• Critically ill patients in intensive care units (ICUs)

• Healthcare professionals — physicians and nurses

• Hospitals and medical institutions

HiThings (Healthcare Internet of Things) is a unified medical IoT platform built on Wi-Fi and FHIR international standards. It brings together real-time data from a wide range of medical devices to support clinical decision-making in critical care, enabling patient-centric and digital-twin applications across healthcare informatics.

• Built on Wi-Fi and FHIR international standards for seamless data exchange and interoperability

• Equipped with a no-code/low-code automated FHIR translator

• High-performance, cost-effective integration architecture: containerized and open-source design, scalable to 60,000 medical devices, with 2.5 ms latency, over 3 years of data retention, and carrier-grade reliability

• Flexible connectivity and expansion on both device and application sides Real-time video streaming powered by go2rtc, with latency reduced to 0.4 seconds (compared to 5–10 seconds in traditional systems)

• Combines IoT and AI to enable early detection of ARDS and timely clinical intervention

• Currently integrated with 6 types of medical devices, comprising 650 units in total

• Annual data accumulation (compressed): 334 million records / 5.98 GB from patient monitors, 147 million records / 4.27 GB from ventilators, and 900,000 records / 5.27 GB from hematology analyzers

• Platform latency of 2.57 ms; scalable to 50 device types and up to 60,000 devices, with reliability reaching 99.9999%

• Integrated with 6 medical AI services — LungGuard AI, Antibiotic AI, Cardio Rescue AI, NeuroCare AI, NutriGuide AI, and the MIRA Smart Medical Record Assistant — accumulating 2,243,179 uses as of May 31, 2025

• Deployed across 6 ICUs at the hospital, including RICU, CCU, SICU, PICU, NICU, and NSCU

• 2024 rollout and pilot operation: 5 system hospitals, 17 healthcare institutions, and 2 strategic partner hospitals

• ARDS in-hospital mortality declined from 55% to 38%, a 17-percentage-point reduction

• Compliance with lung-protective ventilation within 24 hours rose from 52.2% to 90.7%

• Physician time spent retrieving patient data was reduced by 44%, saving each intensivist 16.75 hours per month; across the hospital's 50 critical care specialists, this amounts to 10,050 hours annually

• Nursing time spent on equipment checks at shift handover was reduced by 62%, saving 22.81 minutes per shift; across the hospital's 14 ICUs, this amounts to 5,827 nursing hours annually

• System reliability reaches 99.9999%, meeting telecom-grade standards

• Built on a three-node Kafka distributed architecture, achieving 99.9999% reliability in line with telecom-grade standards

• Governed by the hospital's Medical Data Application Policy; all data requests must obtain IRB approval and include signed confidentiality and conflict-of-interest declarations

• Standard operating procedures for de-identification of clinical data warehouse records and medical imaging datasets are established in accordance with ISO/IEC 29100, ISO/IEC 29191, and CNS 29100-2

• AI inference results serve solely as clinical decision support and are not used as the sole basis for diagnosis; all outputs require physician confirmation prior to clinical adoption

• Patients: ARDS in-hospital mortality declined from 55% to 38%, substantially improving outcomes for critically ill patients

• Physicians: Real-time integrated dashboards during ICU rounds reduced patient data retrieval time by 44%, alleviating cognitive workload

• Nurses: Manual transcription of physiological and device data is no longer required, and equipment-checking time at shift handover was reduced by 62%

• Multidisciplinary adoption: Deployed across 6 ICUs, with users including intensivists, infection-control physicians, pharmacists, respiratory therapists, perfusionists, dietitians, and nurses; each unit maintains a dedicated communication channel for continuous feedback

• External recognition: Received the 2023 HIMSS Davies Award (the sole recipient in Asia) and was invited to present at the HIMSS Global Health Conference and the HIMSS CIO Masterclass Malaysia

• Received the 2023 HIMSS Davies Award of Excellence, the sole recipient in Asia, recognized alongside leading institutions such as the Cleveland Clinic and UCLA Health

• International publications:

  • W.-S. Feng et al., "Design and Implementation of an Intensive Care Unit Command Center for Medical Data Fusion," Sensors, vol. 24, art. 3929, 2024

  • H.-Y. Tseng et al., "Using a Real-Time Visualization System for Data-Driven Decision Support to Achieve Lung-Protective Strategy," Critical Care, vol. 26, art. 253, 2022

• Invited international keynotes:

  • HIMSS Global Health Conference & Exhibition, March 2024: "Use of Data and AI for Improved Patient and Population Health"

  • HIMSS CIO Masterclass Malaysia, July 2024: "Building Analytics Maturity"

• Clinical impact: ARDS mortality was reduced by 17 percentage points, and lung-protective ventilation compliance increased to 90.7%, substantially improving critical-care outcomes

• Workforce efficiency: An estimated 10,050 physician-hours of data retrieval and 5,827 nursing-hours of equipment checks are saved annually, alleviating clinical workload

• Standardization: The FHIR Observation format has been adopted by device manufacturers, including the B.Braun Infusomat Space infusion pump and the Beckman Hematology Analyzer DxH 900; FHIR for AI specifications have been submitted to the Electronic Medical Record Exchange Center (EEC) under the Ministry of Health and Welfare

• Expansion: Planned rollout to affiliated hospitals, including the An Nan, Beigang, and Hsinchu branches of China Medical University Hospital