.png){kind=logo}
Detect CKD risk from clinical variables and prioritize patients for enhaced care and cost reduction.
The median prevalence of CKD in LatinAmerica is higher than the global average (10.5% vs. 9.5%).
CKD ranks among the top 10 causes of deathworldwide. In 2017, CKD-related deaths reached 1.2 million, comparable to roadtraffic fatalities, and are projected to rise to 2.2 million by 2040 [1].
Low-cost Screening Models: Prevent CKD progression to the point of requiring renalreplacement therapies by implementing early detection methods.
Patient Classification: Facilitate the classification of patients within care pathwaysto ensure close monitoring, aligning with high-cost account goals [3].
The model's synthetic datasetincludes health variables such as blood glucose levels, blood pressurereadings, age, and other key indicators of kidney health. Studies from the USRDS (1) and the NIH NIDDK (3) helped shape the variables used in the model to reflect real-world clinical scenarios, improving its predictive reliability for CKD.
The median prevalence of CKD in LatinAmerica is higher than the global average (10.5% vs. 9.5%).
CKD ranks among the top 10 causes of deathworldwide. In 2017, CKD-related deaths reached 1.2 million, comparable to roadtraffic fatalities, and are projected to rise to 2.2 million by 2040 [1].
Low-cost Screening Models: Prevent CKD progression to the point of requiring renalreplacement therapies by implementing early detection methods.
Patient Classification: Facilitate the classification of patients within care pathwaysto ensure close monitoring, aligning with high-cost account goals [3].
Economic and Social Burden: CKD accounts for 5.8% of deaths and 3.5% of disability-adjusted life years [4].
High-income countries allocate over 2-3% of their annual healthcare budgets to treat end-stage renal disease [5].
- Early interventions reduce advanced CKD cases,lowering costs and improving patient outcomes.
- AI tools for CKD riskassessment can streamline early detection, helping redistribute healthcareresources efficiently.
The model's synthetic datasetincludes health variables such as blood glucose levels, blood pressurereadings, age, and other key indicators of kidney health. Studies from the USRDS (1) and the NIH NIDDK (3) helped shape the variables used in the model to reflect real-world clinical scenarios, improving its predictive reliability for CKD.
