Episode
How AI Is Predicting Hospital Readmissions Before Discharge
- Published
- Jul 11, 2026
- Duration seconds
- 507
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/healthtech-talks-with-fexingo-digital-health-telemedicine-and-medical-software-7871821/episodes/how-ai-is-predicting-hospital-readmissions-before-discharge/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/healthtech-talks-with-fexingo-digital-health-telemedicine-and-medical-software-7871821/how-ai-is-predicting-hospital-readmissions-before-discharge.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
In this episode of Healthtech Talks with Fexingo, hosts Lucas and Luna dive into how machine learning models are now predicting 30-day hospital readmissions with over 80% accuracy — before the patient even walks out the door. They focus on Mount Sinai's SPOT Readmission Prediction Tool, which analyzes over 200 variables from electronic health records, social determinants, and real-time vitals to flag high-risk patients. Lucas breaks down the specific features that matter most, like prior admissions and lab trends, while Luna questions how clinicians actually use the alerts without alert fatigue. They also touch on the cost implications: a single readmission costs Medicare an average of $15,000, and early prediction could save billions. The hosts discuss the integration challenges, including data standardization across hospitals and the need for explainable AI to build clinician trust. Tune in for a concrete look at how predictive analytics is shifting from reactive to proactive care. #AI #MachineLearning #PredictiveAnalytics #HospitalReadmissions #MountSinai #Healthtech #DigitalHealth #ClinicalDecisionSupport #EHR #Medicare #CostSavings #PatientOutcomes #DataScience #ExplainableAI #BusinessAndTechnology #HealthcareInnovation #FexingoBusiness #BusinessPodcast Keep every episode free: buymeacoffee.com/fexingo