Transforming Digital Phenotyping Raw Data Into Actionable Biomarkers, Quality Metrics, and Data Visualizations Using Cortex Software Package: Tutorial.

As digital phenotyping, the capture of active and passive data from consumer devices such as smartphones, becomes more common, the need to properly process the data and derive replicable features from it has become paramount. Cortex is an open-source data processing pipeline for digital phenotyping data, optimized for use with the mindLAMP apps, which is used by nearly 100 research teams across the world. Cortex is designed to help teams (1) assess digital phenotyping data quality in real time, (2) derive replicable clinical features from the data, and (3) enable easy-to-share data visualizations. Cortex offers many options to work with digital phenotyping data, although some common approaches are likely of value to all teams using it. This paper highlights the reasoning, code, and example steps necessary to fully work with digital phenotyping data in a streamlined manner. Covering how to work with the data, assess its quality, derive features, and visualize findings, this paper is designed to offer the reader the knowledge and skills to apply toward analyzing any digital phenotyping data set. More specifically, the paper will teach the reader the ins and outs of the Cortex Python package. This includes background information on its interaction with the mindLAMP platform, some basic commands to learn what data can be pulled and how, and more advanced use of the package mixed with basic Python with the goal of creating a correlation matrix. After the tutorial, different use cases of Cortex are discussed, along with limitations. Toward highlighting clinical applications, this paper also provides 3 easy ways to implement examples of Cortex use in real-world settings. By understanding how to work with digital phenotyping data and providing ready-to-deploy code with Cortex, the paper aims to show how the new field of digital phenotyping can be both accessible to all and rigorous in methodology.

A randomized trial of behavioral interventions yielding sustained reductions in distracted driving.

Distracted driving is responsible for nearly 1 million crashes each year in the United States alone, and a major source of driver distraction is handheld phone use. We conducted a randomized, controlled trial to compare the effectiveness of interventions designed to create sustained reductions in handheld use while driving (NCT04587609). Participants were 1,653 consenting Progressive® Snapshot® usage-based auto insurance customers ages 18 to 77 who averaged at least 2 min/h of handheld use while driving in the month prior to study invitation. They were randomly assigned to one of five arms for a 10-wk intervention period. Arm 1 (control) got education about the risks of handheld phone use, as did the other arms. Arm 2 got a free phone mount to facilitate hands-free use. Arm 3 got the mount plus a commitment exercise and tips for hands-free use. Arm 4 got the mount, commitment, and tips plus weekly goal gamification and social competition. Arm 5 was the same as Arm 4, plus offered behaviorally designed financial incentives. Postintervention, participants were monitored until the end of their insurance rating period, 25 to 65 d more. Outcome differences were measured using fractional logistic regression. Arm 4 participants, who received gamification and competition, reduced their handheld use by 20.5% relative to control (P < 0.001); Arm 5 participants, who additionally received financial incentives, reduced their use by 27.6% (P < 0.001). Both groups sustained these reductions through the end of their insurance rating period.

Feedback and Financial Incentives for Reducing Cell Phone Use While Driving: A Randomized Clinical Trial.

Importance: Handheld phone use while driving is a major factor in vehicle crashes. Scalable interventions are needed to encourage drivers not to use their phones. Objective: To test whether interventions involving social comparison feedback and/or financial incentives can reduce drivers' handheld phone use. Design, Setting, and Participants: In a randomized clinical trial, interventions were administered nationwide in the US via a mobile application in the context of a usage-based insurance program (Snapshot Mobile application). Customers were eligible to be invited to participate in the study if enrolled in the usage-based insurance program for 30 to 70 days. The study was conducted from May 13 to June 30, 2019. Analysis was completed December 22, 2023. Interventions: Participants were randomly assigned to 1 of 6 trial arms for a 7-week intervention period: (1) control; (2) feedback, with weekly push notification about their handheld phone use compared with that of similar others; (3) standard incentive, with a maximum $50 award at the end of the intervention based on how their handheld phone use compared with similar others; (4) standard incentive plus feedback, combining interventions of arms 2 and 3; (5) reframed incentive plus feedback, with a maximum $7.15 award each week, framed as participant's to lose; and (6) doubled reframed incentive plus feedback, a maximum $14.29 weekly loss-framed award. Main Outcome and Measure: Proportion of drive time engaged in handheld phone use in seconds per hour (s/h) of driving. Analyses were conducted with the intention-to-treat approach. Results: Of 17 663 customers invited by email to participate, 2109 opted in and were randomized. A total of 2020 drivers finished the intervention period (68.0% female; median age, 30 [IQR, 25-39] years). Median baseline handheld phone use was 216 (IQR, 72-480) s/h. Relative to control, feedback and standard incentive participants did not reduce their handheld phone use. Standard incentive plus feedback participants reduced their use by -38 (95% CI, -69 to -8) s/h (P = .045); reframed incentive plus feedback participants reduced their use by -56 (95% CI, -87 to -26) s/h (P < .001); and doubled reframed incentive plus feedback participants reduced their use by -42 s/h (95% CI, -72 to -13 s/h; P = .007). The 5 active treatment arms did not differ significantly from each other. Conclusions and Relevance: In this randomized clinical trial, providing social comparison feedback plus incentives reduced handheld phone use while individuals were driving. Trial Registration: ClinicalTrials.gov Identifier: NCT03833219.

Associations of Sex and Sport Contact-Level with Recovery Timelines Among Collegiate Athletes with Sport-Related Concussion.

BACKGROUND: Growing interest has motivated recent studies to examine differences in recovery after sport-related concussion (SRC) by sex. However, heterogeneity in study design, participants, and recovery outcomes has led to mixed findings. Further work is needed to evaluate potential differences by sex and to investigate the role of related characteristics, such as sport contact-level, in recovery timelines. This study aimed to investigate whether concussion recovery trajectories differ by sex, considering a priori clinical and demographic covariates, and accounting for the sequence of recovery outcomes. Our secondary question was whether sport contact-level modifies the relationship between sex and time to outcomes. Using data from the Ivy League-Big Ten Epidemiology of Concussion Study, we included SRCs reported across five academic years; 2015-2020 (February 2020). We used Cox proportional hazards regressions to estimate associations between sex and time from injury to three outcomes: (1) symptom resolution, (2) return to academics, (3) return to full play, accounting for measured confounders. RESULTS: Among 1160 SRCs (male, n = 667; female, n = 493) with complete data, median age overall was 20 years (25th-75th percentiles:19-21), and most occurred among athletes playing high-contact sports (78.0%). Males were slightly more likely to complete symptom resolution over time compared to females (HR = 1.18, 95%CI = 1.05-1.33), but results were attenuated in fully adjusted models (HR 1.13, 95%CI = 0.99-1.29). Similarly, the HR of full academic return for males compared to females was 1.22 (95%CI = 1.07-1.38), but was attenuated in fully adjusted models (HR = 1.11, 95%CI = 0.97-1.28). The HR of full return to play for males compared to females was 1.14 (95%CI = 1.02-1.28), and was attenuated after adjustment (HR = 1.06, 95%CI = 0.93-1.20) as well. The interaction between sex and playing a high/low-contact sport was not statistically significant across models, though differences were apparent. CONCLUSIONS: Among a cohort of collegiate athletes with SRC, recovery timelines appeared similar between male and female athletes, adjusting for measured confounders. Differences by sex, considering sport contact-level, were evident and may be important clinically and in future studies. This study used robust methods, accounting for nesting in the sequence of RTP outcomes. Results inform concussion management protocols and planned qualitative work to further elucidate how collegiate athletes experience concussion recovery. KEY POINTS: Heterogeneity in study design, participants, and recovery outcomes has led to mixed findings in determining differences in recovery trajectories after concussion by sex. We found that having longer time to symptom resolution, and also the sequence of having academic return before symptoms resolve and longer time to academic return were confounders in the relationship between sex and RTP timelines. Time to sequential recovery outcomes appeared similar between male and female athletes, adjusting for observable confounders. Further differences by sex were evident when considering contact-level, and may be important to consider clinically and in future research. Results indicate that differences in concussion recovery trajectories by sex may be largely attributed to and driven by differences in sports with a men's or women's team only, such as football, and this should be explored further.

The Potential for Digital Phenotyping in Understanding Mindfulness App Engagement Patterns: A Pilot Study.

Background: Low app engagement is a central barrier to digital mental health efficacy. With mindfulness-based mental health apps growing in popularity, there is a need for new understanding of factors influencing engagement. This study utilized digital phenotyping to understand real-time patterns of engagement around app-based mindfulness. Different engagement metrics are presented that measure both the total number of app-based activities participants completed each week, as well as the proportion of days that participants engaged with the app each week. Method: Data were derived from two iterations of a four-week study exploring app engagement in college students (n = 169). This secondary analysis investigated the relationships between general and mindfulness-based app engagement with passive data metrics (sleep duration, home time, and screen duration) at a weekly level, as well as the relationship between demographics and engagement. Additional clinically focused analysis was performed on three case studies of participants with high mindfulness activity completion. Results: Demographic variables such as gender, race/ethnicity, and age lacked a significant association with mindfulness app-based engagement. Passive data variables such as sleep and screen duration were significant predictors for different metrics of general and mindfulness-based app engagement at a weekly level. There was a significant interaction effect for screen duration between the number of mindfulness activities completed and whether or not the participant received a mindfulness notification. K-means clusters analyses using passive data features to predict mindfulness activity completion had low performance. Conclusions: While there are no simple solutions to predicting engagement with mindfulness apps, utilizing digital phenotyping approaches at a population and personal level offers new potential. The signal from digital phenotyping warrants more investigation; even small increases in engagement with mindfulness apps may have a tremendous impact given their already high prevalence of engagement, availability, and potential to engage patients across demographics.

Using mobile health to expedite access to specialty care for youth presenting to the emergency department with concussion at highest risk of developing persisting symptoms: a protocol paper for a non-randomised hybrid implementation-effectiveness trial.

INTRODUCTION: Paediatric concussion is a common injury. Approximately 30% of youth with concussion will experience persisting postconcussion symptoms (PPCS) extending at least 1 month following injury. Recently, studies have shown the benefit of early, active, targeted therapeutic strategies. However, these are primarily prescribed from the specialty setting. Early access to concussion specialty care has been shown to improve recovery times for those at risk for persisting symptoms, but there are disparities in which youth are able to access such care. Mobile health (mHealth) technology has the potential to improve access to concussion specialists. This trial will evaluate the feasibility of a mHealth remote patient monitoring (RPM)-based care handoff model to facilitate access to specialty care, and the effectiveness of the handoff model in reducing the incidence of PPCS. METHODS AND ANALYSIS: This study is a non-randomised type I, hybrid implementation-effectiveness trial. Youth with concussion ages 13-18 will be enrolled from the emergency department of a large paediatric healthcare network. Patients deemed a moderate-to-high risk for PPCS using the predicting and preventing postconcussive problems in paediatrics (5P) stratification tool will be registered for a web-based chat platform that uses RPM to collect information on symptoms and activity. Those patients with escalating or plateauing symptoms will be contacted for a specialty visit using data collected from RPM to guide management. The primary effectiveness outcome will be the incidence of PPCS, defined as at least three concussion-related symptoms above baseline at 28 days following injury. Secondary effectiveness outcomes will include the number of days until return to preinjury symptom score, clearance for full activity and return to school without accommodations. The primary implementation outcome will be fidelity, defined as the per cent of patients meeting specialty care referral criteria who are ultimately seen in concussion specialty care. Secondary implementation outcomes will include patient-defined and clinician-defined appropriateness and acceptability. ETHICS AND DISSEMINATION: This study was approved by the Institutional Review Board of the Children's Hospital of Philadelphia (IRB 22-019755). Study findings will be published in peer-reviewed journals and disseminated at national and international meetings. TRIAL REGISTRATION NUMBER: NCT05741411.

Association of Remote Patient-Reported Outcomes and Step Counts With Hospitalization or Death Among Patients With Advanced Cancer Undergoing Chemotherapy: Secondary Analysis of the PROStep Randomized Trial.

BACKGROUND: Patients with advanced cancer undergoing chemotherapy experience significant symptoms and declines in functional status, which are associated with poor outcomes. Remote monitoring of patient-reported outcomes (PROs; symptoms) and step counts (functional status) may proactively identify patients at risk of hospitalization or death. OBJECTIVE: The aim of this study is to evaluate the association of (1) longitudinal PROs with step counts and (2) PROs and step counts with hospitalization or death. METHODS: The PROStep randomized trial enrolled 108 patients with advanced gastrointestinal or lung cancers undergoing cytotoxic chemotherapy at a large academic cancer center. Patients were randomized to weekly text-based monitoring of 8 PROs plus continuous step count monitoring via Fitbit (Google) versus usual care. This preplanned secondary analysis included 57 of 75 patients randomized to the intervention who had PRO and step count data. We analyzed the associations between PROs and mean daily step counts and the associations of PROs and step counts with the composite outcome of hospitalization or death using bootstrapped generalized linear models to account for longitudinal data. RESULTS: Among 57 patients, the mean age was 57 (SD 10.9) years, 24 (42%) were female, 43 (75%) had advanced gastrointestinal cancer, 14 (25%) had advanced lung cancer, and 25 (44%) were hospitalized or died during follow-up. A 1-point weekly increase (on a 32-point scale) in aggregate PRO score was associated with 247 fewer mean daily steps (95% CI -277 to -213; P<.001). PROs most strongly associated with step count decline were patient-reported activity (daily step change -892), nausea score (-677), and constipation score (524). A 1-point weekly increase in aggregate PRO score was associated with 20% greater odds of hospitalization or death (adjusted odds ratio [aOR] 1.2, 95% CI 1.1-1.4; P=.01). PROs most strongly associated with hospitalization or death were pain (aOR 3.2, 95% CI 1.6-6.5; P<.001), decreased activity (aOR 3.2, 95% CI 1.4-7.1; P=.01), dyspnea (aOR 2.6, 95% CI 1.2-5.5; P=.02), and sadness (aOR 2.1, 95% CI 1.1-4.3; P=.03). A decrease in 1000 steps was associated with 16% greater odds of hospitalization or death (aOR 1.2, 95% CI 1.0-1.3; P=.03). Compared with baseline, mean daily step count decreased 7% (n=274 steps), 9% (n=351 steps), and 16% (n=667 steps) in the 3, 2, and 1 weeks before hospitalization or death, respectively. CONCLUSIONS: In this secondary analysis of a randomized trial among patients with advanced cancer, higher symptom burden and decreased step count were independently associated with and predictably worsened close to hospitalization or death. Future interventions should leverage longitudinal PRO and step count data to target interventions toward patients at risk for poor outcomes. TRIAL REGISTRATION: ClinicalTrials.gov NCT04616768; https://clinicaltrials.gov/study/NCT04616768. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2021-054675.

Digital phenotyping data and anomaly detection methods to assess changes in mood and anxiety symptoms across a transdiagnostic clinical sample.

INTRODUCTION: Clinical assessment of mood and anxiety change often relies on clinical assessment or self-reported scales. Using smartphone digital phenotyping data and resulting markers of behavior (e.g., sleep) to augment clinical symptom scores offers a scalable and potentially more valid method to understand changes in patients' state. This paper explores the potential of using a combination of active and passive sensors in the context of smartphone-based digital phenotyping to assess mood and anxiety changes in two distinct cohorts of patients to assess the preliminary reliability and validity of this digital phenotyping method. METHODS: Participants from two different cohorts, each n = 76, one with diagnoses of depression/anxiety and the other schizophrenia, utilized mindLAMP to collect active data (e.g., surveys on mood/anxiety), along with passive data consisting of smartphone digital phenotyping data (geolocation, accelerometer, and screen state) for at least 1 month. Using anomaly detection algorithms, we assessed if statistical anomalies in the combination of active and passive data could predict changes in mood/anxiety scores as measured via smartphone surveys. RESULTS: The anomaly detection model was reliably able to predict symptom change of 4 points or greater for depression as measured by the PHQ-9 and anxiety as measured for the GAD-8 for both patient populations, with an area under the ROC curve of 0.65 and 0.80 for each respectively. For both PHQ-9 and GAD-7, these AUCs were maintained when predicting significant symptom change at least 7 days in advance. Active data alone predicted around 52% and 75% of the symptom variability for the depression/anxiety and schizophrenia populations respectively. CONCLUSION: These results indicate the feasibility of anomaly detection for predicting symptom change in transdiagnostic cohorts. These results across different patient groups, different countries, and different sites (India and the US) suggest anomaly detection of smartphone digital phenotyping data may offer a reliable and valid approach to predicting symptom change. Future work should emphasize prospective application of these statistical methods.

Optimizing the Combination of Common Clinical Concussion Batteries to Predict Persistent Postconcussion Symptoms in a Prospective Cohort of Concussed Youth.

BACKGROUND: Studies have evaluated individual factors associated with persistent postconcussion symptoms (PPCS) in youth concussion, but no study has combined individual elements of common concussion batteries with patient characteristics, comorbidities, and visio-vestibular deficits in assessing an optimal model to predict PPCS. PURPOSE: To determine the combination of elements from 4 commonly used clinical concussion batteries and known patient characteristics and comorbid risk factors that maximize the ability to predict PPCS. STUDY DESIGN: Cohort study; Level of evidence, 2. METHODS: We enrolled 198 concussed participants-87 developed PPCS and 111 did not-aged 8 to 19 years assessed within 14 days of injury from a suburban high school and the concussion program of a tertiary care academic medical center. We defined PPCS as a Post-Concussion Symptom Inventory (PCSI) score at 28 days from injury of ≥3 points compared with the preinjury PCSI score-scaled for younger children. Predictors included the individual elements of the visio-vestibular examination (VVE), Sport Concussion Assessment Tool, 5th Edition (SCAT-5), King-Devick test, and PCSI, in addition to age, sex, concussion history, and migraine headache history. The individual elements of these tests were grouped into interpretable factors using sparse principal component analysis. The 12 resultant factors were combined into a logistic regression and ranked by frequency of inclusion into the combined optimal model, whose predictive performance was compared with the VVE, initial PCSI, and the current existing predictive model (the Predicting and Prevention Postconcussive Problems in Pediatrics (5P) prediction rule) using the area under the receiver operating characteristic curve (AUC). RESULTS: A cluster of 2 factors (SCAT-5/PCSI symptoms and VVE near point of convergence/accommodation) emerged. A model fit with these factors had an AUC of 0.805 (95% CI, 0.661-0.929). This was a higher AUC point estimate, with overlapping 95% CIs, compared with the PCSI (AUC, 0.773 [95% CI, 0.617-0.912]), VVE (AUC, 0.736 [95% CI, 0.569-0.878]), and 5P Prediction Rule (AUC, 0.728 [95% CI, 0.554-0.870]). CONCLUSION: Among commonly used clinical assessments for youth concussion, a combination of symptom burden and the vision component of the VVE has the potential to augment predictive power for PPCS over either current risk models or individual batteries.