Full-Time
Posted on 9/16/2025
AI-powered guide for virtual patient care
No salary listed
London, UK
In Person
Corti provides an AI-powered guide for healthcare providers to augment, automate, and analyze patient encounters across virtual and in-person care. It listens during interactions to offer real-time prompts and supports clinicians with decision guidance and quality assurance by analyzing every call, aiming to boost encounter productivity. The AI is trained on data from over 16 million patients and 550,000 hours of audio, and is integrated into existing workflows to reduce documentation load and save time. Its goal is to help healthcare teams engage patients more effectively, streamline operations, and improve care delivery and safety.
Company Size
51-200
Company Stage
Series B
Total Funding
$96M
Headquarters
Copenhagen, Denmark
Founded
2016
Help us improve and share your feedback! Did you find this helpful?
Health Insurance
Dental Insurance
Vision Insurance
401(k) Retirement Plan
Hybrid Work Options
Remote Work Options
Corti, an AI company, has developed a new model called Symphony for Medical Coding to address inefficiencies in the US healthcare billing system, which uses 72,000 standardised medical codes to classify patient visits. The system costs the US $36 billion annually, and coding errors can lead to rejected insurance claims and incorrect patient records. The International Classification of Diseases codes cover everything from common ailments to highly specific scenarios, including injuries from water skis on fire, contact with cows, and knitting-related injuries. Each patient visit requires healthcare professionals to select the correct code from tens of thousands of options. Joakim Edin, an AI researcher at Corti and one of Symphony's architects, said the new model aims to reduce costly and potentially harmful coding errors whilst supporting the complex classification system.
Corti releases agentic model for medical coding, says it outperforms OpenAI, Anthropic. Corti, maker of AI foundation models for healthcare, has released a new agentic model for medical coding that it says outperforms a number of Big Tech models. Symphony for Medical Coding outperforms those from OpenAI, Anthropic, Amazon, Oracle and Google by over 25% in clinical accuracy benchmarks. The product, available via API, builds on Corti's flagship model, Symphony, already used by 200 teams in the U.S. today. The company works with electronic health record vendors, virtual care platforms, practice management systems and life sciences organizations globally. Medical coding is extremely complicated. The U.S. coding system, ICD-10, has about 70,000 diagnosis codes. The automated process converts clinical notes into structured data to inform reimbursement, research and policy. Being able to capture the right codes amid nuance is crucial; errors can be costly both in terms of missed revenue and under-captured diagnoses. In a recent study of Danish patient data, Corti found three times as many suicide attempts as had been coded. Missed trends like these impact resource allocation and intervention design. "Most AI systems fall short in medical coding because they treat it as labeling, not reasoning. Correct coding depends on evidence, context, hierarchy and guideline interpretation," Lars Maaløe, Ph.D., chief technology officer and co-founder of Corti, said in an announcement. "We built Symphony for Medical Coding to follow the same decision process expert coders use, and that is why the performance gap is so meaningful." Symphony was evaluated on two widely used public benchmarks in medical coding research, according to Corti: ACI-BENCH and MDACE. These were created by independent academic teams and professional medical coders. Symphony for Medical Coding is also validated on real-world clinical data from a large U.S. health system spanning emergency and outpatient care settings. All models, including Corti's and the Big Tech companies' to which it was compared, were evaluated under identical conditions and run five times each to ensure consistency and reproducibility. Specifically, Corti's model outperformed Anthropic's Claude Opus 4.6, OpenAI's GPT-5.4 and Google's Gemini 3.1 Pro. It was also compared against systems built on top of those foundation models, including Oracle Health & AI's MedDCR (built on GPT) and AWS AI's fine-tuned coding model (built on Claude). Existing models that automate coding typically rely on memorizing patterns from annotated datasets through supervised or semi-supervised learning, per Corti. This approach is not the best for rare codes, multiple specialties or frequent system updates. Corti's model, based on targeted LLMs, rethinks medical coding as a reasoning process using four agents that mimic the work of human coders. The agents identify evidence, reason through hierarchies, validate against guidelines and reconcile ambiguity, the company said. The need for clear coding has never been greater, Maaløe told Fierce Healthcare, because with the advent of ambient scribes, unstructured clinical notes are getting longer. That means more potential missed opportunities to code. Though the main use case for Corti is revenue cycle management, the platform can also track indications of fraud, per Maaløe. Corti is compliant with HIPAA and GDPR privacy standards. Maaløe is finding that U.S. customers are requesting Corti's product with GDPR-level compliance amid lagging privacy regulations in the U.S. Corti began in 2016 as a research company trying to understand how to stream a large language model in real time to reduce administrative burden and augment clinician workflow. It has raised $100 million to date. Steve West, managing director of Healthliant Ventures and Tanner Health, said in an announcement that Corti's methodology "is the most promising approach to medical coding we've seen. We've been co-developing with Corti because we believe specialized AI infrastructure is how this problem gets solved - and we're excited to see it move into production." Let Google know we are your trusted source. Add our editorial as a preferred source in your search results.
Corti's innovative Symphony AI outperforms OpenAI and Anthropic in Medical Coding. Corti Unveils Advanced Medical Coding AI: Symphony Corti, a health AI enterprise headquartered in Copenhagen, has developed Symphony, leveraging insights from a peer-reviewed investigation heralded as the most extensive medical coding study to date. This innovative tool redefines medical coding as a cognitive task rather than a mere labeling exercise; it is now accessible via API. Medical coding - the intricate process of transforming clinical documents, diagnoses, and procedures into standardized alphanumeric codes - serves critical functions in billing, reporting, and public health analytics. Despite its significance, it remains one of healthcare's most error-laden and impactful administrative endeavors. In the American coding schema, ICD-10-CM, there are a staggering 70,000 diagnosis codes. Consequently, the prevalence of inaccuracies is a routine, costly issue, often eluding detection. Corti has unveiled Symphony for Medical Coding, a novel solution purportedly outperforming offerings from tech titans such as OpenAI, Anthropic, Amazon, Oracle, and Microsoft by up to 25% in clinical accuracy assessments. The system is available via API as of today. Corti's claims hinge upon a pivotal methodological differentiation. Conventional AI frameworks typically approach medical coding as a classification dilemma, predicting the most probable code from a training distribution based on clinical notes. Such a strategy falters, as coding guidelines are perpetually evolving, rendering historically trained models insufficient. Corti's methodology, developed through a rigorously peer-reviewed framework titled Code Like Humans and acknowledged at EMNLP 2025 - an esteemed machine learning symposium - regards coding as an intellectual reasoning exercise. "The majority of AI solutions falter in the realm of medical coding because they conflate it with mere labeling rather than sophisticated reasoning. Accurate coding is contingent on the synthesis of evidence, contextual nuances, hierarchical structures, and interpretative guidelines. Symphony for Medical Coding was crafted to replicate the decision-making processes employed by expert coders, which elucidates the substantial performance differential," noted Lars Maaløe, PhD, CTO and co-founder of Corti. Symphony employs a sequential process of four agents: an evidence extractor identifies conditions within clinical notes, an index navigator explores the ICD alphabetical index for potential codes, a tabular validator scrutinizes candidates against established guidelines, and a code reconciler ensures that final outputs are accurately sequenced and validated. Each phase mirrors the actions of a trained human coder. This research was predicated on data from 1.8 million patient encounters, thus marking it as the largest peer-reviewed study of its kind. The ramifications of inadequate coding extend beyond financial implications. Corti references a peer-reviewed examination of Danish patient data, which revealed that its system identified three times the number of suicide attempts compared to official coding records - cases present in clinical documentation and medication logs that were overlooked by overburdened coders. "For decades, medical coding has been perceived merely as an administrative cost center; however, it constitutes the foundational data layer underpinning healthcare systems. Accurate coding profoundly influences what health organizations can perceive, decide, and execute," assertedAndreas Cleve, CEO and co-founder of Corti. Omitting such instances hampers health systems' capabilities to monitor trends, allocate resources, or devise effective interventions. The coding framework is not merely overhead; it fundamentally shapes how health systems comprehend their realities. Symphony for Medical Coding stands as Corti's inaugural system designed to perform across both US coding landscapes - ICD-10-CM for diagnoses, ICD-10-PCS and CPT for procedures - and European contexts without requiring localized retraining. ICD-10 coverage for Europe, overseen by the WHO, is currently operational in beta as the company expands its reach to the UK, Germany, France, and Denmark. The system generates auditable outputs: each code assigned is directly tied to the clinical evidence backing it, with any ambiguities flagged for human scrutiny. Accessible through the Corti Console, Symphony integrates with the Corti Agentic Framework and accommodates both A2A and MCP standards. Solutions for enterprise and sovereign cloud deployments are also on offer. Founded in Copenhagen, Corti maintains additional offices in New York and London. The company has raised a total of $100 million and serves more than 100 million patients yearly across various health systems, including the NHS. The introduction of Symphony represents the commercial realization of the Code Like Humans research, aligning with Corti's ethos of validating concepts through peer-reviewed discourse prior to their development into production-grade infrastructures.
Corti has released Symphony for Medical Coding, an AI model that outperforms OpenAI, Anthropic, Amazon, Oracle and Google in medical coding accuracy by over 25%. The system is now available via API for healthcare software developers. Built on research from 5.8 million patient encounters, Symphony uses a multi-agent framework that mirrors professional coders' decision-making processes. The approach, detailed in a paper accepted to EMNLP 2025, treats coding as a reasoning task rather than simple labelling. The system operates across US coding systems (ICD-10-CM, ICD-10-PCS, CPT) and European environments without requiring local retraining. ICD-10 support is currently in beta for markets including the UK, Germany, France and Denmark. Corti serves over 100 million patients annually across health systems including the NHS.
VIENNA, Austria and COPENHAGEN, Denmark, Sept. 3, 2025 /PRNewswire/ - Speech Processing Solutions (SPS), the global leader behind Philips SpeechLive, today announced a strategic partnership with Corti, the specialized AI infrastructure company for healthcare, to introduce ambient clinical documentation directly into the SpeechLive platform.