Risk Management
Repsol needed to move beyond generic occupational-health campaigns and traditional cardiovascular risk tables that were insufficiently personalized, carried male bias, and left employees under 40 effectively unassessed.
Reported impact
Repsol shifted from reactive and generic occupational-health outreach to personalized, predictive cardiovascular prevention, enabling earlier identification of at-risk employees, gender-calibrated interventions, inclusion of younger employees, and real-time monitoring of campaign effectiveness.
Repsol built SaludIA as an in-house occupational-health AI system to replace generic wellness campaigns with predictive, individualized cardiovascular prevention. The implementation ingests employee medical examinations, lab analytics, and habit surveys, then uses machine-learning models inside SaludIA to process the combined health dataset and segment the workforce into gender-specific risk clusters, including employees under 40 who are not covered well by SCORE2. The system automates SCORE2-style risk calculation, extends it with additional correlations, and surfaces low-, medium-, and high-risk profiles to doctors and medical staff so they can prioritize appointments, diagnostic tests, and targeted nutrition or weight campaigns. Health data is anonymized and governed under informed consent, GDPR, and compliance controls. Power BI is used as the serving layer to monitor campaign impact and adjust interventions in real time, while the architecture is described as scalable to future musculoskeletal and mental-health models.
Medical examinations, analytics, and habit surveys feed SaludIA, which analyzes the combined data and assigns gender-specific cardiovascular risk profiles that extend SCORE2 logic. Doctors and medical reference staff use those profiles to prioritize appointments, diagnostic tests, and targeted prevention campaigns, while Power BI tracks intervention impact for continuous adjustment.
"And we do this by monitoring the real impact through a dashboard (Power BI) to measure and improve each action, allowing us to adjust strategies in real time."
"SaludIA is an artificial intelligence system designed to process and analyze large volumes of health data - such as medical examinations, analytics, and habit surveys."
"SaludIA stems from a deep need: to move from generic health campaigns - the 'one-size-fits-all' that proved insufficient - to a personalized, inclusive, and proactive prevention system."
"Thanks to Machine Learning, we have managed to segment our population into eight distinct clusters: four groups of profiles for men and, crucially, four for women."
"This project has already made it possible to automate the calculation of cardiovascular risk provided by the SCORE2 table and, more importantly, to overcome it, including those to which the official table does not attribute risk."
"We are detecting at-risk employees to send them for diagnostic testing before the event occurs."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Our main headquarters is the Repsol Campus, which is located on Calle Méndez Álvaro, 44 in Madrid, Spain.
Related
In-house Sample Oct 17, 2024 OMV OMV needs to reduce uncertainty in complex geothermal and carbon capture and storage decisions, while also making large volumes of structured and unstructured subsurface data easier for geoscientists to find, summarize,… AI-driven decision-making tool · OMV Energy Chat Bot · knowledge graphs In-house Sample Oct 9, 2026 BBVA BBVA's trading desk needs to respond to institutional client requests for bond, interest-rate swap, and foreign-exchange quotes within milliseconds while balancing competitiveness, profitability, portfolio risk, and… within milliseconds Atalaya · Bloomberg · Viriato In-house Sample Sep 24, 2026 Mastercard Fraudsters are using AI to find vulnerabilities, adapt tactics, and scale attacks across more payment channels, while traditional transaction-by-transaction controls struggle to catch coordinated fraud and authorized… Last year, scam losses globally were estimated at $442 billion 