This systematic review protocol is designed to provide a comprehensive and transparent plan for evaluating the effectiveness of telemedicine in diabetes management. Following these steps will ensure rigor and reduce bias in the review process.

Systematic Review Protocol: Effectiveness of Telemedicine for Diabetes Management

Protocol Registration: This protocol will be registered with PROSPERO (International Prospective Register of Systematic Reviews) prior to commencing the systematic review process (i.e., before screening studies). The registration number will be included here once obtained.

Review Team:

• [Your Name/Team Member 1]


• [Your Name/Team Member 2]


• [Your Name/Team Member 3 - if applicable, e.g., for arbitration]

1. Introduction and Background

Diabetes mellitus is a chronic metabolic disorder affecting millions worldwide, leading to severe complications if not properly managed. Effective management typically involves regular monitoring of blood glucose, medication adherence, lifestyle modifications, and frequent interactions with healthcare providers. Telemedicine, which utilizes telecommunication technologies to provide healthcare services remotely, offers a promising approach to enhance diabetes management, improve access to care, and potentially reduce healthcare costs. This systematic review aims to synthesize the current evidence on the effectiveness of telemedicine interventions for adults with diabetes.

Objectives:
The primary objective of this systematic review is to assess the effectiveness of telemedicine interventions compared to standard care or alternative telemedicine modalities in improving clinical, behavioral, and patient-reported outcomes in adults with diabetes.

2. PICO Question Formulation

PICO Question:
In Population (adults with diagnosed diabetes – Type 1, Type 2, or gestational diabetes), what is the effectiveness of Intervention (telemedicine interventions, e.g., remote monitoring, virtual consultations, mobile health apps, web-based platforms, tele-coaching, or a combination) compared to Comparison (standard diabetes care – e.g., face-to-face consultations, routine self-management education without telemedicine components – or alternative telemedicine modalities), on Outcomes (including glycemic control [HbA1c], blood pressure, lipid profiles, weight management, diabetes-related complications, healthcare utilization, quality of life, and patient satisfaction)?

Breakdown:

• P (Population): Adults (≥18 years) with diagnosed diabetes (Type 1 Diabetes Mellitus, Type 2 Diabetes Mellitus, or Gestational Diabetes Mellitus).


• I (Intervention): Telemedicine interventions, broadly defined to include technologies and services that deliver healthcare remotely. Examples include:


• Remote monitoring (e.g., continuous glucose monitoring [CGM] data transmitted remotely, blood pressure monitoring, weight scales).


• Virtual consultations (e.g., video calls, secure messaging with healthcare providers).


• Mobile health (mHealth) applications (e.g., apps for self-management, medication reminders, diet tracking).


• Web-based platforms (e.g., patient portals, online educational modules).


• Tele-coaching or tele-education (e.g., remote health coaching, group education sessions via video conference).


• Phone calls (structured interventions beyond routine check-ups).


• Hybrid models combining several of these.


• C (Comparison):


• Standard/usual diabetes care (e.g., routine face-to-face consultations, conventional self-management education, usual care without specific telemedicine components).


• Another telemedicine modality (e.g., comparing an app-based intervention to a video-consultation intervention).


• O (Outcomes):


• Primary Outcome:


• Glycemic control (e.g., Glycated Hemoglobin A1c [HbA1c] levels).


• Secondary Outcomes:


• Cardiovascular risk factors (e.g., systolic and diastolic blood pressure, LDL cholesterol, HDL cholesterol, triglycerides).


• Anthropometric measures (e.g., body weight, BMI).


• Diabetes-related complications (e.g., retinopathy, nephropathy, neuropathy, cardiovascular events, amputations, hypoglycemia incidence).


• Healthcare utilization (e.g., emergency department visits, hospitalizations, primary care visits, medication changes).


• Patient-reported outcomes (PROs) such as:


• Quality of life (QoL).


• Patient satisfaction with care.


• Self-efficacy/self-management behaviors.


• Diabetes distress.


• Cost-effectiveness (if reported).

3. Comprehensive Search Strategy

The search strategy will be developed systematically using a combination of keywords and controlled vocabulary (e.g., MeSH terms for PubMed, Emtree terms for Embase). It will be adapted for each database's specific syntax.

Databases to be searched:

• PubMed (MEDLINE)


• Embase


• Cochrane Central Register of Controlled Trials (CENTRAL) within The Cochrane Library


• CINAHL (Cumulative Index to Nursing and Allied Health Literature)


• Web of Science (Core Collection)


• Scopus

• Human studies only.


• English language only.


• No date restrictions (to capture all available evidence).


• Randomized Controlled Trials (RCTs) will be prioritized using specific study type filters where available (e.g., "randomized controlled trial" as a publication type or MeSH term).

• Population (Diabetes):


• "Diabetes Mellitus"[Mesh] OR "Diabetes Mellitus, Type 1"[Mesh] OR "Diabetes Mellitus, Type 2"[Mesh] OR "Gestational Diabetes"[Mesh] OR diabetes[tiab] OR diabetic[tiab] OR T1DM[tiab] OR T2DM[tiab] OR GDM[tiab]


• Intervention (Telemedicine):


• "Telemedicine"[Mesh] OR "Telehealth"[Mesh] OR "Mobile Applications"[Mesh] OR telemedicine[tiab] OR telehealth[tiab] OR eHealth[tiab] OR mHealth[tiab] OR mobile health[tiab] OR remote monitoring[tiab] OR virtual consultation[tiab] OR teleconsultation[tiab] OR telecoaching[tiab] OR web-based[tiab] OR internet-based[tiab] OR mobile app[tiab] OR app[tiab] OR digital health[tiab] OR remote care[tiab] OR connected health[tiab] OR tele-education[tiab] OR videoconference[tiab] OR SMS[tiab] OR text message[tiab] OR wearable device[tiab]


• Study Design (RCTs):


• "Randomized Controlled Trial"[pt] OR "Controlled Clinical Trial"[pt] OR randomized[tiab] OR randomised[tiab] OR RCT[tiab] OR trial[tiab]

( ("Diabetes Mellitus"[Mesh] OR "Diabetes Mellitus, Type 1"[Mesh] OR "Diabetes Mellitus, Type 2"[Mesh] OR "Gestational Diabetes"[Mesh] OR diabetes[tiab] OR diabetic[tiab] OR T1DM[tiab] OR T2DM[tiab] OR GDM[tiab]) )
AND
( ("Telemedicine"[Mesh] OR "Telehealth"[Mesh] OR "Mobile Applications"[Mesh] OR telemedicine[tiab] OR telehealth[tiab] OR eHealth[tiab] OR mHealth[tiab] OR "mobile health"[tiab] OR "remote monitoring"[tiab] OR "virtual consultation"[tiab] OR teleconsultation[tiab] OR telecoaching[tiab] OR "web-based"[tiab] OR "internet-based"[tiab] OR "mobile app"[tiab] OR app[tiab] OR "digital health"[tiab] OR "remote care"[tiab] OR "connected health"[tiab] OR "tele-education"[tiab] OR videoconference[tiab] OR SMS[tiab] OR "text message"[tiab] OR "wearable device"[tiab]) )
AND
( ("Randomized Controlled Trial"[pt] OR "Controlled Clinical Trial"[pt] OR randomized[tiab] OR randomised[tiab] OR RCT[tiab] OR trial[tiab]) )

Additional Search Methods:

• Reference lists of included studies and relevant systematic reviews will be screened for additional eligible studies.


• Key journals in the field (e.g., Diabetes Care, Journal of Medical Internet Research, Telemedicine and e-Health) will be hand-searched if initial searches yield limited results.

4. Inclusion and Exclusion Criteria

Types of Studies:

• Included: Randomized Controlled Trials (RCTs).


• Excluded: Quasi-RCTs, non-randomized studies (e.g., cohort studies, case-control studies, observational studies, qualitative studies), reviews, editorials, commentaries, conference abstracts without full text, protocols without results, animal studies, in vitro studies.

• Included: Adults (≥18 years old) with a formal diagnosis of any type of diabetes (Type 1, Type 2, or gestational diabetes).


• Excluded: Children/adolescents (<18 years), individuals without a diabetes diagnosis, healthy volunteers, participants with only pre-diabetes.

• Included: Telemedicine interventions (as broadly defined in the PICO question, e.g., remote monitoring, virtual consultations, mobile health apps, web-based platforms, tele-coaching, or a combination). The intervention must have a clear telemedicine component aimed at diabetes management.


• Excluded: Interventions primarily focused on general health promotion without specific diabetes management, face-to-face interventions only, or interventions where the telemedicine component is not clearly described or is negligible.

• Included: Standard/usual diabetes care (e.g., routine face-to-face consultations, conventional self-management education, usual care without specific telemedicine components) OR alternative telemedicine modalities.


• Excluded: No comparison group (e.g., uncontrolled before-and-after studies).

• Included: Studies reporting at least one primary outcome (HbA1c) or any of the specified secondary outcomes.


• Excluded: Studies that only report process measures (e.g., number of logins) without clinical or patient-reported outcomes.

Publication Status: Peer-reviewed journal articles.

5. Study Selection Process

• De-duplication: All search results will be imported into a reference management software (e.g., EndNote, Zotero, Rayyan) and duplicates will be removed.


• Title and Abstract Screening: Two independent reviewers will screen the titles and abstracts of all identified records against the inclusion and exclusion criteria. Records clearly not meeting the criteria will be excluded. Any discrepancies will be resolved by discussion between the two reviewers or, if necessary, by a third reviewer.


• Full-Text Screening: The full text of potentially eligible articles will be retrieved. Two independent reviewers will then critically assess these articles against the inclusion and exclusion criteria. Reasons for exclusion at the full-text stage will be recorded. Discrepancies will be resolved by discussion or by a third reviewer.


• Reporting: A PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram will be used to illustrate the study selection process.

6. Quality Assessment (Risk of Bias)

The methodological quality and risk of bias of all included Randomized Controlled Trials (RCTs) will be independently assessed by two reviewers using the Cochrane Risk of Bias tool for Randomized Trials (RoB 2.0).

RoB 2.0 Domains:
The tool assesses bias across five domains:

• Bias arising from the randomization process.


• Bias due to deviations from intended interventions (effect of assignment to intervention).


• Bias due to missing outcome data.


• Bias in measurement of the outcome.


• Bias in selection of the reported result.

• For each domain, studies will be categorized as "low risk of bias," "some concerns," or "high risk of bias."


• Discrepancies between reviewers will be resolved through discussion or, if consensus cannot be reached, by a third reviewer.


• The results of the risk of bias assessment will be presented in tables and graphs within the review and will be considered during data synthesis and interpretation.

7. Data Extraction and Synthesis

Data Extraction:
A standardized, pre-piloted data extraction form will be used to extract relevant information from the included studies. Two independent reviewers will extract data, and discrepancies will be resolved by discussion or by a third reviewer.
The following data will be extracted:

• Study Characteristics: Author(s), year of publication, country, study design, funding source, duration of intervention and follow-up.


• Participant Characteristics: Total number of participants, age (mean/SD), gender distribution, type of diabetes (Type 1, Type 2, GDM), duration of diabetes, baseline HbA1c, comorbidities, inclusion/exclusion criteria.


• Intervention Details: Specific type of telemedicine intervention (e.g., app, video, remote monitoring), components (e.g., education, feedback, coaching), frequency and duration of interaction, personnel involved, technology used.


• Comparator Details: Description of standard care or alternative telemedicine intervention.


• Outcome Data:


• For continuous outcomes (e.g., HbA1c, blood pressure, weight): Mean and standard deviation (or median and interquartile range) at baseline and end-of-intervention/follow-up, or mean change from baseline for both intervention and control groups.


• For dichotomous outcomes (e.g., incidence of complications): Number of events and total participants in each group.


• Time points of outcome assessment.


• Measures of effect (if reported by study, e.g., confidence intervals).


• Risk of Bias Assessment: Summary of RoB 2.0 findings for each study.

• Qualitative (Narrative) Synthesis:


• If meta-analysis is not appropriate due to substantial clinical or methodological heterogeneity, a narrative synthesis will be conducted. This will involve describing the characteristics of included studies, interventions, populations, and outcomes, highlighting similarities and differences.


• The narrative will systematically group studies based on key characteristics (e.g., type of telemedicine, type of diabetes, duration of intervention) to identify patterns and potential explanations for observed effects.


• Quantitative Synthesis (Meta-analysis):


• If studies are sufficiently homogeneous in terms of PICO elements and outcome measures, a meta-analysis will be performed using RevMan (Review Manager) software or R statistical software.


• Measures of Effect:


• For continuous outcomes (e.g., HbA1c, blood pressure, weight): Mean Difference (MD) or Standardized Mean Difference (SMD) will be calculated with 95% confidence intervals (CI). MD will be used when outcomes are measured on the same scale; SMD will be used when outcomes are measured on different scales.


• For dichotomous outcomes (e.g., complications, hospitalizations): Risk Ratios (RR) or Odds Ratios (OR) will be calculated with 95% CI.


• Heterogeneity: Statistical heterogeneity will be assessed using the I² statistic (quantifying the proportion of total variation across studies due to heterogeneity rather than chance) and the Chi-squared test (with p < 0.10 indicating significant heterogeneity).


• If I² < 40%, heterogeneity is considered low, and a fixed-effect model may be used.


• If I² ≥ 40%, heterogeneity is considered substantial, and a random-effects model will be used, as it accounts for both within-study and between-study variance.


• Subgroup Analysis: If sufficient data are available, subgroup analyses will be conducted to explore potential sources of heterogeneity based on:


• Type of diabetes (Type 1 vs. Type 2 vs. Gestational).


• Specific telemedicine modality (e.g., app-based vs. video consultations vs. remote monitoring).


• Duration of intervention (<6 months vs. 6-12 months vs. >12 months).


• Baseline HbA1c levels (e.g., controlled vs. uncontrolled).


• Geographic region/healthcare setting.


• Sensitivity Analysis: To assess the robustness of the findings, sensitivity analyses will be performed by:


• Excluding studies with high risk of bias.


• Excluding studies with small sample sizes.


• Excluding studies funded by industry.


• Publication Bias: Funnel plots and Egger's test (if there are at least 10 studies in a meta-analysis) will be used to assess potential publication bias.

8. Registration on PROSPERO

This protocol will be registered with PROSPERO (International Prospective Register of Systematic Reviews) prior to the commencement of screening studies. The registration number will be obtained and included in the final review. Registering the protocol ensures transparency, reduces duplication of efforts, and allows for public access to the planned review methodology. Any significant deviations from this protocol will be documented and justified in the final systematic review report.

Reporting Guidelines:
This systematic review will adhere to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for reporting.