6–9 Jul 2026
Europe/Warsaw timezone

Creating a structured dataset of vital sign values extracted from clinical notes in Electronic Health Records of the public health system of the City of Buenos Aires

8 Jul 2026, 13:20
20m
Lightning Talk (5 minutes) Virtual Presentation Room

Speaker

Carolina Mengoni Goñalons (Health Information and Statistics Office within the Ministry of Health of the City Buenos Aires)

Description

Notes written by healthcare professionals within Electronic Health Records (EHR) are shaped by the specialty of the professional, the type of data to be depicted, the usability of the application, and the formats allowed by the system. Vital signs are mostly structured data that typically have their own dedicated entry section within an EHR. Yet, it is very common for healthcare professionals to document them within the free-text clinical notes they are already redacting.
The Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires is responsible for processing the databases generated from EHR records, in order to analyse them and generate reports with useful information for decision-making. In this regard, our team carried out an extraction and transformation process of vital sign values found in free-text clinical notes, for subsequent loading into a structured dataset within the DataWarehouse maintained by our office. The process was evaluated within an iterative improvement cycle aimed at achieving an acceptable positive predictive value. The aim of this paper is to report the main results of the process.
We successfully populated the table with structured values of the chosen vital signs, with a total of 685,219 current height records and 1,080,925 current weight found in 19,629,293 clinical notes for the years 2024 and 2025. The positive predictive values (PPV) were 93.6% and 98%, for weight and height respectively.
We are currently working on incorporating glycated hemoglobin values and, subsequently, blood pressure.

If you used AI tools or services to support the preparation of this submission, please state the name and reason for using each of them.

No AI tools/services were used

Keywords: Please list up to 5 keywords to help us find the right session for your contribution. patient follow-up, anthropometric values, free text, ETL, data warehouse
Virtual Option This submission is for pre-recorded virtual presentation only
Video Recording Video sharing is fine
The author(s) agree(s) to take responsibility and be accountable for the contents of the submission and is/are authorized to present it. Confirm

Authors

Ariana Bardauil (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Camila Ebensrtejin (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Carmín Alejandra Zangari (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Carolina Mengoni Goñalons (Health Information and Statistics Office within the Ministry of Health of the City Buenos Aires) Florencia Faretta (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Nelson Poma Guzmán (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Pedro Dalvit (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires) Sofía Anastasía (Health Information and Statistics Office within the Ministry of Health of the City of Buenos Aires)

Presentation materials

There are no materials yet.