Digital Biomarkers最新文献

Introduction: Changes in speech have the potential to provide important information on the diagnosis and progression of various neurological diseases. Many researchers have relied on open-source speech features to develop algorithms for measuring speech changes in clinical populations as they are convenient and easy to use. However, the repeatability of open-source features in the context of neurological diseases has not been studied.

Methods: We used a longitudinal sample of healthy controls, individuals with amyotrophic lateral sclerosis, and individuals with suspected frontotemporal dementia, and we evaluated the repeatability of acoustic and language features separately on these 3 data sets.

Results: Repeatability was evaluated using intraclass correlation (ICC) and the within-subjects coefficient of variation (WSCV). In 3 sets of tasks, the median ICC were between 0.02 and 0.55, and the median WSCV were between 29 and 79%.

Conclusion: Our results demonstrate that the repeatability of speech features extracted using open-source tool kits is low. Researchers should exercise caution when developing digital health models with open-source speech features. We provide a detailed summary of feature-by-feature repeatability results (ICC, WSCV, SE of measurement, limits of agreement for WSCV, and minimal detectable change) in the online supplementary material so that researchers may incorporate repeatability information into the models they develop.

Analyzing human gait with inertial sensors provides valuable insights into a wide range of health impairments, including many musculoskeletal and neurological diseases. A representative and reliable assessment of gait requires continuous monitoring over long periods and ideally takes place in the subjects' habitual environment (real-world). An inconsistent sensor wearing position can affect gait characterization and influence clinical study results, thus clinical study protocols are typically highly proscriptive, instructing all participants to wear the sensor in a uniform manner. This restrictive approach improves data quality but reduces overall adherence. In this work, we analyze the impact of altering the sensor wearing position around the waist on sensor signal and step detection. We demonstrate that an asymmetrically worn sensor leads to additional odd-harmonic frequency components in the frequency spectrum. We propose a robust solution for step detection based on autocorrelation to overcome sensor position variation (sensitivity = 0.99, precision = 0.99). The proposed solution reduces the impact of inconsistent sensor positioning on gait characterization in clinical studies, thus providing more flexibility to protocol implementation and more freedom to participants to wear the sensor in the position most comfortable to them. This work is a first step towards truly position-agnostic gait assessment in clinical settings.

Introduction: A major challenge in the monitoring of rehabilitation is the lack of long-term individual baseline data which would enable accurate and objective assessment of functional recovery. Consumer-grade wearable devices enable the tracking of individual everyday functioning prior to illness or other medical events which necessitate the monitoring of recovery trajectories.

Methods: For 1,324 individuals who underwent surgery on a lower limb, we collected their Fitbit device data of steps, heart rate, and sleep from 26 weeks before to 26 weeks after the self-reported surgery date. We identified subgroups of individuals who self-reported surgeries for bone fracture repair (n = 355), tendon or ligament repair/reconstruction (n = 773), and knee or hip joint replacement (n = 196). We used linear mixed models to estimate the average effect of time relative to surgery on daily activity measurements while adjusting for gender, age, and the participant-specific activity baseline. We used a sub-cohort of 127 individuals with dense wearable data who underwent tendon/ligament surgery and employed XGBoost to predict the self-reported recovery time.

Results: The 1,324 study individuals were all US residents, predominantly female (84%), white or Caucasian (85%), and young to middle-aged (mean age 36.2 years). We showed that 12 weeks pre- and 26 weeks post-surgery trajectories of daily behavioral measurements (steps sum, heart rate, sleep efficiency score) can capture activity changes relative to an individual's baseline. We demonstrated that the trajectories differ across surgery types, recapitulate the documented effect of age on functional recovery, and highlight differences in relative activity change across self-reported recovery time groups. Finally, using a sub-cohort of 127 individuals, we showed that long-term recovery can be accurately predicted, on an individual level, only 1 month after surgery (AUROC 0.734, AUPRC 0.8). Furthermore, we showed that predictions are most accurate when long-term, individual baseline data are available.

Discussion: Leveraging long-term, passively collected wearable data promises to enable relative assessment of individual recovery and is a first step towards data-driven intervention for individuals.

Background: Data derived from wearable activity trackers may provide important clinical insights into disease progression and response to intervention, but only if clinicians can interpret it in a meaningful manner. Longitudinal activity data can be visually presented in multiple ways, but research has failed to explore how clinicians interact with and interpret these visualisations. In response, this study developed a variety of visualisations to understand whether alternative data presentation strategies can provide clinicians with meaningful insights into patient's physical activity patterns.

Objective: To explore clinicians' opinions on different visualisations of actigraphy data.

Methods: Four visualisations (stacked bar chart, clustered bar chart, linear heatmap and radial heatmap) were created using Matplotlib and Seaborn Python libraries. A focus group was conducted with 14 clinicians across 2 hospitals. Focus groups were audio-recorded, transcribed and analysed using inductive thematic analysis.

Results: Three major themes were identified: (1) the importance of context, (2) interpreting the visualisations and (3) applying visualisations to clinical practice. Although clinicians saw the potential value in the visualisations, they expressed a need for further contextual information to gain clinical benefits from them. Allied health professionals preferred more granular, temporal information compared to doctors. Specifically, physiotherapists favoured heatmaps, whereas the remaining members of the team favoured stacked bar charts. Overall, heatmaps were considered more difficult to interpret.

Conclusion: The current lack of contextual data provided by wearables hampers their use in clinical practice. Clinicians favour data presented in a familiar format and yet desire multi-faceted filtering. Future research should implement user-centred design processes to identify ways in which all clinical needs can be met, potentially using an interactive system that caters for multiple levels of granularity. Irrespective of how data is displayed, unless clinicians can apply it in a manner that best supports their role, the potential of this data cannot be fully realised.

Background: Fatigue is a broad, multifactorial concept encompassing feelings of reduced physical and mental energy levels. Fatigue strongly impacts patient health-related quality of life across a huge range of conditions, yet, to date, tools available to understand fatigue are severely limited.

Methods: After using a recurrent neural network-based algorithm to impute missing time series data form a multisensor wearable device, we compared supervised and unsupervised machine learning approaches to gain insights on the relationship between self-reported non-pathological fatigue and multimodal sensor data.

Results: A total of 27 healthy subjects and 405 recording days were analyzed. Recorded data included continuous multimodal wearable sensor time series on physical activity, vital signs, and other physiological parameters, and daily questionnaires on fatigue. The best results were obtained when using the causal convolutional neural network model for unsupervised representation learning of multivariate sensor data, and random forest as a classifier trained on subject-reported physical fatigue labels (weighted precision of 0.70 ± 0.03 and recall of 0.73 ± 0.03). When using manually engineered features on sensor data to train our random forest (weighted precision of 0.70 ± 0.05 and recall of 0.72 ± 0.01), both physical activity (energy expenditure, activity counts, and steps) and vital signs (heart rate, heart rate variability, and respiratory rate) were important parameters to measure. Furthermore, vital signs contributed the most as top features for predicting mental fatigue compared to physical ones. These results support the idea that fatigue is a highly multimodal concept. Analysis of clusters from sensor data highlighted a digital phenotype indicating the presence of fatigue (95% of observations) characterized by a high intensity of physical activity. Mental fatigue followed similar trends but was less predictable. Potential future directions could focus on anomaly detection assuming longer individual monitoring periods.

Conclusion: Taken together, these results are the first demonstration that multimodal digital data can be used to inform, quantify, and augment subjectively captured non-pathological fatigue measures.

Artificial intelligence offers the promise of transforming biomedical research and helping clinicians put the "care" back in healthcare. Digital medicine is on its way to becoming just plain medicine. But who will digitize how we define health and disease? And who will deploy this knowledge to improve the lives of patients that medicine - and digital medicine - exists to serve? Here we define the emerging field of digital medicine and identify the disciplines and skills needed for success. We examine the current and projected skills gaps. We also consider the impact of the culture clash that occurs at the intersection of healthcare and technology, and the lack of diversity in the workforce of both of these fields. We conclude by describing the requirements for the skills pivot needed to ensure that the digital transformation of healthcare is successful: (1) big tent thinking to recognize the critical importance of new technical skills alongside more traditional clinical disciplines, (2) the integration of clinical and technical skill sets within educational curricula, companies, and professional institutions, and (3) a commitment to diversity that goes beyond lip service.

Innovative tools are urgently needed to accelerate the evaluation and subsequent approval of novel treatments that may slow, halt, or reverse the relentless progression of Parkinson disease (PD). Therapies that intervene early in the disease continuum are a priority for the many candidates in the drug development pipeline. There is a paucity of sensitive and objective, yet clinically interpretable, measures that can capture meaningful aspects of the disease. This poses a major challenge for the development of new therapies and is compounded by the considerable heterogeneity in clinical manifestations across patients and the fluctuating nature of many signs and symptoms of PD. Digital health technologies (DHT), such as smartphone applications, wearable sensors, and digital diaries, have the potential to address many of these gaps by enabling the objective, remote, and frequent measurement of PD signs and symptoms in natural living environments. The current climate of the COVID-19 pandemic creates a heightened sense of urgency for effective implementation of such strategies. In order for these technologies to be adopted in drug development studies, a regulatory-aligned consensus on best practices in implementing appropriate technologies, including the collection, processing, and interpretation of digital sensor data, is required. A growing number of collaborative initiatives are being launched to identify effective ways to advance the use of DHT in PD clinical trials. The Critical Path for Parkinson's Consortium of the Critical Path Institute is highlighted as a case example where stakeholders collectively engaged regulatory agencies on the effective use of DHT in PD clinical trials. Global regulatory agencies, including the US Food and Drug Administration and the European Medicines Agency, are encouraging the efficiencies of data-driven engagements through multistakeholder consortia. To this end, we review how the advancement of DHT can be most effectively achieved by aligning knowledge, expertise, and data sharing in ways that maximize efficiencies.

As the role of technology expands in healthcare, so does the need to support its implementation and integration into the clinic. The concept of a new team member, the digital navigator, able to assume this role is introduced as a solution. With a digital navigator, any clinic today can take advantage of digital health and smartphone tools to augment and expand existing telehealth and face to face care. The role of a digital navigator is suitable as an entry level healthcare role, additional training for an experienced clinician, and well suited to peer specialists. To facilitate the training of digital navigators, we draw upon our experience in creating the role and across health education to introduce a 10-h curriculum designed to train digital navigators across 5 domains: (1) core smartphone skills, (2) basic technology troubleshooting, (3) app evaluation, (4) clinical terminology and data, and (5) engagement techniques. This paper outlines the curricular content, skills, and modules for this training and features a rich online supplementary Appendix with step by step instructions and resources.

Health care has had to adapt rapidly to COVID-19, and this in turn has highlighted a pressing need for tools to facilitate remote visits and monitoring. Digital health technology, including body-worn devices, offers a solution using digital outcomes to measure and monitor disease status and provide outcomes meaningful to both patients and health care professionals. Remote monitoring of physical mobility is a prime example, because mobility is among the most advanced modalities that can be assessed digitally and remotely. Loss of mobility is also an important feature of many health conditions, providing a read-out of health as well as a target for intervention. Real-world, continuous digital measures of mobility (digital mobility outcomes or DMOs) provide an opportunity for novel insights into health care conditions complementing existing mobility measures. Accepted and approved DMOs are not yet widely available. The need for large collaborative efforts to tackle the critical steps to adoption is widely recognised. Mobilise-D is an example. It is a multidisciplinary consortium of 34 institutions from academia and industry funded through the European Innovative Medicines Initiative 2 Joint Undertaking. Members of Mobilise-D are collaborating to address the critical steps for DMOs to be adopted in clinical trials and ultimately health care. To achieve this, the consortium has developed a roadmap to inform the development, validation and approval of DMOs in Parkinson's disease, multiple sclerosis, chronic obstructive pulmonary disease and recovery from proximal femoral fracture. Here we aim to describe the proposed approach and provide a high-level view of the ongoing and planned work of the Mobilise-D consortium. Ultimately, Mobilise-D aims to stimulate widespread adoption of DMOs through the provision of device agnostic software, standards and robust validation in order to bring digital outcomes from concept to use in clinical trials and health care.