Mandaya Royal Hospital Puri needed a generative AI clinical decision support approach that clinicians could trust, after staff were already using unapproved public GenAI tools such as Gemini and ChatGPT that posed hallucination, bias, and governance risks in patient care.
Reported impact
The hospital strengthened clinician decision support with faster access to trusted evidence, reduced dependence on unapproved public GenAI tools, and aimed to improve care quality and patient outcomes while keeping final clinical decisions with physicians.
Mandaya Royal Hospital Puri implemented UpToDate clinical decision support with UpToDate Expert AI as part of its digitalization strategy for clinician decision-making. In the hospital workflow, clinicians enter natural-language questions at the point of care, and UpToDate Expert AI acts as a generative AI conversational layer over UpToDate’s rigorously reviewed clinical interpretations and evidence-based clinical database. The hospital did not deploy the tool blindly: it appointed clinicians to test the system with patient cases and assess whether responses appropriately summarized medical background, flagged issues to watch, proposed care plans, suggested follow-up questions, and presented answers in a structured, concise format. Transparency was also a gating requirement, so clinicians could inspect the supporting evidence behind recommendations before using them. The resulting deployment is designed to strengthen, not replace, physician judgment while reducing reliance on shadow AI.
Clinicians submit natural-language clinical questions into UpToDate Expert AI at the point of care. The AI layer draws on UpToDate’s rigorously reviewed clinical database and interpretations to synthesize structured responses, which clinicians then review alongside supporting evidence before applying the information to diagnosis, treatment, and care planning.
"Clinicians can input natural language prompts and receive context-rich responses to each question through a conversational experience."
"If technologies such as AI-powered clinical decision support can help reduce the risk of error and improve the quality of care, then we should embrace that opportunity."
"In 2026, the hospital marked another technological milestone by becoming the first in Indonesia – and in the Southeast Asia region – to adopt UpToDate clinical decision support (CDS) with UpToDate Expert AI, a generative AI-powered layer on top of the rigorously reviewed UpToDate clinical interpretations trusted by 3 million healthcare professionals worldwide."
"Mandaya Royal Hospital Puri – the first hospital in Southeast Asia to implement UpToDate Expert AI – shares how it evaluated and integrated the platform to help strengthen clinician decision-making."
"The hospital appointed several clinicians with assessing each system using test patient cases."
"These platforms come with the risk of errors and hallucinations. In contrast, a dedicated clinical repository like UpToDate Expert AI ensures our clinicians access only expert-vetted information that has met strict governance standards."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Google Cloud Sample Archived · Oct 9, 2026 Angelus Founded by a dentist whose first product was based on a patent, Angelus competes on differentiation, developing bioceramic products and fiberglass post lines that require clinical proof, intellectual property… 50,000 pages of proprietary data now powering AI-generated documents Gemini Google Cloud Sample Modified · Oct 9, 2026 Lillia Lillia needed to reduce the friction of manual meal, medication, and vital tracking for chronic disease patients while freeing human care coaches from routine tasks and still meeting enterprise reliability and data… Automates 95% of early patient care interactions using Gemini APIs Artifact Registry · Cloud Build · Cloud Load Balancing Google Cloud Sample Modified · Oct 9, 2026 Quadrivia Quadrivia needed a healthcare assistant that could automate clinical work in real time, preserve patient safety, and connect to electronic health records without sacrificing latency or privacy. Cloud Healthcare API · Gemini Flash · Google Kubernetes Engine 
