Developing a utility decision framework to evaluate predictive models in breast cancer risk estimation

Wu, Yirong; Abbey, Craig K.; Chen, Xianqiao; Liu, Jie; Page, David; Alagöz, Oğuzhan; Peissig, Peggy L.; Onitilo, Adedayo A.; Burnside, Elizabeth S.

doi:10.1117/1.jmi.2.4.041005

Cited by 5 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, several studies have already shown significant improvement by adding breast density (34,35). Wu et al (36) used Gail features with and without mined mammographic features by employing a logistic regression-based model that resulted in an AUC of 0.71 versus 0.60, respectively. This, however, relied on the radiologist's analysis and interpretation of the index DM.…”

Section: Discussionmentioning

confidence: 99%

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms

et al. 2019

View full text Add to dashboard Cite

reast cancer is the second leading cause of cancer-related deaths and the most commonly diagnosed cancer in women across the world (1). Digital mammography (DM) is the primary imaging modality of breast cancer screening in women who are asymptomatic. In a diagnostic workup setting (2), DM has been shown to reduce breast cancer mortality (3). In standard clinical practice, a radiologist reads mammograms and classifies the findings according to the American College of Radiology (4) Breast Imaging Reporting and Data System (BI-RADS) lexicon. An abnormal finding depicted at DM typically requires a diagnostic workup, which may include additional mammographic views or possibly additional imaging modalities. If a lesion is suspicious for cancer, further evaluation with a biopsy is recommended. Analyzing these images is challenging because of the subtle differences between lesions and background fibroglandular tissue, different lesion types, the nonrigid nature of the breast, and the relatively small proportion of cancers in a screening population of women at average risk (2). This leads to substantial intraobserver and interobserver variability (5). The average performance measures for screening mammography by a radiologist was reported by Lehman et al (6) to be 86.9% sensitivity and 88.9% specificity. Breast cancer risk prediction models on the basis of clinical features can help physicians estimate the probability of an individual or population to develop breast cancer within certain time frames. As a result, they are often used to recommend an individual screening plan. In a systematic survey of risk prediction models, Meads et al (7) reported a limited performance when applied to general populations (area under the receiver operating characteristic curve [AUC], 0.67; 95% confidence interval [CI]: 0.65, 0.68), and showed improved results when applied to high-risk populations (AUC, 0.76; 95% CI: 0.70, 0.82).

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms

et al. 2019

View full text Add to dashboard Cite

show abstract

“…We use a value of $100,000/QALY, which is consistent (although at the low end of the scale) with published reports [17]. The diagnostic utilities used are those published by Wu et al [4], which assign true-negative outcomes a value of 0 QALYs as a reference. False-negative outcomes are assigned a value of −2.52 QALYs.…”

Section: Resultsmentioning

confidence: 91%

“…If such measures are to be adopted in any widespread sense, they must be shown to be cost-effective. This work builds on previous investigations into the utility of risk-prediction in the context of breast cancer screening [4, 5] using utility approaches derived for ROC measures [6-13]. …”

Section: Introductionmentioning

confidence: 99%

A utility/cost analysis of breast cancer risk prediction algorithms

Abbey

Burnside

et al. 2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk-prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.

show abstract

“…Different sets of machine learning algorithms are taken into account for obtaining data. The algorithms include Support Vector Machine (SVM), Decision Tree (C4.5), Naive Bayes (NB), and k-Nearest Neighbors (KNN) [27]. The major objective of these algorithms is to find out the correctness of classifying the data using machine learning.…”

Section: Detection Of Breast Cancer Using Machine Learning Algorithmsmentioning

confidence: 99%

A Feature Fusion Based Hybrid Approach for Breast Cancer Classification

Iftikhar

Amin

Abbas

2022

JCBI

View full text Add to dashboard Cite

A detected type of cancer is breast cancer commonly in women. According to some estimate one in nine women is diagnosed with breast cancer. It is unfortunate that due to a lack of proper facilities, the diagnosis of breast cancer in patients is being delayed, which is leading to an increase in the possible death rate. Many different statistical methods and Machine Learning algorithms are often employed in the study to make breast cancer detection more accurate. Machine learning (ML) has allowed doctors to achieve remarkable results, and healthcare is using ML-based models to detect breast cancer in women. This allows analyzing the healthcare data and uses the traditional computer-aided detection (CAD) to assess breast cancer. Machine learning has become an accepted clinical practice and allows doctors to evaluate the ML model to detect breasts at an early stage. A major aim is to diagnose patients with breast cancer by analyzing the data of patients and classifying them into two categories, having diagnosis results as Benign "B" or Malignant “M”. In this study different machine learning algorithms are used to classify cancer as either its malignant or benign. The Kaggle data set was used for applying these algorithms to get the best accuracy. MLP is more efficient and accurate algorithm to classify the breast tumor. And here also fitted the matthews_corrcoef for MLP is 0.89% and accuracy score for the random forest is 0.94%.

show abstract

Developing a utility decision framework to evaluate predictive models in breast cancer risk estimation

Cited by 5 publications

References 39 publications

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms

A utility/cost analysis of breast cancer risk prediction algorithms

A Feature Fusion Based Hybrid Approach for Breast Cancer Classification

Contact Info

Product

Resources

About