Laya Medical Escalation (impacte/laya-medical-escalation)

⚠️ NOT A MEDICAL DEVICE — NOT FOR CLINICAL USE

This is a research and educational artifact. It was trained to reproduce the acuity levels recorded in a historical, de-identified dataset. It must never be used to triage, diagnose, or make care decisions for real patients. Acuity assessment is subjective and population dependent; a model that under-triages can cause serious harm.

Laya Medical Escalation is convaiinnovations/laya (421M, ModernBERT-large + typed decision head) fine-tuned to assign the Emergency Severity Index (ESI 1–5) from an emergency-department triage record. Laya is non-autoregressive: it scores each ESI level at its own [MASK] marker and softmaxes over the levels in one forward pass (~23 ms), returning a calibrated distribution rather than free text.

Base	convaiinnovations/laya (Apache-2.0)
Architecture	ModernBERT-large encoder + 2-layer decision head + option-marker scorer (421M)
Task	choice over ESI 1–5, from a text triage record
Training	RLCD (GRPO + strictly proper scoring rule + soft cross-entropy) with inverse-frequency class weights
License	Apache-2.0 (inherited from Laya)
Latency	~23 ms p50, single request, RTX 5060 Ti

Usage

import laya

router = laya.load("impacte/laya-medical-escalation")

criteria = {
    "esi-1": "ESI 1 Resuscitation: requires immediate life-saving intervention "
             "(e.g. cardiac arrest, intubation, severe respiratory distress).",
    "esi-2": "ESI 2 Emergent: high-risk, drowsy/confused, severe pain; should not wait.",
    "esi-3": "ESI 3 Urgent: needs two or more resources (labs, imaging, IV fluids); vitals stable.",
    "esi-4": "ESI 4 Less urgent: needs one resource (x-ray, prescription, simple procedure).",
    "esi-5": "ESI 5 Non-urgent: needs no resources; can be referred or discharged.",
}

res = router.predict(
    "Emergency department triage record. Patient: 58-year-old male. "
    "Chief complaint: chest pain, shortness of breath. "
    "Triage vitals: HR 118, BP 88/54, RR 28, SpO2 89% on room air, temperature 98.4 F. "
    "Arrival: ambulance. History: 3 prior ED visits.",
    {"route": {
        "type": "choice",
        "instructions": "You are an emergency department triage nurse. Based only on the triage "
                        "record, assign the correct Emergency Severity Index (ESI) level.",
        "criteria": criteria,
    }},
)
print(res["answers"]["route"]["choice"])         # -> esi-2
print(res["answers"]["route"]["probabilities"])

Results

Held-out evaluation — 2500 rows, class-balanced (chance 0.20):

Accuracy	Macro-F1	Under-triage ↓	Within ±1 level	Ordinal MAE	ECE ↓	p50 latency
0.6860	0.6829	0.1564	0.9476	0.3852	0.0223	22.87 ms

ESI level	Precision	Recall	F1	Support
esi-1	0.769	0.860	0.812	500
esi-2	0.666	0.570	0.614	500
esi-3	0.618	0.566	0.591	500
esi-4	0.621	0.674	0.646	500
esi-5	0.742	0.760	0.751	500

Under-triage = predicted a less urgent ESI level than gold (the dangerous error); the high-acuity (gold ESI-1/2) under-triage rate is 0.189.

Accuracy & response time vs local LLMs (same 300 held-out rows)

System	Accuracy	Macro-F1	Under-triage ↓	p50 latency
Laya Medical Escalation	0.7033	0.6978	0.1600	22.8 ms
gemma4:e4b	0.4333	0.4279	0.3933	173.5 ms
oamazonasgabriel/qwen3.8-27b:iq4-xs-64k-text-q4kv	0.3233	0.3347	0.2925	943.9 ms
oamazonasgabriel/minicpm-2b:bf16	0.2967	0.2880	0.4735	2538.9 ms
random	0.2200	0.2175	0.3733	—
always esi-3	0.2000	0.0667	0.4000	—
laya-base (zero-shot)	0.2133	0.1336	0.2533	23.6 ms

LLMs were given a 192-token budget and a parser that strips thinking/tool-call wrappers, so this is not a formatting strawman.

Same-dataset baselines (identical train/test split)

Method	Features	Accuracy	Macro-F1	Under-triage ↓	High-acuity under-triage ↓	Ordinal MAE
Laya Medical Escalation	text template	0.6860	0.6829	0.1564	0.1890	0.3852
xgboost (laya)	214	0.6072	0.5969	0.1624	0.2730	0.5016
xgboost (full)	970	0.6136	0.6018	0.1524	0.2650	0.5116
deterministic ESI v5 (full)	cc + vitals rules	0.4176	0.3963	0.2724	0.5820	0.752

XGBoost uses the full 970-column table; the deterministic model is the partial ESI v5 clinical algorithm (resource count inferred — the dataset has no resource, pain, or mental-status fields, so this is a lower bound on it).

Dataset

Trained on the Yale School of Medicine emergency-department triage dataset:

Hong WS, Haimovich AD, Taylor RA. Predicting hospital admission at emergency department triage using machine learning. PLOS ONE 13(7): e0201016 (2018). DOI 10.1371/journal.pone.0201016

560,486 de-identified ED visits × 972 variables. The model consumes a text state built only from at-triage fields — chief complaint (from 200 chief-complaint one-hots), triage vitals (HR, BP, RR, SpO2, temperature), age, sex, arrival mode, prior ED visits, previous disposition and outpatient medication count. HF mirror used: kondratevakate/hospital-triage-and-patient-history-data (lossless RData→Parquet re-host). Citation is required for any use of this data; do not redistribute it.

Training

• 57,271 training rows (ESI-1 4,771 · ESI-2 15,000 · ESI-3 15,000 · ESI-4 15,000 · ESI-5 7,500).
• 2 epochs, bf16 + gradient checkpointing, one RTX 5060 Ti 16 GB, ~75 min.
• Temperature calibrated to 1.046 on held-out logits.
• No leakage: esi / disposition never enter the state text.

Limitations

• Research artifact only — not for clinical use (see the banner above).
• English only; the base Laya checkpoint is English.
• The state is a template over structured fields, not free-text clinician notes.
• ESI is a nurse-assigned, partly subjective label; class boundaries are fuzzy.
• ESI-2/3 are the hardest classes; under-triage is the metric that matters and it is not zero.
• Performance may not transfer to other hospitals, populations, or triage protocols.

Credits

• convaiinnovations/laya — base model and RLCD recipe (Apache-2.0).
• Hong, Haimovich & Taylor (Yale) / PLOS ONE — the triage dataset.

Citation

@misc{laya_medical_escalation2026,
  title  = {Laya Medical Escalation: a calibrated ESI decision model},
  author = {oamazonasgabriel},
  year   = {2026},
  url    = {https://huggingface.co/impacte/laya-medical-escalation}
}