A ground-truth-labeled, mechanistic in-silico testbed for fetal physiological development โ enabling biomarker discovery where clinical data cannot go.
Mechanistic, not generative
Physiology is simulated from first principles โ cardiovascular, metabolic, autonomic โ not learned from data.
Latent ground truth
pH, lactate, perfusion pressure, and injury states are co-registered with every synthetic monitoring signal.
In-silico controls
Disable noise, ablate reflexes, quantize signals โ interventions impossible in live subjects.
Instrument, not a digital twin
Calibration-grade, population-level. Not a validated patient-specific clinical predictor.
Detector artifacts can fabricate HRV
Naive beat detectors inject spurious beats scaling as tยทแนช/Tยฒ under a time-varying period. Up to 94.5% of detected beats can be spurious โ making apparent HRV amplitude a property of the detector, not the fetus.
HRV requires an explicit stochastic driver
Beat-to-beat variability does not arise as a self-sustained oscillation of the deterministic autonomic loop โ it requires an injected noise source.
Fidelity-matched biomarker selection
Deceleration area survives 4 Hz CTG sampling. RMSSD is corrupted by quantization jitter at 4 Hz and requires fetal-ECG-grade acquisition.
Early warning via autonomic exhaustion
HRV-based predictors track autonomic exhaustion ahead of metabolic decompensation โ providing a regime-dependent lead time before pH threshold crossing.
Rise-then-collapse motivates a pacemaker hypothesis
Autonomic modulation alone cannot reproduce the published RMSSD rise-then-collapse trajectory โ motivating, but not proving, an intrinsic sinoatrial pacemaker contribution.
Fetal Twin integrates five physiological layers, each contributing to the synthetic monitoring signal.
Cardiovascular
Heart rate, blood pressure, umbilical cord occlusion response
Metabolic / Acid-Base
pH, lactate, aerobic/anaerobic metabolism, buffer dynamics
Autonomic
Fast/slow vagal split, sympathetic drive, chemoreflex, exhaustion
HRV / Pacemaker
AR(2) intrinsic surrogate โ coupled-clock sinoatrial model in development
Gestational Development
Antepartum scaling, growth, organ maturation across gestation
33-state ODE system ยท Explicit integer seeds ยท Reproducible to numerical tolerance ยท Phase-accumulator beat detector
ODE state variables
33
Spurious beats (naive detector)
94.5%
CTG sampling (RMSSD fails)
4 Hz
DTH lead time (moderate severity)
~57 min
Synthetic signal stack
โ๏ธ Research use only โ not a medical device.
Outputs are synthetic and calibration-grade; they are not validated against patient outcomes and must not be used for clinical diagnosis, treatment, triage, or any decision affecting the care of an actual patient.
Source-available under the PolyForm Noncommercial License 1.0.0. Methods implemented in the software are the subject of a pending U.S. patent application assigned to JoyBeat Medical, Inc.; the license grants noncommercial rights only. Commercial use, or any commercial practice of the pending patents, requires a separate license โ licensing@joybeatmed.com.
A commercial license also unlocks the full research program beyond this open engine: mechanistic (emergent coupled-clock) intrinsic-HRV, and calibrated hypoxia- and inflammation-response axes for mechanism-dissociable biomarker discovery โ with the production-calibrated corpora and validated predictors held as trade secrets.
Implements and extends the fetal umbilical-cord-occlusion model of Wang et al. (2015), Bulletin of Mathematical Biology 77(12):2264โ2293 โ PubMed 26582358 ยท DOI 10.1007/s11538-015-0122-4. Please cite it alongside Fetal Twin.
ยฉ 2026 JoyBeat Medical, Inc. ยท github.com/martinfrasch/fetaltwin