Retinal Image Risk Scoring for Early DVT and PE Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current hospital practices do not include retinal scans in assessing hospitalized patients for the risk of deep vein thrombosis (DVT) and pulmonary embolism, despite retinal scans being a non-invasive indicator of blood clots, which can lead to fatal conditions like pulmonary embolism, heart attack, or cerebral stroke.
Innovation Solution
A system that analyzes retinal images in conjunction with patient health records using machine learning models to determine a risk score for DVT, generating recommendations for further screening or treatment based on the risk level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If retinal scans are integrated into standard hospital care for DVT risk assessment, then early detection capability is improved, but device complexity and implementation cost increase
Solution Approach 1:
The system segments the DVT risk assessment process into distinct functional modules: retinal image acquisition, feature extraction (using CNNs to identify vascular patterns), machine learning-based risk scoring, and clinical recommendation generation. This modular architecture allows each component to be optimized independently and facilitates integration into existing hospital workflows without requiring complete system replacement.
Solution Approach 2:
The patent introduces an intermediary AI processing layer between the retinal scan device and the clinical decision-making process. This intermediary automatically extracts features from retinal images and generates risk scores, serving as a bridge that translates complex medical imaging data into actionable clinical insights without requiring direct human interpretation of the imaging data.
2Measurement precision
If comprehensive patient data analysis is performed to improve risk assessment accuracy, then measurement precision is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary processing of patient data and retinal images during routine hospital admissions, before clinical decisions are required. Retinal images are captured and analyzed as part of standard intake procedures, and risk scores are pre-calculated and stored in the patient's electronic health record, allowing clinicians to access results immediately when making treatment decisions without experiencing delays.
Solution Approach 2:
The machine learning model dynamically adjusts analysis parameters based on patient-specific risk factors and clinical context. The system processes only the most relevant features and data elements for each individual patient, adapting the depth and scope of analysis to match the clinical scenario, thereby optimizing the balance between accuracy and processing efficiency.
Data Source
AI summary
A patient screening system for providing recommendations for screening of a hospitalized patient for risk of developing deep vein thrombosis (DVT) or pulmonary embolism (PE) based on their health records and retinal images, is described herein. The patient screening system may include an optical imaging device for capturing retinal images, and a DVT risk assessment system configured to generate the recommendation for further screening tests. The DVT risk assessment system may implement various AI/ML models trained on a training dataset of anonymized patient data. The patient screening system may also implement detectors for various ophthalmic features correlated with blood clot-related conditions of the patient. Any patient screening based on the recommendation may be followed up, and results of such screening used to improve performance of the patient screening system.