Costa Rica's social security agency CCSS has piloted LIDIA, an algorithm scanning over a million records in its EDUS digital health system to flag patients at risk of type 2 diabetes before diagnosis, identifying 130 undiagnosed cases at the Clorito Picado clinic alone.
public health, predictive analytics, machine learning, electronic health records
Context
Costa Rica's CCSS has since 2023 piloted LIDIA, predictive AI models built on the EDUS national digital health record, covering diabetes, lung health, acute coronary syndrome and breast cancer.
Results
In a pilot at the Clorito Picado clinic, LIDIA's diabetes module flagged patients later confirmed by clinical fieldwork to include 130 undiagnosed cases; the AI Observatory Costa Rica lists it as a verified pilot, but no peer-reviewed accuracy, sensitivity or bias-audit data has been published.
Implementation
Indicative cost
Medium (€50k–€500k)
Time to results
Medium (1–3 years)
Staffing & skills
CCSS medical, IT and administrative staff (trained across rollout)
Conditions for success
Built on the existing EDUS nationwide digital health record
Staff training paired with rollout
Commonly funded by
National / regional programmes
Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.
Do you run this practice?
Claim it —
verified implementers get a public contact pathway and can propose corrections.
Data sources
Where this practice's information was retrieved from, and when.
India's ICMR-run network of tertiary hospitals turned six years of resistance data into machine-learning early-warning signals, flagging cefotaxime resistance as …
Statistics Sierra Leone and the GRID3 partnership use machine-learning building-footprint detection on satellite imagery to map population at 1-hectare resolution, …
