to compare a prognostic model that has been derived from logistic regression with another one that has been derived with the random forest (Breiman, 2001b). For example, in a recent study Bartfay et al (2006) used the Brier score and the AUC to compare neural network models to logistic regression models. In a Bayesian framework, one could think of competing scientists that choose different modelling strategies and the aim is to elicit the best forecast.…”

Section: Summary and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The Performance of Risk Prediction Models

Gerds¹,

Cai²,

2008

View full text Add to dashboard Cite

SummaryFor medical decision making and patient information, predictions of future status variables play an important role. Risk prediction models can be derived with many different statistical approaches. To compare them, measures of predictive performance are derived from ROC methodology and from probability forecasting theory. These tools can be applied to assess single markers, multivariable regression models and complex model selection algorithms. This article provides a systematic review of the modern way of assessing risk prediction models. Particular attention is put on proper benchmarks and resampling techniques that are important for the interpretation of measured performance. All methods are illustrated with data from a clinical study in head and neck cancer patients.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

“…For example, the area under the ROC curve and the Brier score often provide similar answers (e.g. Redelmeier et al, 1991;Bartfay et al, 2006). However, the predictive performance of a risk prediction model has various aspects and components, and different measures of predictive performance give different emphasize to these components.…”

Section: Introductionmentioning

confidence: 99%

The Performance of Risk Prediction Models

Gerds¹,

Cai²,

2008

View full text Add to dashboard Cite

show abstract

“…Logistic regression was developed by the statistics community, whereas the remaining methods were developed by the machine-learning community. Logistic regression, a statistical fitting model, is widely used to model medical problems because the methodology is well established and coefficients can have intuitive clinical interpretations (4,5). Decision trees are graphical models that contain rules for predicting the target variable.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Logistic Regression and Artificial Neural Network Models in Breast Cancer Risk Estimation

Ayer¹,

Chhatwal²,

Alagöz³

et al. 2010

RadioGraphics

155

100

View full text Add to dashboard Cite

Computer models in medical diagnosis are being developed to help physicians differentiate between healthy patients and patients with disease. These models can aid in successful decision making by allowing calculation of disease likelihood on the basis of known patient characteristics and clinical test results. Two of the most frequently used computer models in clinical risk estimation are logistic regression and an artificial neural network. A study was conducted to review and compare these two models, elucidate the advantages and disadvantages of each, and provide criteria for model selection. The two models were used for estimation of breast cancer risk on the basis of mammographic descriptors and demographic risk factors. Although they demonstrated similar performance, the two models have unique characteristics-strengths as well as limitations-that must be considered and may prove complementary in contributing to improved clinical decision making.

show abstract

“…For the best performing model, we generated a ROC (receiver operating characteristic) curve as a graphical plot of sensitivity/specificity as the discrimination threshold is varied. [17][18][19] …”

Section: Immunohistochemistrymentioning

confidence: 99%

Osteopontin‐c is a selective marker of breast cancer

Mirza

Shaughnessy

Hurley

et al. 2007

Intl Journal of Cancer

123

128

View full text Add to dashboard Cite

While the acquisition of invasiveness is a critical step in early stage breast carcinomas (DCIS), no established molecular markers reliably identify tumor progression. The metastasis gene osteopontin is subject to alternative splicing, which yields 3 messages, osteopontin-a, osteopontin-b and osteopontin-c. Osteopontin-c is selectively expressed in invasive, but not in noninvasive, breast tumor cell lines, and it effectively supports anchorage independence. We evaluated osteopontin-c as a biomarker. The RNA message for osteopontin-c was present in 16 of 20 breast cancers (80%), but was undetectable in 22 normal specimens obtained from reduction mammoplasty. In contrast, osteopontin-a RNA was expressed at various levels in all 20 breast cancers, 11 tumor-surrounding tissues and 21 normal samples. The splice variant osteopontin-b was present at barely detectable levels in 18 of 20 cancers and in 6 of 22 normal breasts. By immunohistochemistry, 66 of 69 normal breasts were negative, while 3 showed low level staining. Among the breast cancers, 43 of 56 cores (77%) stained positive for osteopontin-c. When correlated with tumor grade, the staining for osteopontin-c increased from grade 1 to grade 3. In a total of 178 breast specimens analyzed, osteopontin-c was present in 78% of cancers, 36% of surrounding tissues and 0% of normal tissues. Furthermore, osteopontin-c detects a higher fraction of breast cancers than estrogen receptor (ER), progesterone receptor or HER2. In conjunction, osteopontin-c, ER and HER2 reliably predict grade 2-3 breast cancer. Hence, osteopontin-c is a diagnostic and prognostic marker that may have value in a diagnostic panel together with conventional breast cancer markers. ' 2007 Wiley-Liss, Inc.

show abstract

Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients

Cited by 29 publications

References 33 publications

The Performance of Risk Prediction Models

The Performance of Risk Prediction Models

Comparison of Logistic Regression and Artificial Neural Network Models in Breast Cancer Risk Estimation

Osteopontin‐c is a selective marker of breast cancer

Contact Info

Product

Resources

About