Lesson 1Foundations of sepsis pathophysiology an clinical criteria (SIRS, qSOFA, SOFA, Sepsis-3)Reviews sepsis biology an host response, den links dese mechanisms to bedside signs like low blood pressure, fast heart rate, an organ dysfunction. Compares SIRS, qSOFA, SOFA, an Sepsis-3 criteria an dem use in ED triage.
Host response to infection and organ dysfunctionHemodynamic changes and microcirculatory failureSIRS, qSOFA, SOFA: components and thresholdsSepsis-3 definition and septic shock criteriaLimitations of clinical scores in the EDLesson 2Safety, failure modes, an mitigation: false positives/negatives, model drift, data quality issues, adversarial inputsIdentifies safety risks like false positives, false negatives, model drift, an poor data quality. Explores adversarial or unexpected inputs, robust monitoring, guardrails, human oversight, an processes fi safe model updates.
False positives, false negatives, and harm modesData quality checks and anomaly detectionModel drift, recalibration, and retrainingAdversarial or unexpected input handlingHuman oversight, overrides, and governanceLesson 3Evaluation metrics an validation strategies fi sepsis prediction: AUROC, AUPRC, calibration, lead time, decision curve analysisDefines key performance metrics fi sepsis prediction, including AUROC, AUPRC, calibration, an lead time. Explains internal an external validation, temporal validation, an decision curve analysis fi clinical utility assessment.
AUROC, AUPRC, and class imbalanceCalibration curves and risk stratificationLead time and horizon-specific performanceInternal, external, and temporal validationDecision curve analysis and net benefitLesson 4Feature engineering an temporal modeling: time-series preprocessing, sliding windows, trend extractionExplains how to clean an align ED time-series data fi modeling. Covers resampling, handling irregular intervals, sliding windows, trend an variability features, an encoding interventions an clinical context over time.
Time alignment, resampling, and interpolationSliding windows and prediction horizonsTrend, variability, and derivative featuresEncoding interventions and care escalationHandling irregular and sparse time-seriesLesson 5Machine learning models fi acute risk prediction: logistic regression, gradient boosted trees, RNNs, temporal convolutional networks, transformer-based time-seriesCompares modeling approaches fi acute sepsis risk prediction, from logistic regression to gradient boosted trees an deep sequence models. Highlights strengths, limitations, interpretability, an suitability fi ED time constraints.
Logistic regression and regularization choicesGradient boosted trees and feature importanceRecurrent neural networks for sequencesTemporal convolutional networks for time-seriesTransformers for clinical time-series dataLesson 6Data modalities fi real-time sepsis detection: vitals, labs, nursing notes, medication, waveformsDescribes key real-time data streams in di ED, including vital signs, laboratory tests, medications, nursing documentation, an physiologic waveforms. Discusses sampling rates, reliability, an how each modality signals evolving sepsis.
Vital signs and continuous monitoring feedsLaboratory panels, cultures, and turnaround timesMedication orders, fluids, and vasopressorsNursing notes, triage text, and flowsheetsWaveforms from monitors and bedside devicesLesson 7Integration wid ED workflows an EHR systems: event streams, FHIR, HL7, SMART on FHIR apps, CDS HooksDescribes how AI sepsis models integrate into ED workflows an EHRs. Reviews event streams, HL7, FHIR resources, SMART on FHIR apps, an CDS Hooks, emphasizing usability, reliability, an minimal disruption to clinical practice.
Event-driven architectures and data streamsHL7 and FHIR resources for sepsis signalsSMART on FHIR apps for bedside decision supportCDS Hooks for context-aware recommendationsWorkflow mapping and usability testingLesson 8Clinical alert design an human factors: thresholds, alarm fatigue mitigation, escalating workflows, who receives alertsCovers principles of alert design fi ED clinicians, including threshold selection, tiered alerts, an routing to appropriate roles. Addresses alarm fatigue, alert timing, escalation pathways, an presenting explanations an context.
Choosing thresholds and alert tiersAlarm fatigue and suppression strategiesWho receives alerts and on which channelsEscalation workflows and handoff supportExplaining alerts and providing contextLesson 9Regulatory an evidence requirements fi diagnostic AI: FDA/CMS considerations, clinical validation study design, prospective pilots, reporting standards (TRIPOD, CONSORT-AI)Outlines regulatory an evidence expectations fi diagnostic AI in sepsis, including FDA pathways, CMS considerations, an clinical validation. Reviews prospective pilots an reporting standards such as TRIPOD an CONSORT-AI.
FDA pathways for diagnostic support toolsCMS, reimbursement, and quality programsDesigning robust clinical validation studiesProspective pilots and phased rolloutsTRIPOD and CONSORT-AI reporting guidanceLesson 10Deployment frequency an latency considerations: near-real-time streaming vs batch scoring, handling missing an delayed dataDiscusses deployment architectures fi sepsis models, comparing near-real-time streaming wid batch scoring. Addresses latency budgets, handling missing or delayed data, backfilling, an monitoring data pipeline health in di ED.
Near-real-time streaming vs batch scoringLatency budgets and SLA definitionsImputation for missing and delayed inputsBackfilling, replay, and late-arriving dataMonitoring pipelines and system resilience
