Lesson 1Foundations of sepsis pathophysiology and clinical criteria (SIRS, qSOFA, SOFA, Sepsis-3)Looks at how sepsis affects the body and patient reactions, linking to signs doctors see like low blood pressure, fast heart rate, and organ problems. Compares SIRS, qSOFA, SOFA, and Sepsis-3 for sorting patients at emergency intake.
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, and mitigation: false positives/negatives, model drift, data quality issues, adversarial inputsPoints out risks like wrong alarms, missed cases, models going off track, and bad data. Looks at tricky inputs, strong monitoring, safety barriers, doctor checks, and safe ways to update models.
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 and validation strategies for sepsis prediction: AUROC, AUPRC, calibration, lead time, decision curve analysisExplains main measures for sepsis forecasts like AUROC, AUPRC, how well calibrated, early warnings, and decision curves for real usefulness.
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 and temporal modeling: time-series preprocessing, sliding windows, trend extractionShows cleaning and lining up emergency time data for models. Covers even spacing, odd timings, moving windows, trends, changes, and noting treatments 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 for acute risk prediction: logistic regression, gradient boosted trees, RNNs, temporal convolutional networks, transformer-based time-seriesCompares ways to predict sudden sepsis risk, from simple regression to boosted trees and deep time models. Notes strengths, weaknesses, explanations, and fit for quick emergency needs.
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 for real-time sepsis detection: vitals, labs, nursing notes, medication, waveformsDescribes live data flows in emergencies like vital signs, blood tests, nurse notes, drugs, and body signals. Talks rates, trust, and how each shows worsening 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 with ED workflows and EHR systems: event streams, FHIR, HL7, SMART on FHIR apps, CDS HooksExplains fitting AI sepsis tools into emergency routines and records. Reviews data flows, HL7, FHIR, apps, hooks, stressing ease, reliability, least change to work.
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 and human factors: thresholds, alarm fatigue mitigation, escalating workflows, who receives alertsCovers alert making for emergency staff, picking levels, steps, right people. Tackles alert tiredness, timing, steps up, showing reasons.
Choosing thresholds and alert tiersAlarm fatigue and suppression strategiesWho receives alerts and on which channelsEscalation workflows and handoff supportExplaining alerts and providing contextLesson 9Regulatory and evidence requirements for diagnostic AI: FDA/CMS considerations, clinical validation study design, prospective pilots, reporting standards (TRIPOD, CONSORT-AI)Outlines rules and proof for diagnostic AI in sepsis, FDA paths, CMS notes, validation. Reviews forward tests, reports like TRIPOD, 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 and latency considerations: near-real-time streaming vs batch scoring, handling missing and delayed dataDiscusses setups for sepsis models, live streams vs batches. Covers time limits, missing data, delays, filling gaps, watching data lines in emergencies.
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
