Digital Biomarkers最新文献

Introduction: Myasthenia gravis (MG) is a chronic autoimmune neuromuscular disease. Patients with MG are typically evaluated by neuromuscular experts through in-person neurologic examinations. These assessments are time-consuming, require significant disease expertise, and capture only a snapshot of disease.

Methods: Given this need, we developed a multimodal digital health technology (DHT) called BioDigit MG, for monitoring MG symptoms and objectively measuring disease severity. BioDigit MG includes tablet-guided speech and video-based assessments, electronic patient-reported outcomes relevant to MG, and a wearable sensor to measure physical activity and posture during activities of daily living.

Results: We assessed the feasibility and acceptability of BioDigit MG by conducting a clinical study with 20 participants with MG who used the DHT. During the study, a total of 219 speech tasks and 119 videos were collected by the DHT, achieving 100% reliability in data collection and transfer. To evaluate technology acceptance and usability, we conducted face-to-face interviews with the 20 MG patients and 5 expert clinicians. Participants found the DHT highly effective, easy to use, and well-suited to their needs. Efficient and reliable data transfer capabilities of BioDigit MG ensured that patient-generated data were promptly and securely delivered to healthcare providers.

Conclusion: These feasibility findings demonstrate that BioDigit MG is capable of reliable multimodal data collection and is acceptable to both patients and clinicians, supporting its potential for use in future larger scale validation studies.

Introduction: Incorporating outcome measures that assess the most impactful symptoms is a priority for clinical trials. We qualitatively examined whether caregivers of individuals with Rett syndrome deemed breathing dysfunction as a meaningful and measurable aspect of health.

Methods: We conducted semi-structured interviews (N = 13) with caregivers of individuals with Rett syndrome followed by thematic analysis grounded in theory to examine themes.

Results: Themes and subthemes for experiences with breathing dysfunction emerged: (1) meaningfulness; (2) impact; and (3) connecting with other symptoms. Two themes for preferences for digitally measuring breathing dysfunction emerged: (1) conditional willingness and (2) benefits of digital measurement.

Conclusion: Caregivers reported that breathing dysfunction was meaningful and measurable and had significant impacts on their child's lives as well as theirs and their families. This study lays the groundwork for guiding the development of novel measures and outcomes within future clinical trials managing breathing dysfunction in Rett syndrome.

Introduction: Cognitive performance declines with age and predicts important life outcomes, making it a promising - yet underutilized - biomarker of aging. In this study, we aimed to establish the feasibility and value of game-based digital biomarkers of cognitive aging using data from a home-based cognitive assessment game.

Methods: Participants (N = 871; age 18-75) completed Tunnel Runner, a 20-25 min cognitive game measuring reaction speed, response inhibition, interference control, response-rule switching, and decision-making. To assess the game's out-of-sample predictive accuracy, we trained machine learning models to predict participants' chronological age based on 17 game-based cognitive metrics and evaluated their performance using nested cross-validation. Cognitive aging scores were calculated as out-of-sample prediction errors from the best-performing model, and then adjusted for age-dependence using generalized additive models. These aging scores were then considered alongside three other variables: depression, ADHD, and gamer identity.

Results: The best-performing model, stacked ensemble from the automated machine learning framework AutoGluon, predicted out-of-sample chronological age with a mean absolute error of 6.97 years, a correlation of 0.626, and concordance of 0.698. No evidence of bias in predictive accuracy was found for gender or gaming identity. Prediction patterns and cognitive aging values met several expectations based on previous research: reduced cognitive aging in participants with self-reported ADHD, negative association between cognitive aging and gamer identity, and limited predictive differentiation under age 30. Findings regarding self-reported depression were inconclusive, though consistent with prior work.

Conclusion: Game-based assessment can produce accessible digital biomarkers of cognitive aging that reflect meaningful individual differences. This approach enables scalable and low-burden cognitive aging assessment, with potential applications for early detection of cognitive decline, longitudinal tracking, and intervention evaluation.

Introduction: A primary goal of physical medicine and rehabilitation is restoring community mobility after injury or illness. However, there is no clinically accepted real-world method to measure community mobility, which fundamentally limits our ability to evaluate treatment effectiveness. This study aimed to develop and validate a digital framework using GPS-enabled smartphones and inertial sensors to monitor community mobility and estimate clinical function in individuals with chronic stroke or lower limb amputation (LLA).

Methods: Ninety individuals with chronic stroke or LLA underwent remote monitoring for 3-9 months. Participants completed standard clinical assessments, and daily mobility data were extracted from GPS and step count features. We conducted four analyses: (1) characterization of group- and individual-level community mobility, (2) evaluation of mobility changes following a mobility-targeted intervention in a single case participant, (3) development of machine-learned models to predict clinical gait outcomes using community data, and (4) estimation of the minimum number of days needed to reliably predict functional outcomes.

Results: Community mobility measures revealed substantial variability both across and within individuals, reflecting diverse functional profiles. In a case study, a participant with LLA demonstrated increased activity and movement diversity following a personalized intervention. Machine-learned models estimated 6-Minute Walk Test and 10-Meter Walk Test scores with clinically acceptable error margins (7-10%) using as few as 14 days of community data. Reliable predictions were achievable with just 3-6 days of monitoring.

Conclusions: GPS- and smartphone-based monitoring offer a feasible and scalable approach to assess real-world mobility. This approach could close a critical gap in the care continuum and enable us to fully evaluate the real-world impact of treatment interventions while also reducing reliance on frequent in-person evaluations.

Introduction: Gait is a critical indicator of neurological health, with changes often signaling underlying decline. We developed a remote gait monitoring protocol using off-the-shelf shoe-based sensors (RunScribe) to assess gait parameters in real-world home settings. This protocol, known as Gait Assessment with Innovative Technologies - Home-based Use and Benefit (GAIT-HUB), was tested in individuals with multiple sclerosis (MS), a population at high risk for gait impairment due to the disease's variable progression.

Methods: Participants with MS completed an in-clinic baseline gait assessment using a validated sensor (G-Sensor®) and three weekly, remotely supervised gait assessments at home using the RunScribe sensors. Gait parameters were compared across devices using intra-class correlation coefficients (ICCs) and Bland-Altman analyses. Longitudinal reliability of remote assessments and system usability score (SUS) were evaluated.

Results: Twenty-nine participants (76% women, ages 19-67, PDDS range 0-5) successfully completed the home-based assessments. High agreement between devices was observed for gait speed, stride length, and cadence (ICCs >0.90), though phases like stance and swing showed more variability. Bland-Altman analyses indicated minimal bias in most parameters. Longitudinal assessments demonstrated strong reliability (ICCs >0.87) for key metrics, and SUS indicated good-to-excellent usability of the remote protocol.

Conclusion: The GAIT-HUB protocol enables reliable and feasible home-based gait monitoring using wearable sensors that patients can easily self-apply. This approach provides valuable insights into daily mobility patterns beyond clinical visits, supporting more precise and timely assessments of functional status between appointments and offering the potential for seamless integration into telemedicine routine care.

Introduction: Detecting positional nystagmus is essential for diagnosing benign paroxysmal positional vertigo (BPPV). Therefore, developing methods to streamline this diagnosis can improve timely patient management and help prevent unnecessary emergency department visits. We aimed to evaluate the accuracy of a smartphone eye-tracking application in quantifying eye movements during positional testing to detect positional nystagmus.

Methods: We recruited patients with positional dizziness suspected of having BPPV from the vestibular rehabilitation clinic and the consult service for dizzy patients (Tele-Dizzy) at Johns Hopkins Hospital. Using an in-house smartphone app (EyePhone), we recorded eye movements during the Dix-Hallpike and supine roll tests. Two expert clinicians reviewed the videos, and a third one adjudicated the disagreements. Eye position data obtained from the EyePhone app were analyzed with an embedded algorithm to identify positional nystagmus. Using the adjudicated expert review as the reference standard, we evaluated EyePhone's accuracy in detecting positional nystagmus by calculating the sensitivity, specificity, and predictive values.

Results: We recruited ten participants, 60% women, with an average age of 61.8 years. We reviewed 23 positional eye movement videos of participants while undergoing positional testing. The final adjudicated expert review identified positional nystagmus in 3 (13%) videos. The phone application traces indicated nystagmus in all 3 of these videos (sensitivity = 100% [95% CI = 44-100%]) and correctly ruled it out in 20 traces (specificity = 100% [95% CI = 84-100%]). The app demonstrated a positive predictive value of 100% (95% CI = 43-100%) and a negative predictive value of 100% (95% CI = 84-100%).

Conclusions: This small pilot study shows proof-of-concept that a smartphone eye-tracking app without special phone attachments can detect positional nystagmus.

Introduction: Hypertension is the leading risk factor for cardiovascular disorders. Early detection and initiation of treatment have been identified as the most effective ways to reduce the burden of hypertension. The most common method for detecting hypertension is blood pressure measurement, typically performed with cuff-based devices, where systolic pressure (SBP) and diastolic pressure (DBP) are measured through Korotkoff sounds. Although this method is accurate and non-invasive, it requires technical expertise and is often inaccessible in rural and remote areas. In this study, we investigated the feasibility of using overt speech (random speech corpora) through multiple short recordings for hypertension screening based on two hypertension guidelines: (1) SBP ≥135 mm Hg OR DBP ≥85 mm Hg, and (2) SBP ≥140 mm Hg OR DBP ≥90 mm Hg.

Methods: We incorporated speech recordings from 573 participants (197 women) with diverse ages and body mass index and extracted temporal, spectral, and nonlinear acoustic features through three different frameworks, all of which are based on classical and boosted machine learning models. The models were evaluated using a leave-one-subject-out cross-validation scheme.

Results: Our proposed pipeline achieved a balanced accuracy (BACC) of 61% for males and 70% for females under the relaxed criterion (SBP ≥135 OR DBP ≥85), and a BACC of 71% for males and 78% for females under the stricter European Society of Hypertension (ESH) guidelines (SBP ≥140 OR DBP ≥90).

Conclusion: These results demonstrate the potential of employing overt speech alongside acoustic analysis for hypertension screening.

Introduction: Preoperative physical functional assessments (i.e., assessments that measure capability to perform physical activity) are integral to estimate perioperative risk for older adults. However, these assessments are not routinely performed in-clinic prior to surgery. Walking cadence, or the number of steps walked in a specified amount of time (i.e., steps/min), measures activity intensity and may be able to identify high-risk patients prior to surgery. Smartphones can measure walking characteristics and guide patients through remote functional assessments. Here, we assess feasibility, acceptability, and accuracy of Walk Test, a smartphone application designed to measure walking cadence.

Methods: We performed a prospective cohort study of older adults prior to abdominal surgery and enrolled them remotely to perform at-home usual- and fast-paced walks with subsequent validation in-clinic. Each walk (usual- and fast-paced) was 2 min in duration. Feasibility was assessed if 80% of patients could perform all study procedures; acceptability was measured using the Post-Study Survey Usability Questionnaire (PSSUQ); accuracy of our approach was assessed with Lin's concordance coefficient (CCC). activPAL thigh worn accelerometer worn during the in-clinic walk served as a gold standard comparison. We used the CCC to compare the at-home and in-clinic walks as performed by Walk Test.

Results: We enrolled 41 participants (mean age 69 ± 5 years, 26 (63%) female); 88% (36/41) successfully completed entire study protocol including independent installation of the application, walk tests (at-home and in-clinic) and questionnaires. Median (interquartile range) overall score of PSSUQ was 1 (1, 1) indicating strong acceptability and usability. The Lin's CCC between the in-clinic activPAL and Walk Test for usual-paced walk was 0.97 (95% CI: 0.96, 0.99, p < 0.001) and for fast-paced walks 0.96 (95% CI: 0.93, 0.98, p < 0.001). The CCC between the at-home and in-clinic walks for usual-paced walks was 0.70 (95% CI: 0.53, 0.86) and for fast-paced walks was 0.46 (95% CI: 0.21, 0.72).

Conclusion: We successfully demonstrated the feasibility, acceptability and accuracy of Walk Test to measure walking cadence. Future work is needed to standardize walk test performance at-home to ensure consistency between in-clinic and at-home measures.

Introduction: Impaired walking performance significantly impacts the quality of life in individuals with Parkinson's disease (PD). This study aimed to examine the effects of medication "on" and "off" periods on walking performance, focusing on an alternative aspect of traditional gait analysis by assessing movement components or synergies (i.e., principal movements, PMs).

Methods: Principal component analysis was used to decompose kinematic marker data from 22 PD patients (64.1 ± 10.5 years) during self-selected speed overground walking into a set of PMs that cooperatively contribute to the locomotion task. Gait adaptation between medication periods was assessed using two PM-based variables: relative explained variance (rVAR) of the PM's position, reflecting movement structure, and root mean square (RMS) of the PM's acceleration, indicating movement acceleration magnitude and reflecting changes in force or speed.

Results: The on-medication condition increased the contribution (greater rVAR) of PM₂, representing the swing-phase movement component (p = 0.001), and enhanced movement acceleration magnitudes (greater RMS) in PM₄, characterizing the single-leg support phase coupled with trunk rotation (p = 0.026).

Conclusion: Although medication enhances propulsion by increasing the contribution of swing-phase movement components, thereby improving forward movement and walking efficiency, it may also lead to instability during the single-leg stance phase.

Introduction: Benign paroxysmal positional vertigo (BPPV) is a common cause of dizziness that is diagnosed by detecting nystagmus through positional maneuvers. Limited access to expert clinicians to correctly perform and interpret the eye movement findings of positional tests can hamper the diagnosis and delay the treatment. We aimed to assess the usability of a smartphone-based eye-tracking application (EyePhone) for self-recording eye movements during positional testing.

Methods: Healthy volunteers were enrolled and provided instructions to perform Dix-Hallpike and Supine Roll tests using the EyePhone application to record themselves. A study team member was instructed to observe the process without interfering. They recorded the time each section took and the accuracy of performing positional tests. Usability was assessed using the mHealth App Usability Questionnaire (MAUQ), and expert evaluation of recorded videos determined quality.

Results: All participants successfully performed the tests and recorded their eye movements. On average, after watching the instruction, it took participants 3 min 31 s to record the Dix-Hallpike test and 3 min 4 s to record the Supine Roll test. Nine participants completed Dix-Hallpike without major errors, and all completed the Supine Roll successfully. An expert review found that 95% of videos had clear eye visibility. Participants rated the app as easy to use and stated that they would use the app again.

Conclusion: We demonstrated the usability and feasibility of the EyePhone app for self-recording positional tests. This application offers the potential for remote BPPV diagnosis and improved patient access to care.