If you’re launching a digital therapeutic or navigating MedTech commercialization in 2026, you’ve probably noticed something frustrating: the gap between clinical trial success and real-world adoption keeps widening. Your product works. The data’s solid. But payers want proof beyond RCTs, providers hesitate to prescribe, and you’re flying blind on actual utilization patterns once you launch.
Here’s what I’ve observed working with pharmaceutical and MedTech teams across Central Europe and the broader European market — the companies gaining traction aren’t just relying on traditional clinical evidence anymore. They’re integrating aggregated all-payer claims data with emerging synthetic datasets to generate the kind of real-world evidence (RWE) that actually moves the needle on reimbursement decisions and market access strategies.
And honestly? The timing couldn’t be better. Germany’s DiGA program has expanded to 59-64 reimbursed apps, the U.S. just rolled out new CMS billing codes for digital mental health, and recent NEJM AI research confirms what we’ve suspected — medical AI device adoption is growing, but it’s slower and more uneven than anyone expected.
Why Digital Therapeutics and MedTech Rely on Claims-Based Analytics
The digital therapeutics adoption RWD landscape has fundamentally shifted. Five years ago, you could maybe get away with a well-designed pivotal trial and some enthusiastic KOL endorsements. Not anymore.
Today’s market access teams need to answer questions like: Which patient populations are actually receiving our DTx prescription? How does real-world persistence compare to trial data? Are there geographic disparities in adoption? What’s the actual impact on downstream healthcare utilization and costs?
Claims data — particularly aggregated medical and pharmacy claims from statutory health insurance providers — answers these questions because it captures what actually gets reimbursed. Every billed procedure, every diagnosis code (ICD-10-GM in Germany), every prescription (coded via ATC classification), every healthcare encounter across inpatient, outpatient, and ambulatory settings.
Providers like IQVIA’s PharMetrics Plus, Komodo Health, and Definitive Healthcare’s Atlas All-Payor Claims have built their businesses on this foundation. But what makes claims data particularly valuable for DTx and MedTech is the longitudinal nature — you’re not just seeing a snapshot, you’re tracking patient journeys over months or years.
The Fundamental Value Proposition
When you’re working with health technology adoption data, you need three things: breadth of coverage, depth of detail, and compliance with privacy regulations. Aggregated claims datasets deliver all three.
Breadth means population-level insights. In Germany, for instance, statutory health insurance (GKV) claims cover approximately 90% of the insured population — roughly 73 million lives. That’s not a convenience sample. That’s near-comprehensive visibility into treatment patterns, disease burden, and healthcare utilization across federal states.
Depth means you can map treatment pathways from diagnosis through intervention, follow-up care, and outcomes. You see the comorbidities. You track switches between therapies. You identify care gaps. Kim et al.’s 2024 framework in the Journal of Medical Internet Research emphasizes this longitudinal perspective as critical for digital therapeutics real-world evidence generation.
And compliance? Well, that’s where aggregation and anonymization become absolutely essential. You’re working with de-identified data that’s been properly processed to meet GDPR Article 9 requirements for special category health data, plus Germany’s BDSG (Federal Data Protection Act) and the broader EU regulatory framework.
Tracking Adoption Patterns: What the Data Actually Shows
Now here’s where things get interesting — and maybe a bit uncomfortable if you’re a DTx manufacturer expecting smooth sailing after regulatory approval.
The adoption patterns we’re seeing in behavioral health analytics, RWD, and remote patient monitoring datasets tell a story of potential hampered by persistent barriers. Even in Germany, where the DiGA program offers arguably the most progressive digital therapeutics reimbursement pathway globally, a recent 2024 analysis by Goeldner and Gehder shows physician prescribing rates hovering around 31%.
Think about that. You’ve got full reimbursement. Regulatory clearance. Evidence of efficacy. And still… only about one-third of physicians are actually prescribing these solutions.
What Claims Data Reveals About Utilization
When we analyze MedTech patient journey analytics through aggregated claims, several patterns emerge consistently:
Geographic Disparities: Adoption isn’t uniform. Urban centers with academic medical centers show higher uptake. Rural regions lag significantly. Federal state-level analysis in Germany reveals variations that correlate with provider density, digital infrastructure, and local payer policies.
Provider Hesitancy: Claims reveal which specialties embrace digital interventions and which remain skeptical. For prescription digital therapeutics treating opioid use disorder, Maricich et al.’s real-world evidence study documented meaningful clinical outcomes — but adoption required intensive provider education and workflow integration support.
Patient Persistence Gaps: Initial prescription doesn’t equal sustained engagement. Claims-based DTx insights show drop-off rates that often exceed what controlled trials suggested. For chronic insomnia digital therapeutics, Forma and colleagues documented long-term healthcare resource utilization patterns that revealed both the promise and the challenges of maintaining patient engagement.
Reimbursement Code Challenges: Early-stage MedTech products often lack dedicated billing codes, leading to undercapture in claims databases. This creates a chicken-and-egg problem — you need utilization data to justify dedicated codes, but without codes, utilization is poorly tracked.
The Germany DiGA Experience: A Case Study in Real-World Evidence
Germany’s Digital Health Applications (DiGA) program offers a fascinating natural experiment in accelerated market access for digital therapeutics. The fast-track reimbursement pathway — products can be provisionally covered based on plausible evidence, then prove long-term benefit within 12-24 months — seemed revolutionary when launched in 2020.
But Schmidt et al.’s three-year evolution analysis reveals the complexity. As of mid-2024, 59-64 apps hold DiGA status, but many face evidence development delays, and some have been delisted for failing to demonstrate required benefits. The program works — it’s genuinely innovative — but it’s also exposed the difficulty of generating robust real-world evidence quickly.
This is where Germany MedTech reimbursement database access becomes strategically valuable. Claims data lets you track actual prescribing patterns, identify barriers to adoption, and demonstrate value through reduced hospitalizations or improved treatment adherence before your provisional approval window closes.
Bridging the Reimbursement and Commercialization Challenge
Every MedTech market access director I’ve worked with faces the same fundamental challenge: payers want proof of value that goes beyond efficacy. They want health economics data. They want budget impact models. They want evidence that your solution doesn’t just work in controlled settings — it works in the messy reality of clinical practice and actually reduces overall healthcare spending.
Traditional RCTs can’t provide this. They’re too controlled, too short-term, too divorced from real-world care patterns. But aggregated MedTech patient data from claims sources can.
Building the Value Story Payers Actually Need
When you integrate health technology utilization database access into your evidence strategy, you can demonstrate:
Cost-Effectiveness in Practice: Claims reveal downstream impacts. Does your digital therapeutic for diabetes management actually reduce emergency department visits and hospitalizations? Do patients on your remote monitoring platform have fewer acute complications? The medical device claims datasets can answer these questions with statistical rigor.
Treatment Pathway Positioning: Where does your solution fit in the continuum of care? Claims data shows what happens before and after patients receive your intervention. You can identify the patient segments most likely to benefit, the optimal timing for intervention, and the competitive alternatives your solution actually replaces.
Market Sizing and Opportunity Assessment: Before you launch, you need realistic forecasts. Claims-based market sizing uses actual diagnostic prevalence, current treatment patterns, and utilization trends to build bottom-up models. For a digital therapeutic targeting major depressive disorder in Germany, for instance, you can estimate the addressable population by severity level, prior treatment exposure, and comorbidity profiles using aggregated insurance data Germany sources.
The FDA’s updated guidance on real-world evidence for medical devices explicitly recognizes claims data as an acceptable source for regulatory decision-making, provided appropriate study designs and data quality standards are met. This regulatory acceptance opens doors for both U.S. 510(k) submissions and post-market surveillance requirements.
Commercial Analytics That Actually Drive Growth
Beyond reimbursement, claims-based analytics inform commercial strategy in ways that traditional market research simply can’t match.
You can identify high-potential providers and institutions. Which hospitals perform the most relevant procedures? Which physician groups already prescribe similar interventions? Where are the geographic hotspots of unmet need? This intelligence drives territory allocation, sales targeting, and partnership development.
You can track competitive dynamics. When a rival MedTech solution launches, claims data reveals market share shifts in near real-time. You see which segments they’re penetrating, which payers are covering them, and where defensive strategies might be needed.
You can optimize pricing strategy. Real-world utilization patterns — how often devices are used, typical patient duration on therapy, average episode costs — inform pricing models that align with payer willingness-to-pay while maximizing your commercial opportunity.
The Emerging Role of Synthetic Healthcare Datasets
So we’ve established that aggregated claims data provides crucial insights. But there’s a complementary innovation that’s gaining serious traction in 2026: synthetic healthcare datasets in Germany and beyond.
Synthetic data — artificially generated datasets that statistically mirror real claims data while eliminating re-identification risks — addresses several persistent challenges in digital health adoption datasets development.
Why Synthetic Data Matters for DTx and MedTech
The privacy-innovation tension is real. You need granular patient-level data to build sophisticated analytics, train machine learning models, and conduct detailed outcomes research. But GDPR, HIPAA, and other privacy frameworks create legitimate barriers to accessing and sharing such data.
Synthetic data generation — typically using generative adversarial networks (GANs) with differential privacy guarantees — creates datasets that preserve statistical properties and relationships while eliminating individual patient identifiability. Azizi et al.’s comprehensive 2023 review in Nature Digital Medicine outlines the technical approaches and validates the utility for healthcare innovation.
Here’s what this means practically: You can share data with external research collaborators without complex data use agreements. You can build predictive algorithms without privacy review board delays. You can conduct scenario modeling and “what-if” analyses that would be impossible with actual patient data.
Gonzales, Guruswamy, and Smith’s narrative review emphasizes how synthetic datasets enable broader participation in research — smaller organizations without dedicated privacy infrastructure can access realistic healthcare data for algorithm development and validation.
Practical Applications in Digital Therapeutics
For DTx companies, synthetic data solves several pain points:
Algorithm Development and Testing: You’re building a machine learning model to predict which patients will benefit most from your digital intervention. Training on real claims data raises privacy concerns and access barriers. Training on synthetic data that preserves the statistical distribution of diagnoses, treatments, and outcomes? Much cleaner path forward.
Clinical Trial Design Optimization: Before launching an expensive RCT, you can use synthetic datasets to simulate different patient selection criteria, estimate required sample sizes, and model expected effect sizes based on real-world population characteristics. This reduces trial risk and improves efficiency.
Rare Disease Research: When patient populations are small, privacy protections make data sharing nearly impossible. Synthetic data generation can create larger datasets for statistical analysis while protecting the privacy of individual patients. This is particularly relevant for MedTech devices targeting orphan indications.
Multi-Site Research Without Data Sharing: Federated learning approaches combined with synthetic data generation allow institutions to collaborate on research questions without actually exchanging patient records. Each site generates synthetic data locally, researchers analyze across sites, and privacy is preserved.
Current Limitations and Future Directions
I want to be transparent about the limitations here, because this is an evolving field and not a silver bullet.
Synthetic data quality depends entirely on the underlying real data used for generation. If your source claims dataset has biases, missing data, or quality issues, the synthetic version inherits these problems. Validation is essential.
Regulatory acceptance is still developing. While research applications are well-established, using synthetic data for regulatory submissions remains less common. The FDA and EMA are developing frameworks, but this space is moving fast, and guidelines are catching up.
Complex temporal patterns and rare events can be difficult to capture accurately in synthetic data. If you’re studying infrequent outcomes or long-term disease progression, synthetic datasets may not fully represent the variability and nuance of real patient journeys.
That said — the trajectory is clear. Major U.S. agencies like AHRQ have released synthetic datasets (SyH-DR) for research. European regulatory bodies are actively exploring synthetic data applications. The technology is maturing rapidly, and 2026 will likely see expanded adoption across digital health and MedTech sectors.
Overcoming Adoption Barriers with Hybrid Data Approaches
The reality is that no single data source tells the complete story. Claims data excels at capturing reimbursed utilization and healthcare encounters but misses non-covered services, patient-reported outcomes, and detailed clinical parameters. Electronic health records (EHRs) provide clinical depth but lack cross-institutional continuity. Patient-generated data from apps and wearables offers engagement insights but suffers from selection bias and incomplete capture.
The companies successfully navigating digital therapeutics adoption RWD challenges are those implementing hybrid approaches — integrating multiple data sources to build comprehensive patient profiles.
Practical Integration Strategies
Claims + EHR Linkage: When possible, linking de-identified claims data with EHR data creates rich longitudinal profiles. You get the breadth of claims (all care settings, all payers) combined with the clinical depth of EHRs (lab values, vital signs, clinical notes). Privacy-preserving record linkage methodologies — using tokens rather than direct identifiers — make this feasible within regulatory frameworks.
Claims + App Usage Analytics: For DTx products, combining reimbursement data (claims) with actual engagement metrics (app logs) reveals critical insights. You can identify the gap between prescription and active use, understand which patient segments engage most effectively, and correlate usage patterns with clinical outcomes captured in downstream claims.
Claims + Patient-Reported Outcomes: Longitudinal surveys capturing quality of life, symptom severity, and treatment satisfaction complement the utilization patterns visible in claims. This triangulation strengthens evidence packages for payers and provides a fuller understanding of patient experience.
Synthetic Data for Privacy-Preserving Integration: When direct data linkage isn’t feasible due to privacy constraints, synthetic data generation from each source, followed by integration of synthetic datasets, can enable multi-modal analysis while maintaining privacy compliance.
Addressing the Interoperability Challenge
One of the persistent barriers to effective data integration is the fragmented nature of healthcare IT systems. Claims databases use different coding schemes than EHRs. Payer-specific data formats vary. International datasets require harmonization of clinical terminologies.
The good news? Standards are improving. FHIR (Fast Healthcare Interoperability Resources) is gaining adoption as a common framework for healthcare data exchange. The U.S. Trusted Exchange Framework and Common Agreement (TEFCA) is establishing a national interoperability infrastructure. Germany’s Gematik Telematikinfrastruktur is creating standardized health data exchange pathways.
For DTx and MedTech companies, the strategic implication is clear: build your data infrastructure with interoperability in mind from day one. Design your analytics pipelines to ingest multiple data formats. Implement common data models (like OMOP or Sentinel) that facilitate integration. Partner with data providers who prioritize interoperability.
Regulatory and Evidence Requirements: What’s Actually Changing
The regulatory landscape for digital health and MedTech is evolving rapidly, and claims-based analytics sits at the intersection of multiple emerging requirements.
The EU Perspective: MDR, IVDR, and EHDS
Europe’s Medical Device Regulation (MDR) and In Vitro Diagnostic Regulation (IVDR) have raised evidence requirements significantly. Post-market surveillance is no longer optional — it’s a continuous obligation. Claims data provides an efficient mechanism for ongoing safety monitoring and real-world performance assessment.
The proposed European Health Data Space (EHDS) — expected to be fully operational in phases through 2025-2026 — will create standardized frameworks for secondary use of health data across member states. This infrastructure should, in theory, make cross-border real-world evidence generation more feasible. Germany’s advanced digitalization under the gematik framework positions German claims data as a particularly valuable asset within EHDS.
Germany’s DiGA Evolution and Evidence Standards
What Germany’s DiGA program has taught us — sometimes painfully — is that fast-track reimbursement creates pressure for rapid, rigorous evidence generation. The three-year evolution analysis shows that approximately one-third of provisionally approved apps have faced evidence development challenges.
The successful DiGA manufacturers are those who designed evidence strategies from launch, using real-world data collection integrated with their digital platforms. They’re tracking engagement, outcomes, and healthcare utilization continuously, then linking this data to claims information when possible to demonstrate broader system-level impact.
The AI Act and Synthetic Data
Europe’s AI Act, taking effect in phases through 2026, classifies medical AI systems as high-risk applications requiring extensive documentation, validation, and ongoing monitoring. Synthetic data plays a dual role here:
First, as a tool for algorithm development and testing that reduces privacy risks during the development phase. Second, as a potential source of evidence for performance validation — though with appropriate caveats about synthetic data limitations.
The intersection of AI Act requirements, MDR post-market surveillance obligations, and GDPR data protection creates a complex compliance landscape. Companies that proactively integrate GDPR-compliant analytics and real-world evidence database Germany access into their regulatory strategies will have significant advantages.
Patient Journey Mapping: From Diagnosis to Intervention to Outcomes
One of the most powerful applications of MedTech patient journey analytics is the ability to map complete treatment pathways longitudinally. This goes beyond simple utilization metrics to understand the patient experience across time and care settings.
What Complete Journey Mapping Reveals
Consider a patient with Type 2 diabetes. Claims data can track:
The diagnosis date and initial treatment regimen (metformin monotherapy). The trajectory of medication intensification (addition of GLP-1 agonist, eventual insulin therapy). The frequency of endocrinology visits and primary care encounters. The occurrence of complications (retinopathy screening, foot care, cardiovascular events). The introduction of a digital therapeutic for medication adherence or lifestyle modification. The downstream impact on A1c control (inferred from changes in treatment intensity), hospitalization rates, and overall healthcare costs.
This longitudinal perspective is what Platt et al.’s National Evaluation System for Health Technology analysis emphasizes as critical for understanding real-world device performance. You’re not just seeing a snapshot — you’re watching the movie.
For DTx companies, this means you can identify the optimal timing for intervention. When in the disease course does your solution have maximum impact? Should you target newly diagnosed patients, those failing first-line therapy, or patients with established complications? Claims-based treatment pathway analysis of real-world data answers these questions empirically.
Comorbidity Analysis and Patient Segmentation
Real patients don’t have single conditions. They have diabetes plus depression plus osteoarthritis, plus hypertension. The clinical trial population — carefully selected for minimal comorbidity — doesn’t reflect the actual patient population you’ll serve.
Claims data captures the full comorbidity profile. You can segment patient populations by disease complexity, identify which comorbidities predict better or worse outcomes with your intervention, and tailor your commercial strategy and clinical positioning accordingly.
For MedTech outcomes database applications, this comorbidity analysis informs real-world evidence generation that payers find more credible than controlled trial results. You’re showing you understand their patient population — not an idealized research cohort.
Commercialization Strategy: From Launch to Scale
All the evidence in the world doesn’t matter if you can’t translate it into commercial success. Claims-based analytics informs commercialization strategy at every stage.
Pre-Launch Market Sizing and Opportunity Assessment
Before investing in market entry, you need realistic forecasts. Traditional top-down sizing — “TAM is $X billion” — doesn’t cut it for sophisticated CFOs and commercial leaders.
Bottom-up sizing using DTx usage database access builds credibility: How many patients with your target condition exist in your addressable market? (claims-based prevalence). What percentage currently receives treatment? (treatment rate analysis). What’s the current treatment mix? (competitive landscape mapping). What’s realistic penetration based on analogous digital health launches? (benchmark analysis). What’s the revenue per patient based on expected utilization patterns? (economic modeling).
This level of granularity — feasible with comprehensive medical device real-world data — transforms investor conversations and board presentations.
Launch Analytics and Early Adoption Tracking
In the crucial first 6-12 months post-launch, you need rapid feedback on market traction. Claims data — typically available with 60-90 day lag — provides early signals on adoption patterns, geographic uptake, prescriber engagement, and payer coverage decisions.
You can identify early adopters and understand what distinguishes them from non-adopters. You can spot geographic gaps requiring targeted commercial investment. You can monitor payer coverage policies and identify where coverage denials create barriers.
Mature Market Management and Lifecycle Evidence
As products mature, claims-based analytics shifts to lifecycle management: monitoring competitive threats, identifying line extension opportunities, demonstrating sustained value to maintain reimbursement, and supporting label expansion or indication development.
For mature digital therapeutics, real-world use studies like those for opioid use disorder treatments demonstrate that benefits extend beyond controlled trial settings, supporting continued coverage and potentially expanding approved indications.
The Future of Claims-Based Analytics in Digital Health
So where is this heading? Based on current trends and emerging technologies, I see several developments likely to accelerate in 2026 and beyond.
AI-Powered Real-World Evidence Generation
Machine learning applied to large-scale claims datasets enables increasingly sophisticated analyses: predictive models identifying patients likely to benefit from specific interventions, natural language processing extracting insights from unstructured claims notes and appeals, causal inference methods estimating treatment effects from observational data, and anomaly detection identifying safety signals or quality issues.
The integration of AI Act compliance frameworks with medical device regulations will create clearer pathways for AI-augmented analytics while ensuring appropriate validation and oversight.
Expanding Global Reimbursement Models
Germany’s DiGA program has inspired similar initiatives globally. France, Belgium, and the Netherlands are developing digital therapeutics reimbursement pathways. As these programs mature, cross-country real-world evidence generation becomes increasingly valuable for multi-market launches.
The challenge? Each country has unique claims data structures, coding systems, and privacy regulations. Companies that invest in multi-country data integration capabilities — leveraging common data models and privacy-preserving analytics — will have significant competitive advantages.
Synthetic Data Maturation and Regulatory Acceptance
By 2026-2027, I expect synthetic data to be broadly accepted for specific regulatory applications: post-market surveillance and safety monitoring, health economic modeling and budget impact analyses, algorithm development and validation (with real-world validation required), and rare disease research where patient populations are small.
The key will be establishing clear quality standards and validation methodologies. Regulatory bodies are working on this now, and industry consortia are developing best practices.
Real-Time Analytics and Adaptive Interventions
Current claims data has inherent lag — typically 60-90 days from service delivery to data availability. But infrastructure improvements and near-real-time adjudication systems may reduce this lag significantly.
Faster access to utilization data enables adaptive interventions: commercial strategies adjusted based on emerging adoption patterns, clinical protocols modified based on real-world effectiveness signals, and payer negotiations informed by current utilization rather than projections.
Common Questions from MedTech and DTx Teams
How quickly can we access claims data after product launch?
Typical lag is 60-90 days from service delivery to data availability in aggregated datasets. However, some payers and data vendors offer accelerated pipelines, reducing this to 30-45 days for recent quarters. For Germany-specific market access database needs, expect similar timelines for GKV claims data.
What if our DTx product doesn’t have a dedicated billing code yet?
This is common for novel digital interventions. Approaches include: analyzing data for related billing codes that providers might use as proxies, working with payers to establish temporary tracking codes even before permanent codes exist, integrating patient-reported data directly from your platform with claims data using privacy-preserving linkage, and advocating for dedicated codes through professional societies and regulatory channels (codes enable better tracking and support broader adoption).
How do we demonstrate causality from observational claims data?
Rigorous observational study designs can approximate causal inference: propensity score matching to create comparable treatment and control groups, interrupted time series analysis to evaluate pre-post intervention changes, instrumental variable approaches when appropriate natural experiments exist, and synthetic control methods comparing treated populations to matched control populations. These methods won’t replace RCTs for regulatory approval, but they provide compelling real-world evidence for payer negotiations and lifecycle management.
What about patient privacy and GDPR compliance?
Reputable claims data providers implement strict privacy protections: Data is de-identified or anonymized before analysis, aggregation ensures individual patients cannot be re-identified, access controls limit data use to approved research purposes, and data processing agreements ensure GDPR Article 9 compliance. Synthetic data generation adds a layer of privacy protection for particularly sensitive analyses.
How do we integrate claims data with our existing analytics infrastructure?
Most MedTech outcomes database vendors provide multiple access methods: API access for programmatic integration into your analytics platforms, secure data transfer for one-time analyses, cloud-based analytics environments where you can work with data without local storage, and standardized data formats (CSV, Parquet) compatible with common analytics tools. The key is choosing vendors who support interoperability and offer technical documentation for integration.
Your Next Steps with MEDDDICAL
If you’re navigating digital therapeutics adoption or MedTech market access challenges in Germany or broader European markets, the strategic question isn’t whether to use claims-based analytics — it’s how to integrate these insights most effectively into your evidence strategy, commercial planning, and regulatory approach.
MEDDDICAL provides GDPR-compliant access to Germany’s most comprehensive statutory health insurance claims data — covering 90% of the population with federal state granularity. Our analysis-ready datasets integrate seamlessly with your existing workflows, and our advanced synthetic data capabilities enable privacy-preserving innovation without compromising analytical power.
Whether you need to size your market opportunity, support a G-BA submission, track post-launch adoption, or demonstrate long-term value to payers, we’ve built our data infrastructure specifically for the needs of pharmaceutical and MedTech companies navigating German and European market access.
The digital health and MedTech market is projected to reach $32-45 billion by 2030-2033. The companies that will capture this opportunity are those building evidence strategies today — integrating real-world data from launch, demonstrating value continuously, and adapting based on actual utilization patterns rather than projections.
Want to explore how MEDDDICAL’s aggregated claims data and synthetic datasets can accelerate your market access strategy? Visit our MedTech Market Access page or request a comprehensive data sample to see what’s possible.
Sources and References
- Kim M, Patrick K, Nebeker C, et al. The Digital Therapeutics Real-World Evidence Framework: An Approach for Guiding Evidence-Based Digital Therapeutics Design, Development, Testing, and Monitoring. J Med Internet Res. 2024;26:e49208. https://www.jmir.org/2024/1/e49208
- Maricich YA, Xiong X, Gerwien R, et al. Real-world evidence for a prescription digital therapeutic to treat opioid use disorder. Curr Med Res Opin. 2021;37(10):1757-1765. https://pubmed.ncbi.nlm.nih.gov/33140981/
- Schmidt L, Pawlitzki M, Renard BY, Meuth SG, Masanneck L. The three-year evolution of Germany’s Digital Therapeutics reimbursement program and its path forward. NPJ Digit Med. 2024;7(1):139. https://pmc.ncbi.nlm.nih.gov/articles/PMC11126413/
- Gonzales GG, Guruswamy G, Smith SR. Synthetic data in health care: A narrative review. PLOS Digit Health. 2023;2(1):e0000082. https://pmc.ncbi.nlm.nih.gov/articles/PMC9931305/
- Jameel S, et al. Characterizing the Clinical Adoption of Medical AI Devices through U.S. Insurance Claims. NEJM AI. 2023. https://ai.nejm.org/doi/full/10.1056/AIoa2300030
- U.S. Food and Drug Administration. Use of Real-World Evidence to Support Regulatory Decision-Making for Medical Devices: Guidance for Industry and Food and Drug Administration Staff. 2017 (updated). https://www.fda.gov/regulatory-information/search-fda-guidance-documents/use-real-world-evidence-support-regulatory-decision-making-medical-devices
- Forma F, et al. Real-World Evaluation of Clinical Response and Long-Term Healthcare Resource Utilization Patterns Following Treatment with a Digital Therapeutic for Chronic Insomnia. Adv Ther. 2022;39(9):4146-4156. https://pubmed.ncbi.nlm.nih.gov/35983014/
- Azizi Z, et al. Harnessing the power of synthetic data in healthcare: innovation, application, and privacy. NPJ Digit Med. 2023;6:191. https://www.nature.com/articles/s41746-023-00927-3
- Goeldner M, Gehder S. Digital Health Applications (DiGAs) on a Fast Track: Insights From a Data-Driven Analysis of Prescribable Digital Therapeutics in Germany From 2020 to Mid-2024. J Med Internet Res. 2024;26:e59013. https://www.jmir.org/2024/1/e59013
- Velez FF, et al. Real-world use and clinical outcomes after 24 weeks of treatment with a prescription digital therapeutic for opioid use disorder. Postgrad Med. 2021;133(8):986-994. https://pubmed.ncbi.nlm.nih.gov/34461801/
- Espie CA, et al. Evidence-informed is not enough: digital therapeutics also need to be evidence-based. World Psychiatry. 2022;21(2):269-270. https://pubmed.ncbi.nlm.nih.gov/35524617/
- Platt R, et al. Lessons on the use of real-world data in medical device research: findings from the National Evaluation System for Health Technology Test-Cases. J Clin Epidemiol. 2024 (PMC11367563). https://pmc.ncbi.nlm.nih.gov/articles/PMC11367563/
Related Reading:
- Previous: Aggregated and Synthetic Insurance Data for Pharma
- Next: Treatment Pathway Analysis with Real-World Data
