Itch is a common clinical symptom and major driver of disease-related morbidity across a wide range of medical conditions. A substantial unmet need is for objective, accurate measurements of itch. In this article, we present a noninvasive technology to objectively quantify scratching behavior via a soft, flexible, and wireless sensor that captures the acousto-mechanic signatures of scratching from the dorsum of the hand. A machine learning algorithm validated on data collected from healthy subjects (n = 10) indicates excellent performance relative to smartwatch-based approaches. Clinical validation in a cohort of predominately pediatric patients (n = 11) with moderate to severe atopic dermatitis included 46 sleep-nights totaling 378.4 hours. The data indicate an accuracy of 99.0% (84.3% sensitivity, 99.3% specificity) against visual observation. This work suggests broad capabilities relevant to applications ranging from assessing the efficacy of drugs for conditions that cause itch to monitoring disease severity and treatment response.
Introduction: Pruritus is a common symptom across various dermatologic conditions, with a negative impact on quality of life. Devices to quantify itch objectively primarily use scratch as a proxy. This review compares and evaluates the performance of technologies aimed at objectively measuring scratch behavior.Methods: Articles identified from literature searches performed in October 2020 were reviewed and those that did not report a primary statistical performance measure (eg, sensitivity, specificity) were excluded. The articles were independently reviewed by 2 authors. Results:The literature search resulted in 6231 articles, of which 24 met eligibility criteria. Studies were categorized by technology, with actigraphy being the most studied (n = 21). Wrist actigraphy's performance is poorer in pruritic patients and inherently limited in finger-dominant scratch detection. It has moderate correlations with objective measures (Eczema and Area Severity Index/Investigator's Global Assessment: r s (r) = 0.70-0.76), but correlations with subjective measures are poor (r 2 = 0.06, r s (r) = 0.18-0.40 for itch measured using a visual analog scale). This may be due to varied subjective perception of itch or actigraphy's underestimation of scratch. Conclusion:Actigraphy's large variability in performance and limited understanding of its specificity for scratch merits larger studies looking at validation of data analysis algorithms and device performance, particularly within target patient populations.
Pruritus is a prominent symptom in many systemic (e.g. renal failure, cholestasis) and dermatologic (e.g. urticaria, xerosis) conditions. Atopic dermatitis (AD) is characterized by the itch-scratch cycle, whereby the reflexive scratching leads to greater skin inflammation and worsens pruritus. Itch in AD has also been associated with certain stages of the circadian rhythm. Therefore, an objective method of measuring nocturnal scratching behaviour as a proxy for itch symptom severity would prove useful and insightful in the management of a patient’s AD. The purpose of this study is to validate the performance of a novel wearable sensor, the advanced acousto-mechanic (ADAM) device, in regard to the detection of nocturnal scratching behaviour in paediatric and adult populations with AD. The sensor is able to detect both the accelerometer data (movement in space) and acoustic data generated by finger and wrist movements in scratching. Performance metrics used to evaluate the sensor include sensitivity, specificity, positive predictive value (PPV) and F1 score (combination of precision and recall). The sensor’s performance was compared to video recordings, the gold standard for objectively measuring scratch. A total of 60 healthy adult subjects (22 males and 38 females) were recruited and asked to perform a series of scratching behaviours and non-scratching behaviours while wearing the ADAM sensor on their dorsal hand using a one-use adhesive in a controlled environment. The data were used to create a machine-learning algorithm for scratch detection and validation in both a paediatric and adult AD cohort. Individuals with mild-to-severe AD were recruited to monitor their nocturnal scratching behaviour in the home environment. An infrared camera was provided for each subject to record the patient’s scratching and compared it to data collected by the ADAM sensor worn on the subject’s dominant dorsal hand. Video recordings were graded for scratching activity by at least two graders; scratch was defined as lasting at least 4.5 s. The scratch algorithm’s classification of scratch and non-scratch was then compared to the gold standard video recording and generated performance metrics. The initial scratch algorithm yielded sensitivity of 88%, specificity of 88% and F1 score of 90% when cross-validated with data from 10 healthy adult subjects. When cross-validated with data from all 60 healthy adult subjects, the algorithm yielded a sensitivity of 92%, specificity of 98% and F1 score of 95%. A total of 11 paediatric AD subjects (1 : 3 male-to-female ratio, ages 10.5 ± 9.1) and 46 nights of data were collected in the home setting, yielding a total of 378.4 h of video. The scratch algorithm was able to detect scratching behaviour with sensitivity of 84%, specificity of 99% and F1 score of 83% in the paediatric cohort. In the adult cohort, a total of 11 adults with atopic dermatitis (two males and nine females, ages 29 ± 13) and 73 nights of data were collected, resulting in a total of 457.7 h of video. When the data was applied to the scratch algorithm, the algorithm yielded a sensitivity of 93%, specificity of 100% and F1 score of 91%. The use of a flexible wearable sensor on the dorsal hand for detection of nocturnal scratching behaviour in both paediatric and adult subjects with atopic dermatitis can provide valuable information regarding the degree of scratching and severity of pruritus the wearer is experiencing when compared to video recording. Its ability to serve as an accurate objective measure of itch may be helpful in drug development and can help serve as a tool to guide the clinical management of symptoms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.