JMIR Publications

JMIR Research Protocols

Ongoing Trials, Grant Proposals, Formative Research, Methods, Early Results


Journal Description


JMIR Research Protocols (ISSN 1929-0748) publishes peer-reviewed, openly accessible research ideas and grant proposals, study and trial protocols, reports of ongoing research, current methods and approaches, and preliminary results from pilot studies or formative research informing the design of medical and health-related research and technology innovations.

JMIR Res Protoc is a new journal spin-off of JMIR, the worlds' leading medical journal in health sciences / health services research and health informatics (Impact Factor 2015: 4.532)

JMIR Res Protoc publishes protocols and grant proposals in all areas of medicine (and their peer-review reports, if available), as well as feasibility studies, early reports and formative/process evaluations of ongoing studies and descriptions of the development and pilot evaluations of innovations and software applications or other interventions

JMIR Res Protoc is fully open access, with full text articles deposited in PubMed Central

Publishing research protocols, grant proposals, pilot/feasibility studies and early reports of ongoing and planned work encourages collaboration and early feedback, and reduces duplication of effort 

JMIR Res Protoc will be a valuable ressource for researchers who want to learn about current research methodologies and how to write a winning grant proposal

JMIR Res Protoc creates an early scientific record for researchers who have developed novel methodologies, software, innovations or elaborate protocols

JMIR Res Protoc faciliates subsequent publication of results demonstrating that the methodology has already been reviewed, and reduces the effort of writing up the results, as the protocol can be easily referenced

JMIR Res Protoc demonstrates to reviewers of subsequent results papers that authors followed and adhered to carefully developed and described a-priori methods

Studies whose protocols or grant proposal have been accepted in JMIR Res Protoc are "in principle accepted" for subsequent publication of results in other JMIR journals as long as authors adhere to their original protocol - regardless of study results (even if they are negative), reducing publication bias in medicine

Authors publishing their protocols in JMIR Res Protoc will receive a 20% discount on the article processing fee if they publish their results in another journal of the JMIR journal family (for example, JMIR for ehealth studies, i-JMR for others)


Recent Articles:

  • PredART logo. Image sourced and copyright owned by author Friedrich Thienemann.

    Preventing Paradoxical Tuberculosis-Associated Immune Reconstitution Inflammatory Syndrome in High-Risk Patients: Protocol of a Randomized Placebo-Controlled...


    Background: Early antiretroviral therapy (ART) initiation in patients diagnosed with HIV-associated tuberculosis (TB) reduces mortality among those with the lowest CD4 counts. At the same time, both early ART and a low CD4 count heighten the risk of paradoxical TB-associated immune reconstitution inflammatory syndrome (TB-IRIS). TB is common in patients starting ART in sub-Saharan Africa. Safe interventions that reduce the incidence or severity of TB-IRIS are needed. Prednisone has been shown to reduce symptoms and markers of inflammation when used to treat TB-IRIS. Objective: To determine whether prophylactic prednisone in patients at high risk for paradoxical TB-IRIS initiating ART reduces the incidence of TB-IRIS. Methods: We are conducting a randomized, double-blind, placebo-controlled trial of prophylactic prednisone (40 mg/day for 2 weeks, followed by 20 mg/day for 2 weeks) initiated at the same time as ART in patients at high risk for TB-IRIS (starting ART within 30 days of TB treatment and CD4 count ≤100/μL). The primary endpoint is development of TB-IRIS, defined using an international consensus case definition. Secondary endpoints include time to TB-IRIS event, severity of TB-IRIS, quality of life, mortality, hospitalization, other infections and malignancies, and adverse events including corticosteroid adverse effects. Results: Enrollment for the trial began in August 2013. All 240 participants have been enrolled, and safety follow-up will be completed in March 2017. Conclusion: No preventive strategies for TB-IRIS currently exist. If results of this trial demonstrate the efficacy and safety of prednisone, this will provide clinicians with an evidence-based preventive strategy in patients at high risk for paradoxical TB-IRIS when initiating ART.

  • Parkinson@Home system. Picture obtained by the authors (Copyright©2016 Parkinson@Home research team).

    Large-Scale Wearable Sensor Deployment in Parkinson’s Patients: The Parkinson@Home Study Protocol


    Background: Long-term management of Parkinson’s disease does not reach its full potential because we lack knowledge about individual variations in clinical presentation and disease progression. Continuous and longitudinal assessments in real-life (ie, within the patients’ own home environment) might fill this knowledge gap. Objective: The primary aim of the Parkinson@Home study is to evaluate the feasibility and compliance of using multiple wearable sensors to collect clinically relevant data. Our second aim is to address the usability of these data for answering clinical research questions. Finally, we aim to build a database for future validation of novel algorithms applied to sensor-derived data from Parkinson’s patients during daily functioning. Methods: The Parkinson@Home study is a two-phase observational study involving 1000 Parkinson’s patients and 250 physiotherapists. Disease status is assessed using a short version of the Parkinson's Progression Markers Initiative protocol, performed by certified physiotherapists. Additionally, participants will wear a set of sensors (smartwatch, smartphone, and fall detector), and use these together with a customized smartphone app (Fox Insight), 24/7 for 3 months. The sensors embedded within the smartwatch and fall detector may be used to estimate physical activity, tremor, sleep quality, and falls. Medication intake and fall incidents will be measured via patients’ self-reports in the smartphone app. Phase one will address the feasibility of the study protocol. In phase two, mathematicians will distill relevant summary statistics from the raw sensor signals, which will be compared against the clinical outcomes. Results: Recruitment of 300 participants for phase one was concluded in March, 2016, and the follow-up period will end in June, 2016. Phase two will include the remaining participants, and will commence in September, 2016. Conclusions: The Parkinson@Home study is expected to generate new insights into the feasibility of integrating self-collected information from wearable sensors into both daily routines and clinical practices for Parkinson’s patients. This study represents an important step towards building a reliable system that translates and integrates real-life information into clinical decisions, with the long-term aim of delivering personalized disease management support. ClinicalTrial: NCT02474329; (Archived at

  • Source:; CCSA2.0.

    A Dyadic Behavioral Intervention to Optimize Same Sex Male Couples’ Engagement Across the HIV Care Continuum: Development of and Protocol for an Innovative...


    Background: An estimated one- to two-thirds of new human immunodeficiency virus (HIV) infections among US men who have sex with men (MSM) occur within the context of primary partnerships. Thus, HIV interventions that recognize and harness the power of relationships are needed. Increasingly, HIV prevention efforts are being directed toward improving engagement across the HIV care continuum from testing to linkage to care, antiretroviral therapy (ART) adherence, engagement in care, and viral suppression. However, to our knowledge, no behavioral interventions have attempted to address the HIV care continuum using a dyadic approach. Objective: The objective of this paper is to describe the development of and protocol for an innovative couples-based approach to improving treatment adherence and engagement in care among HIV serodiscordant and concordant HIV-positive same sex male couples in the United States. Methods: We developed the Partner Steps intervention by drawing from relationship-oriented theory, existing efficacious individual-level ART adherence interventions, couple-focused HIV prevention interventions, and expert consultation. We incorporated new content to address all aspects of the HIV care continuum (eg, linkage to and retention in care) and to draw on relationship strengths through interactive activities. Results: The resulting theory-based Partner Steps intervention is delivered by a trained bachelors-level counselor (interventionist) over 2 in-person sessions with male-male dyads in which at least 1 partner has recent suboptimal engagement in HIV care. Each session is designed to use relationship strengths to increase motivation for HIV care and treatment, and cover sequential intervention “steps” relating to specific challenges in HIV care engagement and barriers to ART adherence. For each step, couples work with a trained interventionist to identify their unique challenges, actively problem-solve with the interventionist, and articulate and commit to working together to implement a plan in which each partner agrees to complete specific tasks. Conclusions: We drew on theory and evidence to develop novel intervention strategies that leverage strengths of relationships to address engagement across the entire HIV care continuum. We provide details on intervention development and content that may be of use to researchers as well as medical and mental health professionals for whom a dyadic approach to HIV prevention and care may best suit their patient population.

  • Prototype of a strengths-based IT tool. Image source and copyright: study authors.

    Patient Insights Into the Design of Technology to Support a Strengths-Based Approach to Health Care


    Background: An increasing number of research studies in the psychological and biobehavioral sciences support incorporating patients’ personal strengths into illness management as a way to empower and activate the patients, thus improving their health and well-being. However, lack of attention to patients’ personal strengths is still reported in patient–provider communication. Information technology (IT) has great potential to support strengths-based patient–provider communication and collaboration, but knowledge about the users’ requirements and preferences is inadequate. Objective: This study explored the aspirations and requirements of patients with chronic conditions concerning IT tools that could help increase their awareness of their own personal strengths and resources, and support discussion of these assets in consultations with health care providers. Methods: We included patients with different chronic conditions (chronic pain, morbid obesity, and chronic obstructive pulmonary disease) and used various participatory research methods to gain insight into the participants’ needs, values, and opinions, and the contexts in which they felt strengths-based IT tools could be used. Results: Participants were positive toward using technology to support them in identifying and discussing their personal strengths in clinical consultation, but also underlined the importance of fitting it to their specific requirements and the right contexts of use. Participants recommended that technology be designed for use in preconsultation settings (eg, at home) and felt that it should support them in both identifying strengths and in finding out new ways how strengths can be used to attain personal health-related goals. Participants advocated use of technology to support advance preparation for consultations and empower them to take a more active role. IT tools were suggested to be potentially useful in specific contexts, including individual or group consultations with health care providers (physician, nurse, specialist, care team) in clinical consultations but also outside health care settings (eg, as a part of a self-management program). Participants’ requirements for functionality and design include, among others: providing examples of strengths reported by other patients with chronic conditions, along with an option to extend the list with personal examples; giving an option to briefly summarize health-related history; using intuitive, easy-to-use but also engaging user interface design. Additionally, the findings are exemplified with a description of a low-fidelity paper prototype of a strengths-based tool, developed with participants in this study. Conclusions: Users requirements for IT support of a strengths-based approach to health care appear feasible. The presented findings reflect patients’ values and lists potential contexts where they feel that technology could facilitate meaningful patient–provider communication that focuses not just on symptoms and problems, but also takes into account patients’ strengths and resources. The findings can be used to inform further development of IT tools for use in clinical consultations.

  • Amazon MTurK.

    Cloud Based Surveys to Assess Patient Perceptions of Health Care: 1000 Respondents in 3 days for US $300


    Background: There are many challenges in conducting surveys of study participants, including cost, time, and ability to obtain quality and reproducible work. Cloudsourcing (an arrangement where a cloud provider is paid to carry out services that could be provided in-house) has the potential to provide vastly larger, less expensive, and more generalizable survey pools. Objective: The objective of this study is to evaluate, using Amazon's Mechanical Turk (MTurk), a cloud-based workforce to assess patients’ perspectives of health care. Methods: A national online survey posted to Amazon's MTurk consisted of 33 multiple choice and open-ended questions. Continuous attributes were compared using t tests. Results: We obtained 1084 responses for a total cost of US $298.10 in less than 3 days with 300 responses in under 6 hours. Of those, 44.74% (485/1084) were male and 54.80% (594/1084) female, representing 49 out of 50 states and aged 18 to 69 years. Conclusions: Amazon’s MTurk is a potentially useful survey method for attaining information regarding public opinions and/or knowledge with the distinct advantage of cost, speed, and a wide and relatively good representation of the general population, in a confidential setting for respondents.

  • The MedExercise device used in this study. Source and copyright: the authors.

    Application of a Web-Enabled Leg Training System for the Objective Monitoring and Quantitative Analysis of Exercise-Induced Fatigue


    Background: Sustained cardiac rehabilitation is the key intervention in the prevention and treatment of many human diseases. However, implementation of exercise programs can be challenging because of early fatigability in patients with chronic diseases, overweight individuals, and aged people. Current methods of fatigability assessment are based on subjective self-reporting such as rating of perceived exertion or require specialized laboratory conditions and sophisticated equipment. A practical approach allowing objective measurement of exercise-induced fatigue would be useful for the optimization of sustained delivery of cardiac rehabilitation to improve patient outcomes. Objectives: The objective of this study is to develop and validate an innovative approach, allowing for the objective assessment of exercise-induced fatigue using the Web-enabled leg rehabilitation system. Methods: MedExercise training devices were equipped with wireless temperature sensors in order to monitor their usage by temperature rise in the resistance unit (Δt°). Since Δt° correlated with the intensity and duration of exercise, this parameter was used to characterize participants’ leg work output (LWO). Personal smart devices such as laptop computers with wireless gateways and relevant software were used for monitoring of self-control training. Connection of smart devices to the Internet and cloud-based software allowed remote monitoring of LWO in participants training at home. Heart rates (HRs) were measured by fingertip pulse oximeters simultaneously with Δt° in 7 healthy volunteers. Results: Exercise-induced fatigue manifested as the decline of LWO and/or rising HR, which could be observed in real-time. Conversely, training at the steady-state LWO and HR for the entire duration of exercise bout was considered as fatigue-free. The amounts of recommended daily physical activity were expressed as the individual Δt° values reached during 30-minute fatigue-free exercise of moderate intensity resulting in a mean of 8.1°C (SD 1.5°C, N=7). These Δt° values were applied as the thresholds for sending automatic notifications upon taking the personalized LWO doses by self-control training at home. While the mean time of taking LWO doses was 30.3 (SD 4.1) minutes (n=25), analysis of times required to reach the same Δt° by the same participant revealed that longer durations were due to fatigability, manifesting as reduced LWO at the later stages of training bouts. Typically, exercising in the afternoons associated with no fatigue, although longer durations of evening sessions suggested a diurnal fatigability pattern. Conclusions: This pilot study demonstrated the feasibility of objective monitoring of fatigue development in real-time and online as well as retrospective fatigability quantification by the duration of training bouts to reach the same exercise dose. This simple method of leg training at home accompanied by routine fatigue monitoring might be useful for the optimization of exercise interventions in primary care and special populations.

  • Bant2. Image sourced and created by authors Shivani et al.

    Evaluation of a Behavioral Mobile Phone App Intervention for the Self-Management of Type 2 Diabetes: Randomized Controlled Trial Protocol


    Background: Patients with type 2 diabetes mellitus (T2DM) struggle with the management of their condition due to difficulty relating lifestyle behaviors with glycemic control. While self-monitoring of blood glucose (SMBG) has proven to be effective for those treated with insulin, it has been shown to be less beneficial for those only treated with oral medications or lifestyle modification. We hypothesized that the effective self-management of non-insulin treated T2DM requires a behavioral intervention that empowers patients with the ability to self-monitor, understand the impact of lifestyle behaviors on glycemic control, and adjust their self-care based on contextualized SMBG data. Objective: The primary objective of this randomized controlled trial (RCT) is to determine the impact of bant2, an evidence-based, patient-centered, behavioral mobile app intervention, on the self-management of T2DM. Our second postulation is that automated feedback delivered through the mobile app will be as effective, less resource intensive, and more scalable than interventions involving additional health care provider feedback. Methods: This study is a 12-month, prospective, multicenter RCT in which 150 participants will be randomly assigned to one of two groups: the control group will receive current standard of care, and the intervention group will receive the mobile phone app system in addition to standard of care. The primary outcome measure is change in glycated hemoglobin A1c from baseline to 12 months. Results: The first patient was enrolled on July 28, 2015, and we anticipate completing this study by September, 2018. Conclusions: This RCT is one of the first to evaluate an evidence-based mobile app that focuses on facilitating lifestyle behavior change driven by contextualized and structured SMBG. The results of this trial will provide insights regarding the usage of mobile tools and consumer-grade devices for diabetes self-care, the economic model of using incentives to motivate behavior change, and the consumption of test strips when following a rigorously structured approach for SMBG. Trial Registration: NCT02370719; (Archived at

  • Source and copyright: The authors, license to use under creative commons.

    Designing an Adverse Drug Event Reporting System to Prevent Unintentional Reexposures to Harmful Drugs: Study Protocol for a Multiple Methods Design


    Background: Adverse drug events (ADEs) are unintended and harmful events related to medication use. Up to 30% of serious ADEs recur within six months because culprit drugs are unintentionally represcribed and redispensed. Improving the electronic communication of ADE information between care providers, and across care settings, has the potential to reduce recurrent ADEs. Objective: We aim to describe the methods used to design Action ADE, a novel electronic ADE reporting system that can be leveraged to prevent unintentional reexposures to harmful drugs in British Columbia, Canada. Methods: To develop the new system, our team will use action research and participatory design, approaches that employ social scientific research methods and practitioner participation to generate insights into work settings and problem resolution. We will develop a systematic search strategy to review existing ADE reporting systems identified in academic and grey literature, and analyze the content of these systems to identify core data fields used to communicate ADE information. We will observe care providers in the emergency departments and on the wards of two urban tertiary hospitals and one urban community hospital, in one rural ambulatory care center, and in three community pharmacies in British Columbia, Canada. We will also conduct participatory workshops with providers to understand their needs and priorities related to communicating ADEs and preventing erroneous represcribing or redispensing of culprit medications. These methods will inform the iterative development of a preliminary paper-based reporting form, which we will then pilot test with providers in a real-world setting. Results: This is an ongoing project with results being published as analyses are completed. The systematic review has been completed; field observations, focus groups, and pilot testing of a preliminary paper-based design are ongoing. Results will inform the development of software that will enable clinically useful user-friendly documentation and communication of ADEs. Conclusions: We take this approach with the recognition that information technology-based solutions in health care often fall short of expectations as a result of designers’ failure to account for organizational and work practice considerations, and the needs of end-users. We describe how integrating qualitative methods into an iterative participatory design process (planned in partnership with end-users) will allow us to address specific clinical needs, conceptualize linkages between systems, integrate the reporting system into clinicians’ workflow, and design the system to optimize its uptake into practice.

  • Copyright and source: Private photo taken by Marije Geldof.

    Protocol for a Randomized Controlled Trial Evaluating Mobile Text Messaging to Promote Retention and Adherence to Antiretroviral Therapy for People Living...


    Background: Retention in care and adherence to antiretroviral therapy (ART) among people living with human immunodeficiency virus (PLHIV) is a critical challenge in many African countries including Burkina Faso. Delivering text messaging (short message service, SMS) interventions through mobile phones may help facilitate health service delivery and improve patient health. Despite this potential, no evaluations have been delivered for national scale settings to demonstrate the impact of mobile health (mHealth) for PLHIV. Objectives: This study aims to test the impact of SMS text messaging reminders for PLHIV in Burkina Faso, who are under ART. The evaluation identifies whether patients who receive SMS text messages are more likely to (1) retain in care (measured as a dichotomous variable), (2) adhere to antiretroviral regimens (measured as the number of doses missed in the past 7 days), and (3) experience slower disease progression (measured with T-lymphocytes cells). The second objective is to assess its effects on the frequency of health center visits, physical and psychosocial health, nutrition and whether the type of message (text vs image) and frequency (weekly vs semiweekly) have differential impacts including the possibility of message fatigue over time. Methods: This 24-month, wide-scale intervention implements a randomized controlled trial (RCT) to evaluate the impact of four variants of a mHealth intervention versus a control group. Our sample comprises adult patients (>15 years of age) undergoing antiretroviral therapy with access to mobile phone services. Multivariate regression analysis will be used to analyze the effect of the intervention on the study population. Data collection is done at baseline and three follow-up waves 6, 12, and 24 months after the intervention starts. Results: The targeted 3800 patients were recruited between February 2015 and May 2015. But political uncertainty delayed the launch of the intervention until October 2015. Data analysis has not yet started. The first follow-up data collection started in April 2016. To the best of our knowledge, this is the first research that explores the effects of mobile message reminders using a wide-spread sample across an entire nation over a 2-year horizon, especially in a Francophone African country. Conclusions: We hypothesize that the interventions have a positive impact on retention in care and adherence to ART schemes and that a more sluggish disease progression will be observed in the short run. However, these benefits may fade out in the long run. The study expects to advance the research on how long mHealth interventions remain effective and when fatigue sets in the context of wide-scale interventions. This information will be useful in designing future wide-scale mHealth interventions in developing countries.

  • MIRROR laptop/bench. Source and copyright: the authors.

    A Cross-Sectional Comparison of Druggable Mutations in Primary Tumors, Metastatic Tissue, Circulating Tumor Cells, and Cell-Free Circulating DNA in Patients...


    Background: Characterization of the driver mutations in an individual metastatic breast cancer (MBC) patient is critical to selecting effective targeted therapies. Currently, it is believed that the limited efficacy of many targeted drugs may be due to the expansion of drug resistant clones with different genotypes that were already present in the primary tumor. Identifying the genomic alterations of these clones, and introducing combined or sequential targeted drug regimens, could lead to a significant increase in the efficacy of currently available targeted therapies. Objective: The primary objective of this study is to assess the concordance/discordance of mutations between the primary tumor and metastatic tissue in MBC patients. Secondary objectives include comparing the genomic profiles of circulating tumor cells (CTCs) and circulating free DNA (cfDNA) from peripheral blood with those of the primary tumor and metastatic tissue for each patient, evaluating these mutations in the signaling pathways that are relevant to the disease, and testing the feasibility of introducing liquid biopsy as a translational laboratory tool in clinical practice. Methods: The multicenter, transversal, observational MIRROR study is currently ongoing in three participating hospitals. All consecutive patients with MBC confirmed by radiologic findings will be screened for eligibility, either at first relapse or if tumor regrowth occurs while on treatment for metastatic disease. Results: Patient recruitment is currently ongoing. To date, 41 patients have a complete set of tissue samples available (plasma, CTCs, and formalin-fixed, paraffin-embedded primary tumor and metastatic tumor). However, none of these samples have undergone nucleic acids extraction or targeted deep sequencing. Conclusions: The results of this study may have a significant influence on the practical management of patients with MBC, and may provide clues to clinicians that lead towards a better stratification of patients, resulting in more selective and less toxic treatments. Additionally, if genomic mutations found in metastatic tissues are similar to those detected in CTCs and/or cfDNA, liquid biopsies could prove to be a more convenient, non-invasive, and easily accessible source of genomic material for the analysis of mutations and other genomic aberrations in MBC. Trial Registration: NCT02626039; (Archived by WebCite at

  • HHP device. Source and copyright: the authors.

    An Exploratory Clinical Trial of a Novel Treatment for Giant Congenital Melanocytic Nevi Combining Inactivated Autologous Nevus Tissue by High Hydrostatic...


    Background: Giant congenital melanocytic nevi (GCMNs) are large brown to black skin lesions that appear at birth and are associated with a risk of malignant transformation. It is often difficult to reconstruct large full-thickness skin defects after the removal of GCMNs. Objective: To overcome this difficulty we developed a novel treatment to inactivate nevus tissue and reconstruct the skin defect using the nevus tissue itself. For this research, we designed an exploratory clinical study to investigate the safety and efficacy of a novel treatment combining the engraftment of autologous nevus tissue inactivated by high hydrostatic pressurization with a cultured epidermal autograft (CEA). Methods: Patients with congenital melanocytic nevi that were not expected to be closed by primary closure will be recruited for the present study. The target number of nevi is 10. The full-thickness nevus of the target is removed and pressurized at 200 MPa for 10 minutes. The pressurized and inactivated nevus is sutured to the original site. A small section of the patient’s normal skin is taken from around the nevus region and a CEA is prepared after a 3-week culturing process. The CEA is then grafted onto the engrafted inactivated nevus at four weeks after its retransplantation. The primary endpoint is the engraftment of the CEA at 8 weeks after its transplantation and is defined as being engrafted when the engraftment area of the inactivated nevus is 60% or more of the pretransplantation nevus area and when 80% or more of the transplanted inactivated nevus is epithelialized. Results: The study protocol was approved by the Institutional Review Board of Kansai Medical University (No. 1520-2, January 5, 2016: version 1.3). The study opened for recruitment in February 2016. Conclusions: This protocol is designed to show feasibility in delivering a novel treatment combining the engraftment of inactivated autologous nevus tissue and CEA. This is the first-in-man clinical trial of this treatment, and it should be a promising treatment of patients suffering from GCMN. Trial Registration: University Hospital Medical Information Network: UMIN000020732; (Archived by WebCite at

  • Image source and copyright: the authors. Permission to use under Creative Commons License.

    Predicting Negative Emotions Based on Mobile Phone Usage Patterns: An Exploratory Study


    Background: Prompt recognition and intervention of negative emotions is crucial for patients with depression. Mobile phones and mobile apps are suitable technologies that can be used to recognize negative emotions and intervene if necessary. Objective: Mobile phone usage patterns can be associated with concurrent emotional states. The objective of this study is to adapt machine-learning methods to analyze such patterns for the prediction of negative emotion. Methods: We developed an Android-based app to capture emotional states and mobile phone usage patterns, which included call logs (and use of apps). Visual analog scales (VASs) were used to report negative emotions in dimensions of depression, anxiety, and stress. In the system-training phase, participants were requested to tag their emotions for 14 consecutive days. Five feature-selection methods were used to determine individual usage patterns and four machine-learning methods were tested. Finally, rank product scoring was used to select the best combination to construct the prediction model. In the system evaluation phase, participants were then requested to verify the predicted negative emotions for at least 5 days. Results: Out of 40 enrolled healthy participants, we analyzed data from 28 participants, including 30% (9/28) women with a mean (SD) age of 29.2 (5.1) years with sufficient emotion tags. The combination of time slots of 2 hours, greedy forward selection, and Naïve Bayes method was chosen for the prediction model. We further validated the personalized models in 18 participants who performed at least 5 days of model evaluation. Overall, the predictive accuracy for negative emotions was 86.17%. Conclusion: We developed a system capable of predicting negative emotions based on mobile phone usage patterns. This system has potential for ecological momentary intervention (EMI) for depressive disorders by automatically recognizing negative emotions and providing people with preventive treatments before it escalates to clinical depression.

Citing this Article

Right click to copy or hit: ctrl+c (cmd+c on mac)

Latest Submissions Open for Peer-Review:

View All Open Peer Review Articles
  • Safety, acceptability and use of a telephone application, BlueIce, for young people who self-harm: protocol for an open Phase 1 trial.

    Date Submitted: Aug 21, 2016

    Open Peer Review Period: Aug 24, 2016 - Sep 7, 2016

    Background: Up to 18% of adolescents will engage in an act of self-harm before young adulthood. Of those who self-harm, half will harm more than once. 1 in 8 acts of self-harm result in a presentation...

    Background: Up to 18% of adolescents will engage in an act of self-harm before young adulthood. Of those who self-harm, half will harm more than once. 1 in 8 acts of self-harm result in a presentation to hospital with most acts occurring in private. Mobile apps may provide a way of supporting young people at times of distress. Young people are familiar with, and regular users of technology with 90% of young people aged 15 having a smart phone. . Objective: This is a proof of concept study designed to assess the safety, acceptability, feasibility and usability of a telephone app, BlueIce, with young people who are self-harming Methods: In this phase 1 open trial we will evaluate BlueIce, a telephone app developed and co-produced with young people with lived experience of self-harm. BlueIce includes a mood monitoring diary, selection of mood lifting techniques based on cognitive behaviour therapy and dialectical behaviour therapy and direct access to emergency telephone numbers. We will recruit young people (n=20) attending specialist child and adolescent mental health services with a current or past history of self-harm to try BlueIce as an adjunct to their usual care. Questionnaires and interviews will be conducted at baseline, post familiarisation (2 weeks) and at follow-up, 12 weeks after the baseline assessment. We will assess safety, app use, acceptability and feasibility of use within a clinical setting. Results: The study is currently recruiting. Conclusions: This study is the first to evaluate an app developed with young people for young people who self-harm. It will determine whether BlueIce is acceptable, how often it is used and whether it is safe and does not have any unintentional adverse effects. This information will determine whether a feasibility trial to test recruitment, randomisation, retention and appropriate outcome measures should be pursued.

  • Use of eHealth and provider-based health services by patients with diabetes mellitus: protocol for a cross-sectional study

    Date Submitted: Aug 22, 2016

    Open Peer Review Period: Aug 23, 2016 - Sep 1, 2016

    Background: The prevalence of diabetes and the use of eHealth is increasing. People with diabetes are in need of frequent monitoring and follow-up of health parameters, and eHealth services can be of...

    Background: The prevalence of diabetes and the use of eHealth is increasing. People with diabetes are in need of frequent monitoring and follow-up of health parameters, and eHealth services can be of great significance in this regard. However, little is known about the extent to which different kinds of eHealth tools are used, and how the use of eHealth is associated with the use of provider-based health care services among people with diabetes. Objective: The primary objective of this study is to investigate the use of eHealth and its association with the use of provider-based health care services. The secondary objectives include investigations of which eHealth services that are used (apps, searching engines, video services, social media), investigations of the relationship between socio-economic status and the use of different eHealth tools, whether the use of eHealth is discussed in the clinical encounter, and whether it might lead to or prevent doctor visits and referrals. Methods: We will conduct cross-sectional studies based on self-reported questionnaire data from the population-based seventh Tromsø Study. Participants will be diabetic patients aged 40 years and over. According to our estimates, around 1050 participants will be eligible for inclusion. Data will be analysed by descriptive statistics, chi-square tests, and univariable and multivariable logistic regressions. Results: The grant proposal was approved by The Northern Norway Health Authorities November 23, 2015 (HST 1306-16). Recruitment of participants for The Tromsø Study started in 2015 and will continue throughout 2016. The project period for this particular project started July 1, 2016. Conclusions: The project may gain benefits for patients, health care providers, hospitals, and society as a whole. Benefits are related to improvement of prevention services, health, experience of care services, self-management tools and services, organisational structures, a more efficient use of specialist care, allocation of recourses, and a better understanding of how to meet the challenges from the increasing prevalence of diabetes. The project do have a potential of generalisation to other groups with chronic disease.

  • Supporting the delivery of total knee replacements care for both patients and their clinicians with a mobile app and online tool: study protocol

    Date Submitted: Aug 19, 2016

    Open Peer Review Period: Aug 19, 2016 - Sep 2, 2016

    Background: Total knee replacement (TKR) surgeries have increased in recent years. Exercise programs and other interventions following surgery can facilitate the recovery process. With limited clinici...

    Background: Total knee replacement (TKR) surgeries have increased in recent years. Exercise programs and other interventions following surgery can facilitate the recovery process. With limited clinician contact time, patients of TKR have a substantial burden of self-management and limited communication with their care team, thus often fail to implement an effective rehabilitation plan. Objective: We have developed a digital orthopedic rehabilitation platform that comprises a mobile phone application (app), a wearable activity tracker, and a clinical web portal; in order to address the self- management tasks in addition to engaging patients by encouraging adherence to, and completion of rehabilitation. The study will determine the efficacy of the TKR platform in delivering: a) information and assistance to patients in their preparation and recovery from TKR surgery; and b) a portal for clinician care teams (e.g. surgeons and physiotherapists) to remotely support and monitor patient progress. Methods: The study will evaluate the TKR platform through a randomized controlled trial (RCT), conducted at multiple sites in a number of states in Australia, with 262 patients undergoing TKR surgery, and running for 13 months for each patient. Participants will be randomized to either a control group or the intervention group; both receiving usual care as provided by their surgeon or hospital. The intervention group will receive the app and wearable activity tracker in addition to usual care. All participants will be assessed at four different time points over one year (4 weeks before surgery, immediately before surgery, 12 weeks after surgery, and 52 weeks after surgery). The primary outcome measure is the Oxford Knee Score (OKS). Secondary outcome measures include, Quality of Life (SF-36), depression, anxiety and stress (DASS21), self-motivation, self-efficacy , and the level of satisfaction with the knee surgery and care delivery. The study will also collect quantitative usage data related to for all components (app, activity tracker, and portal) of the TKR platform, and qualitative data on the perceptions of the platform as a tool for patients, carers, and clinicians. Finally, an economical evaluation of the impact of the platform will be conducted. Results: N/A Conclusions: The TKR platform is designed to provide flexibility in care delivery, and increased engagement with rehabilitation services. This trial will investigate the efficacy and effectiveness of the platform, service satisfaction and allow us to model the economic benefits of the provision of digital services. Clinical Trial: The trial has been registered in the Australian New Zealand Clinical Trials Registry (ANZCTR) with number ACTRN12616000504415.

  • A Remote Feasibility Study Protocol Using A Consumer Wearable Device

    Date Submitted: Aug 19, 2016

    Open Peer Review Period: Aug 19, 2016 - Sep 2, 2016

    Background: As technology increasingly becomes an integral part of everyday life, many individuals are choosing to use wearable technology such as Fitbit to track their daily physical activity and oth...

    Background: As technology increasingly becomes an integral part of everyday life, many individuals are choosing to use wearable technology such as Fitbit to track their daily physical activity and other health-related goals. Researchers would benefit from being able to remotely access the physical activity and health data, without meeting face-to-face with participants and avoiding the high cost of providing consumer wearables to participants for the study duration. Objective: The present study will seek to test the feasibility of remotely collecting physical activity and health-related data from participants without ever meeting them face-to-face. Methods: To assess feasibility of the proposed protocol, 30 participants will be recruited on Mechanical Turk Prime (Mturk Prime) and asked to complete a short online questionnaire. They will also be asked to connect their personal Fitbit device to an online third party software system, called Fitabase, which will allow access to 1 month’s retrospective data and 1 month’s prospective data from the date of sign-up. Results: The feasibility of the protocol will be determined at the end of data collection. Conclusions: The present study will test a protocol whereby respondents connect their own personal consumer wearable device to an online data downloading software system, without the need to meet face-to-face with the research team, or provide them with study-owned devices.

  • Adjuvant Endocrine Therapy in Breast Cancer: A Novel E-Health Approach in Optimizing Treatment for Seniors (OPTIMUM Study): A two-group controlled comparison pilot study

    Date Submitted: Aug 19, 2016

    Open Peer Review Period: Aug 19, 2016 - Sep 2, 2016

    Background: In women with hormone receptor positive (HR+) breast cancer, adjuvant endocrine therapy (AET) is associated with a significant survival advantage. Nonadherence is a particular challenge in...

    Background: In women with hormone receptor positive (HR+) breast cancer, adjuvant endocrine therapy (AET) is associated with a significant survival advantage. Nonadherence is a particular challenge in older women, even though they stand to benefit the most from AET. Therefore, a novel e-health tool (OPTIMUM) that integrates real-time analysis of health administrative claims data was developed to provide point-of-care decision support for clinicians. Objective: 1) To determine the effectiveness of a patient-specific, real-time e-health alerts delivered at point-of-care in reducing rates of AET discontinuation and to understand patient-level factors related to AET discontinuation. 2) To assess integration of e-health alerts regarding deviations from best practices in administration of AET by cancer care teams. Methods: A prospective, two group controlled comparison pilot study will be conducted at two urban, McGill University-affiliated hospitals, the Royal Victoria Hospital and St. Mary’s Hospital. A minimum of 43 patients per study arm will be enrolled through site-level allocation. Follow-up is 1.5 years. Healthcare professionals at the intervention site will have access to the e-health tool which will report to them in real-time: medical events with known associations to AET discontinuation, AET adherence monitor, and a discontinuation alert. Results: This protocol has been approved and funded by the Canadian Institutes of Health Research. The study will evaluate site-level differences between AET discontinuation and AET adherence, and asses care team actions at the intervention site. Participant enrollment into this project is expected to start September 2016 with primary data to present by June 2018. Conclusions: This study will offer an opportunity to verify the feasibility of integrating an e-health tool that aims to improve the long-term management of the breast cancer in a high-risk population, by allowing more timely intervention to prevent or rapidly address AET discontinuation. Clinical Trial: We submitted our protocol to on August 16, 2016. We will provide you with the clinical registry number as soon as we receive it.

  • Feasibility of ecological momentary assessment of daily text messaging social interaction and substance use among young adult sexual minority Black men

    Date Submitted: Aug 19, 2016

    Open Peer Review Period: Aug 19, 2016 - Sep 2, 2016

    Background: Young adult sexual minority Black men bear the greatest burden of new HIV infections among sexual minority men in the United States. Ecological momentary assessment (EMA) methods, such as...

    Background: Young adult sexual minority Black men bear the greatest burden of new HIV infections among sexual minority men in the United States. Ecological momentary assessment (EMA) methods, such as short message service (SMS) texting, may serve as a viable counterpart to retrospective evaluation methods by using real-time data collection to assess behaviors as they occur in the environment. Limited research has focused on the use of EMA among young adult sexual minority Black men. Objective: The objective of this pilot study was to assess the feasibility of using text messaging as a method of EMA to examine daily text messaging social interaction and substance use behaviors among young adult sexual minority Black men. Methods: Participants were recruited through flyers and snowball sampling during the spring and summer of 2015 at a community-based organization in Washington, DC, serving sexual minority men. Eligible participants were enrolled in a one-time in-person study visit that consisted of: informed written consent to participate in the study, a self-administered survey, a semi-structured qualitative interview and enrollment and training in EMA data collection. The day after the study visit, a random prompt survey consisting of eight questions was texted to participants on their personal cell phones three times a day over a 14-day data collection period assessing mood, social interaction via text messaging and substance use. Results: EMA feasibility was tested with 25 participants between the ages of 21 to 25 (M=23.48, SD=1.5). There were 104 total days of EMA observation and the retention rate was 72%. Participants responded to the random prompt surveys with a 57.3% survey compliance rate, providing a total of 544 completed surveys. The overall mean response time to complete a survey was 6.1 minutes. Conclusions: The use of an EMA protocol in this relatively underrepresented and understudied population has the potential to be a very useful research tool for future studies. This pilot study demonstrated that young adult sexual minority Black men are willing to participate in health, technology and innovation research and use text messaging to report their behavior. Additional research is needed on how to increase survey compliance.