An interpretable, formally verified point-of-care ultrasound risk equation for difficult videolaryngoscopy: development and internal validation
Abstract
BackgroundVideolaryngoscopy still requires adjuncts or hyperangulated rescue in a clinically important minority, and bedside screening discriminates modestly. Point-of-care ultrasound (POCUS) of the anterior airway is a promising alternative, but existing prediction models are opaque or assume a pre-specified functional form. We developed and internally validated a parsimonious, fully disclosed POCUS risk equation whose form is recovered from data and whose structural properties are machine-checked by formal proof -- to our knowledge the first formally verified clinical risk predictor -- following TRIPOD+AI 2024.
MethodsIn a prospective single-centre, single-operator cohort of 259 adults undergoing elective videolaryngoscopy (no-Easy airway 68/259, 26.3%), Sequentially Thresholded Least Squares with bootstrap stability selection (B = 300) screened a 71-term library of nine POCUS features and retained a seven-term logistic equation; a two-term bootstrap-stable model was pre-specified as robustness analysis. Internal validation used 5 x 10 repeated cross-validation plus temporal and device hold-outs, with pre-specified overfitting and optimism assessments. Five behavioural properties of the deployed equation were machine-checked in Lean 4.
ResultsTwo interactions met the |c|/{sigma}c > 2 stability criterion: skin-to-epiglottis x skin-to-hyoid-bone distance and tongue volume x sagittal tongue area. The seven-term equation reached a 5 x 10 cross-validated C-statistic of 0.966 (optimism-corrected 0.968) and held across temporal and device hold-outs (0.94-0.97). Calibration-in-the-large matched prevalence, with cross-validated slope 0.90 attenuating to 0.625 out-of-time; standard recalibration restored 0.92 without loss of discrimination. The pre-specified two-term robustness model reproduced this performance (C-statistic 0.964-0.968; events-per-parameter 34; shrinkage 0.99), confirming the result is not an artefact of the screening stage. Net benefit over a clinical baseline was positive across 10-50% thresholds. All five Lean 4 theorems compiled without sorry.
ConclusionsA sparse, formally verified POCUS equation predicts difficult videolaryngoscopy with high internally validated discrimination and quantified, modest overfitting. Because the equation was developed in a single-operator cohort and its inputs are operator-dependent, external validation requires prior harmonisation of the measurement protocol and operator credentialing.
Related
- Development and Internal Validation of a Preoperative Risk Stratification Model for Difficult Laparoscopic Cholecystectomy in Acute Cholecystitis
- Development and validation of an interpretable machine learning model for early prediction of mortality in ICU patients with chronic obstructive pulmonary disease and heart failure
- Development and validation of an interpretable prediction model for high-grade vesicoureteral reflux in children with urinary tract infections
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
- Ultrasound guidance versus near-infrared light versus the standard technique for first-attempt success of peripheral intravenous catheterisation in adults with difficult venous access in a medical imaging department (RÉUSSIR-VVP): protocol for a single-centre, three arms, randomised controlled trial
BibTeX
@misc{oyarzunsilva2026interpretable,
title = {{An interpretable, formally verified point-of-care ultrasound risk equation for difficult videolaryngoscopy: development and internal validation}},
author = {R. A. Oyarzun-Silva and P. Hernandez-Hernandez and M. A. Fernandez-Vaquero and N. De Luis-Cabezon},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.28.26361621},
url = {https://www.medrxiv.org/content/10.64898/2026.08.28.26361621v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - An interpretable, formally verified point-of-care ultrasound risk equation for difficult videolaryngoscopy: development and internal validation
AU - R. A. Oyarzun-Silva
AU - P. Hernandez-Hernandez
AU - M. A. Fernandez-Vaquero
AU - N. De Luis-Cabezon
PY - 2026
DA - 2026/08/28
PB - medRxiv
DO - 10.64898/2026.08.28.26361621
UR - https://www.medrxiv.org/content/10.64898/2026.08.28.26361621v1
AB - BackgroundVideolaryngoscopy still requires adjuncts or hyperangulated rescue in a clinically important minority, and bedside screening discriminates modestly. Point-of-care ultrasound (POCUS) of the anterior airway is a promising alternative, but existing prediction models are opaque or assume a pre-specified functional form. We developed and internally validated a parsimonious, fully disclosed POCUS risk equation whose form is recovered from data and whose structural properties are machine-checked by formal proof -- to our knowledge the first formally verified clinical risk predictor -- following TRIPOD+AI 2024. MethodsIn a prospective single-centre, single-operator cohort of 259 adults undergoing elective videolaryngoscopy (no-Easy airway 68/259, 26.3%), Sequentially Thresholded Least Squares with bootstrap stability selection (B = 300) screened a 71-term library of nine POCUS features and retained a seven-term logistic equation; a two-term bootstrap-stable model was pre-specified as robustness analysis. Internal validation used 5 x 10 repeated cross-validation plus temporal and device hold-outs, with pre-specified overfitting and optimism assessments. Five behavioural properties of the deployed equation were machine-checked in Lean 4. ResultsTwo interactions met the |c|/{sigma}c > 2 stability criterion: skin-to-epiglottis x skin-to-hyoid-bone distance and tongue volume x sagittal tongue area. The seven-term equation reached a 5 x 10 cross-validated C-statistic of 0.966 (optimism-corrected 0.968) and held across temporal and device hold-outs (0.94-0.97). Calibration-in-the-large matched prevalence, with cross-validated slope 0.90 attenuating to 0.625 out-of-time; standard recalibration restored 0.92 without loss of discrimination. The pre-specified two-term robustness model reproduced this performance (C-statistic 0.964-0.968; events-per-parameter 34; shrinkage 0.99), confirming the result is not an artefact of the screening stage. Net benefit over a clinical baseline was positive across 10-50% thresholds. All five Lean 4 theorems compiled without sorry. ConclusionsA sparse, formally verified POCUS equation predicts difficult videolaryngoscopy with high internally validated discrimination and quantified, modest overfitting. Because the equation was developed in a single-operator cohort and its inputs are operator-dependent, external validation requires prior harmonisation of the measurement protocol and operator credentialing.
ER -