Dataset Information

A Pilot Study to Assess the Reliability of Digital Image-Based PASI Scores Across Patient Skin Tones and Provider Training Levels.

ABSTRACT:

Introduction

The ability to perform psoriasis skin assessments remotely through digital image-based psoriasis area and severity index (DIB-PASI) would be a valuable tool for psoriasis clinical trials. An ideal teledermatological assessment would be robust across patients of diverse skin tones as well as across assessors of varying experience levels. In this pilot study, we evaluated the reliability of face-to-face (FTF) versus DIB-PASI scores determined by trained clinical assessors with a spectrum of experience and with patients of different skin tones.

Methods

Fourteen subjects of varying skin tones with moderate-to-severe plaque psoriasis were treated with adalimumab. In-person PASI assessments and digital photography were performed in the clinic at weeks 0, 12, and 24. Photographs were reviewed by four independent assessors to derive a digital image-based PASI score. The concordance of face-to-face PASI (FTF-PASI) and DIB-PASI were analyzed across patient and assessor factors.

Results

Overall concordance between FTF-PASI and DIB-PASI was high (ICC 0.82, p < 0.0001), with good agreement across individual assessors. When analyzed by PASI score component or body region, digital assessors also demonstrated good agreement with the FTF assessor. Similarly, DIB-PASI showed high concordance with FTF-PASI for patients with light skin tones and patients with medium-to-dark skin tones, and across clinical training levels.

Conclusion

Overall, PASI scores derived from digital images showed good agreement with those determined in person. Importantly, these remote assessments were reliable for both light and medium-to-dark skin tones, and robust to training level of the assessor. The findings from this pilot study lay the foundation for expanding teledermatology-based clinical trials for patients with psoriasis and enabling accurate, remote monitoring of disease severity and therapy response.

SUBMITTER: Wu D

PROVIDER: S-EPMC9276898 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:INTRODUCTION:Reliable and accurate assessment of severity in psoriasis is very important in order to meet indication criteria for initiation of systemic treatment or to evaluate treatment efficacy. The most acknowledged tool for measuring the extent of psoriatic skin changes is the Psoriasis Area and Severity Index (PASI). However, the calculation of PASI can be tedious and subjective and high intraobserver and interobserver variability is an important concern. Therefore, there is a great need for a standardised and objective method that guarantees a reproducible PASI calculation. Within this study we will investigate the precision and reproducibility of automated, computer-guided PASI measurements in comparison to trained physicians to address these limitations. METHODS AND ANALYSIS:Non-interventional analyses of PASI calculations by either physicians in a prospective versus retrospective setting or an automated computer-guided algorithm in 120 patients with plaque psoriasis. All retrospective PASI calculations by physicians or by the computer algorithm are based on total body digital images. The primary objective of this study is comparison of automated computer-guided PASI measurements by means of digital image analysis versus conventional, prospective or retrospective physicians' PASI assessments. Secondary endpoints include (1) the assessment of physicians' interobserver variance in PASI calculations, (2) the assessment of physicians' intraobserver variance in PASI assessments of the same patients' images after a time interval of at least 4 weeks, (3) the assessment of the deviation between physicians' prospective versus retrospective PASI calculations, and (4) the reproducibility of automated computer-guided PASI measurements by assessment of two sets of total body digital images of the same patients taken at one time point. ETHICS:Ethical approval was provided by the Ethics Committee of the Medical Faculty of the University of Heidelberg (ethics approval number S-379/2016). TRIAL REGISTRATION NUMBER:DRKS00011818; Results.

Project description:BackgroundComputer-aided diagnosis (CADx) software that provides a second opinion has been widely used to assist physicians with various tasks. In dermatology, however, CADx has been mostly limited to melanoma or melanocytic skin cancer diagnosis. The frequency of non-melanocytic skin cancers and the accessibility of regular digital macrographs have raised interest in developing CADx for broader applications.ObjectivesTo investigate the feasibility of using CADx to diagnose both melanocytic and non-melanocytic skin lesions based on conventional digital photographic images.MethodsThis study was approved by an institutional review board, and the requirement to obtain informed consent was waived. In total, 769 conventional photographs of melanocytic and non-melanocytic skin lesions were retrospectively reviewed and used to develop a CADx system. Conventional and new color-related image features were developed to classify the lesions as benign or malignant using support vector machines (SVMs). The performance of CADx was compared with that of dermatologists.ResultsThe clinicians' overall sensitivity, specificity, and accuracy were 83.33%, 85.88%, and 85.31%, respectively. New color correlation and principal component analysis (PCA) features improved the classification ability of the baseline CADx (p = 0.001). The estimated area under the receiver operating characteristic (ROC) curve (Az) of the proposed CADx system was 0.949, with a sensitivity and specificity of 85.63% and 87.65%, respectively, and a maximum accuracy of 90.64%.ConclusionsWe have developed an effective CADx system to classify both melanocytic and non-melanocytic skin lesions using conventional digital macrographs. The system's performance was similar to that of dermatologists at our institute. Through improved feature extraction and SVM analysis, we found that conventional digital macrographs were feasible for providing useful information for CADx applications. The new color-related features significantly improved CADx applications for skin cancer.

Project description:Measuring musical abilities in childhood can be challenging. When music training and maturation occur simultaneously, it is difficult to separate the effects of specific experience from age-based changes in cognitive and motor abilities. The goal of this study was to develop age-equivalent scores for two measures of musical ability that could be reliably used with school-aged children (7-13) with and without musical training. The children's Rhythm Synchronization Task (c-RST) and the children's Melody Discrimination Task (c-MDT) were adapted from adult tasks developed and used in our laboratories. The c-RST is a motor task in which children listen and then try to synchronize their taps with the notes of a woodblock rhythm while it plays twice in a row. The c-MDT is a perceptual task in which the child listens to two melodies and decides if the second was the same or different. We administered these tasks to 213 children in music camps (musicians, n = 130) and science camps (non-musicians, n = 83). We also measured children's paced tapping, non-paced tapping, and phonemic discrimination as baseline motor and auditory abilities We estimated internal-consistency reliability for both tasks, and compared children's performance to results from studies with adults. As expected, musically trained children outperformed those without music lessons, scores decreased as difficulty increased, and older children performed the best. Using non-musicians as a reference group, we generated a set of age-based z-scores, and used them to predict task performance with additional years of training. Years of lessons significantly predicted performance on both tasks, over and above the effect of age. We also assessed the relation between musician's scores on music tasks, baseline tasks, auditory working memory, and non-verbal reasoning. Unexpectedly, musician children outperformed non-musicians in two of three baseline tasks. The c-RST and c-MDT fill an important need for researchers interested in evaluating the impact of musical training in longitudinal studies, those interested in comparing the efficacy of different training methods, and for those assessing the impact of training on non-musical cognitive abilities such as language processing.