Flexible Bayesian inference on partially observed epidemics.

Individual-based models of contagious processes are useful for predicting epidemic trajectories and informing intervention strategies. In such models, the incorporation of contact network information can capture the non-randomness and heterogeneity of realistic contact dynamics. In this article, we consider Bayesian inference on the spreading parameters of an SIR contagion on a known, static network, where information regarding individual disease status is known only from a series of tests (positive or negative disease status). When the contagion model is complex or information such as infection and removal times is missing, the posterior distribution can be difficult to sample from. Previous work has considered the use of Approximate Bayesian Computation (ABC), which allows for simulation-based Bayesian inference on complex models. However, ABC methods usually require the user to select reasonable summary statistics. Here, we consider an inference scheme based on the Mixture Density Network compressed ABC, which minimizes the expected posterior entropy in order to learn informative summary statistics. This allows us to conduct Bayesian inference on the parameters of a partially observed contagious process while also circumventing the need for manual summary statistic selection. This methodology can be extended to incorporate additional simulation complexities, including behavioural change after positive tests or false test results.

Upper limb movements as digital biomarkers in people with ALS.

BACKGROUND: Objective evaluation of people with amyotrophic lateral sclerosis (PALS) in free-living settings is challenging. The introduction of portable digital devices, such as wearables and smartphones, may improve quantifying disease progression and hasten therapeutic development. However, there is a need for tools to characterize upper limb movements in neurologic disease and disability. METHODS: Twenty PALS wore a wearable accelerometer, ActiGraph Insight Watch, on their wrist for six months. They also used Beiwe, a smartphone application that collected self-entry ALS Functional Rating Scale-Revised (ALSFRS-RSE) survey responses every 1-4 weeks. We developed several measures that quantify count and duration of upper limb movements: flexion, extension, supination, and pronation. New measures were compared against ALSFRS-RSE total score (Q1-12), and individual responses to specific questions related to handwriting (Q4), cutting food (Q5), dressing and performing hygiene (Q6), and turning in bed and adjusting bed clothes (Q7). Additional analysis considered adjusting for total activity counts (TAC). FINDINGS: At baseline, PALS with higher Q1-12 performed more upper limb movements, and these movements were faster compared to individuals with more advanced disease. Most upper limb movement metrics had statistically significant change over time, indicating declining function either by decreasing count metrics or by increasing duration metric. All count and duration metrics were significantly associated with Q1-12, flexion and extension counts were significantly associated with Q6 and Q7, supination and pronation counts were also associated with Q4. All duration metrics were associated with Q6 and Q7. All duration metrics retained their statistical significance after adjusting for TAC. INTERPRETATION: Wearable accelerometer data can be used to generate digital biomarkers on upper limb movements and facilitate patient monitoring in free-living environments. The presented method offers interpretable monitoring of patients' functioning and versatile tracking of disease progression in the limb of interest. FUNDING: Mitsubishi-Tanabe Pharma Holdings America, Inc.

The Pain Intervention & Digital Research Program: an operational report on combining digital research with outpatient chronic disease management.

Chronic pain affects up to 28% of U.S. adults, costing ∼$560 billion each year. Chronic pain is an instantiation of the perennial complexity of how to best assess and treat chronic diseases over time, especially in populations where age, medical comorbidities, and socioeconomic barriers may limit access to care. Chronic disease management poses a particular challenge for the healthcare system's transition from fee-for-service to value and risk-based reimbursement models. Remote, passive real-time data from smartphones could enable more timely interventions and simultaneously manage risk and promote better patient outcomes through predicting and preventing costly adverse outcomes; however, there is limited evidence whether remote monitoring is feasible, especially in the case of older patients with chronic pain. Here, we introduce the Pain Intervention and Digital Research (Pain-IDR) Program as a pilot initiative launched in 2022 that combines outpatient clinical care and digital health research. The Pain-IDR seeks to test whether functional status can be assessed passively, through a smartphone application, in older patients with chronic pain. We discuss two perspectives-a narrative approach that describes the clinical settings and rationale behind changes to the operational design, and a quantitative approach that measures patient recruitment, patient experience, and HERMES data characteristics. Since launch, we have had 77 participants with a mean age of 55.52, of which n = 38 have fully completed the 6 months of data collection necessitated to be considered in the study, with an active data collection rate of 51% and passive data rate of 78%. We further present preliminary operational strategies that we have adopted as we have learned to adapt the Pain-IDR to a productive clinical service. Overall, the Pain-IDR has successfully engaged older patients with chronic pain and presents useful insights for others seeking to implement digital phenotyping in other chronic disease settings.

Returning Individual Research Results from Digital Phenotyping in Psychiatry.

Psychiatry is rapidly adopting digital phenotyping and artificial intelligence/machine learning tools to study mental illness based on tracking participants' locations, online activity, phone and text message usage, heart rate, sleep, physical activity, and more. Existing ethical frameworks for return of individual research results (IRRs) are inadequate to guide researchers for when, if, and how to return this unprecedented number of potentially sensitive results about each participant's real-world behavior. To address this gap, we convened an interdisciplinary expert working group, supported by a National Institute of Mental Health grant. Building on established guidelines and the emerging norm of returning results in participant-centered research, we present a novel framework specific to the ethical, legal, and social implications of returning IRRs in digital phenotyping research. Our framework offers researchers, clinicians, and Institutional Review Boards (IRBs) urgently needed guidance, and the principles developed here in the context of psychiatry will be readily adaptable to other therapeutic areas.

Open-Source, Step-Counting Algorithm for Smartphone Data Collected in Clinical and Nonclinical Settings: Algorithm Development and Validation Study.

BACKGROUND: Step counts are increasingly used in public health and clinical research to assess well-being, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristics, and heterogeneous health states. OBJECTIVE: Our goal was to evaluate an open-source, step-counting method for smartphones under various measurement conditions against step counts estimated from data collected simultaneously from different body locations ("cross-body" validation), manually ascertained ground truth ("visually assessed" validation), and step counts from a commercial activity tracker (Fitbit Charge 2) in patients with advanced cancer ("commercial wearable" validation). METHODS: We used 8 independent data sets collected in controlled, semicontrolled, and free-living environments with different devices (primarily Android smartphones and wearable accelerometers) carried at typical body locations. A total of 5 data sets (n=103) were used for cross-body validation, 2 data sets (n=107) for visually assessed validation, and 1 data set (n=45) was used for commercial wearable validation. In each scenario, step counts were estimated using a previously published step-counting method for smartphones that uses raw subsecond-level accelerometer data. We calculated the mean bias and limits of agreement (LoA) between step count estimates and validation criteria using Bland-Altman analysis. RESULTS: In the cross-body validation data sets, participants performed 751.7 (SD 581.2) steps, and the mean bias was -7.2 (LoA -47.6, 33.3) steps, or -0.5%. In the visually assessed validation data sets, the ground truth step count was 367.4 (SD 359.4) steps, while the mean bias was -0.4 (LoA -75.2, 74.3) steps, or 0.1%. In the commercial wearable validation data set, Fitbit devices indicated mean step counts of 1931.2 (SD 2338.4), while the calculated bias was equal to -67.1 (LoA -603.8, 469.7) steps, or a difference of 3.4%. CONCLUSIONS: This study demonstrates that our open-source, step-counting method for smartphone data provides reliable step counts across sensor locations, measurement scenarios, and populations, including healthy adults and patients with cancer.

Cost-based feature selection for network model choice.

Selecting a small set of informative features from a large number of possibly noisy candidates is a challenging problem with many applications in machine learning and approximate Bayesian computation. In practice, the cost of computing informative features also needs to be considered. This is particularly important for networks because the computational costs of individual features can span several orders of magnitude. We addressed this issue for the network model selection problem using two approaches. First, we adapted nine feature selection methods to account for the cost of features. We show for two classes of network models that the cost can be reduced by two orders of magnitude without considerably affecting classification accuracy (proportion of correctly identified models). Second, we selected features using pilot simulations with smaller networks. This approach reduced the computational cost by a factor of 50 without affecting classification accuracy. To demonstrate the utility of our approach, we applied it to three different yeast protein interaction networks and identified the best-fitting duplication divergence model. Supplemental materials, including computer code to reproduce our results, are available online.

Flexible Bayesian Inference on Partially Observed Epidemics.

Individual-based models of contagious processes are useful for predicting epidemic trajectories and informing intervention strategies. In such models, the incorporation of contact network information can capture the non-randomness and heterogeneity of realistic contact dynamics. In this paper, we consider Bayesian inference on the spreading parameters of an SIR contagion on a known, static network, where information regarding individual disease status is known only from a series of tests (positive or negative disease status). When the contagion model is complex or information such as infection and removal times is missing, the posterior distribution can be difficult to sample from. Previous work has considered the use of Approximate Bayesian Computation (ABC), which allows for simulation-based Bayesian inference on complex models. However, ABC methods usually require the user to select reasonable summary statistics. Here, we consider an inference scheme based on the Mixture Density Network compressed ABC (MDN-ABC), which minimizes the expected posterior entropy in order to learn informative summary statistics. This allows us to conduct Bayesian inference on the parameters of a partially observed contagious process while also circumventing the need for manual summary statistic selection. This methodology can be extended to incorporate additional simulation complexities, including behavioral change after positive tests or false test results.

Framework for converting mechanistic network models to probabilistic models.

There are two prominent paradigms for the modelling of networks: in the first, referred to as the mechanistic approach, one specifies a set of domain-specific mechanistic rules that are used to grow or evolve the network over time; in the second, referred to as the probabilistic approach, one describes a model that specifies the likelihood of observing a given network. Mechanistic models (models developed based on the mechanistic approach) are appealing because they capture scientific processes that are believed to be responsible for network generation; however, they do not easily lend themselves to the use of inferential techniques when compared with probabilistic models. We introduce a general framework for converting a mechanistic network model (MNM) to a probabilistic network model (PNM). The proposed framework makes it possible to identify the essential network properties and their joint probability distribution for some MNMs; doing so makes it possible to address questions such as whether two different mechanistic models generate networks with identical distributions of properties, or whether a network property, such as clustering, is over- or under-represented in the networks generated by the model of interest compared with a reference model. The proposed framework is intended to bridge some of the gap that currently exists between the formulation and representation of mechanistic and PNMs. We also highlight limitations of PNMs that need to be addressed in order to close this gap.

Insurance-Based Disparities in Stroke Center Access in California: A Network Science Approach.

BACKGROUND: Our objectives were to determine whether there is an association between ischemic stroke patient insurance and likelihood of transfer overall and to a stroke center and whether hospital cluster modified the association between insurance and likelihood of stroke center transfer. METHODS: This retrospective network analysis of California data included every nonfederal hospital ischemic stroke admission from 2010 to 2017. Transfers from an emergency department to another hospital were categorized based on whether the patient was discharged from a stroke center (primary or comprehensive). We used logistic regression models to examine the relationship between insurance (private, Medicare, Medicaid, uninsured) and odds of (1) any transfer among patients initially presenting to nonstroke center hospital emergency departments and (2) transfer to a stroke center among transferred patients. We used a network clustering method to identify clusters of hospitals closely connected through transfers. Within each cluster, we quantified the difference between insurance groups with the highest and lowest proportion of transfers discharged from a stroke center. RESULTS: Of 332 995 total ischemic stroke encounters, 51% were female, 70% were ≥65 years, and 3.5% were transferred from the initial emergency department. Of 52 316 presenting to a nonstroke center, 3466 (7.1%) were transferred. Relative to privately insured patients, there were lower odds of transfer and of transfer to a stroke center among all groups (Medicare odds ratio, 0.24 [95% CI, 0.22-0.26] and 0.59 [95% CI, 0.50-0.71], Medicaid odds ratio, 0.26 [95% CI, 0.23-0.29] and odds ratio, 0.49 [95% CI, 0.38-0.62], uninsured odds ratio, 0.75 [95% CI, 0.63-0.89], and 0.72 [95% CI, 0.6-0.8], respectively). Among the 14 identified hospital clusters, insurance-based disparities in transfer varied and the lowest performing cluster (also the largest; n=2364 transfers) fully explained the insurance-based disparity in odds of stroke center transfer. CONCLUSIONS: Uninsured patients had less stroke center access through transfer than patients with insurance. This difference was largely explained by patterns in 1 particular hospital cluster.

Maximum likelihood estimation for reversible mechanistic network models.

Mechanistic network models specify the mechanisms by which networks grow and change, allowing researchers to investigate complex systems using both simulation and analytical techniques. Unfortunately, it is difficult to write likelihoods for instances of graphs generated with mechanistic models, and thus it is near impossible to estimate the parameters using maximum likelihood estimation. In this paper, we propose treating the node sequence in a growing network model as an additional parameter, or as a missing random variable, and maximizing over the resulting likelihood. We develop this framework in the context of a simple mechanistic network model, used to study gene duplication and divergence, and test a variety of algorithms for maximizing the likelihood in simulated graphs. We also run the best-performing algorithm on one human protein-protein interaction network and four nonhuman protein-protein interaction networks. Although we focus on a specific mechanistic network model, the proposed framework is more generally applicable to reversible models.

Leveraging Contact Network Information in Clustered Randomized Studies of Contagion Processes.

In a randomized study, leveraging covariates related to the outcome (e.g. disease status) may produce less variable estimates of the effect of exposure. For contagion processes operating on a contact network, transmission can only occur through ties that connect affected and unaffected individuals; the outcome of such a process is known to depend intimately on the structure of the network. In this paper, we investigate the use of contact network features as efficiency covariates in exposure effect estimation. Using augmented generalized estimating equations (GEE), we estimate how gains in efficiency depend on the network structure and spread of the contagious agent or behavior. We apply this approach to simulated randomized trials using a stochastic compartmental contagion model on a collection of model-based contact networks and compare the bias, power, and variance of the estimated exposure effects using an assortment of network covariate adjustment strategies. We also demonstrate the use of network-augmented GEEs on a clustered randomized trial evaluating the effects of wastewater monitoring on COVID-19 cases in residential buildings at the the University of California San Diego.

Machine Learning and the Digital Measurement of Psychological Health.

Since its inception, the discipline of psychology has utilized empirical epistemology and mathematical methodologies to infer psychological functioning from direct observation. As new challenges and technological opportunities emerge, scientists are once again challenged to define measurement paradigms for psychological health and illness that solve novel problems and capitalize on new technological opportunities. In this review, we discuss the theoretical foundations of and scientific advances in remote sensor technology and machine learning models as they are applied to quantify psychological functioning, draw clinical inferences, and chart new directions in treatment.

Menstrual cycle length variation by demographic characteristics from the Apple Women's Health Study.

Menstrual characteristics are important signs of women's health. Here we examine the variation of menstrual cycle length by age, ethnicity, and body weight using 165,668 cycles from 12,608 participants in the US using mobile menstrual tracking apps. After adjusting for all covariates, mean menstrual cycle length is shorter with older age across all age groups until age 50 and then became longer for those age 50 and older. Menstrual cycles are on average 1.6 (95%CI: 1.2, 2.0) days longer for Asian and 0.7 (95%CI: 0.4, 1.0) days longer for Hispanic participants compared to white non-Hispanic participants. Participants with BMI ≥ 40 kg/m2 have 1.5 (95%CI: 1.2, 1.8) days longer cycles compared to those with BMI between 18.5 and 25 kg/m2. Cycle variability is the lowest among participants aged 35-39 but are considerably higher by 46% (95%CI: 43%, 48%) and 45% (95%CI: 41%, 49%) among those aged under 20 and between 45-49. Cycle variability increase by 200% (95%CI: 191%, 210%) among those aged above 50 compared to those in the 35-39 age group. Compared to white participants, those who are Asian and Hispanic have larger cycle variability. Participants with obesity also have higher cycle variability. Here we confirm previous observations of changes in menstrual cycle pattern with age across reproductive life span and report new evidence on the differences of menstrual variation by ethnicity and obesity status. Future studies should explore the underlying determinants of the variation in menstrual characteristics.

Validation of an open-source smartphone step counting algorithm in clinical and non-clinical settings.

Background: Step counts are increasingly used in public health and clinical research to assess wellbeing, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristics, and heterogeneous health states. Objective: Our goal was to evaluate an open-source step-counting method for smartphones under various measurement conditions against step counts estimated from data collected simultaneously from different body locations ("internal" validation), manually ascertained ground truth ("manual" validation), and step counts from a commercial activity tracker (Fitbit Charge 2) in patients with advanced cancer ("wearable" validation). Methods: We used eight independent datasets collected in controlled, semi-controlled, and free-living environments with different devices (primarily Android smartphones and wearable accelerometers) carried at typical body locations. Five datasets (N=103) were used for internal validation, two datasets (N=107) for manual validation, and one dataset (N=45) used for wearable validation. In each scenario, step counts were estimated using a previously published step-counting method for smartphones that uses raw sub-second level accelerometer data. We calculated mean bias and limits of agreement (LoA) between step count estimates and validation criteria using Bland-Altman analysis. Results: In the internal validation datasets, participants performed 751.7±581.2 (mean±SD) steps, and the mean bias was -7.2 steps (LoA -47.6, 33.3) or -0.5%. In the manual validation datasets, the ground truth step count was 367.4±359.4 steps while the mean bias was -0.4 steps (LoA -75.2, 74.3) or 0.1 %. In the wearable validation dataset, Fitbit devices indicated mean step counts of 1931.2±2338.4, while the calculated bias was equal to -67.1 steps (LoA -603.8, 469.7) or a difference of 0.3 %. Conclusions: This study demonstrates that our open-source step counting method for smartphone data provides reliable step counts across sensor locations, measurement scenarios, and populations, including healthy adults and patients with cancer.

Daily Pain Prediction Using Smartphone Speech Recordings of Patients With Spine Disease.

BACKGROUND: Pain evaluation remains largely subjective in neurosurgical practice, but machine learning provides the potential for objective pain assessment tools. OBJECTIVE: To predict daily pain levels using speech recordings from personal smartphones of a cohort of patients with diagnosed neurological spine disease. METHODS: Patients with spine disease were enrolled through a general neurosurgical clinic with approval from the institutional ethics committee. At-home pain surveys and speech recordings were administered at regular intervals through the Beiwe smartphone application. Praat audio features were extracted from the speech recordings to be used as input to a K-nearest neighbors (KNN) machine learning model. The pain scores were transformed from a 0 to 10 scale to low and high pain for better discriminative capacity. RESULTS: A total of 60 patients were enrolled, and 384 observations were used to train and test the prediction model. Using the KNN prediction model, an accuracy of 71% with a positive predictive value of 0.71 was achieved in classifying pain intensity into high and low. The model showed 0.71 precision for high pain and 0.70 precision for low pain. Recall of high pain was 0.74, and recall of low pain was 0.67. The overall F1 score was 0.73. CONCLUSION: Our study uses a KNN to model the relationship between speech features and pain levels collected from personal smartphones of patients with spine disease. The proposed model is a stepping stone for the development of objective pain assessment in neurosurgery clinical practice.

Wearable device and smartphone data quantify ALS progression and may provide novel outcome measures.

Amyotrophic lateral sclerosis (ALS) therapeutic development has largely relied on staff-administered functional rating scales to determine treatment efficacy. We sought to determine if mobile applications (apps) and wearable devices can be used to quantify ALS disease progression through active (surveys) and passive (sensors) data collection. Forty ambulatory adults with ALS were followed for 6-months. The Beiwe app was used to administer the self-entry ALS functional rating scale-revised (ALSFRS-RSE) and the Rasch Overall ALS Disability Scale (ROADS) surveys every 2-4 weeks. Each participant used a wrist-worn activity monitor (ActiGraph Insight Watch) or an ankle-worn activity monitor (Modus StepWatch) continuously. Wearable device wear and app survey compliance were adequate. ALSFRS-R highly correlated with ALSFRS-RSE. Several wearable data daily physical activity measures demonstrated statistically significant change over time and associations with ALSFRS-RSE and ROADS. Active and passive digital data collection hold promise for novel ALS trial outcome measure development.

Randomized trial of inosine for urate elevation in amyotrophic lateral sclerosis.

INTRODUCTION/AIMS: Higher urate levels are associated with improved ALS survival in retrospective studies, however whether raising urate levels confers a survival advantage is unknown. In the Safety of Urate Elevation in Amyotrophic Lateral Sclerosis (SURE-ALS) trial, inosine raised serum urate and was safe and well-tolerated. The SURE-ALS2 trial was designed to assess longer term safety. Functional outcomes and a smartphone application were also explored. METHODS: Participants were randomized 2:1 to inosine (n = 14) or placebo (n = 9) for 20 weeks, titrated to serum urate of 7-8 mg/dL. Primary outcomes were safety and tolerability. Functional outcomes were measured with the Amyotrophic Lateral Sclerosis Functional Rating Scale Revised (ALSFRS-R). Mobility and ALSFRS-R were also assessed by a smartphone application. RESULTS: During inosine treatment, mean urate ranged 5.68-6.82 mg/dL. Treatment-emergent adverse event (TEAE) incidence was similar between groups (p > .10). Renal TEAEs occurred in three (21%) and hypertension in one (7%) of participants randomized to inosine. Inosine was tolerated in 71% of participants versus placebo 67%. Two participants (14%) in the inosine group experienced TEAEs deemed related to treatment (nephrolithiasis); one was a severe adverse event. Mean ALSFRS-R decline did not differ between groups (p = .69). Change in measured home time was similar between groups. Digital and in-clinic ALSFRS-R correlated well. DISCUSSION: Inosine met pre-specified criteria for safety and tolerability. A functional benefit was not demonstrated in this trial designed for safety and tolerability. Findings suggested potential utility for a smartphone application in ALS clinical and research settings.

A "one-size-fits-most" walking recognition method for smartphones, smartwatches, and wearable accelerometers.

The ubiquity of personal digital devices offers unprecedented opportunities to study human behavior. Current state-of-the-art methods quantify physical activity using "activity counts," a measure which overlooks specific types of physical activities. We propose a walking recognition method for sub-second tri-axial accelerometer data, in which activity classification is based on the inherent features of walking: intensity, periodicity, and duration. We validate our method against 20 publicly available, annotated datasets on walking activity data collected at various body locations (thigh, waist, chest, arm, wrist). We demonstrate that our method can estimate walking periods with high sensitivity and specificity: average sensitivity ranged between 0.92 and 0.97 across various body locations, and average specificity for common daily activities was typically above 0.95. We also assess the method's algorithmic fairness to demographic and anthropometric variables and measurement contexts (body location, environment). Finally, we release our method as open-source software in Python and MATLAB.