Commercial wearable devices are surfacing as an appealing mechanism to detect COVID-19 and potentially other public health threats, due to their widespread use. To assess the validity of wearable devices as population health screening tools, it is essential to evaluate predictive methodologies based on wearable devices by mimicking their real-world deployment. Several points must be addressed to transition from statistically significant differences between infected and uninfected cohorts to COVID-19 inferences on individuals. We demonstrate the strengths and shortcomings of existing approaches on a cohort of 32,198 individuals who experience influenza like illness (ILI), 204 of which report testing positive for COVID-19. We show that, despite commonly made design mistakes resulting in overestimation of performance, when properly designed wearables can be effectively used as a part of the detection pipeline. For example, knowing the week of year, combined with naive randomised test set generation leads to substantial overestimation of COVID-19 classification performance at 0.73 AUROC. However, an average AUROC of only 0.55 ± 0.02 would be attainable in a simulation of real-world deployment, due to the shifting prevalence of COVID-19 and non-COVID-19 ILI to trigger further testing. In this work we show how to train a machine learning model to differentiate ILI days from healthy days, followed by a survey to differentiate COVID-19 from influenza and unspecified ILI based on symptoms. In a forthcoming week, models can expect a sensitivity of 0.50 (0-0.74, 95% CI), while utilising the wearable device to reduce the burden of surveys by 35%. The corresponding false positive rate is 0.22 (0.02-0.47, 95% CI). In the future, serious consideration must be given to the design, evaluation, and reporting of wearable device interventions if they are to be relied upon as part of frequent COVID-19 or other public health threat testing infrastructures.
Background In 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental health, limited access to medical care, and barriers due to cost. Objective This study aimed to determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes. Methods Here, we present the development of PSYCHE-D (Prediction of Severity Change-Depression), a predictive model developed using PGHD from more than 4000 individuals, which forecasts the long-term increase in depression severity. PSYCHE-D uses a 2-phase approach. The first phase supplements self-reports with intermediate generated labels, and the second phase predicts changing status over a 3-month period, up to 2 months in advance. The 2 phases are implemented as a single pipeline in order to eliminate data leakage and ensure results are generalizable. Results PSYCHE-D is composed of 2 Light Gradient Boosting Machine (LightGBM) algorithm–based classifiers that use a range of PGHD input features, including objective activity and sleep, self-reported changes in lifestyle and medication, and generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect an increase in depression severity over a 3-month interval, with a sensitivity of 55.4% and a specificity of 65.3%, nearly tripling sensitivity while maintaining specificity when compared with a random model. Conclusions These results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual’s mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals experiencing depression.
Objective Determining the amount of hair on the scalp has always been an important metric of patient satisfaction for hair growth and hair retention technologies. While simple in concept, this measurement is a difficult, resource intensive task for the dermatologist and the research scientist. Specifically, counting and measuring hair in phototrichogram images is very time consuming and labour intensive. Due to cost, often only a fraction of available images is manually analysed. There is a need for an automated method that can significantly increase speed and throughput while reducing the cost of counting and measuring hair in phototrichogram images. Methods Recent advances in machine learning and deep convolutional neural networks (deep learning) have led to a revolution in the analysis of image, video, speech, text and other sensor data. Image diagnostics have seen remarkable improvements with completely automated methods outperforming both human experts and human‐engineered analysis methods. Deep learning methods can also provide speed and cost benefits. To enable use of a deep learning, we created a data set of 288 manually annotated phototrichogram images with marked location and length of each hair (the training dataset). We designed a custom neural network architecture and custom image processing algorithms to best utilize the available training data and to maximize performance for hair counting and length measurement. The performance of the algorithm was qualified by comparing hair count and length measurements to an independent ground truth method, the semi‐manual Canfield's Hair Metrix method. Results Leveraging deep neural networks, we have developed capability to apply machine learning to reduce the time needed to acquire data from phototrichograms of patients’ scalp from months to seconds. Our algorithm enables fast and fully automated hair counting and length measurement. The algorithm shows high agreement with human manually assisted analysis (ground truth). Conclusions We have trained and deployed an algorithm utilizing this technology and have demonstrated the reproducibility, accuracy and speed of this algorithm that, once deployed, requires little to no recurring cost or manual intervention for its operation. The method allows fast analysis of large number of images, reducing study cost and significantly reducing study analysis time.
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.