Cloud-Based COVID-19 Diagnosis Workflows with Privacy-Aware AI

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The rapid evolution and mutation of the SARS-CoV-2 virus complicates COVID-19 diagnosis and treatment, necessitating a system that can rapidly process big data to facilitate intelligent identification of diagnoses and treatments tailored to individual patients.

Innovation Solution

A cloud-based application using trained machine-learning models processes subject data to predict COVID-19 diagnoses and suitable treatments, while ensuring data privacy compliance through obfuscation and adherence to jurisdictional regulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If cloud-based registries and machine learning models are used to process big data for COVID-19 diagnosis and treatment, then diagnostic accuracy and treatment personalization are improved, but data privacy risks and computational complexity increase

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the computational workload by distributing data storage across multiple cloud-based registries and organizing machine learning models into modular components. Subject data is divided into structured records with specific attributes (demographics, clinical findings, lab results) that can be independently processed, allowing parallel computation while maintaining diagnostic accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary layer between raw data and diagnostic output through structured subject records and trained machine learning models. These intermediaries transform complex big data into standardized formats that can be processed efficiently, reducing computational complexity while preserving diagnostic precision through systematic data organization and algorithmic processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If subject data is stored in cloud-based registries for AI processing, then treatment personalization is improved, but data privacy compliance becomes more difficult

Engineering Contradiction:
Improvetreatment personalizationVSAvoiddata privacy compliance
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system applies local quality by implementing jurisdiction-specific data governance rules within the cloud registry structure. Different data fields are tagged with applicable jurisdictional requirements, allowing the system to apply appropriate privacy protections locally to each data element while maintaining overall treatment personalization capabilities across diverse regulatory environments.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements preliminary action by establishing data governance frameworks and privacy compliance mechanisms before data is stored in the cloud registry. Subject records are structured with built-in privacy protections and access controls from the outset, enabling treatment personalization through AI processing while ensuring data privacy compliance is embedded in the system architecture rather than added later.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4154274B1Intelligent workflow analysis for treating covid-19 using exposable cloud-based registries
Publication Date: 2025.08.27 F HOFFMANN LA ROCHE & CO AG
  • EP4154274B1 patent drawingFigure 1
  • EP4154274B1 patent drawingFigure 2
  • EP4154274B1 patent drawingFigure 3

AI summary

Disclosed herein are systems, methods, and techniques for building and using a data platform to facilitate intelligent identification of coronavirus disease 2019 (COVID-19) related diagnoses, treatment selection, and interaction tracing. The present disclosure relates to a cloud-based application that generates outputs predictive of a subject's COVID-19 diagnoses and/or suitability for COVID-19 treatments.