Continuous Activity Monitoring During Concurrent Chemoradiotherapy

Machine Learning-Based Prediction of Hospitalization During Chemoradiotherapy With Daily Step Counts

Importance

Toxic effects of concurrent chemoradiotherapy (CRT) can cause treatment interruptions and hospitalizations, reducing treatment efficacy and increasing health care costs. Physical activity monitoring may enable early identification of patients at high risk for hospitalization who may benefit from proactive intervention.

Objective

To develop and validate machine learning (ML) approaches based on daily step counts collected by wearable devices on prospective trials to predict hospitalizations during CRT.

Design, Setting, and Participants

This study included patients with a variety of cancers enrolled from June 2015 to August 2018 on 3 prospective, single-institution trials of activity monitoring using wearable devices during CRT. Patients were followed up during and 1 month following CRT. Training and validation cohorts were generated temporally, stratifying for cancer diagnosis (70:30). Random forest, neural network, and elastic net-regularized logistic regression (EN) were trained to predict short-term hospitalization risk based on a combination of clinical characteristics and the preceding 2 weeks of activity data. To predict outcomes of activity data, models based only on activity-monitoring features and only on clinical features were trained and evaluated. Data analysis was completed from January 2022 to March 2023.

Main Outcomes and Measures

Model performance was evaluated in terms of the receiver operating characteristic area under curve (ROC AUC) in the stratified temporal validation cohort.

Results

Step counts from 214 patients (median [range] age, 61 [53-68] years; 113 [52.8%] male) were included. EN based on step counts and clinical features had high predictive ability (ROC AUC, 0.83; 95% CI, 0.66-0.92), outperforming random forest (ROC AUC, 0.76; 95% CI, 0.56-0.87; P = .02) and neural network (ROC AUC, 0.80; 95% CI, 0.71-0.88; P = .36). In an ablation study, the EN model based on only step counts demonstrated greater predictive ability than the EN model with step counts and clinical features (ROC AUC, 0.85; 95% CI, 0.70-0.93; P = .09). Both models outperformed the EN model trained on only clinical features (ROC AUC, 0.53; 95% CI, 0.31-0.66; P < .001).

Conclusions and Relevance

This study developed and validated a ML model based on activity-monitoring data collected during prospective clinical trials. Patient-generated health data have the potential to advance predictive ability of ML approaches. The resulting model from this study will be evaluated in an upcoming multi-institutional, cooperative group randomized trial.

Feasibility and acceptability of C-PRIME: A health promotion intervention for family caregivers of patients with colorectal cancer

PURPOSE

This study aimed to test the feasibility and acceptability of a digital health promotion intervention for family caregivers of patients with advanced colorectal cancer and explore the intervention's preliminary efficacy for mitigating the impact of caregiving on health and well-being.

METHODS

We conducted a single-arm pilot feasibility trial of C-PRIME (Caregiver Protocol for Remotely Improving, Monitoring, and Extending Quality of Life), an 8-week digital health-promotion behavioral intervention involving monitoring and visualizing health-promoting behaviors (e.g., objective sleep and physical activity data) and health coaching (NCT05379933). A priori benchmarks were established for feasibility (≥ 50% recruitment and objective data collection; ≥ 75% session engagement, measure completion, and retention) and patient satisfaction (> 3 on a 1-5 scale). Preliminary efficacy was explored with pre- to post-intervention changes in quality of life (QOL), sleep quality, social engagement, and self-efficacy.

RESULTS

Participants (N = 13) were M = 52 years old (SD = 14). Rates of recruitment (72%), session attendance (87%), assessment completion (87%), objective data collection (80%), and retention (100%) all indicated feasibility. All participants rated the intervention as acceptable (M = 4.7; SD = 0.8). Most participants showed improvement or maintenance of QOL (15% and 62%), sleep quality (23% and 62%), social engagement (23% and 69%), and general self-efficacy (23% and 62%).

CONCLUSION

The C-PRIME digital health promotion intervention demonstrated feasibility and acceptability among family caregivers of patients with advanced colorectal cancer. A fully powered randomized controlled trial is needed to test C-PRIME efficacy, mechanisms, and implementation outcomes, barriers, and facilitators in a divserse sample of family caregivers.

TRIAL REGISTRATION

The Caregiver Protocol for Remotely Improving, Monitoring, and Extending Quality of Life (C-PRIME) study was registered on clinicaltrials.gov, NCT05379933, in May 2022.

A proposed multi-domain, digital model for capturing functional status and health-related quality of life in oncology

Whereas traditional oncology clinical trial endpoints remain key for assessing novel treatments, capturing patients' functional status is increasingly recognized as an important aspect for supporting clinical decisions and assessing outcomes in clinical trials. Existing functional status assessments suffer from various limitations, some of which may be addressed by adopting digital health technologies (DHTs) as a means of collecting both objective and self-reported outcomes. In this mini-review, we propose a device-agnostic multi-domain model for oncology capturing functional status, which includes physical activity data, vital signs, sleep variables, and measures related to health-related quality of life enabled by connected digital tools. By using DHTs for all aspects of data collection, our proposed model allows for high-resolution measurement of objective data as patients navigate their daily lives outside of the hospital setting. This is complemented by electronic questionnaires administered at intervals appropriate for each instrument. Preliminary testing and practical considerations to address before adoption are also discussed. Finally, we highlight multi-institutional pre-competitive collaborations as a means of successfully transitioning the proposed digitally enabled data collection model from feasibility studies to interventional trials and care management.

Data-Driven Personalized Care in Lung Cancer: Scoping Review and Clinical Recommendations on Performance Status and Activity Level of Patients With Lung Cancer Using Wearable Devices

PURPOSE

Performance status (PS) is a crucial assessment for research and clinical practice in lung cancer (LC), including its usage for the assessment of the suitability and toxicity of treatment or eligibility for clinical trials of patients with LC. These PS assessments are subjective and lead to substantial discrepancies between observers. To improve the objectivity of PS assessments, Electronic Activity Monitoring devices (EAMs) are increasingly used in oncology, but how these devices are used for PS assessments in LC is an issue that remains unclear. The goal of this study is to address the challenges and opportunities of the use of digital tools to support PS assessments in patients with LC.

METHODS

The literature review followed PRISMA-ScR methodology. Searches were performed in the ScienceDirect, PsycInfo, ACM, IEEE Xplore, and PubMed databases. Furthermore, a panel discussion was performed to address the clinical use cases.

RESULTS

Thirty-two publications were found. Most of the studies used wrist accelerometry-based wearables (59%) and monitored sleep activity (SA; 28%) or physical activity (PA; 72%). Critical findings include positive usefulness of the use of wearables to categorize moderate-to-vigorous/light PA, which was associated with better sleep and health. In addition, steps and time awake immobile were found to be associated with risk of hospitalization and survival. Use cases identified included the health assessment of patients and clinical research.

CONCLUSION

There are positive experiences in the use of EAM to complement PS assessment in LC. However, there is a need for adapting thresholds to the particularities of patients with LC, for example, differentiating moderate-to-vigorous and light. Moreover, developing methodologies combining PS assessments and the use of EAM adapted to clinical and research practice is needed.

Daily physical activity monitoring in older adults with metastatic prostate cancer on active treatment: Feasibility and associations with toxicity

INTRODUCTION

Physical activity may be associated with cancer treatment toxicity, but generalizability to geriatric oncology is unclear. As many older adults have low levels of physical activity and technology use, this area needs further exploration. We evaluated the feasibility of daily step count monitoring and the association between step counts and treatment-emergent symptoms.

MATERIALS AND METHODS

Adults aged 65+ starting treatment (chemotherapy, enzalutamide/abiraterone, or radium-223) for metastatic prostate cancer were enrolled in a prospective cohort study. Participants reported step counts (measured via smartphone) and symptoms (Edmonton Symptom Assessment Scale) daily for one treatment cycle (i.e., 3-4 weeks). Embedded semi-structured interviews were performed upon completion of the study. The feasibility of daily monitoring was evaluated with descriptive statistics and thematic analysis. The predictive validity of a decline in daily steps (compared to pre-treatment baseline) for the emergence of symptoms was examined using sensitivity and positive predictive value (PPV). Associations between a 15% decline in steps and the emergence of moderate (4-6/10) to severe (7-10/10) symptoms and pain in the next 24 h were assessed using logistic regression.

RESULTS

Of 90 participants, 47 engaged in step count monitoring (median age = 75, range = 65-88; 52.2% participation rate). Daily physical activity monitoring was found to be feasible (94% retention rate; 90.5% median response rate) with multiple patient-reported benefits including increased self-awareness and motivation to engage in physical activity. During the first treatment cycle, instances of a 15% decline in steps were common (n = 37, 78.7%), as was the emergence of moderate to severe symptoms overall (n = 40, 85.1%) and pain (n = 26, 55.3%). The predictive validity of a 15% decline in steps on the emergence of moderate to severe symptoms was good (sensitivity = 81.8%, 95% confidence interval [CI] = 68.7-95.0; PPV = 73.0%, 95% CI = 58.7-87.3), although the PPV for pain was poor (sensitivity = 77.8%, 95% CI = 58.6-97.0; PPV = 37.8%, 95% CI = 22.2-53.5). In the regression models, changes in daily physical activity were not associated with symptoms or pain.

DISCUSSION

Changes in physical activity had modest ability to predict moderate to severe symptoms overall. Although participation was suboptimal, daily activity monitoring in older adults with cancer appears feasible and may have other uses such as improving physical activity levels. Further studies are warranted.

The Impact of a Wearable Activity Tracker and Structured Feedback Program on Physical Activity in Hemodialysis Patients: The Step4Life Pilot Randomized Controlled Trial

RATIONALE & OBJECTIVE

People with end-stage kidney disease (ESKD) have very low physical activity, and the degree of inactivity is strongly associated with morbidity and mortality. We assessed the feasibility and effectiveness of a 12-week intervention coupling a wearable activity tracker (FitBit) and structured feedback coaching versus wearable activity tracker alone on changes in physical activity in hemodialysis patients.

STUDY DESIGN

Randomized controlled trial.

SETTING & PARTICIPANTS

55 participants with ESKD receiving hemodialysis who were able to walk with or without assistive devices recruited from a single academic hemodialysis unit between January 2019 and April 2020.

INTERVENTIONS

All participants wore a Fitbit Charge 2 tracker for a minimum of 12 weeks. Participants were randomly assigned 1:1 to a wearable activity tracker plus a structured feedback intervention versus the wearable activity tracker alone. The structured feedback group was counseled weekly on steps achieved after randomization.

OUTCOME

The outcome was step count, and the main parameter of interest was the absolute change in daily step count, averaged per week, from baseline to completion of 12 weeks intervention. In the intention-to-treat analysis, mixed-effect linear regression analysis was used to evaluate change in daily step count from baseline to 12-weeks in both arms.

RESULTS

Out of 55 participants, 46 participants completed the 12-week intervention (23 per arm). The mean age was 62 (± 14 SD) years; 44% were Black, and 36% were Hispanic. At baseline, step count (structured feedback intervention: 3,704 [1,594] vs wearable activity tracker alone: 3,808 [1,890]) and other participant characteristics were balanced between the arms. We observed a larger change in daily step count in the structured feedback arm at 12 weeks relative to use of the wearable activity tracker alone arm (Δ 920 [±580 SD] versus Δ 281 [±186 SD] steps; between-group difference Δ 639 [±538 SD] steps; P<0.05).

LIMITATIONS

Single-center study and small sample size.

CONCLUSION

This pilot randomized controlled trial demonstrated that structured feedback coupled with a wearable activity tracker led to a greater daily step count that was sustained over 12 weeks relative to a wearable activity tracker alone. Future studies are required to determine longer-term sustainability of the intervention and potential health benefits in hemodialysis patients.

FUNDING

Grants from industry (Satellite Healthcare) and government (National Institute for Diabetes and Digestive and Kidney Diseases (NIDDK).

TRIAL REGISTRATION

Registered at ClinicalTrials.gov with study number NCT05241171.

Triaxial accelerometer-measured physical activity and functional behaviours among people with High Grade Glioma: The BrainWear Study

BACKGROUND

High-grade gliomas (HGG) account for 60-75% of all adult gliomas. The complexity of treatment, recovery and survivorship creates a need for novel monitoring approaches. Accurate assessment of physical function plays a vital role in clinical evaluation. Digital wearable tools could help us address unmet needs by offering unique advantages such as scale, cost and continuous real-world objective data. We present data from 42 patients enrolled into the BrainWear study.

METHODS

An AX3 accelerometer was worn by patients from diagnosis or at recurrence. Age-, sex-matched UK Biobank control groups were chosen for comparison.

RESULTS

80% of data were categorised as high-quality demonstrating acceptability. Remote, passive monitoring identifies moderate activity reduces both during a course of radiotherapy (69 to 16 minutes/day) and at the time of progressive disease assessed by MRI (72 to 52 minutes/day). Mean acceleration (mg) and time spent walking daily (h/day) correlated positively with the global health quality of life and physical functioning scores and inversely with the fatigue score. Healthy controls walked on average 2.91h/day compared to 1.32h/day for the HGG group on weekdays and 0.91h/day on the weekend. The HGG cohort slept for longer on weekends (11.6h/day) than weekdays (11.2h/day) compared to healthy controls (8.9h/day).

CONCLUSION

Wrist-worn accelerometers are acceptable and longitudinal studies feasible. HGG patients receiving a course of radiotherapy reduce their moderate activity by 4-fold and are at least half as active as healthy controls at baseline. Remote monitoring can provide a more informed and objective understanding of patient activity levels to help optimise health related quality of life (HRQoL) among a patient cohort with an extremely limited lifespan.

Using remotely monitored patient activity patterns after hospital discharge to predict 30 day hospital readmission: a randomized trial

Hospital readmission prediction models often perform poorly, but most only use information collected until the time of hospital discharge. In this clinical trial, we randomly assigned 500 patients discharged from hospital to home to use either a smartphone or wearable device to collect and transmit remote patient monitoring (RPM) data on activity patterns after hospital discharge. Analyses were conducted at the patient-day level using discrete-time survival analysis. Each arm was split into training and testing folds. The training set used fivefold cross-validation and then final model results are from predictions on the test set. A standard model comprised data collected up to the time of discharge including demographics, comorbidities, hospital length of stay, and vitals prior to discharge. An enhanced model consisted of the standard model plus RPM data. Traditional parametric regression models (logit and lasso) were compared to nonparametric machine learning approaches (random forest, gradient boosting, and ensemble). The main outcome was hospital readmission or death within 30 days of discharge. Prediction of 30-day hospital readmission significantly improved when including remotely-monitored patient data on activity patterns after hospital discharge and using nonparametric machine learning approaches. Wearables slightly outperformed smartphones but both had good prediction of 30-day hospital-readmission.

Wearable-Triggered Ecological Momentary Assessments Are Feasible in People With Advanced Cancer and Their Family Caregivers: Feasibility Study from an Outpatient Palliative Care Clinic at a Cancer Center

Background: Emerging digital health approaches could play a role in better personalized palliative care. Aim: We conducted a feasibility study testing wearable sensor (WS)-triggered ecological momentary assessments (EMAs) and electronic patient-reported outcomes in community palliative care with patient-caregiver dyads. Design: All wore consumer-grade WS for five weeks. Sensor-detected "stress" (heart rate variability algorithm) that passed individualized thresholds triggered a short smartphone survey. Daily sleep surveys, weekly symptom surveys (Integrated Palliative care Outcome Scale), and a poststudy experience survey were conducted. Setting/Participants: Fifteen dyads (n = 30) were recruited from an outpatient palliative care clinic for people with cancer. Results: Daytime sensor wear-time had 73% adherence. Participants perceived value in this support. Quantity and severity of "stress" events were higher in patients. Sleep disturbance was similar but for different reasons: patients (physical symptoms) and caregivers (worrying about the patient). Conclusions: EMAs are feasible and valued in community palliative care.

Remote Activity Monitoring and Electronic Patient-Reported Outcomes Collection During Radiotherapy for Head and Neck Cancer: A Pilot Study

PURPOSE

Modern wearable devices provide objective and continuous activity data that could be leveraged to enhance cancer care. We prospectively studied the feasibility of monitoring physical activity using a commercial wearable device and collecting electronic patient-reported outcomes (ePROs) during radiotherapy (RT) for head and neck cancer (HNC).

METHODS

Patients planned for a course of external beam RT with curative intent for HNC were instructed to use a commercial fitness tracker throughout the RT course. During weekly clinic visits, physician-scored adverse events were recorded during using Common Terminology Criteria for Adverse Events version 4.0, and patients completed ePRO surveys using a clinic tablet or computer. Feasibility of activity monitoring was defined as collection of step data for at least 80% of the RT course for at least 80% of patients. Exploratory analyses described associations between step counts, ePROs, and clinical events.

RESULTS

Twenty-nine patients with HNC were enrolled and had analyzable data. Overall, step data were recorded on 70% of the days during patients' RT courses, and there were only 11 patients (38%) for whom step data were collected on at least 80% of days during RT. Mixed effects linear regression models demonstrated declines in daily step counts and worsening of most PROs during RT. Cox proportional hazards models revealed a potential association between high daily step counts and both reduced risk of feeding tube placement (hazard ratio [HR], 0.87 per 1,000 steps, P < .001) and reduced risk of hospitalization (HR, 0.60 per 1,000 steps, P < .001).

CONCLUSION

We did not achieve our feasibility end point, suggesting that rigorous workflows are required to achieve continuous activity monitoring during RT. Although limited by a modest sample size, our findings are consistent with previous reports indicating that wearable device data can help identify patients who are at risk for unplanned hospitalization.

The association between wearable device metrics and clinical outcomes in oncology: a systematic review with evidence synthesis and meta-analysis

BACKGROUND

The emerging study of wearable devices (WDs) in patients with cancer provides opportunities to harness real-time patient data for predicting clinical outcomes. We conducted a systematic review with best evidence synthesis to examine the association between WD metrics and clinical outcomes in patients with cancer.

METHODS

MEDLINE and Embase were searched from inception until June 2022. Risk of bias assessment and best evidence synthesis were performed and, If possible, meta-analysis was conducted.

RESULTS

A total of 34 studies was included. We found moderate-to-strong evidence for associations between circadian rest-activity metrics and OS. Disrupted I<O was associated with increased hazard for death (HR 2.08; 95 %CI: 1.50-2.88). For most associations there was insufficient evidence due to lack of studies (n = 32) or inconsistent results (n = 14).

CONCLUSION

Meta-analysis was greatly hampered due to heterogeneity and different methodology used between studies. Studies primarily designed to investigate the association between WD metrics and clinical outcomes are warranted.

Assessing Physical and Cognitive Function in Individuals With Head and Neck Cancer: A Feasibility Study

BACKGROUND

Head and neck cancer (HNC) and associated treatments have significant long-term and late adverse effects that can impair function. Therefore, there is a need for reliable common metrics to assess function in HNC that limit participant burden and are cost-effective and easy to use in clinical settings.

OBJECTIVE

The aim of this study was to assess the feasibility of using the Fitbit Zip, NIH Toolbox, and REDCap electronic data collection tool to measure function and symptoms in individuals with HNC and to explore preliminary findings.

METHODS

A prospective descriptive design with a total of 16 participants was used to assess function and symptoms pretreatment to 3 months post treatment initiation.

RESULTS

The enrollment rate was 49%, the retention rate was 81%, and the Fitbit Zip adherence rate was 86%. Exploratory analyses suggested a possible decline in physical activity and worsening symptom burden alongside improved attention and cognitive flexibility abilities ( P ≤ .05). There were no differences in strength, functional mobility, information processing, or perceived attentional function.

CONCLUSION

The results of this study suggest that use of the Fitbit Zip, NIH Toolbox, and REDCap data collection tool in HNC is feasible. Exploratory analyses suggest that the Fitbit Zip may be a sensitive measure of physical activity in HNC.

IMPLICATIONS FOR PRACTICE

This study provides preliminary evidence for metrics that could be used in the clinical settings to assess function and symptom distress in HNC. Integration of these measures, upon further validation, could help providers better identify patients in need of intervention.

Predictors of Financial Toxicity in Patients Receiving Concurrent Radiation Therapy and Chemotherapy

Purpose

Financial toxicity (FT) is a significant concern for patients with cancer. We reviewed prospectively collected data to explore associations with FT among patients undergoing concurrent, definitive chemoradiation therapy (CRT) within a diverse, urban, academic radiation oncology department.

Methods and Materials

Patients received CRT in 1 of 3 prospective trials. FT was evaluated before CRT (baseline) and then weekly using the European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire Core-30 questionnaire. Patients were classified as experiencing FT if they answered ≥2 on a Likert scale question (1-4 points) asking if they experienced FT. Rate of change of FT was calculated using linear regression; worsening FT was defined as increase ≥1 point per month. χ², t tests, and logistic regression were used to assess predictors of FT.

Results

Among 233 patients, patients attended an average of 9 outpatient and 4 radiology appointments over the 47 days between diagnosis and starting CRT. At baseline, 52% of patients reported experiencing FT. Advanced T stage (odds ratio, 2.47; P = .002) was associated with baseline FT in multivariate analysis. The mean rate of FT change was 0.23 Likert scale points per month. In total, 26% of patients demonstrated worsening FT during CRT. FT at baseline was not associated with worsening FT (P = .98). Hospitalization during treatment was associated with worsening FT (odds ratio, 2.30; P = .019) in multivariate analysis.

Conclusions

Most patients reported FT before CRT. These results suggest that FT should be assessed (and, potentially, addressed) before starting definitive treatment because it develops early in a patient's cancer journey. Reducing hospitalizations may mitigate worsening FT. Further research is warranted to design interventions to reduce FT and avoid hospitalizations.

Continuous Long-Term Physical Activity Monitoring in Hemodialysis Patients

Background

Physical inactivity is common in patients receiving hemodialysis, but activity patterns throughout the day and in relation to dialysis are largely unknown. This knowledge gap can be addressed by long-term continuous activity monitoring, but this has not been attempted and may not be acceptable to patients receiving dialysis.

Methods

Ambulatory patients with end-stage kidney disease receiving thrice-weekly hemodialysis wore commercially available wrist-worn activity monitors for 6 months. Step counts were collected every 15 minutes and were linked to dialysis treatments. Physical function was assessed using the Short Physical Performance Battery (SPPB). Fast time to recovery from dialysis was defined as ≤2 hours. Mixed effects models were created to estimate step counts over time.

Results

Of 52 patients enrolled, 48 were included in the final cohort. The mean age was 60 years, and 75% were Black or Hispanic. Comorbidity burden was high, 38% were transported to and from dialysis by paratransit, and 79% had SPPB <10. Median accelerometer use (199 days) and adherence (95%) were high. Forty-two patients (of 43 responders) reported wearing the accelerometer every day, and few barriers to adherence were noted. Step counts were lower on dialysis days (3991 [95% CI, 3187 to 4796] versus 4561 [95% CI, 3757 to 5365]), but step-count intensity was significantly higher during the hour immediately after dialysis than during the corresponding time on nondialysis days (188 steps per hour increase [95% CI, 171 to 205]); these levels were the highest noted at any time. Postdialysis increases were more pronounced among patients with fast recovery time (225 [95% CI, 203 to 248] versus 134 [95% CI, 107 to 161] steps per hour) or those with SPPB ≥7. Estimates were unchanged after adjustment for demographics, diabetes status, and ultrafiltration rate.

Conclusions

Long-term continuous monitoring of physical activity is feasible in patients receiving hemodialysis. Highly granular data collection and analysis yielded new insights into patterns of activity after dialysis treatments.

Considerations for Conducting Bring Your Own “Device” (BYOD) Clinical Studies

Background

Digital health technologies are attracting attention as novel tools for data collection in clinical research. They present alternative methods compared to in-clinic data collection, which often yields snapshots of the participants' physiology, behavior, and function that may be prone to biases and artifacts, e.g., white coat hypertension, and not representative of the data in free-living conditions. Modern digital health technologies equipped with multi-modal sensors combine different data streams to derive comprehensive endpoints that are important to study participants and are clinically meaningful. Used for data collection in clinical trials, they can be deployed as provisioned products where technology is given at study start or in a bring your own “device” (BYOD) manner where participants use their technologies to generate study data.

Summary

The BYOD option has the potential to be more user-friendly, allowing participants to use technologies that they are familiar with, ensuring better participant compliance, and potentially reducing the bias that comes with introducing new technologies. However, this approach presents different technical, operational, regulatory, and ethical challenges to study teams. For example, BYOD data can be more heterogeneous, and recruiting historically underrepresented populations with limited access to technology and the internet can be challenging. Despite the rapid increase in digital health technologies for clinical and healthcare research, BYOD use in clinical trials is limited, and regulatory guidance is still evolving.

Key Messages

We offer considerations for academic researchers, drug developers, and patient advocacy organizations on the design and deployment of BYOD models in clinical research. These considerations address: (1) early identification and engagement with internal and external stakeholders; (2) study design including informed consent and recruitment strategies; (3) outcome, endpoint, and technology selection; (4) data management including compliance and data monitoring; (5) statistical considerations to meet regulatory requirements. We believe that this article acts as a primer, providing insights into study design and operational requirements to ensure the successful implementation of BYOD clinical studies.

Acceptance of physical activity monitoring in cancer patients during radiotherapy, the GIROfit phase 2 pilot trial

•

Activity trackers were well accepted and regularly worn by cancer patients during treatment.

•

In some patients a decrease in step counts correlated with the onset of side effects or quality of life impairments.

•

Activity trackers may be a useful tool to remotely identify patients who are in need of supportive care.

Background

In radiotherapy the timely identification of patients needing intervention and supportive care due to side effects is an important task especially in the outpatient setting. Activity trackers as an increasingly used lifestyle device may enable physicians to monitor patient’s physical activity (PA) and to intervene early during the course of radiotherapy.

Objective

The primary aim of this trial was to assess patient acceptance of PA monitoring in an outpatient setting and to correlate changes in PA with toxicity and changes in quality of life.

Methods

Patients undergoing radio(chemo-)therapy with a curative intent were eligible to participate in this prospective pilot phase II trial. Patients were instructed to wear a commercially available activity tracker during the course of radiotherapy and four weeks afterwards. Quality of life (QoL) and fatigue was scored using the Functional assessment of Chronic Illness Therapy questionnaire. A linear regression was performed to determine baseline activity and changes in step counts during radiotherapy.

Results

We included 23 patients in this trial. Two withdrew consent before the start of treatment, two patients were excluded after prophylactic feeding tube placement and prolonged recovery. Compliance in the remaining 19 patients was high, with availability of step-counts on 92% of the days. Baseline step counts were 6274 for breast cancer patients and 3621 for patients with other entities. Decreasing activity during radiotherapy coincided with the development of side effects and declines in quality of life.

Conclusions

Activity trackers as tool to monitor PA during and after radiotherapy were accepted by a majority of the patients included in the current trial. Observed changes in PA correlated with patient reported side effects and QoL in some of the patients.

Digital technologies in cancer care: a review from the clinician's perspective

Physicians are increasingly utilizing digital health technologies (DHT) such as smartphone applications, network-enabled wearable devices, web-based communication platforms, videoconferencing, chatbots, artificial intelligence and virtual reality to improve access to, and quality of, care. DHT aid in cancer screening, patient education, shared decision-making, promotion of positive health habits, symptom monitoring and intervention, patient-provider communication, provision of psychological support and delivery of effective survivorship care. This narrative review outlines how physicians may utilize digital health to improve or augment their delivery of cancer care. For the full potential of DHT to be realized, experts must develop appropriate solutions to issues surrounding the regulation, liability, quality, security, equity and reimbursement of DHT.

Pilot Study of a Wearable Activity Monitor During Head and Neck Radiotherapy to Predict Clinical Outcomes

PURPOSE

Given the established associations between performance status and survival in a variety of cancers, there is significant interest in using a biometric wearable device (WD) to predict outcomes in the oncology population. In this pilot study, we investigated the ability of a WD to predict meaningful clinical end points in patients undergoing head and neck radiotherapy.

METHODS

Patients receiving head and neck definitive chemoradiotherapy or postoperative radiotherapy/chemoradiotherapy were enrolled in this pilot study, designed to show 90% compliance with using the device. Individuals were asked to wear the WD for 23 hours a day, and hospital admissions, pain medication usage, and FACT-G quality-of-life (QoL) score were prospectively recorded.

RESULTS

Fifty-one patients were enrolled and started using the WD, but eight patients stopped wearing it, resulting in a compliance probability of only 84%. There were 15 hospital admissions, 13 of which were planned for feeding tube placement. There was no step count threshold that predicted the need for admission or more pain medications. However, among the 25 patients with a significant reduction in FACT-G score, the average reductions in daily steps during the week and weekend before the decline were 988 (P = .005) and 1,311 (P = .018), respectively, and the odds of a QoL reduction were more than 4-fold higher among patients experiencing a week-to-week reduction of at least 1,000 daily steps. There was no association between heart rate and any end point.

CONCLUSION

Although not meeting the compliance goal, the majority of patients did use the WD. The WD signal could not identify patients requiring hospitalization or significantly more pain medication, but the finding of reduced step counts before a significant reduction in QoL is provocative.

Activity Monitoring for Toxicity Detection and Management in Patients Undergoing Chemoradiation for Gastrointestinal Malignancies

PURPOSE

Physical activity is associated with decreased hospitalization during cancer treatment. We hypothesize that activity data can help identify and triage high-risk patients with GI cancer undergoing concurrent chemoradiation.

MATERIALS AND METHODS

This prospective study randomly assigned patients to activity monitoring versus observation. In the intervention arm, a 20% decrease in daily steps or 20% increase in heart rate triggered triage visits to provide supportive care, medication changes, and escalation of care. In the observation group, activity data were recorded but not monitored. The primary objective was to show a 20% increase in triage visits in the intervention group. Secondary objectives were estimating the rates of emergency department (ED) visits and hospitalizations. Crude and adjusted odds ratios were computed using logistic regression modeling.

RESULTS

There were 22 patients in the intervention and 18 in the observation group. Baseline patient and treatment characteristics were similar. The primary objective was met, with 3.4 more triage visits in the intervention group than in the observation group (95% CI, 2.10 to 5.50; P < .0001). Twenty-six (65.0%) patients required at least one triage visit, with a higher rate in the intervention arm compared with that in the observation arm (86.4% v 38.9%; odds ratio, 9.95; 95% CI, 2.13 to 46.56; P = .004). There was no statistically significant difference in ED visit (9.1% v 22.2%; P = .38) or hospitalization (4.5% v 16.7%; P = .31).

CONCLUSION

It is feasible to use activity data to trigger triage visits for symptom management. Further studies are investigating whether automated activity monitoring can assist with early outpatient management to decrease ED visits and hospitalizations.

Remote Monitoring of the Performance Status and Burden of Symptoms of Patients With Gastrointestinal Cancer Via a Consumer-Based Activity Tracker: Quantitative Cohort Study

BACKGROUND

The number of older patients with gastrointestinal cancer is increasing due to an aging global population. Minimizing reliance on an in-clinic patient performance status test to determine a patient's prognosis and course of treatment can improve resource utilization. Further, current performance status measurements cannot capture patients' constant changes. These measurements also rely on self-reports, which are subjective and subject to bias. Real-time monitoring of patients' activities may allow for a more accurate assessment of patients' performance status while minimizing resource utilization.

OBJECTIVE

This study investigates the validity of consumer-based activity trackers for monitoring the performance status of patients with gastrointestinal cancer.

METHODS

A total of 27 consenting patients (63% male, median age 58 years) wore a consumer-based activity tracker 7 days before chemotherapy and 14 days after receiving their first treatment. The provider assessed patients using the Eastern Cooperative Oncology Group Performance Status (ECOG-PS) scale and Memorial Symptom Assessment Scale-Short Form (MSAS-SF) before and after chemotherapy visits. The statistical correlations between ECOG-PS and MSAS-SF scores and patients' daily step counts were assessed.

RESULTS

The daily step counts yielded the highest correlation with the patients' ECOG-PS scores after chemotherapy (P<.001). The patients with higher ECOG-PS scores experienced a higher fluctuation in their step counts. The patients who walked more prechemotherapy (mean 6071 steps per day) and postchemotherapy (mean 5930 steps per day) had a lower MSAS-SF score (lower burden of symptoms) compared to patients who walked less prechemotherapy (mean 5205 steps per day) and postchemotherapy (mean 4437 steps per day).

CONCLUSIONS

This study demonstrates the feasibility of using inexpensive, consumer-based activity trackers for the remote monitoring of performance status in the gastrointestinal cancer population. The findings need to be validated in a larger population for generalizability.

Overcoming Barriers to Radiation Oncology Access in Low-Resource Settings in the United States

Providing high-quality radiation therapy in medically underserved, low-resource environments can be challenging in the United States. During the American Society of Radiation Oncology 2020 Annual Meeting, the American Society for Radiation Oncology Committee on Health Equity, Diversity, and Inclusion hosted 4 radiation oncologists from both academic and community practices in an educational session. Speakers discussed creative ways to overcome barriers to equitable cancer care and outcomes for their vulnerable patient populations in both rural and urban settings. Successful tactics have included applying for state-sponsored grants, lobbying hospital leadership for equipment upgrades, implementing quality improvement programs specifically targeting the needs of the patient population, studying novel hypofractionation schedules, monitoring toxicities using wearable devices, and expanding transportation options.

Artificial Intelligence in Brain Tumour Surgery-An Emerging Paradigm

Artificial intelligence (AI) platforms have the potential to cause a paradigm shift in brain tumour surgery. Brain tumour surgery augmented with AI can result in safer and more effective treatment. In this review article, we explore the current and future role of AI in patients undergoing brain tumour surgery, including aiding diagnosis, optimising the surgical plan, providing support during the operation, and better predicting the prognosis. Finally, we discuss barriers to the successful clinical implementation, the ethical concerns, and we provide our perspective on how the field could be advanced.

Impact of Physical Inactivity on the Risk of Disability and Hospitalization in Older Patients with Advanced Lung Cancer

Purpose

This prospective observational study aimed to explore the influence of physical inactivity during initial chemotherapy on the risk of disability and hospitalization in later life among older patients with advanced non-small-cell lung cancer (NSCLC).

Patients and Methods

Patients aged 70 or above who were scheduled to receive first-line chemotherapy for newly diagnosed advanced NSCLC were recruited for the study. An electronic pedometer was used to measure daily steps; based on the change rate (cutoff: −12.5%) from pretreatment to 12 ± 4 weeks after enrolment, patients were classified as active or inactive. The Barthel Index estimated activities of daily living. We compared disability-free survival time, mean cumulative functions of hospital stays, and medical costs, between the active and inactive groups.

Results

Among the 29 patients enrolled, 21 were evaluable. Compared with active patients (n = 11), inactive patients (n = 10) showed shorter disability-free survival (6.4 vs 19.9 months, p < 0.05) and tended to have longer hospital stays (23.7 vs 6.3 days/person) and higher inpatient care cost (¥1.6 vs ¥0.3 million/person [US$16,000 vs US$3000/person]) during the first year.

Conclusion

Physical inactivity during initial chemotherapy may be a risk factor for developing disability and requiring hospitalization in later life for older patients with advanced NSCLC. Our findings may indicate the need for lifestyle interventions with multidisciplinary teams, which include physicians, nurses, and physiotherapists, for older patients with advanced lung cancer during an active cancer treatment. A large-sample-sized study is needed to validate our findings.

The association between wearable activity monitor metrics and performance status in oncology: a systematic review

PURPOSE

The expanding armamentarium of wearable activity monitors (WAMs) offers new opportunities to supplement physician-assessed performance status (PS) with real-life patient activity data. These data could guide clinical decision making or serve as a measure of treatment outcome. However, information on the association between physical activity (PA) and sedentary behavior (SB) monitored with wearables (i.e., WAM metrics) and PS in patients with cancer is needed. Therefore, we conducted a systematic review to examine the association between WAM metrics and PS in patients with cancer.

METHODS

We searched MEDLINE and Embase for studies that assessed the association between WAM metrics and performance status among adults with cancer. We extracted information on study design and population, WAM type and different activity metrics, outcome definitions, and results. Included studies were subjected to risk of bias assessment and subsequent best evidence synthesis.

RESULTS

Fourteen studies were included in this review. All studies reported on different combinations of WAM metrics including: daily steps (n = 8), SB (n = 5), mean activity counts (n = 4), dichotomous circadian rest-activity index (n = 3), and time spent in moderate-to-vigorous PA (MVPA) (n = 3). Much heterogeneity was observed regarding study population, WAM used, and reporting of results. We found moderate evidence for a positive weak-to-moderate association between WAM-assessed PA and PS and a weak-to-moderate negative association between WAM-assessed SB metrics and PS.

CONCLUSION

Weak-to-moderate associations between WAM metrics and PS suggest that WAM data and physician-assessed PS cannot be used interchangeably. Instead, WAM data could serve as a dynamic and objective supplement measurement of patients' physical performance.

[Use of telehealth services in the oncology setting: Daily routine and during sanitary crisis]

Telemedicine is booming with different sub-domains, including telehealth consultation. Pathology chronicity as well as the increased use of health services are two characteristics that underline the importance of telehealth consultation for patient's needs and health professionals. The actual viral pandemic has inadvertently aided the adoption of telehealth, including in medical oncology, radiotherapy and hematology departments. To date, numerous tools are available to accelerate the digital transformation in clinical practice. In this review of the literature, we detail the historical and legal set up of telemedicine, focusing especially on teleconsultation and teleoncology.

Physical activity in hemodialysis patients on nondialysis and dialysis days: Prospective observational study

INTRODUCTION

The physical decline in patients with end-stage kidney disease (ESKD) is associated with morbidity and mortality. Prior studies have attempted to promote physical activity at the time of dialysis; however, physical activity patterns on the nondialysis days are unknown. This study aimed to quantify physical activity on dialysis and nondialysis days in hemodialysis patients using a wearable actigraph.

METHODS

In this prospective study, subjects receiving hemodialysis were recruited from two outpatient dialysis units in urban San Diego and rural Imperial County, CA, between March 2018 and April 2019. Key inclusion criteria included: (1) receiving thrice weekly hemodialysis for ≥3 months, (2) age ≥ 18 years, and (3) able to walk with or without assistive devices. All participants wore a Fitbit Charge 2 tracker for a minimum of 4 weeks. The primary outcome was the number of steps per day. Each participant completed the Physical Activity Questionnaire, the Patient Health Questionnaire (PHQ)-9, the PROMIS Short form Fatigue Questionnaire at baseline, and the Participant Technology Experience Questionnaire at day 7 after study enrolment.

FINDINGS

Of the 52 recruited, 45 participants (urban = 25; rural = 20) completed the study. The mean age was 61 ± 15 years, 42% were women, 64% were Hispanic, and the mean dialysis vintage was 4.4 ± 3.0 years. For those with valid Fitbit data (defined as ≥10 hours of wear per day) for 28 days (n = 45), participants walked an average of 3688 steps per day, and 73% of participants were sedentary (<5000 steps/day). Participants aged >80 years were less active than younger (age < 65 years) participants (1232 vs. 4529 steps, P = 0.01). There were no statistical differences between the groups when stratified by gender (women vs. men [2817 vs. 4324 steps, respectively]), urbanicity (rural vs. urban dialysis unit [3141 vs. 4123 steps, respectively]), and dialysis/nondialysis day (3177 vs. 4133 steps, respectively). Due to the small sample size, we also calculated effect sizes. The effect size was medium for the gender differences (cohen's d = 0.57) and small to medium for urbanicity and dialysis/nondialysis day (d = 0.37 and d = 0.33, respectively). We found no association between physical activity and self-reported depression and fatigue scale. The majority of participants (62%, 28/45) found the Fitbit tracker easy to wear and comfortable.

DISCUSSION

ESKD participants receiving hemodialysis are frequently sedentary, and differences appear more pronounced in older patients. These findings may assist in designing patient-centered interventions to increase physical activity among hemodialysis patients.

The Use of Wearables in Clinical Trials During Cancer Treatment: Systematic Review

Background

Interest in the use of wearables in medical care is increasing. Wearables can be used to monitor different variables, such as vital signs and physical activity. A crucial point for using wearables in oncology is if patients already under the burden of severe disease and oncological treatment can accept and adhere to the device. At present, there are no specific recommendations for the use of wearables in oncology, and little research has examined the purpose of using wearables in oncology.

Objective

The purpose of this review is to explore the use of wearables in clinical trials during cancer treatment, with a special focus on adherence.

Methods

PubMed and EMBASE databases were searched prior and up to October 3, 2019, with no limitation in the date of publication. The search strategy was aimed at studies using wearables for monitoring adult patients with cancer during active antineoplastic treatment. Studies were screened independently by 2 reviewers by title and abstract, selected for inclusion and exclusion, and the full-text was assessed for eligibility. Data on study design, type of wearable used, primary outcome, adherence, and device outcome were extracted. Results were presented descriptively.

Results

Our systematic search identified 1269 studies, of which 25 studies met our inclusion criteria. The types of cancer represented in the studies were breast (7/25), gastrointestinal (4/25), lung (4/25), and gynecologic (1/25); 9 studies had multiple types of cancer. Oncologic treatment was primarily chemotherapy (17/25). The study-type distribution was pilot/feasibility study (12/25), observational study (10/25), and randomized controlled trial (3/25). The median sample size was 40 patients (range 7-180). All studies used a wearable with an accelerometer. Adherence varied across studies, from 60%-100% for patients wearing the wearable/evaluable sensor data and 45%-94% for evaluable days, but was differently measured and reported. Of the 25 studies, the most frequent duration for planned monitoring with a wearable was 8-30 days (13/25). Topics for wearable outcomes were physical activity (19/25), circadian rhythm (8/25), sleep (6/25), and skin temperature (1/25). Patient-reported outcomes (PRO) were used in 17 studies; of the 17 PRO studies, only 9 studies reported correlations between the wearable outcome and the PRO.

Conclusions

We found that definitions of outcome measures and adherence varied across studies, and limited consensus among studies existed on which variables to monitor during treatment. Less heterogeneity, better consensus in terms of the use of wearables, and established standards for the definitions of wearable outcomes and adherence would improve comparisons of outcomes from studies using wearables. Adherence, and the definition of such, seems crucial to conclude on data from wearable studies in oncology. Additionally, research using advanced wearable devices and active use of the data are encouraged to further explore the potential of wearables in oncology during treatment. Particularly, randomized clinical studies are warranted to create consensus on when and how to implement in oncological practice.

Harnessing consumer smartphone and wearable sensors for clinical cancer research

As smartphones and consumer wearable devices become more ubiquitous, there is a growing opportunity to capture rich mobile sensor data continuously, passively, and in real-world settings with minimal burden. In the context of cancer, changes in these passively sensed digital biomarkers may reflect meaningful variation in functional status, symptom burden, quality of life, and risk for adverse clinical outcomes. These data could enable real-time remote monitoring of patients between clinical encounters and more proactive, comprehensive, and personalized care. Over the past few years, small studies across a variety of cancer populations support the feasibility and potential clinical value of mobile sensors in oncology. Barriers to implementing mobile sensing in clinical oncology care include the challenges of managing and making sense of continuous sensor data, patient engagement issues, difficulty integrating sensor data into existing electronic health systems and clinical workflows, and ethical and privacy concerns. Multidisciplinary collaboration is needed to develop mobile sensing frameworks that overcome these barriers and that can be implemented at large-scale for remote monitoring of deteriorating health during or after cancer treatment or for promotion and tailoring of lifestyle or symptom management interventions. Leveraging digital technology has the potential to enrich scientific understanding of how cancer and its treatment affect patient lives, to use this understanding to offer more timely and personalized support to patients, and to improve clinical oncology outcomes.

Treating Hematologic Malignancies During a Pandemic: Utilizing Telehealth and Digital Technology to Optimize Care

In late January 2020, Severe Acute Respiratory Syndrome Coronavirus-2 (SARS CoV-2) was reported as an outbreak in Wuhan, China. Within 2 months it became a global pandemic. Patients with cancer are at highest risk for both contracting and suffering complications of its resultant disease, Coronavirus 19 (COVID-19). Healthcare systems across the world had to adapt quickly to mitigate this risk, while continuing to provide potentially lifesaving treatment to patients. Bringing care to the home through the use of telehealth, home based chemotherapy, and remote patient monitoring technologies can help minimize risk to the patient and healthcare workers without sacrificing quality of care delivered. These care models provide the right treatment, to the right patient, at the right time, in the right place. Whether these patient-centered models of care will continue to be embraced by key stakeholders after the pandemic remains uncertain.

Cardiac Irradiation Predicts Activity Decline in Patients Receiving Concurrent Chemoradiation for Locally Advanced Lung Cancer

PURPOSE

Many patients with lung cancer are inactive due to their disease and underlying comorbidities, and activity levels can decline further during cancer therapy. Here we explore dosimetric predictors of activity decline in a cohort of patients who underwent continuous activity monitoring during definitive concurrent chemoradiotherapy (CRT) for locally advanced lung cancer.

METHODS AND MATERIALS

We identified patients who participated in prospective clinical trials involving the use of a commercial fitness tracker throughout the course of CRT. For each patient, we applied linear regression to log-transformed daily step counts to compute the weekly rate of activity change from 1 week before radiation therapy (RT) initiation to 2 weeks after RT completion. Clinical and dosimetric factors were tested as predictors of activity change using linear regressions.

RESULTS

Forty-six patient met the eligibility criteria. Median age was 66 years (range, 38-90). Pretreatment Eastern Cooperative Oncology Group performance status was 0, 1, and 2 for 17%, 70%, and 13%, respectively. Mean lung dose ranged from 5.0 to 23.5 Gy, mean esophagus dose from 1.1 to 39.6 Gy, and mean heart dose from 0.6 to 31.5 Gy. Median daily step count average was 5861 (interquartile range, 3540-8282) before RT and 3422 (interquartile range, 2364-5395) 2 weeks after RT completion. Rate of activity change was not significantly associated with age, performance status, or mean RT dose received by lungs or esophagus. In multivariate analysis, mean heart dose was significantly associated with rate of activity decline, with a 3.1% reduction in step count per week for every 10 Gy increase in mean heart dose (95% confidence interval: 0.5-5.7, P = .023).

CONCLUSIONS

Extent of cardiac irradiation is associated with the rate of physical activity decline during CRT for lung cancer. Our novel finding contributes to the growing body of evidence that adverse effects of cardiac irradiation may be manifested at early time points.

Big Data From Small Devices: The Future of Smartphones in Oncology

Technological advancements in the capabilities of modern smartphones offer tremendous potential to generate big data from small devices that could influence oncologists' decision-making. Here we describe the value of patient-generated health data (PGHD) that can be captured using mobile devices. We comment on the current use of smartphones in oncology clinical research and describe how smartphones will bring big data into the oncology clinic by enabling continuous patient monitoring, information sharing, and personalized clinical decision making in cancer care. Lastly, we describe practical considerations about how we can access and store PGHD in the future, describing how to harness the clinical value of PGHD and comment on the emerging applications for digital biomarkers captured by smartphones.

Real-time, personalized medicine through wearable sensors and dynamic predictive modeling: a new paradigm for clinical medicine

Accurately predicting the onset and course of a disease in an individual is a major unmet challenge in medicine due to the complex and dynamic nature of disease progression. Continuous data from wearable technologies and biomarker data with a fine time resolution provide a unique opportunity to learn more about disease evolution and to usher in a new era of personalized and real-time medicine. Herein, we propose the potential of real-time, continuously measured physiological data as a noninvasive biomarker approach for detecting disease transitions, using allogeneic hematopoietic stem cell transplant (HCT) patient care as an example. Additionally, we review a recent computational technique, the landscape dynamic network biomarker method, that uses biomarker data to identify transition states in disease progression and explore how to use it with both biomarker and physiological data for earlier detection of graft-versus-host disease specifically. Throughout, we argue that increased collaboration across multiple fields is essential to realizing the full potential of wearable and biomarker data in a new paradigm of personalized and real-time medicine.

A Research Roadmap: Connected Health as an Enabler of Cancer Patient Support

The evidence that quality of life is a positive variable for the survival of cancer patients has prompted the interest of the health and pharmaceutical industry in considering that variable as a final clinical outcome. Sustained improvements in cancer care in recent years have resulted in increased numbers of people living with and beyond cancer, with increased attention being placed on improving quality of life for those individuals. Connected Health provides the foundations for the transformation of cancer care into a patient-centric model, focused on providing fully connected, personalized support and therapy for the unique needs of each patient. Connected Health creates an opportunity to overcome barriers to health care support among patients diagnosed with chronic conditions. This paper provides an overview of important areas for the foundations of the creation of a new Connected Health paradigm in cancer care. Here we discuss the capabilities of mobile and wearable technologies; we also discuss pervasive and persuasive strategies and device systems to provide multidisciplinary and inclusive approaches for cancer patients for mental well-being, physical activity promotion, and rehabilitation. Several examples already show that there is enthusiasm in strengthening the possibilities offered by Connected Health in persuasive and pervasive technology in cancer care. Developments harnessing the Internet of Things, personalization, patient-centered design, and artificial intelligence help to monitor and assess the health status of cancer patients. Furthermore, this paper analyses the data infrastructure ecosystem for Connected Health and its semantic interoperability with the Connected Health economy ecosystem and its associated barriers. Interoperability is essential when developing Connected Health solutions that integrate with health systems and electronic health records. Given the exponential business growth of the Connected Health economy, there is an urgent need to develop mHealth (mobile health) exponentially, making it both an attractive and challenging market. In conclusion, there is a need for user-centered and multidisciplinary standards of practice to the design, development, evaluation, and implementation of Connected Health interventions in cancer care to ensure their acceptability, practicality, feasibility, effectiveness, affordability, safety, and equity.

Clinical Integration of Digital Solutions in Health Care: An Overview of the Current Landscape of Digital Technologies in Cancer Care

Digital health constitutes a merger of both software and hardware technology with health care delivery and management, and encompasses a number of domains, from wearable devices to artificial intelligence, each associated with widely disparate interaction and data collection models. In this review, we focus on the landscape of the current integration of digital health technology in cancer care by subdividing digital health technologies into the following sections: connected devices, digital patient information collection, telehealth, and digital assistants. In these sections, we give an overview of the potential clinical impact of such technologies as they pertain to key domains, including patient education, patient outcomes, quality of life, and health care value. We performed a search of PubMed ( www.ncbi.nlm.nih.gov/pubmed ) and www.ClinicalTrials.gov for numerous terms related to digital health technologies, including digital health, connected devices, smart devices, wearables, activity trackers, connected sensors, remote monitoring, electronic surveys, electronic patient-reported outcomes, telehealth, telemedicine, artificial intelligence, chatbot, and digital assistants. The terms health care and cancer were appended to the previously mentioned terms to filter results for cancer-specific applications. From these results, studies were included that exemplified use of the various domains of digital health technologies in oncologic care. Digital health encompasses the integration of a vast array of technologies with health care, each associated with varied methods of data collection and information flow. Integration of these technologies into clinical practice has seen applications throughout the spectrum of care, including cancer screening, on-treatment patient management, acute post-treatment follow-up, and survivorship. Implementation of these systems may serve to reduce costs and workflow inefficiencies, as well as to improve overall health care value, patient outcomes, and quality of life.

The HOPE Pilot Study: Harnessing Patient-Reported Outcomes and Biometric Data to Enhance Cancer Care

PURPOSE

Integrating patient-reported outcomes (PROs) into clinical practice is an increasingly promising strategy for improving patients' symptoms, communication, and clinical outcomes. The objective of the current study was to assess the feasibility, acceptability, and perceived effectiveness of a mobile health intervention that was designed to collect PROs and activity data as a measure of health status.

PATIENTS AND METHODS

This work was a pilot intervention with 10 patients with gynecologic cancers who received palliative chemotherapy. The HOPE (Helping Our Patients Excel) study used wearable accelerometers to assess physical activity and the Beiwe research platform to collect PROs, stratify patient responses by risk, provide tailored symptom management, and notify patients and clinicians of high-risk symptoms. Feasibility and acceptability were assessed through enrollment and adherence rates, and perceived effectiveness was evaluated by patients and oncologists at study completion.

RESULTS

The approach-to-consent rate was 100%, and participants were 90% and 70% adherent to the wearable accelerometers and smartphone surveys, respectively. Participants' mean daily step count was 3,973 (standard deviation [SD], 2,305 steps) and increased from week 1 (mean, 3,520 steps; SD, 1,937 steps) to week 3 (mean, 4,136 steps; SD, 1,578 steps). Active monitoring of participants' heart rates, daily steps, and PROs throughout the study identified anomalies in participants' behavior patterns that suggested poor health for two patients (20%). Patients and clinicians indicated that the intervention improved physical activity, communication, and symptom management.

CONCLUSION

A mobile health intervention that collects PROs and activity data as a measure of health status is feasible, acceptable, and was perceived to be effective in improving symptom management in patients with advanced gynecologic cancers. A larger, multisite, randomized clinical trial to assess the efficacy of the HOPE intervention on patients' symptoms, health-related quality of life, clinical outcomes, and health care use is warranted.

Daily Step Counts: A New Prognostic Factor in Locally Advanced Non-Small Cell Lung Cancer?

PURPOSE

Here we explore the prognostic value of baseline step count data captured using wearable devices for patients treated with definitive chemoradiation therapy for locally advanced non-small cell lung cancer (NSCLC).

METHODS AND MATERIALS

Patients with locally advanced NSCLC wore a commercial fitness tracker during a course of definitive, concurrent chemoradiation therapy as part of a clinical trial. Baseline step count average was defined as the average daily step total from study enrollment until completion of the first week of radiation therapy. Based on data from healthy individuals, study subjects were categorized as inactive (below the 25th percentile), moderately active (25th to 75th percentile), or highly active (above the 75th percentile). Fisher's exact test was used to examine activity level as a predictor of hospitalization during radiation therapy and of completing the planned radiation therapy course without delay exceeding 1 week. Median progression-free survival (PFS) and overall survival (OS) durations were estimated using the Kaplan-Meier method. Inactivity was tested as a predictor of PFS and OS using Cox proportional hazards models.

RESULTS

Fifty subjects met eligibility criteria. Nine (18%) were categorized as highly active, 23 (46%) were moderately active, and 18 (36%) were inactive. Inactive subjects were more likely to be hospitalized during the radiation therapy course than other subjects (50% vs 9%, P = .004) and less likely to complete radiation therapy without delay exceeding 1 week (67% vs 97%, P = .006). Median PFS duration was 5.3 months for inactive subjects and 18.3 months for others (hazard ratio for inactivity = 5.10, P < .001). Median OS duration was 15.0 months for inactive subjects and not reached for others (hazard ratio = 3.91, P = .004). Performance status was not a significant predictor of PFS or OS.

CONCLUSIONS

Baseline activity level measured using wearable devices may help identify patients with NSCLC who are fit for concurrent chemoradiation therapy and can predict clinical outcomes in this setting.

Tracking steps in oncology: the time is now

Purpose

Accurate evaluation of patients’ health status is a key component of the workup, treatment, and follow-up of cancer patients. Assessments by clinicians (eg, performance status, toxicity grade) and patients (eg, quality of life) play a critical role in current practice but have significant limitations. Technological advances now provide an opportunity to track a new class of objective measures of patient activity, such as daily step counts. Here, we describe recent efforts to incorporate this technology into the field of oncology.

Design

We conducted a structured literature search using MEDLINE electronic database to identify published observational studies of tracking steps in cancer patients and trials of exercise programs for cancer survivors incorporating pedometers until February 2016.

Results

Data indicate that physical activity information may supplant existing scales for the assessment of cancer patients’ functional capacity.

Conclusion

Objective activity monitoring is poised to revolutionize the way health care providers assess cancer patients at the time of diagnosis, during treatment, and in the survivorship setting.

Wearable activity monitors to assess performance status and predict clinical outcomes in advanced cancer patients

An objective evaluation of patient performance status (PS) is difficult because patients spend the majority of their time outside of the clinic, self-report to providers, and undergo dynamic changes throughout their treatment experience. Real-time, objective activity data may allow for a more accurate assessment of PS and physical function, while reducing the subjectivity and bias associated with current assessments. Consenting patients with advanced cancer wore a wearble activity monitor for three consecutive visits in a prospective, single-cohort clinical trial. Provider-assessed PS (ECOG/Karnofsky) and NIH PROMIS® patient-reported outcomes (PROs) were assessed at each visit. Associations between wearable activity monitor metrics (steps, distance, stairs) and PS, clinical outcomes (adverse events, hospitalizations, survival), and PROs were assessed using correlation statistics and in multivariable logistic regression models. Thirty-seven patients were evaluated (54% male, median 62 years). Patients averaged 3700 steps, 1.7 miles, and 3 flights of stairs per day. Highest correlations were observed between average daily steps and ECOG-PS and KPS (r = 0.63 and r = 0.69, respectively p < 0.01). Each 1000 steps/day increase was associated with reduced odds for adverse events (OR: 0.34, 95% CI 0.13, 0.94), hospitalizations (OR: 0.21 95% CI 0.56, 0.79), and hazard for death (HR: 0.48 95% CI 0.28–0.83). Significant correlations were also observed between activity metrics and PROs. Our trial demonstrates the feasibility of using wearable activity monitors to assess PS in advanced cancer patients and suggests their potential use to predict clinical and patient-reported outcomes. These findings should be validated in larger, randomized trials.

Wearable activity monitors provide an objective and continuous measure of general wellbeing and physical function among patients with advanced cancer. Gillian Gresham from Cedars-Sinai Medical Center in Los Angeles, California, USA, and colleagues enlisted 37 patients with metastatic or inoperable cancer to wear wristbands that wireless measure heart rate and activity patterns over the span of 2 weeks. At weekly clinic visits, the patients also filled in health questionnaires and their healthcare providers made independent evaluations. The researchers found a reasonably high correlation between the clinician-assessed performance status and the average daily step total calculated by the wristband. More steps also translated into lower odds of serious complications, hospitalizations or death. The study shows the feasibility of using wearable technology to track the ability of patients with advanced cancer to perform certain activities of daily living.