Loading use case index…
Loading use case index…
AI use case
The National Heart Centre Singapore (NHCS) deployed Pair, an AI Assistant developed by Open Government Products (OGP), to analyse patient case notes at a scale that was previous…
Core facts from this catalog record. Primary narrative lives in the hero above; full raw fields follow in the next section.
Every column from the source row, in stable order. URLs open in a new tab.
Title
National Heart Centre Singapore processes 6,128 patient case notes in 2 minutes with Pair AI
Content
The National Heart Centre Singapore (NHCS) deployed Pair — an AI Assistant developed by Open Government Products (OGP) under Singapore's Government Technology Agency — to analyse patient case notes at a scale that was previously impossible under the hospital's IT-policy restrictions. Pair is fast and secure by design, runs inside a government-controlled environment, and let NHCS process 6,128 discharge summaries in just one hour of prompt-generation and upload time, down from 286 hours of manual interpretation. "One important type of information that NHCS chose to examine involved heart attack patients' increasing length of stay over the years." — Lau Yee How, Senior Manager, Singapore Cardiac Data Bank, NHCS. Lau Yee How's team used Pair to conduct a comprehensive audit across thousands of patient case notes retrospectively, focusing on the Charlson Comorbidity Index (CCI) components for heart-attack patients. "NHCS faced a significant hurdle: a database of patient case notes multiple times larger than any other within the hospital, including those for diagnoses, demographics, or lab results. However, IT policy restrictions have made it challenging to develop in-house analytics for processing such a large volume of text data." Pair solved the operational need while keeping data inside a government-governed environment. Technical accuracy: Pair reached 96% overall accuracy across all 19 CCI components versus manual reviews performed by human auditors, with errors randomly distributed around a mean of zero — meaning errors tend to cancel each other out at scale. NHCS scaled Pair's batch processing to 5,000 case-note entries simultaneously in a single document, with batch jobs running in just 2 minutes of clinician time on average. Operationally, the platform saved clinicians an estimated 286 hours of manual review on the 6,128-discharge-summary audit, let the Singapore Cardiac Data Bank team focus on turning data into actionable insights, and produced a reusable prompt framework shared across NHCS and SingHealth. Pair remains under human-in-the-loop oversight to validate output, but its analytical robustness is positioned as a foundation for scaling clinical-text analytics across the network. NHCS, headquartered in Singapore, is a national specialty centre for cardiovascular disease under SingHealth. Source: Pair (Open Government Products) case study, 2026.
Continue exploring AI deployments in the catalog.
Back to use casesCity
Singapore
Company/Organization
National Heart Centre Singapore
Continent
Asia
Country
Singapore
Category
Health Care Providers & Services
Type
Deployment
Id
481521b3-c395-4f51-becd-78d3e122588d
Created At
2026-07-04T08:50:33.783734+00:00