Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

[Preprint]. 2023 Jan 16:rs.3.rs-2423200. [Version 1] doi: 10.21203/rs.3.rs-2423200/v1

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

This work is licensed under a Creative Commons Attribution 4.0 International License, which allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use.

PMC Copyright notice

Figure 4. — a. Histogram for the training and testing set instances for varying DBP values used in PINN model training for a single individual (SID 15). For each 1 mmHg increase in DBP, we randomly select 1 data point for supervised model training, whereas all other points are used in model testing. b. Beat-to-beat DBP estimation (SID 15) based on PINN (shown in green) and reference conventional CNN (shown in orange) models trained with the same number of instances and corresponding true DBP (shown in dashed black). PINN shows a more precise fit to the reference DBP. c. Bland-Altman analysis with data analyzed for a total of N=15 subjects for PINN (green, ME: 0.6 mmHg, SD: 6.4 mmHg) and conventional CNN (orange, ME: 0.5 mmHg, SD: 10.1 mmHg) models. d. Pearson’s correlation analysis with data analyzed for a total of N=15 subjects for PINN (green, correlation coefficient r: 0.89) and conventional CNN (orange, correlation coefficient r: 0.77) models.