![[News] Japan Develops 10nm Nanoimprint Technology, with Potential to Tackle EUV Bottleneck – TrendForce](https://earth-news.info/wp-content/uploads/2025/12/329851-news-japan-develops-10nm-nanoimprint-technology-with-potential-to-tackle-euv-bottleneck-trendforce-360x180.jpg)
It’s widely known that around 80% of patient data in EHRs is unstructured text. The need for automated systems to help actually use this critical data has never been greater.
Dr. Tim O’Connell is cofounder and CEO of emtelligent (Booth 3185 at HIMSS24), a company that offers medical AI platforms that provide actionable insights and auditable answers. He said the platforms meet the stringent requirements for high-quality patient data not only for clinicians but for payers, life sciences and technology companies, as well.
We interviewed O’Connell to discuss what he terms a new generation of clinical-grade AI, the differences between natural language processing of the past and present, the introduction of the next generation of its platform at HIMSS24, and examples of actionable insights that have been taken from this new type of clinical-grade AI NLP.
Q. You’ve been saying a new generation of scalable, clinical-grade AI takes a deep-learning approach to in-context learning for large language models (LLMs). Please describe this for HIMSS24 attendees and why this new generation is important.
A. Users of clinical data across the healthcare spectrum are being overwhelmed by an enormous volume of clinical text, requiring humans all too often to search for a needle in a haystack. While text indexing technology is mature, it only finds what users search for, and without any context.
Medical NLP software can solve some of these problems, but can have a steep learning curve, and isn’t the right solution for use cases that require higher-level thinking as a post-processing step.
Today’s generation of large language models have opened the door to new possibilities for NLP to overcome historical challenges. However, the accuracy and hallucination issues with LLMs are well known, which preclude the use of these models in clinical environments and may put patients or organizations at risk.
Emtelligent has made it its mission to leverage new innovations to make NLP safer and more accurate at scale. In essence, we took AI to medical school.
Here at HIMSS24, emtelligent is unveiling the next generation of its medical AI platform, emtelliPro+, a collaborative effort between medical expertise and the best that artificial intelligence has to offer. The solution uses a customized, medically aligned LLM, producing output that is resilient against hallucinations, and can be used for complex use cases requiring higher-level cognition to get users the data they need in a format they can easily use.
Q. What have you recorded as the differences between the last generation of this NLP technology and the new generation you’re working with today?
A. As a practicing physician, I understand how critical it is for clinicians to have accurate, trustworthy sources of information to make diagnoses and determinations. Previous AI solutions have had issues with non-determinism and hallucinations, and have had difficulties referencing source data reliably, to allow proper human review of results.
The new generation of medical AI that makes up the emtelliPro+ platform combines a simple, intuitive interface with emtelligent’s medically aligned LLM, so both clinical and business users can quickly get the actuarial, clinical and research insights they need about members, patients and population cohorts.
The key is putting the decision in the hands of the expert. The platform provides the information people need to make well-informed decisions, while also maintaining the auditable, verifiable evidence from the source data. With this approach, the model is focused on answering the question at hand. The medical AI platform serves humans in their work, supporting them in applying their expertise to do their jobs.
Q. Please offer a couple examples of actionable insights that have been taken from this new type of clinical-grade AI NLP.
A. Making all that patient data usable to create a full health picture for patients, plan members and population cohorts can have a dramatic impact across the healthcare and life sciences industries for even the most complex use cases.
For example, the emtelliPro+ platform can provide commercial as well as government payers with a holistic view of the health and risk of their members, previously only accessible through manual chart review. With an AI-assisted, conversational interface, it makes critical processes faster and more accurate, including underwriting, Medicare and ACA risk adjustment, and prior authorization approvals.
For pharmaceutical companies and clinical research organizations, this technology dramatically reduces the time and manual effort required to accumulate patients for clinical trials. Researchers can quickly process millions of patients and apply inclusion and/or exclusion criteria, enabling them to seat their panel, monitor real world evidence and evaluate therapeutic efficacy.
Health systems, EHRs and other technology platforms can use the platform to summarize patient medical histories and gain accurate insights instantly to speed care transitions, identify gaps in care, improve coding accuracy and more. This level of AI assistance helps staff work more efficiently while relieving them of manual tasks.
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: [email protected]
Healthcare IT News is a HIMSS Media publication.
>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : Healthcare IT News – https://www.healthcareitnews.com/news/emtelligent-took-ai-medical-school-new-tech-nlp
