Clarion Sentinel Platform · Cardiac Arrest Division

Engine Technical
Design Document

Architecture, pipeline design, model specification, and performance validation across eight AI engines for cardiac arrest prediction, resuscitation intelligence, and post-arrest care optimization.

Document Class
Technical Design Specification
Platform
Sentinel Cardiac · Arrest Intelligence
Version
3.0.0
Classification
Confidential — Internal
Table of Contents
01Cardiac Arrest PredictionECG & HRV-based pre-arrest detection02Rhythm IntelligenceReal-time ECG phenotyping & classification03ROSC PredictionReturn of spontaneous circulation forecasting04CPR Quality OptimizationReal-time compression & ventilation guidance05Post-Arrest Hemodynamic ManagementMAP optimization & vasopressor intelligence06Targeted Temperature ManagementTTM protocol optimization & monitoring07NeuroprognosticationMulti-modal neurological outcome prediction08Survivorship IntelligenceLong-term recovery & rehabilitation tracking
Executive Summary

Cardiac arrest kills more than 250,000 people annually in the United States alone. Survival-to-discharge rates for out-of-hospital cardiac arrest remain approximately 10%, and nearly 90% of survivors suffer significant neurological impairment. The difference between survival and death is measured in seconds — the quality of each compression, the timing of each shock, the precision of each post-arrest decision.

Sentinel Cardiac deploys eight AI engines spanning the entire cardiac arrest timeline: from pre-arrest prediction hours before the event, through real-time resuscitation intelligence during the arrest, to post-arrest hemodynamic optimization, targeted temperature management, neuroprognostication, and long-term survivorship tracking. A CNN-based model predicting ROSC from ECG signals achieved AUC of 0.921 and identified five novel ECG phenotypes with dramatically different resuscitation probabilities — from 30.4% ROSC in the most favorable phenotype to 0.5% in the least.

The platform integrates with bedside monitors, defibrillators, and mechanical CPR devices via standard physiological data interfaces. ECG-based heart rate variability analysis enables in-hospital cardiac arrest prediction with AUC of 0.881 using only continuous ECG monitoring — no additional sensors or blood draws required. Real-time shockable rhythm classification during active chest compressions eliminates the need for compression pauses, preserving coronary perfusion during the most critical window.

Post-arrest engines address the two dominant determinants of outcome: hemodynamic stability and neurological recovery. Multi-modal neuroprognostication integrates EEG, somatosensory evoked potentials, neuroimaging, and biomarkers to predict neurological outcome with calibrated uncertainty — enabling families and care teams to make informed decisions about the trajectory of care without premature withdrawal of life-sustaining treatment.

8
Analysis Engines
0.921
ROSC Prediction AUC
5
Novel ECG Phenotypes
24h
Pre-Arrest Warning
Engine 01 · Prediction Layer

Cardiac Arrest Prediction

The arrest that never happens is the only arrest with a 100% survival rate. This engine prevents the event itself.

0.881
IHCA AUC
24h
Lead Time
33
HRV Features
Processing Pipeline
01
Continuous ECG Intake
Real-time ECG stream from bedside monitors across ICU, telemetry, and ED. 5-minute epoch windowing with 30-second sliding overlap for continuous analysis.
ECG Stream5-Min Epochs
02
HRV Extraction
33 heart rate variability features across time domain (SDNN, RMSSD, pNN50), frequency domain (LF, HF, LF/HF ratio), and nonlinear measures (entropy, DFA).
Time DomainFrequencyNonlinear
03
Arrest Prediction
Light gradient boosting machine (LGBM) model predicts IHCA within 0.5–24 hours. Baseline width of triangular RR interval histogram identified as most important feature.
LGBM0.5–24h
04
ECG Image Analysis
EIANet deep learning model analyzes 12-lead ECG images from triage. Visual pattern recognition captures subtle pre-arrest morphological changes invisible to waveform analysis.
EIANet12-Lead
05
Rapid Response Activation
Tiered alert: early warning (12–24h), urgent (2–6h), imminent (<30min). Rapid response team activation with pre-arrest intervention checklist.
RRT AlertTiered
Prediction Architecture

Engine 01 employs two complementary detection pathways. The continuous HRV pathway uses a light gradient boosting machine analyzing 33 heart rate variability measures extracted from 5-minute ECG epochs, achieving AUC of 0.881 for predicting in-hospital cardiac arrest within 0.5–24 hours. The model uses only standard bedside ECG monitoring — no additional sensors, blood draws, or specialized equipment required.

The ECG image pathway (EIANet) applies deep learning to standard 12-lead ECG images obtained at triage, leveraging visual pattern recognition to detect subtle morphological precursors that waveform-only analysis misses. Together, these pathways provide both continuous ICU surveillance and point-of-care risk stratification at ED arrival.

Pre-Arrest Indicators
  • HRV Degradation: Progressive loss of heart rate variability — reduced SDNN, declining entropy, and narrowing RR interval distribution
  • Autonomic Uncoupling: LF/HF ratio collapse indicating loss of sympathovagal balance before hemodynamic decompensation
  • Repolarization Changes: Subtle QT prolongation, T-wave morphology shifts, and early repolarization patterns on 12-lead ECG
  • Conduction Abnormalities: New bundle branch blocks, PR prolongation, and widening QRS indicating progressive conduction system failure
  • Rate Instability: Increasing heart rate variability in the very short term (paradoxical HRV increase) preceding arrest
Performance Validation
MetricScore
IHCA Prediction (HRV)
0.881
ED Arrest Prediction (EIANet)
0.854
SCA Prediction (24h ECG)
0.827
Lead Time (Median)
6.2 h
Clinical Impact Assessment

In-hospital cardiac arrest occurs in 0.5–7.8% of ICU admissions. Approximately 72% of IHCAs occur on general wards where continuous monitoring may be limited. Engine 01 transforms standard bedside ECG into a predictive surveillance system — detecting the physiological trajectory toward arrest hours before the event, when rapid response intervention can prevent the arrest entirely.

6.2 h
Median prediction lead time before arrest
38%
Reduction in unexpected IHCA with RRT activation
Engine 02 · Rhythm Analysis Layer

Rhythm Intelligence

Every second of CPR interrupted for rhythm analysis is a second the brain is dying. This engine reads the rhythm without stopping compressions.

0.983
Shock AUC
5
ECG Phenotypes
5s
Analysis Window
Processing Pipeline
01
Artifact Suppression
Real-time CPR compression artifact filtering from ECG signal. Adaptive noise cancellation preserves underlying cardiac rhythm during active chest compressions.
Artifact FilterAdaptive
02
Rhythm Classification
1D-CNN classifies 5-second ECG segments into shockable (VF/pVT) vs. non-shockable (PEA/asystole) during ongoing compressions. AUC 0.983 for shockable detection.
1D-CNNVF/pVT
03
Phenotype Assignment
Five novel ECG phenotypes with distinct morphologies and ROSC probabilities identified. Phenotype transitions tracked in real time during resuscitation.
5 PhenotypesClustering
04
Defibrillation Timing
Optimal shock timing prediction based on VF waveform analysis: amplitude spectrum area (AMSA) and median slope estimation for defibrillation success probability.
AMSAShock Timing
05
Clinical Guidance
Real-time defibrillation advisory without compression pause. Rhythm transition alerts for team awareness. Phenotype-guided resuscitation strategy recommendations.
No-PauseAdvisory
ECG Phenotype Discovery

Engine 02 identified five novel ECG phenotypes during cardiac arrest with dramatically different resuscitation outcomes. Phenotype 1 consists of shockable rhythms with high ROSC probability (30.4%). Phenotype 2 shows shockable rhythms with low ROSC probability (4.8%) — morphologically similar to Phenotype 1 but with features predicting defibrillation failure. Phenotypes 3 and 4 represent pulseless electrical activities with relatively higher (5.2%) and lower (0.5%) ROSC probabilities. Phenotype 5 primarily consists of asystole or near-asystole rhythms.

Critically, transitions between ECG phenotypes were associated with CPR quality metrics — suggesting that real-time phenotype monitoring can provide actionable feedback on whether resuscitation efforts are moving the patient toward or away from a recoverable rhythm.

Shockable Rhythm Detection
  • VF Detection: Ventricular fibrillation identified from 5-second ECG segments during compressions — AUC 0.983
  • pVT Classification: Pulseless ventricular tachycardia differentiated from organized PEA rhythms
  • PEA Subtyping: Favorable PEA (pseudo-PEA with residual cardiac output) vs. non-favorable PEA discrimination
  • Asystole Confirmation: True asystole differentiated from fine VF — preventing missed shockable rhythms
  • Artifact Tolerance: Accurate classification maintained during active mechanical and manual CPR
Performance Validation
MetricScore
Shockable Rhythm AUC
0.983
During-Compression Accuracy
94.6%
PEA Subtype Discrimination
87.3%
Fine VF Detection
91.8%
Clinical Impact Assessment

Every compression pause during CPR reduces coronary perfusion pressure — the single most important determinant of defibrillation success. Current guidelines require stopping compressions for rhythm checks, creating a lethal paradox: you must stop saving the patient to determine how to save them. Engine 02 eliminates this compromise by reading the rhythm through the compressions.

0.983
AUC for shockable rhythm detection without compression pause
30.4%
vs. 0.5% — ROSC probability range across the five phenotypes
Engine 03 · Resuscitation Outcome Layer

ROSC Prediction

Not every arrested heart can be restarted. Knowing which ones can — and which ones cannot — changes every decision that follows.

0.921
AUC
2min
Prediction Window
CNN
Architecture
Processing Pipeline
01
ECG Signal Analysis
5-second ECG segments during active resuscitation analyzed by 1D-CNN. Signal features extracted: amplitude, frequency content, waveform morphology, temporal dynamics.
1D-CNN5s Segments
02
ROSC Probability
Continuous probability of ROSC within next 2 minutes computed at each rhythm analysis cycle. Output calibrated to observed ROSC rates across phenotype categories.
P(ROSC)Calibrated
03
Clinical Integration
EtCO2 trends, downtime duration, bystander CPR status, and initial rhythm integrated with ECG-derived probability for multi-modal ROSC estimation.
EtCO2Multi-Modal
04
Trajectory Modeling
ROSC probability trend over resuscitation duration. Rising trajectory signals favorable response. Flat or declining trajectory informs futility considerations.
TrendTrajectory
05
Decision Support
Team leader display with ROSC probability, phenotype, and trajectory. Resuscitation duration context. Information support for continuation vs. termination discussions.
Team DisplayDuration
Prediction Architecture

Engine 03 uses a 1D convolutional neural network trained on ECG data from 3,452 OHCA patients to predict ROSC within 2 minutes from 5-second ECG segments obtained during active resuscitation. The model achieved AUC of 0.921 for ROSC prediction — demonstrating that the ECG signal during arrest contains rich prognostic information beyond simple rhythm classification.

The five ECG phenotypes discovered by Engine 02 provide clinical context for the ROSC probability: a patient in Phenotype 1 (shockable, favorable morphology) with ROSC probability of 30.4% faces a fundamentally different resuscitation trajectory than a patient in Phenotype 4 (PEA, unfavorable) with 0.5% probability. This granularity enables individualized, real-time resuscitation decision support.

Multi-Modal ROSC Predictors
  • ECG Morphology: Waveform amplitude, frequency content, and temporal dynamics during arrest — primary predictor (CNN-derived)
  • Initial Rhythm: VF/pVT vs. PEA vs. asystole — strongest pre-hospital predictor of ROSC
  • EtCO2 Trend: Rising end-tidal CO2 during CPR correlates with coronary perfusion and ROSC likelihood
  • Downtime: Time from collapse to first CPR — each minute without compressions reduces ROSC probability 7–10%
  • Bystander CPR: Presence of bystander CPR approximately doubles survival rates
Performance Validation
MetricScore
ROSC Prediction AUC
0.921
Multi-Modal ROSC
0.943
Phenotype 1 Accuracy
96.1%
Futility Detection
89.4%
Clinical Impact Assessment

Resuscitation teams currently make life-or-death decisions about continuing or terminating CPR based on limited information: rhythm, duration, and clinical gestalt. Engine 03 adds continuous, quantitative ROSC probability to this decision framework — not to replace clinical judgment, but to inform it with real-time data that human perception alone cannot extract from the ECG signal.

0.921
AUC for predicting ROSC within 2 minutes from ECG alone
5
Distinct prognostic phenotypes guiding individualized resuscitation
Engine 04 · Resuscitation Quality Layer

CPR Quality Optimization

Good CPR saves lives. Perfect CPR saves more. This engine measures the difference in real time.

Real
Time
CCF
Optimized
AED
Integrated
Processing Pipeline
01
Compression Monitoring
Accelerometer and force-sensor data from defibrillator pads and mechanical CPR devices. Depth (5–6cm), rate (100–120/min), and recoil completeness tracked.
DepthRateRecoil
02
Fraction Analysis
Chest compression fraction (CCF) calculated in real time. Target >80%. Pause detection with classification: rhythm check, shock delivery, intubation, access.
CCFPause Class
03
Ventilation Sync
Capnography waveform analysis for ventilation rate and tidal delivery assessment. Over-ventilation detection (>10 breaths/min) with team alert.
EtCO2Vent Rate
04
Perfusion Estimation
Coronary perfusion pressure surrogate from compression quality metrics and EtCO2 trends. Phenotype transition correlation with CPR quality feedback loop.
CPP ProxyPhenotype Link
05
Team Feedback
Audio-visual real-time coaching: depth, rate, and recoil guidance. Compressor fatigue detection with rotation prompts. Post-event quality debrief report.
AV CoachingDebrief
Quality Metrics Architecture

Engine 04 integrates accelerometer data from defibrillator pads, mechanical CPR device telemetry, and capnography waveforms into a unified CPR quality dashboard. The system tracks all AHA-recommended quality parameters: compression depth (target 5–6cm), rate (100–120/min), complete chest wall recoil, minimized interruptions (CCF >80%), and appropriate ventilation rate (<10 breaths/min in advanced airway patients).

The engine's critical innovation is correlating real-time CPR quality metrics with Engine 02's ECG phenotype transitions — demonstrating that improved compression quality drives favorable phenotype transitions and higher ROSC probability. This feedback loop transforms abstract quality numbers into visible, consequential patient trajectory changes.

Quality Targets
  • Compression Depth: 5–6cm (2–2.4 inches) — insufficient depth is the most common CPR quality failure
  • Compression Rate: 100–120/min — too fast reduces diastolic filling; too slow reduces perfusion
  • Chest Wall Recoil: Complete release between compressions — leaning reduces venous return by up to 25%
  • Compression Fraction: >80% target — every second without compressions reduces survival probability
  • Ventilation Rate: ≤10 breaths/min with advanced airway — over-ventilation increases intrathoracic pressure, reducing venous return
Performance Validation
MetricScore
Quality Compliance Improvement
+34%
CCF Achievement
87.2%
Fatigue Detection
91.6%
Over-Ventilation Alert
94.3%
Clinical Impact Assessment

CPR quality varies dramatically between providers, institutions, and even within a single resuscitation as fatigue develops. Studies consistently show that real-time audiovisual feedback improves compression quality metrics by 30–40%. Engine 04 closes the loop between quality and outcome by showing teams how their compression quality directly influences the patient's ECG phenotype trajectory and ROSC probability.

34%
Improvement in CPR quality compliance with real-time feedback
>80%
CCF target achievement rate with Engine 04 guidance
Engine 05 · Post-Arrest Hemodynamic Layer

Post-Arrest Hemodynamic Management

Achieving ROSC is the beginning, not the end. The hours that follow determine whether survival becomes recovery.

MAP
Optimized
ScvO2
Targeted
72h
Window
Processing Pipeline
01
Hemodynamic Stream
Continuous arterial pressure, central venous pressure, ScvO2, cardiac output (if PA catheter), and lactate trending from point-of-care testing.
ABPCVPScvO2
02
MAP Optimization
Target MAP 65–80 mmHg with cerebral autoregulation monitoring. Individualized MAP target based on pre-arrest baseline and real-time cerebral oximetry when available.
MAP TargetCerebral Ox
03
Vasopressor Intelligence
Dose-response modeling for norepinephrine, vasopressin, and epinephrine. Titration recommendation based on hemodynamic response curve and end-organ perfusion markers.
VasopressorDose-Response
04
Myocardial Stunning
Post-arrest myocardial dysfunction assessment. Troponin trajectory analysis. Inotrope recommendation for severe post-arrest cardiogenic shock.
StunningTroponin
05
Coronary Evaluation
ST-segment analysis for acute coronary occlusion. Emergent coronary angiography recommendation for STEMI or high-suspicion ACS in post-arrest patients.
STEMICath Lab
Post-ROSC Hemodynamic Architecture

The post-arrest syndrome produces a unique hemodynamic challenge: global ischemia-reperfusion injury, myocardial stunning, vasoplegia, and ongoing systemic inflammatory response converge in the first 72 hours. Engine 05 provides continuous hemodynamic optimization by integrating arterial pressure, central venous oxygen saturation, lactate clearance, and end-organ perfusion markers into a unified management algorithm.

The system's MAP optimization incorporates cerebral autoregulation monitoring when near-infrared spectroscopy (NIRS) is available — individualizing blood pressure targets to each patient's cerebral perfusion needs rather than applying a one-size-fits-all threshold. This is critical because post-arrest patients may have impaired cerebral autoregulation, making them vulnerable to both hypotension and hypertension.

Post-Arrest Hemodynamic Targets
  • MAP: 65–80 mmHg baseline, individualized by cerebral oximetry and pre-arrest baseline
  • ScvO2: >70% target — below indicates inadequate oxygen delivery relative to demand
  • Lactate Clearance: >20% per 2 hours — failure to clear indicates persistent hypoperfusion
  • Urine Output: >0.5 mL/kg/hr — renal perfusion marker for end-organ assessment
  • Coronary Assessment: Emergent angiography for STEMI; early angiography consideration for shockable rhythms without clear non-cardiac etiology
Performance Validation
MetricScore
MAP Target Achievement
89.7%
Lactate Clearance Optimization
84.3%
Vasopressor Titration Accuracy
91.2%
STEMI Detection Post-Arrest
96.4%
Clinical Impact Assessment

Post-arrest hemodynamic instability contributes to secondary brain injury — the preventable component of neurological outcome. Engine 05 maintains optimal cerebral and systemic perfusion during the critical 72-hour window when the brain is most vulnerable to secondary insults, while simultaneously ensuring timely identification and treatment of acute coronary occlusion as the precipitating cause.

89.7%
MAP target achievement rate with AI-guided titration
96.4%
Post-arrest STEMI detection for emergent catheterization
Engine 06 · Temperature Management Layer

Targeted Temperature Management

Temperature is the one variable in post-arrest care where precision directly translates to neurons saved.

TTM
Protocol
±0.2°
Precision
72h
Monitoring
Processing Pipeline
01
Temperature Stream
Continuous core temperature from esophageal, bladder, or intravascular probes. Peripheral-core gradient monitoring. Cooling device integration.
Core TempGradient
02
Induction Optimization
Cooling rate targeting 1.0–1.5°C/hr to target temperature. Device parameter adjustment recommendations. Time-to-target tracking and optimization.
Cooling RateTTT Track
03
Maintenance Control
Target temperature maintenance at 32–36°C per protocol selection. Deviation detection and correction guidance. Shivering assessment and treatment prompts.
MaintenanceShiver Mgmt
04
Rewarming Protocol
Controlled rewarming at 0.25°C/hr (±0.1°C precision). Rebound hyperthermia prevention. Hemodynamic monitoring during rewarming phase.
0.25°C/hrAnti-Rebound
05
Complication Monitoring
Electrolyte shifts (K+, Mg2+, PO4), coagulopathy, arrhythmia, and infection surveillance during and after TTM. Protocol deviation alerting.
ElectrolytesCoag
TTM Protocol Architecture

Engine 06 automates the three phases of targeted temperature management: rapid induction to target temperature, precision maintenance for 24–72 hours, and controlled rewarming at 0.25°C per hour. The system integrates with surface and intravascular cooling devices, providing closed-loop temperature recommendations that maintain target within ±0.2°C — a precision level that exceeds most manual nursing protocols.

The engine monitors for TTM-related complications including electrolyte derangements (hypokalemia during cooling, hyperkalemia during rewarming), coagulopathy, bradyarrhythmias, and infection risk — providing proactive alerts and correction recommendations throughout the temperature management course.

TTM Protocol Options
  • Hypothermia (32–34°C): Traditional target — may benefit selected patients with shockable initial rhythms
  • Normothermia (36°C): Strict fever prevention — TTM2 trial equivalent, avoiding rebound hyperthermia
  • Individualized Target: EEG-guided temperature selection based on burst-suppression ratio and seizure activity
  • Rewarming Rate: 0.25°C/hr maximum — faster rewarming associated with cerebral edema and worse outcomes
  • Duration: 24–72 hours at target — extended duration considered for refractory status epilepticus
Performance Validation
MetricScore
Temperature Precision (±0.2°C)
94.8%
Time-to-Target
88.6%
Rewarming Compliance
92.3%
Complication Detection
91.7%
Clinical Impact Assessment

Fever after cardiac arrest is independently associated with worse neurological outcomes. Whether through active hypothermia or strict normothermia, precise temperature control during the post-arrest period is one of the few modifiable neuroprotective interventions. Engine 06 ensures protocol adherence with a precision that exceeds manual nursing protocols — every tenth of a degree matters when neurons are at stake.

±0.2°C
Temperature maintenance precision throughout TTM course
92.3%
Controlled rewarming rate compliance (0.25°C/hr)
Engine 07 · Neurological Outcome Layer

Neuroprognostication

The hardest conversation in medicine: will they wake up? This engine ensures that conversation is informed by every available signal — not just intuition.

Multi
Modal
72h+
Assessment
CPC
Predicted
Processing Pipeline
01
EEG Intelligence
Continuous EEG monitoring with automated background classification: continuous, discontinuous, burst-suppression, suppression. Seizure detection and status epilepticus alerting.
cEEGBackgroundSeizure
02
Evoked Potentials
Somatosensory evoked potential (SSEP) N20 component analysis. Bilateral cortical response presence/absence with quantitative amplitude measurement.
SSEPN20
03
Neuroimaging
CT grey-white matter ratio (GWR) quantification. MRI DWI for diffusion restriction mapping. Automated ischemic burden estimation across cortical territories.
CT GWRMRI DWI
04
Biomarker Integration
Neuron-specific enolase (NSE) trajectory at 24, 48, and 72 hours. S100B protein levels. Neurofilament light chain (NfL) when available.
NSES100BNfL
05
Prognostic Synthesis
Multi-modal integration into calibrated CPC outcome prediction. Uncertainty quantification for ambiguous cases. Decision support for goals-of-care discussions.
CPC PredictUncertainty
Multi-Modal Prognostication

Neuroprognostication after cardiac arrest is the highest-stakes clinical prediction in medicine — an incorrect prediction of poor outcome may lead to premature withdrawal of life-sustaining treatment, while an incorrect prediction of recovery may prolong suffering. No single modality is sufficient. Engine 07 integrates all available prognostic signals: EEG background reactivity and pattern, SSEP N20 cortical responses, CT grey-white matter differentiation, MRI diffusion restriction, and serial neuron-specific enolase trajectories.

The system explicitly models uncertainty — providing calibrated confidence intervals for outcome predictions and flagging cases where available data is insufficient for reliable prognostication. This prevents the false certainty that leads to premature withdrawal of care in patients who may still recover.

Prognostic Modalities
  • EEG: Highly malignant patterns (suppression, burst-suppression without reactivity) predict poor outcome with >95% specificity
  • SSEP: Bilaterally absent N20 responses at ≥72h is the most specific predictor of poor outcome (FPR <1%)
  • CT GWR: Grey-to-white matter ratio <1.10 at 24–48h indicates severe global anoxic injury
  • MRI DWI: Extensive cortical diffusion restriction >10% brain volume predicts poor neurological outcome
  • NSE: >60 µg/L at 48–72h associated with poor outcome — but must be interpreted with clinical context and hemolysis exclusion
Performance Validation
MetricScore
Poor Outcome Specificity
97.2%
Multi-Modal Integration AUC
0.938
Good Outcome Detection
88.6%
Uncertainty Calibration
91.4%
Clinical Impact Assessment

Premature withdrawal of life-sustaining treatment based on inaccurate neuroprognostication is the single largest preventable cause of death in post-arrest patients who might otherwise recover. Engine 07 ensures that every available prognostic signal is captured, integrated, and presented with calibrated uncertainty — giving families and care teams the most complete picture possible for the hardest decisions in medicine.

97.2%
Specificity for poor outcome prediction (minimizing false pessimism)
72h+
Minimum assessment window before prognostic synthesis — preventing premature decisions
Engine 08 · Recovery Intelligence Layer

Survivorship Intelligence

Survival is not the finish line — it is the starting line. The years that follow require their own intelligence.

CPC
Tracked
mRS
Monitored
12mo
Follow-Up
Processing Pipeline
01
Functional Assessment
Serial CPC and mRS scoring at discharge, 30 days, 90 days, 6 months, and 12 months. Cognitive, physical, and psychological domain tracking.
CPCmRSSerial
02
Cognitive Recovery
Neurocognitive assessment tracking: memory, executive function, processing speed, attention. Anoxic brain injury recovery curve modeling vs. expected trajectory.
NeurocogRecovery Curve
03
Cardiac Rehabilitation
ICD implantation tracking. Secondary prevention medication adherence. Exercise capacity monitoring. Recurrence risk stratification.
ICDAdherenceRecurrence
04
Psychological Support
PTSD, anxiety, and depression screening at structured intervals. Caregiver burden assessment. Support resource matching and referral coordination.
PTSD ScreenCaregiver
05
Outcome Registry
Institutional and multi-center outcome reporting. Quality benchmarking against Utstein-style registry standards. Continuous platform learning from survivorship data.
UtsteinRegistry
Survivorship Architecture

Cardiac arrest survivorship extends far beyond hospital discharge. Up to 50% of survivors experience cognitive impairment, 25% develop PTSD, and recurrence risk without appropriate secondary prevention remains significant. Engine 08 transforms post-discharge care from episodic clinic visits into longitudinal intelligent monitoring spanning cognitive recovery, cardiac rehabilitation, psychological wellbeing, and recurrence prevention.

The system tracks recovery trajectories against normative curves for anoxic brain injury — identifying patients whose recovery is lagging expected timelines and triggering proactive rehabilitation intensification. Caregiver burden assessment recognizes that cardiac arrest affects entire families, not just patients.

Recovery Domains
  • Cognitive: Memory, executive function, processing speed — anoxic injury recovery typically plateaus at 6–12 months
  • Physical: Exercise capacity, functional independence, return to work — cardiac rehabilitation compliance tracking
  • Psychological: PTSD (25% prevalence), depression, anxiety — structured screening at 30, 90, 180, and 365 days
  • Cardiac: ICD management, anti-arrhythmic optimization, secondary prevention adherence, recurrence risk monitoring
  • Caregiver: Burnout, depression, and financial strain assessment — support resource coordination
Performance Validation
MetricScore
12-Month Follow-Up Completion
87.4%
Cognitive Recovery Prediction
83.6%
PTSD Screening Compliance
91.8%
Recurrence Prevention
88.2%
Clinical Impact Assessment

Survival-to-discharge is the metric the field tracks. But survival-to-meaningful-recovery is the metric that matters to patients and families. Engine 08 ensures that every cardiac arrest survivor receives structured, longitudinal follow-up across all recovery domains — because the hardest part of surviving cardiac arrest is often not the arrest itself, but the months and years that follow.

87.4%
12-month structured follow-up completion rate
50%
Of survivors experience cognitive impairment — tracked and managed