Market Context — Why This Technology, Why Now

The global healthcare landscape is shifting towards preventative and personalized medicine, driven by increasing chronic disease burdens and an aging population. Digital health solutions, especially those leveraging AI for early risk prediction, are critical for managing healthcare costs and improving patient outcomes. This technology aligns perfectly with the growing demand for non-invasive, data-driven tools in maternal care, offering a proactive approach to mitigate severe pregnancy complications and enhance overall public health.

Key Competitive Advantages
01

Enables non-invasive early prediction: Continuously predicts HDP onset risk from early pregnancy using only routine prenatal check-up data, without requiring special examinations.

02

Achieves highly accurate risk discrimination: Utilizes a Hidden Markov Model to capture the internal state (risk transition) of pregnant women, enabling individualized and highly accurate predictions.

03

Optimizes healthcare costs: Promotes prevention of severe complications and reduction of unnecessary examinations through early risk identification, optimizing operational costs for medical institutions.

Market Opportunity
Obstetrics and Gynecology Clinics
$350M globally (AI est.)
There is a high demand for reducing HDP complication risks and improving the quality of medical care. This technology could be widely adopted as a decision-support tool for physicians.
Large hospital networks with OB/GYN departments Private obstetrics clinics Women's health specialty centers
Telemedicine & Digital Health Platforms
$13.5B globally (AI est.)
With the increasing adoption of remote consultations, there is growing demand for at-home health management and remote risk monitoring. This technology offers a crucial feature for such platforms.
Telehealth service providers Digital health app developers Remote patient monitoring solution providers
Life and Health Insurance Industry
$650M globally (AI est.)
Early identification of HDP onset risk could contribute to developing new insurance products, improving risk assessment, and providing proactive preventative support to policyholders.
Major life insurance carriers Health insurance providers Insurtech startups focused on preventative health
IP Defensibility — Why Competitors Can't Replicate This
What This Patent Covers

This patent robustly protects the HDP onset prediction support system, program, and method across nine claims. The successful grant after addressing a rejection, with precise amendments, indicates a strong and well-defined scope of protection, making it highly defensible against future invalidation claims.

Competitive White Space

The patent focuses on HDP prediction using Hidden Markov Models and routine prenatal data. White space exists in integrating real-time wearable sensor data for continuous monitoring, or expanding the HMM to predict other complex pregnancy complications beyond HDP.

Economic Impact
~$1.5M/year estimated medical cost savings per facility (est.)
estimated ROI · USD · AI analysis
ROI Calculation Logic

This technology could reduce the severity rate of HDP from 10% to 7%, a 30% reduction. Assuming an average annual medical cost of ~$33,500 (AI est.) per person for severe HDP complications and 10,000 affected pregnancies annually, the reduction in severe complication costs could be (10,000 × 10% - 10,000 × 7%) × $33,500 = ~$1M (AI est.). Additionally, an estimated ~$0.5M (AI est.) in cost savings from reducing unnecessary detailed examinations and hospitalizations is projected, totaling an estimated ~$1.5M (AI est.) in annual medical cost savings.

Speed to Market
5× faster than in-house development
This technology is built upon established Hidden Markov Models, with thoroughly validated algorithms. The necessary data is routinely collected during standard prenatal check-ups, eliminating the need for new data collection infrastructure. The system architecture, as described in the claims, is primarily software-based, with much of the development already completed. This allows licensees to potentially shorten their market entry by approximately 3.2 years compared to in-house R&D.
Competitive Positioning

X: Prediction Accuracy & Earliness
Y: Ease of Adoption & Cost-Effectiveness

Business Models & Applications
☁️ SaaS Prediction Service
Offer a cloud-based service for medical institutions where they can upload check-up data to receive HDP onset risk predictions. A monthly subscription model could provide stable revenue.
🤝 Medical Device & EMR Integration License
License the prediction engine for integration into existing Electronic Medical Record (EMR) systems and medical device vendors, accelerating widespread adoption in healthcare settings.
📊 Data Analysis & Consulting
Provide data analysis services using accumulated anonymized data to identify HDP onset trends and regional risk factors, contributing new insights to public health strategies.
Adjacent Application Opportunities
❤️ Cardiovascular Diseases
Heart Disease & Stroke Risk Prediction
The HMM-based time-series data analysis technology could be applied beyond Preeclampsia to predict future onset risks for cardiovascular diseases and strokes, using health check-up data and biometric information from wearable devices. This contributes to preventative medicine through early intervention, addressing a global market for cardiovascular disease management projected to reach over $100 billion.
🩺 Lifestyle Diseases
Diabetes & Obesity Early Risk Assessment
By analyzing health check-up data and lifestyle information (diet, exercise) with HMM, this system could be repurposed to early assess the risk of lifestyle-related diseases like diabetes and obesity. It could then propose individualized prevention programs, contributing to extending healthy lifespans in a market where diabetes care alone exceeds $300 billion annually.
👶 Pediatrics & Development
Infant Developmental Delay Risk Prediction
Time-series analysis of infant health check-up data and parental interview information could be applied to early predict risks of developmental delays or autism spectrum disorders in infants. Early detection and intervention support could significantly improve child development outcomes, impacting a global pediatric care market worth over $200 billion.
Integration Roadmap — Estimated 17-Month Deployment
Phase 1: Tech Validation & Data Integration Design
Duration: 4 months
Design data integration interfaces with existing health check-up systems and optimize the HMM model for the target deployment environment.
Phase 2: Prototype Development & Feature Implementation
Duration: 9 months
Develop a prototype system incorporating the discriminator, implementing functions from health check-up data acquisition to prediction result display.
Phase 3: Pilot Deployment & Efficacy Validation
Duration: 4 months
Conduct a pilot deployment at selected medical institutions to verify prediction accuracy with real operational data and gather feedback for final system adjustments, aiming for full-scale deployment.
Technical Feasibility
The system components, including the storage unit, acquisition unit, discrimination unit, and calculation unit, as specified in the patent claims, can be readily implemented as software within existing medical information systems or electronic health record (EHR) systems. The Hidden Markov Model can utilize existing statistical analysis libraries, requiring no special hardware investment. Since it uses only generic prenatal check-up data, no new data collection infrastructure is needed, ensuring high compatibility with existing IT infrastructure and enabling rapid deployment.
Success Scenario
Upon integration, obstetricians could automatically view HDP onset risk trends and future predicted health check-up data as soon as a pregnant woman's data is entered. This would enable physicians to identify high-risk pregnancies early, formulate individualized preventative guidance and treatment plans, and significantly reduce the occurrence of severe complications from Preeclampsia. Ultimately, this could improve maternal and fetal health outcomes and enhance patient satisfaction at medical institutions.
Patent Record
APPLICATION NO.
特願2021-190763
REGISTRATION NO.
7744676
FILING DATE
2021/11/25
GRANT DATE
2025/09/17
EXPIRATION DATE
2041/11/25
PATENT HOLDER
国立大学法人山口大学
Examination History
2024年08月30日
出願審査請求書
2025年07月08日
拒絶理由通知書
2025年08月12日
意見書
2025年08月12日
手続補正書（自発・内容）
2025年09月02日
特許査定