Ada Health Study Shows AI Tool Improves Patient Care Decisions in Portugal
Berlin-based Ada Health announced the results of a real-world study conducted with CUF, Portugal’s largest private healthcare network, in a press release. The research, published in NEJM AI, found that Ada’s clinical AI tool significantly improved patient decision-making and the appropriateness of care received.
The ESSENCE study enrolled 1,470 adult participants through CUF’s patient app, which integrates Ada’s symptom assessment with direct care booking. One in three participants changed their intended level of care immediately after completing an Ada assessment, and the proportion of patients uncertain about what to do dropped from 12.6% to 5%.
Tracking through electronic health records and follow-up surveys showed that nearly three in five patients attended a different care setting than originally planned. The proportion of patients receiving clinically appropriate care more than doubled, from 29.8% to 64.4%, according to review by an independent physician panel. Among those who initially planned to visit an emergency department, about 40% ultimately chose a lower-acuity setting rated as appropriate.
No safety issues were identified during follow-up, and the study concluded that access to Ada’s AI assessment helped patients navigate to the right care more effectively.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Life Sciences
Oct 16 Study Tests Smartphone AI for Children's Lung Sounds Oct 16 Manhattan Physician Invests in RunPractice Oct 16 Attilio appoints Buck Institute CEO Eric Verdin as cochairman Oct 16 Aignostics launches HETA Clinical for pathology workflows Oct 16 Specialty1 Partners Invests in AI for Dental Practice OperationsLife AI Weekly
Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Andor Health Receives 2026 Frost & Sullivan Recognition for AI Care Orchestration
AnX Robotica Cites 88.6% ProScan Review Time Reduction
AKASA Launches Autonomous AI Platform for Inpatient Coding
Deerborne Survey Finds AI Cuts Analysis Workload, Not Decision Quality
AINGENS Warns AI Tool Fragmentation Complicates Medical Affairs Work
Daily AI Brief: the AI news that matters, in your inbox.