Modified Clopper-Pearson Confidence Interval for Binomial Proportion

Habtzghi, Desale; Midha, Chand K.; Das, Ashish

doi:10.2991/jsta.2014.13.4.3

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The responses to this test were analyzed to measure the recall (ratio of correctly diagnosed images by dermatologists) of the real and generated images. The 95% CI was calculated using the Clopper-Pearson method [ 37 ] to estimate the uncertainty of the reported results.…”

Section: Methodsmentioning

confidence: 99%

Improving Skin Color Diversity in Cancer Detection: Deep Learning Approach

Rezk¹,

Eltorki²,

El‐Dakhakhni³

2022

JMIR Dermatol

View full text Add to dashboard Cite

Background The lack of dark skin images in pathologic skin lesions in dermatology resources hinders the accurate diagnosis of skin lesions in people of color. Artificial intelligence applications have further disadvantaged people of color because those applications are mainly trained with light skin color images. Objective The aim of this study is to develop a deep learning approach that generates realistic images of darker skin colors to improve dermatology data diversity for various malignant and benign lesions. Methods We collected skin clinical images for common malignant and benign skin conditions from DermNet NZ, the International Skin Imaging Collaboration, and Dermatology Atlas. Two deep learning methods, style transfer (ST) and deep blending (DB), were utilized to generate images with darker skin colors using the lighter skin images. The generated images were evaluated quantitively and qualitatively. Furthermore, a convolutional neural network (CNN) was trained using the generated images to assess the latter’s effect on skin lesion classification accuracy. Results Image quality assessment showed that the ST method outperformed DB, as the former achieved a lower loss of realism score of 0.23 (95% CI 0.19-0.27) compared to 0.63 (95% CI 0.59-0.67) for the DB method. In addition, ST achieved a higher disease presentation with a similarity score of 0.44 (95% CI 0.40-0.49) compared to 0.17 (95% CI 0.14-0.21) for the DB method. The qualitative assessment completed on masked participants indicated that ST-generated images exhibited high realism, whereby 62.2% (1511/2430) of the votes for the generated images were classified as real. Eight dermatologists correctly diagnosed the lesions in the generated images with an average rate of 0.75 (360 correct diagnoses out of 480) for several malignant and benign lesions. Finally, the classification accuracy and the area under the curve (AUC) of the model when considering the generated images were 0.76 (95% CI 0.72-0.79) and 0.72 (95% CI 0.67-0.77), respectively, compared to the accuracy of 0.56 (95% CI 0.52-0.60) and AUC of 0.63 (95% CI 0.58-0.68) for the model without considering the generated images. Conclusions Deep learning approaches can generate realistic skin lesion images that improve the skin color diversity of dermatology atlases. The diversified image bank, utilized herein to train a CNN, demonstrates the potential of developing generalizable artificial intelligence skin cancer diagnosis applications. International Registered Report Identifier (IRRID) RR2-10.2196/34896

show abstract

Section: Methodsmentioning

confidence: 99%

Improving Skin Color Diversity in Cancer Detection: Deep Learning Approach

Rezk¹,

Eltorki²,

El‐Dakhakhni³

2022

JMIR Dermatol

View full text Add to dashboard Cite

show abstract

“…Some CIs for binomial proportions are considered to perform better with small sample data than others with larger ones, the Pearson-Clopper alternative was chosen because it uses the tail method and is common. However, note that "various evaluations indicate that the Clopper-Pearson interval tends to be extremely conservative for small to moderate n (sample sizes)" [35] (p. 297), which is the case in some of the compared countries' domicile category samples.…”

mentioning

confidence: 99%

“…The Pearson-Clopper CI for proportion probability in a binomial distribution was calculated. This particular type of CI has its own pros and cons, which are discussed in the literature [35,36]. Some CIs for binomial proportions are considered to perform better with small sample data than others with larger ones, the Pearson-Clopper alternative was chosen because it uses the tail method and is common.…”

mentioning

confidence: 99%

The Challenges of Mitigating Climate Change Hidden in End-User Beliefs and Expectations

et al. 2021

View full text Add to dashboard Cite

This research explores the potential challenges of reducing climate change hidden in the personal and collective energy use-related beliefs and expectations of end users. The study proposes a new typology of social environments, using the concept of personal and collective efficacy, which is suitable for exploring the level and nature of the challenges of solving social problems that require engaging whole societies. We use empirical data from round eight of the European Social Survey, which covers more than 20 European countries, and we employ the basic statistical methods of descriptive statistics, linear correlation and population proportion. The findings suggest that the challenges to climate-change mitigation by changing energy-use behaviour could be hidden in contradictions between beliefs in personal and collective abilities to contribute and positive outcome expectations. This opportunity could be addressed by relevant policy measures, providing more evidence of positive outcomes, even from personal contributions, and developing suitable means for collective contributions to increase awareness and belief in collective engagement.

show abstract