Data Sharing and storage in healthcare

iHOMIS

computer-based system developed by the Department of Health in the Philippines

Argonaut Project

joint project of major US EHR vendors to advance industry adoption of modern, open interoperability standards

Fast healthcare interoperability resources (FHIR)

Global industry standard for passing healthcare data between systems.

• Free, open, and designed to be quick to learn and implement

REST

defines how you interact with web services

JSON

defines what the data exchanged looks like

Health data storage

one of the foundations of modern healthcare because every clinical descision depends on accurate and accessible information

Major challenges

sheer volume and diversity of healthcare data

Hierarchical Storage (MUMPS)

Massachusetts General Hospital Utility Multi-Programming system

• Tree-like structure

• Used in 1970s-80s

• Fast for clinical applications but rigid and hard to scale

• EHRs, ICU monitoring, fast retrieval of vitals

Relational Databases (SQL)

• Structures Query Language

• Easier querying, relationships between data sets

• Widely used in hospital information systems

• best for hospital billing, patient scheduling, PhilHealth claims.

Cloud storage and Big data

• Flexible, scalable, real-time analytics

• Supports big data research, nationwide studies

Big Data

extremely large, complex, and rapidly growing datasets that are too massive for traditional databases to handle efficiently.

• AI/ML in diagnostic, population health, genomics, national disease surveillance

Natural Language processing

subfield of computer science and artificial intelligence that uses machine learning to enable computers to understand and communicate with human language

Enhancing EHRs

NLP transforms traditional EHRs from static data repositories into intelligent systems that extract, summarize, and vizualize patient information in real time

Clinical documentation

NLP automates summarization of lengthly medical notes into concise reports, reducing physician workload and preventing missed details

Voice-enabled data entry

Clinicians can dictate notes directly into systems with NLP speech recognition, speeding up documentation and improving accuracy

Clinical Decision Support

NLP-powered CDSS analyzes clinical data to detect patterns and risks, guiding evidence-based diagnosis and personalized care.

Risk prediction

NLP identifies high-risk patients and early disease indicators, supporting preventive care and population health management.

Patient Recuitment

NLP scans patient records to match trial eligibility, accelerating clinical research recruitment while ensuring compliance.

Medical Image Annotation

NLP integrates with imaging to generate structured reports, summarize findings, and flag abnormalities automatically

AI Chatbots

NLP-enabled chatbots assist patients with booking, triage, reminders, and FAQs, reducing administrative burden on staff.

Sentiment Analysis

NLP interprets patient feedback and emotions to help providers improve care quality and patient satisfaction.