The ability of machine learning algorithms to predict defibrillation success during cardiac arrest: A systematic review.

OBJECTIVE: To evaluate the existing knowledge on the effectiveness of machine learning (ML) algorithms inpredicting defibrillation success during in- and out-of-hospital cardiac arrest. METHODS: MEDLINE, Embase, CINAHL and Scopus were searched from inception to August 30, 2022. Studies were included that utilized ML algorithms for prediction of successful defibrillation, observed as return of spontaneous circulation (ROSC), survival to hospital or discharge, or neurological status at discharge.Studies were excluded if involving a trauma, an unknown underlying rhythm, an implanted cardiac defibrillator or if focused on the prediction or onset of cardiac arrest. Risk of bias was assessed using the PROBAST tool. RESULTS: There were 2399 studies identified, of which 107 full text articles were reviewed and 15 observational studies (n = 5680) were included for final analysis. 29 ECG waveform features were fed into 15 different ML combinations. The best performing ML model had an accuracy of 98.6 (98.5 - 98.7)%, with 4 second ECG intervals. An algorithm incorporating end-tidal CO2 reported an accuracy of 83.3% (no CI reported). Meta-analysis was not performed due to heterogeneity in study design, ROSC definitions, and characteristics. CONCLUSION: Machine learning algorithms, specifically Neural Networks, have been shown to have potential to predict defibrillation success for cardiac arrest with high sensitivity and specificity.Due to heterogeneity, inconsistent reporting, and high risk of bias, it is difficult to conclude which, if any, algorithm is optimal. Further clinical studies with standardized reporting of patient characteristics, outcomes, and appropriate algorithm validation are still required to elucidate this. PROSPERO 2020 CRD42020148912.

Sex-related differences in sternocleidomastoid muscle morphology in healthy young adults: A cross-sectional magnetic resonance imaging measurement study.

BACKGROUND: Changes in sternocleidomastoid (SCM) muscle cross-sectional area (CSA) and volume may contribute to neck-related concussion symptoms and whiplash-associated disorders. Magnetic resonance imaging (MRI) data on healthy SCM morphology can provide information that may lead to targeted treatment protocols. OBJECTIVES: To examine sex-related differences in MRI-based SCM CSA, SCM volume and neck area in healthy young adults, to analyze associations between measurements and participant variables and to assess inter-rater reliability for measurement quantification. DESIGN: Cross-sectional study. METHODS: 13 males and 14 females underwent MRI scans. Slices obtained from C3-C7 were analyzed by three raters. SCM CSA at C4, total SCM volume from C3-C7 and neck area at C4 were quantified. Measurements were calculated as absolute and normalized values by body mass. Multivariable regression was used to analyze associations between normalized measurement values and participant variables. Inter-rater reliability was determined using intraclass correlation coefficients (ICC). RESULTS: Females had significantly lower normalized overall average SCM CSA (mean difference 1.3 mm2/kg (95% CI 0.4-2.2, p = 0.006) and total SCM volume (mean difference 140.8 mm3/kg (95% CI 66.1-215.5, p < 0.001) than males. Regression models indicated female sex was associated with lower normalized overall average SCM CSA (p = 0.004) and total SCM volume (p < 0.001). Inter-rater reliability was excellent for SCM CSA (ICC3,3 = 0.909), SCM volume (ICC3,3 = 0.910) and neck area (ICC3,3 = 0.995). CONCLUSIONS: These results enhance our understanding of sex-related differences in SCM morphology and will inform future research and clinical practice related to cervical muscle injury.