Berta: an open-source, modular tool for AI-enabled clinical documentation
arXiv:2603.23513v1 Announce Type: new Abstract: Commercial AI scribes cost \$99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta, an open-source modular scribe platform for AI-enabled clinical documentation, and deployed a customized implementation within Alberta Health Services (AHS) integrated with their existing Snowflake AI Data Cloud infrastructure. The system combines automatic speech recognition with large language models while retaining all clinical data within the secure AHS environment. During eight months (November 2024 to July 2025), 198 emergency physicians used the system in 105 urban and rural facilities, generating 22148 clinical sessions and more than 2800 hours of audio. The use grew from 680 to 5530 monthly sessions. Operating costs averaged less than \$30 per physician per month, a 70-95
arXiv:2603.23513v1 Announce Type: new Abstract: Commercial AI scribes cost \$99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta, an open-source modular scribe platform for AI-enabled clinical documentation, and deployed a customized implementation within Alberta Health Services (AHS) integrated with their existing Snowflake AI Data Cloud infrastructure. The system combines automatic speech recognition with large language models while retaining all clinical data within the secure AHS environment. During eight months (November 2024 to July 2025), 198 emergency physicians used the system in 105 urban and rural facilities, generating 22148 clinical sessions and more than 2800 hours of audio. The use grew from 680 to 5530 monthly sessions. Operating costs averaged less than \$30 per physician per month, a 70-95% reduction compared to commercial alternatives. AHS has since approved expansion to 850 physicians. This is the first provincial-scale deployment of an AI scribe integrated with existing health system infrastructure. By releasing Berta as open source, we provide a reproducible, cost-effective alternative that health systems can adapt to their own secure environments, supporting data sovereignty and informed evaluation of AI documentation technology.
Executive Summary
This article presents Berta, an open-source, modular tool for AI-enabled clinical documentation, developed to address the limitations of commercial AI scribes. By integrating with existing health system infrastructure, Berta reduces costs by 70-95% compared to commercial alternatives, while providing institutional control over data governance and quality improvement. The successful deployment of Berta in Alberta Health Services (AHS) demonstrates its potential as a cost-effective alternative for health systems. As an open-source solution, Berta promotes data sovereignty and informed evaluation of AI documentation technology, making it an attractive option for healthcare organizations. The article highlights the importance of data control and the need for cost-effective AI solutions in healthcare.
Key Points
- ▸ Berta is an open-source, modular tool for AI-enabled clinical documentation
- ▸ Berta integrates with existing health system infrastructure for cost-effectiveness
- ▸ Berta reduces costs by 70-95% compared to commercial AI scribes
Merits
Cost-effectiveness
Berta's ability to reduce costs by 70-95% compared to commercial AI scribes makes it an attractive option for healthcare organizations.
Data sovereignty
As an open-source solution, Berta promotes data sovereignty, allowing health systems to maintain control over their data.
Scalability
Berta's successful deployment in AHS demonstrates its potential for scalability and widespread adoption.
Demerits
Limited deployment
The article's focus on a single deployment in AHS may limit the generalizability of the results.
Technical complexity
The technical requirements for implementing Berta may be a barrier for healthcare organizations with limited technical expertise.
Expert Commentary
The development of Berta is a significant step towards addressing the limitations of commercial AI scribes in healthcare. By providing a cost-effective, open-source solution that integrates with existing health system infrastructure, Berta has the potential to improve clinical documentation efficiency and reduce costs. However, the article's focus on a single deployment may limit the generalizability of the results. Furthermore, the technical complexity of implementing Berta may be a barrier for healthcare organizations with limited technical expertise. Nevertheless, the article's findings have important implications for healthcare organizations and policymakers, highlighting the need for data sovereignty and control when adopting AI solutions.
Recommendations
- ✓ Healthcare organizations should consider adopting Berta as a cost-effective alternative to commercial AI scribes.
- ✓ Healthcare policymakers should prioritize data sovereignty and control when adopting AI solutions in healthcare.
Sources
Original: arXiv - cs.CL
