Rural Health Analytics with Oracle Health
summary
Oklahoma State leverages de-identified longitudinal clinical data from Oracle (129M patients) plus 250 rural-provider interviews to build practical tools fast — IRB exemption lets projects start immediately. A concrete result: a 14-variable model (demographics, comorbidities, basic labs) that flags diabetic retinopathy risk, improving from ~60% to an AUC of ~80.89 and 90%+ sensitivity and specificity, so primary care clinics can prioritize high-risk patients for scarce ophthalmology referrals instead of blanket reminders.
AI-written summary · about
chapters (8)
- 0:00Rural health innovation
- 1:55Rural health care overlooked
- 3:19Rural health care challenges
- 6:26Oracle EHR data analytics
- 8:54Longitudinal de-identified data
- 9:17Diabetes care case study
- 11:26AI in rural health predictions
- 12:49Health care transformation
related talks
15mUsing Oracle Tech for Digital Inclusion in Rural Areas
13mOracle Health AI Apps Suite Unifies Analytics
10mTransforming Population Health with Predictive BI
33mPatients as Time-Series: High-Stakes Clinical Alerting With Ope...
25mLow-code development with APEX
41mHealthPlot: Understanding American public health through R
28mClinical Data Management and Clinical Data Science A Practical Approach
10mHow Open Data Can Improve America's Health