EarlySign computational software solutions create predictive insights and predictive risk models, the latter can help to identify individuals and populations at high risk for progressing to various high-burden diseases and chronic medical conditions. Several EarlySign AlgoMarkers are at work in clinical environments today, including:
Identifies individuals at high risk for having lower GI disorders using complete blood count (CBC) test results, age, and sex.
Identifies prediabetic patients at high risk for progressing to diabetes within the next 12-months using routine blood test results, age, sex, and BMI.
The Diabetes-Flag AlgoMarker is helps to identify non-diabetic individuals at high-risk for hyperglycemia and find new cases of undiagnosed diabetes which can lead to better treatment and the potential of preventing further complications.
Identifies Patients without recorded CKD that are at increased risk of harboring chronic kidney disease (CKD) stages 2-4. This model can be applied to Type 2 Diabetic (T2D) patients, and to non-diabetes patients with Hypertension to increase earlier detection of CKD.
Identifies Type 2 Diabetic (T2D) patients at high risk for progressing to chronic kidney disease (CKD) stages 2-4 within 3 years using basic demographic data, routine lab results, diagnostic codes, and drug information.
Identifies hypertensive (‘HTN’) patients at substantial risk for progressing to CKD stages 2-4 within 3 years using basic demographic data, routine lab results, diagnostic codes, and drug information.
Identifies individuals with existing early stages of CKD or without CKD who are at increased risk of fast progression (losing 5 EGFR points per 12 months over 18 months) of renal impairment.
Identifies individuals at elevated risk of developing influenza infection with complications using routine, existing EHR data, diagnostic codes, demographic data, and drug codes.
Identifies individuals at elevated risk of developing influenza infection with complications using routine, existing EHR data, diagnostic codes, demographic data, and drug codes. The convergence of the explosion of data coupled with the rapid adoption of new digital technologies can accelerate care in new ways—leading to strides in personalization of care, prevention of disease complications, and the enhancement of diagnostics.
Identifies Patients without recorded CKD that are at increased risk of harboring chronic kidney disease (CKD) stages 2-4. This model can be applied to Type 2 Diabetic (T2D) patients, and to non-diabetes patients with Hypertension to increase earlier detection of CKD.
Identifies Type 2 Diabetic (T2D) patients at high risk for progressing to chronic kidney disease (CKD) stages 2-4 within 3 years using basic demographic data, routine lab results, diagnostic codes, and drug information.
Identifies hypertensive (‘HTN’) patients at substantial risk for progressing to CKD stages 2-4 within 3 years using basic demographic data, routine lab results, diagnostic codes, and drug information.
Identifies individuals with existing early stages of CKD or without CKD who are at increased risk of fast progression (losing 5 EGFR points per 12 months over 18 months) of renal impairment.
Identifies individuals at elevated risk of developing influenza infection with complications using routine, existing EHR data, diagnostic codes, demographic data, and drug codes.
Identifies patients who may have had respiratory or pulmonary findings, using routine, existing clinical labs, smoking history, EHR, and demographic data.
At the heart of every single AlgoMarker is a commitment to support and address the most challenging clinical questions to improve the health of the people you serve. With every model we develop, we strive to deliver caregivers the insights, tools, and support they need to make informed clinical decisions. The power of a solution is ultimately measured by the value it delivers.