Digital Biomarkers最新文献

Background: This commentary highlights the evolution of our understanding of physical function (PF) and key models/frameworks that have contributed to the current holistic understanding of PF, which encompasses not only a person's performance but also the environment and any adaptations an individual utilizes. This commentary also addresses how digital health tools can facilitate and complement the assessment of holistic PF and enable both objective and subjective input from the participant in their real-world environment. Lastly, we discuss how successful implementation of digital tools within clinical research requires patient input.

Summary: This commentary highlights how our understanding of PF has evolved to be more holistic.

Key messages: Inclusion of digital tools within clinical research can provide a path forward to holistically assess PF in a patient-focused manner.

Background: The global need for rapid diagnostic methods for pathogen identification and antimicrobial susceptibility testing (AST) is underscored by the increasing bacterial resistance and limited therapeutic options, especially critical in sepsis management.

Summary: This review examines the aspects of the eHealth and mHealth in Antimicrobial Stewardship Programs (ASPs) to improve the treatment of infections and rational use of antimicrobials.

Key messages: The evolution from traditional phenotype-based methods to rapid molecular and mass spectrometry techniques has significantly decreased result turnaround times, improving patient outcomes. Despite advancements, the complex decision-making in antimicrobial therapy often exceeds the capacity of many clinicians, highlighting the importance of ASPs. These programs, integrating mHealth and eHealth, leverage technology to enhance healthcare services and patient outcomes, particularly in remote or resource-limited settings. However, the application of such technologies in antimicrobial management remains underexplored in hospitals. The development of platforms combining antimicrobial prescription data with pharmacotherapeutic algorithms and laboratory integration can significantly reduce costs and improve hospitalization times and mortality rates.

Introduction: Existing theories and empirical works link phone use with anxiety; however, most leverage subjective self-reports of phone use (e.g., validated questionnaires) that may not correspond well with true behavior. Moreover, most works linking phone use with anxiety do not interrogate associations within a temporal framework. Accordingly, the present study sought to investigate the utility of passively sensed phone use as a longitudinal predictor of anxiety symptomatology within a population particularly vulnerable to experiencing anxiety.

Methods: Using data from the GLOBEM study, which continuously collected longitudinal behavioral data from a college cohort of N = 330 students, weekly PHQ-4 anxiety subscale scores across 3 years (2019-2021) were paired with median daily phone use records from the 2 weeks prior to anxiety self-report completion. Phone use was operationalized through unlock duration which was passively curated via Apple's "Screen Time" feature. GPS-tracked location data was further utilized to specify whether an individual's phone use was at home or away from home. Within-individual and temporal associations between phone use and anxiety were modeled within an ordinal mixed-effects logistic regression framework.

Results: While there was no significant association between anxiety levels and either median total phone use or median phone use at home, participants in the top quartile of median phone use away from home were predicted to exhibit clinically significant anxiety levels 20% more frequently than participants in the bottom quartile during the first study year; however, this association weakened across successive years. Importantly, these associations remained after controlling for age, physical activity, sleep, and baseline anxiety levels and were not recapitulated when operationalizing phone use with unlock frequency.

Conclusions: These findings suggest that phone use may be leveraged as a means of mitigating or coping with anxiety in social situations outside the home, while pandemic-related developments may also have attenuated this behavior later in the study. Nevertheless, the present results suggest promise in interrogating a larger suite of objectively measured phone use behaviors within the context of social anxiety.

Introduction: Weakened facial movements are early-stage symptoms of amyotrophic lateral sclerosis (ALS). ALS is generally detected based on changes in facial expressions, but large differences between individuals can lead to subjectivity in the diagnosis. We have proposed a computerized analysis of facial expression videos to detect ALS.

Methods: This study investigated the action units obtained from facial expression videos to differentiate between ALS patients and healthy individuals, identifying the specific action units and facial expressions that give the best results. We utilized the Toronto NeuroFace Dataset, which includes nine facial expression tasks for healthy individuals and ALS patients.

Results: The best classification accuracy was 0.91 obtained for the pretending to smile with tight lips expression.

Conclusion: This pilot study shows the potential of using computerized facial expression analysis based on action units to identify facial weakness symptoms in ALS.

Introduction: The complex health, social, and economic consequences of tobacco smoking underscore the importance of incorporating reliable and scalable data collection on smoking status and habits into research across various disciplines. Given that smoking impacts voice production, we aimed to develop a gender and language-specific vocal biomarker of smoking status.

Methods: Leveraging data from the Colive Voice study, we used statistical analysis methods to quantify the effects of smoking on voice characteristics. Various voice feature extraction methods combined with machine learning algorithms were then used to produce a gender and language-specific (English and French) digital vocal biomarker to differentiate smokers from never-smokers.

Results: A total of 1,332‬ participants were included after propensity score matching (mean age = 43.6 [13.65], 64.41% are female, 56.68% are English speakers, 50% are smokers and 50% are never-smokers). We observed differences in voice features distribution: for women, the fundamental frequency F0, the formants F1, F2, and F3 frequencies and the harmonics-to-noise ratio were lower in smokers compared to never-smokers (p < 0.05) while for men no significant disparities were noted between the two groups. The accuracy and AUC of smoking status prediction reached 0.71 and 0.76, respectively, for the female participants, and 0.65 and 0.68, respectively, for the male participants.

Conclusion: We have shown that voice features are impacted by smoking. We have developed a novel digital vocal biomarker that can be used in clinical and epidemiological research to assess smoking status in a rapid, scalable, and accurate manner using ecological audio recordings.

Background: Wearable sensors have been heralded as revolutionary tools for healthcare. However, while data are easily acquired from sensors, users still grapple with questions about how sensors can meaningfully inform everyday clinical practice and research.

Summary: We propose a simple, comprehensive framework for utilizing sensor data in healthcare. The framework includes three key processes that are applied together or separately to (1) automate traditional clinical measures, (2) illuminate novel correlates of disease and impairment, and (3) predict current and future outcomes. We demonstrate applications of the Automate-Illuminate-Predict framework using examples from rehabilitation medicine.

Key messages: Automate-Illuminate-Predict provides a universal approach to extract clinically meaningful data from wearable sensors. This framework can be applied across the care continuum to enhance patient care and inform personalized medicine through accessible, noninvasive technology.

Introduction: Essential tremor is a common movement disorder. Numerous validated clinical rating scales exist to quantify essential tremor severity by employing rater-dependent visual observation but have limitations, including the need for trained human raters and the lack of precision and sensitivity compared to technology-based objective measures. Other continuous objective methods to quantify tremor amplitude have been developed, but frequently provide unitless measures (e.g., tremor power), limiting real-world interpretability. We propose a novel algorithm to measure kinetic tremor amplitude using digital spiral drawings, applying the V3 framework (sensor verification, analytical validation, and clinical validation) to establish reliability and clinical utility.

Methods: Archimedes spiral drawings were recorded on a digitizing tablet from participants (n = 7) enrolled in a randomized placebo control double-blinded crossover pilot trial evaluating the efficacy of oral cannabinoids in reducing essential tremor. We developed an algorithm to calculate the mean and maximum tremor amplitude derived from the spiral tracings. We compared the digitally measured tremor amplitudes to manual measurement to evaluate sensor reliability, determined the test-retest reliability of the digital output across two short-interval repeated measures, and compared the digital measure to kinetic tremor severity graded using The Essential Tremor Rating Assessment Scale (TETRAS) score for spiral drawings.

Results: This algorithm for automated assessment of kinetic tremor amplitude from digital spiral tracings demonstrated a high correlation with manual spot measures of tremor amplitude, excellent test-retest reliability, and a high correlation with human ratings of the TETRAS score for spiral drawing severity when the tremor severity was rated "slight tremor" or worse.

Discussion: This digital measure provides a simple and clinically relevant evaluation of kinetic tremor amplitude that shows promise as a potential future endpoint for use in clinical trials of essential tremor.